The effect of challenge-based gamification on learning: An experiment in the context of statistics education

Gamification is increasingly employed in learning environments as a way to increase student motivation and consequent learning outcomes. However, while the research on the effectiveness of gamification in the context of education has been growing, there are blind spots regarding which types of gamification may be suitable for different educational contexts. This study investigates the effects of the challenge-based gamification on learning in the area of statistics education. We developed a gamification approach, called Horses for Courses, which is composed of main game design patterns related to the challenge-based gamification; points, levels, challenges and a leaderboard. Having conducted a 2 (read: yes vs. no) x 2 (gamification: yes vs. no) between-subject experiment, we present a quantitative analysis of the performance of 365 students from two different academic majors: Electrical and Computer Engineering (n=279), and Business Administration (n=86). The results of our experiments show that the challenge-based gamification had a positive impact on student learning compared to traditional teaching methods (compared to having no treatment and treatment involving reading exercises). The effect was larger for females or for students at the School of Electrical and Computer Engineering.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, National Technical University of Athens, Tampere University, Gamification Group
Contributors: Legaki, N. Z., Xi, N., Hamari, J., Karpouzis, K., Assimakopoulos, V.
Publication date: 1 Dec 2020
Peer-reviewed: Yes

Publication information

Journal: International Journal of Human Computer Studies
Volume: 144
Article number: 102496
ISSN (Print): 1071-5819
Original language: English
ASJC Scopus subject areas: Software, Human Factors and Ergonomics, Education, Engineering(all), Human-Computer Interaction, Hardware and Architecture
Keywords: Applications in education, Gamification, Human-Computer interface, Statistics education, Teaching forecasting
Electronic versions: 
Source: Scopus
Source ID: 85086641706

Research output: Contribution to journalArticleScientificpeer-review

Some SonarQube issues have a significant but small effect on faults and changes. A large-scale empirical study

Context: Companies frequently invest effort to remove technical issues believed to impact software qualities, such as removing anti-patterns or coding styles violations. Objective: We aim to analyze the diffuseness of SonarQube issues in software systems and to assess their impact on code changes and fault-proneness, considering also their different types and severities. Methods: We conducted a case study among 33 Java projects from the Apache Software Foundation repository. Results: We analyzed 726 commits containing 27K faults and 12M changes in Java files. The projects violated 173 SonarQube rules generating more than 95K SonarQube issues in more than 200K classes. Classes not affected by SonarQube issues are less change-prone than affected ones, but the difference between the groups is small. Non-affected classes are slightly more change-prone than classes affected by SonarQube issues of type Code Smell or Security Vulnerability. As for fault-proneness, there is no difference between non-affected and affected classes. Moreover, we found incongruities in the type and severity assigned by SonarQube. Conclusion: Our result can be useful for practitioners to understand which SonarQube issues should be refactored and for researchers to bridge the missing gaps. Moreover, results can also support companies and tool vendors in identifying SonarQube issues as accurately as possible.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, LUT University
Contributors: Lenarduzzi, V., Saarimäki, N., Taibi, D.
Number of pages: 15
Publication date: Dec 2020
Peer-reviewed: Yes

Publication information

Journal: Journal of Systems and Software
Volume: 170
Article number: 110750
ISSN (Print): 0164-1212
Original language: English
ASJC Scopus subject areas: Software, Information Systems, Hardware and Architecture
Keywords: Change-proneness, Empirical study, Fault-proneness, SonarQube

Bibliographical note

EXT="Lenarduzzi, Valentina"

Source: Scopus
Source ID: 85087390369

Research output: Contribution to journalArticleScientificpeer-review

Necessary and sufficient conditions for the existence of solution of generalized fuzzy relation equations A ⇔X = B

In 2013 Li and Jin studied a particular type of fuzzy relational equations on finite sets, where the introduced min-bi-implication composition is based on Łukasiewicz equivalence. In this paper such fuzzy relation equations are studied on a more general level, namely complete residuated lattice valued fuzzy relation equations of type ⋀y∈Y(A(x,y)↔X(y)=B(x) are analyzed, and the existence of solutions S is studied. First a necessary condition for the existence of solution is established, then conditions for lower and upper limits of solutions are given, and finally sufficient conditions for the existence of the smallest and largest solutions, respectively, are characterized. If such general or global solutions do not exist, there might still be partial or point wise solutions; this is a novel way to study fuzzy relation equations. Such point wise solutions are studied on Łukasiewicz, Product and Gödel t-norm based residuated lattices on the real unit interval.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, Research group: Computer Science and Applied Logics
Contributors: Turunen, E.
Number of pages: 7
Pages: 351-357
Publication date: 1 Oct 2020
Peer-reviewed: Yes

Publication information

Journal: Information Sciences
Volume: 536
ISSN (Print): 0020-0255
Original language: English
ASJC Scopus subject areas: Software, Control and Systems Engineering, Theoretical Computer Science, Computer Science Applications, Information Systems and Management, Artificial Intelligence
Keywords: Fuzzy relation equation, Residuated lattice, T-norm
URLs: 
Source: Scopus
Source ID: 85085840362

Research output: Contribution to journalArticleScientificpeer-review

Using Deep Learning for price prediction by exploiting stationary limit order book features

The recent surge in Deep Learning (DL) research of the past decade has successfully provided solution to many difficult problems. The field of Quantitative analysis has been slowly adapting the new methods to its problems, but due to problems such as the non-stationary nature of financial data, significant challenges must be overcome before DL is fully utilized. In this work a new method to construct stationary features is proposed such that allows DL models to be applied effectively. These features are thoroughly tested on the task of predicting mid price movements of the Limit Order Book. Several DL models are evaluated such as recurrent Long Short Term Memory (LSTM) networks and Convolutional Neural Networks (CNN). Finally a novel model that combines the ability of the CNN to extract useful features and the ability of LSTMs’ to analyse time series, is proposed and evaluated. The combined model is able to outperform the individual LSTM and CNN models in the prediction horizons that are tested.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, Aristotle University of Thessaloniki, University of Milan Bicocca, Department of Informatics, Aarhus Universitet
Contributors: Tsantekidis, A., Passalis, N., Tefas, A., Kanniainen, J., Gabbouj, M., Iosifidis, A.
Publication date: 1 Aug 2020
Peer-reviewed: Yes

Publication information

Journal: Applied Soft Computing Journal
Volume: 93
Article number: 106401
ISSN (Print): 1568-4946
Original language: English
ASJC Scopus subject areas: Software
Keywords: Deep Learning, Limit order book, Price forecasting, Stationary features

Bibliographical note

EXT="Tefas, Anastasios"
EXT="Iosifidis, Alexandros"

Source: Scopus
Source ID: 85084845392

Research output: Contribution to journalArticleScientificpeer-review

On the zeros of the partial Hosoya polynomial of graphs

The partial Hosoya polynomial (or briefly the partial H-polynomial) can be used to construct the well-known Hosoya polynomial. The ith coefficient of this polynomial, defined for an arbitrary vertex u of a graph G, is the number of vertices at distance i from u. The aim of this paper is to determine the partial H-polynomial of several well-known graphs and, then, to investigate the location of their zeros. To pursue, we characterize the structure of graphs with the minimum and the maximum modulus of the zeros of partial H-polynomial. Finally, we define another graph polynomial of the partial H-polynomial, see [9]. Also, we determine the unique positive root of this polynomial for particular graphs.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, Shahid Rajaee Teacher Training University, Swiss Distance University of Applied Sciences, Institute for Bioinformatics and Translational Research, Nankai University, Tianjin Polytechnic University, Central South University China, Aalto University, Peking University, Mathematics Faculty of Information Technology and Communication Sciences
Contributors: Ghorbani, M., Dehmer, M., Cao, S., Feng, L., Tao, J., Emmert-Streib, F.
Number of pages: 17
Pages: 199-215
Publication date: 1 Jul 2020
Peer-reviewed: Yes

Publication information

Journal: Information Sciences
Volume: 524
ISSN (Print): 0020-0255
Original language: English
ASJC Scopus subject areas: Software, Control and Systems Engineering, Theoretical Computer Science, Computer Science Applications, Information Systems and Management, Artificial Intelligence
Keywords: Cut-vertex, Distance, Hosoya polynomial, Polynomial roots
Source: Scopus
Source ID: 85083078026

Research output: Contribution to journalArticleScientificpeer-review

Gaussian mixture models for signal mapping and positioning

Maps of RSS from a wireless transmitter can be used for positioning or for planning wireless infrastructure. The RSS values measured at a single point are not always the same, but follow some distribution, which vary from point to point. In existing approaches in the literature this variation is neglected or its mapping requires making many measurements at every point, which makes the measurement collection very laborious. We propose to use GMs for modeling joint distributions of the position and the RSS value. The proposed model is more versatile than methods found in the literature as it models the joint distribution of RSS measurements and the location space. This allows us to model the distributions of RSS values in every point of space without making many measurement in every point. In addition, GMs allow us to compute conditional probabilities and posteriors of position in closed form. The proposed models can model any RSS attenuation pattern, which is useful for positioning in multifloor buildings. Our tests with WLAN signals show that positioning with the proposed algorithm provides accurate position estimates. We conclude that the proposed algorithm can provide useful information about distributions of RSS values for different applications.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, Research group: Automation and Systems Theory, Aalto University, University of Liverpool, Universidad Antonio de Nebrija, Uppsala University
Contributors: Raitoharju, M., García-Fernández, F., Hostettler, R., Piché, R., Särkkä, S.
Publication date: 1 Mar 2020
Peer-reviewed: Yes
Early online date: 10 Oct 2019

Publication information

Journal: Signal Processing
Volume: 168
Article number: 107330
ISSN (Print): 0165-1684
Original language: English
ASJC Scopus subject areas: Control and Systems Engineering, Software, Signal Processing, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering
Keywords: Gaussian mixtures, Indoor positioning, RSS, Signal mapping, Statistical modeling
URLs: 
Source: Scopus
Source ID: 85073693932

Research output: Contribution to journalArticleScientificpeer-review

A custom processor for protocol-independent packet parsing

Networking devices such as switches and routers have traditionally had fixed functionality. They have the logic for the union of network protocols matching the application and market segment for which they have been designed. Possibility of adding new functionality is limited. One of the aims of Software Defined Networking is to make packet processing devices programmable. This provides for innovation and rapid deployment of novel networking protocols. The first step in processing of packets is packet parsing. In this paper, we present a custom processor for packet parsing. The parser is protocol-independent and can be programmed to parse any sequence of headers. It does so without the use of a Ternary Content Addressable Memory. As a result, the area and power consumption are noticeably smaller than in the state of the art. Moreover, its output is the same as that of the parser used in the Reconfigurable Match Tables (RMT). With an area no more than that of parsers in the RMT architecture, it sustains aggregate throughput of 3.4 Tbps in the worst case which is an improvement by a factor of 5.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Electrical Engineering, Research area: Computer engineering, University of Bologna
Contributors: Zolfaghari, H., Rossi, D., Nurmi, J.
Number of pages: 11
Publication date: 1 Feb 2020
Peer-reviewed: Yes
Early online date: 2019

Publication information

Journal: Microprocessors and Microsystems
Volume: 72
ISSN (Print): 0141-9331
Original language: English
ASJC Scopus subject areas: Software, Hardware and Architecture, Computer Networks and Communications, Artificial Intelligence
Keywords: Advanced program control, Packet parsing, Programmable data plane, Software defined networking
Source: Scopus
Source ID: 85074246120

Research output: Contribution to journalArticleScientificpeer-review

Anthropometric clothing measurements from 3D body scans

We propose a full processing pipeline to acquire anthropometric measurements from 3D measurements. The first stage of our pipeline is a commercial point cloud scanner. In the second stage, a pre-defined body model is fitted to the captured point cloud. We have generated one male and one female model from the SMPL library. The fitting process is based on non-rigid iterative closest point algorithm that minimizes overall energy of point distance and local stiffness energy terms. In the third stage, we measure multiple circumference paths on the fitted model surface and use a nonlinear regressor to provide the final estimates of anthropometric measurements. We scanned 194 male and 181 female subjects, and the proposed pipeline provides mean absolute errors from 2.5 to 16.0 mm depending on the anthropometric measurement.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, Research group: Vision, NOMO Technologies Ltd
Contributors: Yan, S., Wirta, J., Kämäräinen, J.
Number of pages: 11
Publication date: 2020
Peer-reviewed: Yes

Publication information

Journal: Machine Vision and Applications
Volume: 31
Issue number: 1-2
Article number: 7
ISSN (Print): 0932-8092
Original language: English
ASJC Scopus subject areas: Software, Hardware and Architecture, Computer Vision and Pattern Recognition, Computer Science Applications
Keywords: 3D body model, Anthropometric measurement, Non-rigid ICP
Source: Scopus
Source ID: 85078296322

Research output: Contribution to journalArticleScientificpeer-review

Shearlet Transform-Based Light Field Compression under Low Bitrates

Light field (LF) acquisition devices capture spatial and angular information of a scene. In contrast with traditional cameras, the additional angular information enables novel post-processing applications, such as 3D scene reconstruction, the ability to refocus at different depth planes, and synthetic aperture. In this paper, we present a novel compression scheme for LF data captured using multiple traditional cameras. The input LF views were divided into two groups: key views and decimated views. The key views were compressed using the multi-view extension of high-efficiency video coding (MV-HEVC) scheme, and decimated views were predicted using the shearlet-transform-based prediction (STBP) scheme. Additionally, the residual information of predicted views was also encoded and sent along with the coded stream of key views. The proposed scheme was evaluated over a benchmark multi-camera based LF datasets, demonstrating that incorporating the residual information into the compression scheme increased the overall peak signal to noise ratio (PSNR) by 2 dB. The proposed compression scheme performed significantly better at low bit rates compared to anchor schemes, which have a better level of compression efficiency in high bit-rate scenarios. The sensitivity of the human vision system towards compression artifacts, specifically at low bit rates, favors the proposed compression scheme over anchor schemes.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Research group: 3D MEDIA, Computing Sciences, Mid Sweden University, Sundsvall
Contributors: Ahmad, W., Vagharshakyan, S., Sjostrom, M., Gotchev, A., Bregovic, R., Olsson, R.
Number of pages: 12
Pages: 4269-4280
Publication date: 2020
Peer-reviewed: Yes

Publication information

Journal: IEEE Transactions on Image Processing
Volume: 29
ISSN (Print): 1057-7149
Original language: English
ASJC Scopus subject areas: Software, Computer Graphics and Computer-Aided Design
Keywords: Light field (LF) coding, multi-view extension of high-efficiency video coding (MV-HEVC), multiple camera system (MCS) coding, shearlet
Source: Scopus
Source ID: 85079506505

Research output: Contribution to journalArticleScientificpeer-review

Validating effectiveness of safety requirements' compliance evaluation in process assessments

Safety is the primary concern when developing systems containing software in the nuclear power domain. Process assessments are used to ensure quality of the development processes for safety-critical systems. Regulators of the nuclear power industry have increased requirements concerning the systems development processes. Now, process assessments are integrated in the qualification of the systems and are expected to provide information not only based on the assessment model but also about the domain-specific requirements. Therefore, a specific activity, compliance evaluation, was inserted into the assessment process to provide detailed information that supports analysis of the compliance to the domain standards. Compliance evaluation utilizes assessment findings to create evidence of the relevant domain-specific requirements. The main purpose of this study is to validate effectiveness of compliance evaluation by analyzing assessment findings and their relation to the requirements of a safety-critical domain. The analysis is based on representing the data in compliance evaluation reports as binary relations. The results of this analysis indicate that process assessment findings are also relevant when evaluating compliance to other sets of requirements. The results can significantly support the trustworthiness of the process assessment method and ensure effective use of process assessments.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, Research group: Software Engineering and Intelligent Systems, Research group: Data-analytics and Optimization, Finnish Software Measurement Association
Contributors: Varkoi, T., Mäkinen, T., Cameron, F., Nevalainen, R.
Number of pages: 16
Publication date: 2020
Peer-reviewed: Yes
Early online date: 2019

Publication information

Journal: Journal of Software: Evolution and Process
Volume: 32
Issue number: 3
Article number: e2177
ISSN (Print): 2047-7473
Original language: English
ASJC Scopus subject areas: Software
Keywords: Nuclear SPICE, process assessment, safety, systems engineering

Bibliographical note

EXT="Varkoi, Timo"
EXT="Nevalainen, Risto"

Source: Scopus
Source ID: 85080987236

Research output: Contribution to journalArticleScientificpeer-review

Censor-Based Cooperative Multi-Antenna Spectrum Sensing with Imperfect Reporting Channels

The present contribution proposes a spectrally efficient censor-based cooperative spectrum sensing (C-CSS) approach in a sustainable cognitive radio network that consists of multiple antenna nodes and experiences imperfect sensing and reporting channels. In this context, exact analytic expressions are first derived for the corresponding probability of detection, probability of false alarm, and secondary throughput, assuming that each secondary user (SU) sends its detection outcome to a fusion center only when it has detected a primary signal. Capitalizing on the findings of the analysis, the effects of critical measures, such as the detection threshold, the number of SUs, and the number of employed antennas, on the overall system performance are also quantified. In addition, the optimal detection threshold for each antenna based on the Neyman-Pearson criterion is derived and useful insights are developed on how to maximize the system throughput with a reduced number of SUs. It is shown that the C-CSS approach provides two distinct benefits compared with the conventional sensing approach, i.e., without censoring: i) the sensing tail problem, which exists in imperfect sensing environments, can be mitigated; and ii) less SUs are ultimately required to obtain higher secondary throughput, rendering the system more sustainable.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Research group: Wireless Communications and Positioning, Electrical Engineering, Taiyuan University of Science and Technology, University of Waterloo, Khalifa University, University of Surrey, University of London, Simon Fraser University
Contributors: Li, M., Alhussein, O., Sofotasios, P. C., Muhaidat, S., Yoo, P. D., Liang, J., Wang, A.
Number of pages: 13
Pages: 48-60
Publication date: 2020
Peer-reviewed: Yes

Publication information

Journal: IEEE Transactions on Sustainable Computing
Volume: 5
Issue number: 1
ISSN (Print): 2377-3782
Original language: English
ASJC Scopus subject areas: Computational Theory and Mathematics, Hardware and Architecture, Software, Renewable Energy, Sustainability and the Environment, Control and Optimization
Keywords: censoring, cooperative spectrum sensing, energy detection, energy efficiency, imperfect reporting channels, multi-antenna systems, Sustainble computing
Source: Scopus
Source ID: 85081759371

Research output: Contribution to journalArticleScientificpeer-review

Compressive sensed video recovery via iterative thresholding with random transforms

The authors consider the problem of compressive sensed video recovery via iterative thresholding algorithm. Traditionally, it is assumed that some fixed sparsifying transform is applied at each iteration of the algorithm. In order to improve the recovery performance, at each iteration the thresholding could be applied for different transforms in order to obtain several estimates for each pixel. Then the resulting pixel value is computed based on obtained estimates using simple averaging. However, calculation of the estimates leads to significant increase in reconstruction complexity. Therefore, the authors propose a heuristic approach, where at each iteration only one transform is randomly selected from some set of transforms. First, they present simple examples, when block-based 2D discrete cosine transform is used as the sparsifying transform, and show that the random selection of the block size at each iteration significantly outperforms the case when fixed block size is used. Second, building on these simple examples, they apply the proposed approach when video block-matching and 3D filtering (VBM3D) is used for the thresholding and show that the random transform selection within VBM3D allows to improve the recovery performance as compared with the recovery based on VBM3D with fixed transform.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, Research group: Computational Imaging-CI, ITMO University, Linköping University, University of Oulu
Contributors: Belyaev, E., Codreanu, M., Juntti, M., Egiazarian, K.
Number of pages: 14
Pages: 1187-1200
Publication date: 2020
Peer-reviewed: Yes

Publication information

Journal: IET Image Processing
Volume: 14
Issue number: 6
ISSN (Print): 1751-9659
Original language: English
ASJC Scopus subject areas: Software, Signal Processing, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering

Bibliographical note

EXT="Belyaev, Evgeny"

Source: Scopus
Source ID: 85084175769

Research output: Contribution to journalArticleScientificpeer-review

On the diffuseness of technical debt items and accuracy of remediation time when using SonarQube

Context. Among the static analysis tools available, SonarQube is one of the most used. SonarQube detects Technical Debt (TD) items—i.e., violations of coding rules—and then estimates TD as the time needed to remedy TD items. However, practitioners are still skeptical about the accuracy of remediation time estimated by the tool. Objective. In this paper, we analyze both diffuseness of TD items and accuracy of remediation time, estimated by SonarQube, to fix TD items on a set of 21 open-source Java projects. Method. We designed and conducted a case study where we asked 81 junior developers to fix TD items and reduce the TD of 21 projects. Results. We observed that TD items are diffused in the analyzed projects and most items are code smells. Moreover, the results point out that the remediation time estimated by SonarQube is inaccurate and, as compared to the actual time spent to fix TD items, is in most cases overestimated. Conclusions. The results of our study are promising for practitioners and researchers. The former can make more aware decisions during project execution and resource management, the latter can use this study as a starting point for improving TD estimation models.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, Universita degli Studi di Bari, LUT University
Contributors: Baldassarre, M. T., Lenarduzzi, V., Romano, S., Saarimäki, N.
Number of pages: 18
Publication date: 2020
Peer-reviewed: Yes

Publication information

Journal: Information and Software Technology
Volume: 128
Article number: 106377
ISSN (Print): 0950-5849
Original language: English
ASJC Scopus subject areas: Software, Information Systems, Computer Science Applications
Keywords: Case study, Effort estimation, Remediation time, Sonarqube, Technical debt

Bibliographical note

EXT="Lenarduzzi, Valentina"

Source: Scopus
Source ID: 85088664918

Research output: Contribution to journalArticleScientificpeer-review

FinnForest dataset: A forest landscape for visual SLAM

This paper presents a novel challenging dataset that offers a new landscape of testing material for mobile robotics, autonomous driving research, and forestry operation. In contrast to common urban structures, we explore an unregulated natural environment to exemplify sub-urban and forest environment. The sequences provide two-natured data where each place is visited in summer and winter conditions. The vehicle used for recording is equipped with a sensor rig that constitutes four RGB cameras, an Inertial Measurement Unit, and a Global Navigation Satellite System receiver. The sensors are synchronized based on non-drifting timestamps. The dataset provides trajectories of varying complexity both for the state of the art visual odometry approaches and visual simultaneous localization and mapping algorithms. The full dataset and toolkits are available for download at: http://urn.fi/urn:nbn:fi:att:9b8157a7-1e0f-47c2-bd4e-a19a7e952c0d. As an alternative, you can browse for the dataset using the article title at: http://etsin.fairdata.fi.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, Research group: 3D MEDIA, JC Inertial Oy
Contributors: Ali, I., Durmush, A., Suominen, O., Yli-Hietanen, J., Peltonen, S., Collin, J., Gotchev, A.
Number of pages: 13
Publication date: 2020
Peer-reviewed: Yes

Publication information

Journal: ROBOTICS AND AUTONOMOUS SYSTEMS
Volume: 132
Article number: 103610
ISSN (Print): 0921-8890
Original language: English
ASJC Scopus subject areas: Control and Systems Engineering, Software, Mathematics(all), Computer Science Applications
Keywords: Autonomous driving, Computer vision, Dataset, Field robotics, Forest, Localization, Mapping, Mobile robotics, Navigation, SLAM, Stereo, Visual odometry
Electronic versions: 
Source: Scopus
Source ID: 85089744434

Research output: Contribution to journalArticleScientificpeer-review

Does code quality affect pull request acceptance? An empirical study

Background: Pull requests are a common practice for making contributions and reviewing them in both open-source and industrial contexts.

Objective: Our goal is to understand whether quality flaws such as code smells, anti-patterns, security vulnerabilities, and coding style violations in a pull request's code affect the chance of its acceptance when reviewed by a maintainer of the project.

Method: We conducted a case study among 28 Java open-source projects, analyzing the presence of 4.7 M code quality flaws in 36 K pull requests. We analyzed further correlations by applying logistic regression and six machine learning techniques. Moreover, we manually validated 10% of the pull requests to get further qualitative insights on the importance of quality issues in cases of acceptance and rejection.

Results: Unexpectedly, quality flaws measured by PMD turned out not to affect the acceptance of a pull request at all. As suggested by other works, other factors such as the reputation of the maintainer and the importance of the delivered feature might be more important than other qualities in terms of pull request acceptance.

Conclusions:. Researchers have already investigated the influence of the developers’ reputation and the pull request acceptance. This is the first work investigating code style violations and specifically PMD rules. We recommend that researchers further investigate this topic to understand if different measures or different tools could provide some useful measures.

General information

Publication status: E-pub ahead of print
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, LUT University
Contributors: Lenarduzzi, V., Nikkola, V., Saarimäki, N., Taibi, D.
Number of pages: 14
Publication date: 2020
Peer-reviewed: Yes

Publication information

Journal: Journal of Systems and Software
Volume: 171
Article number: 110806
ISSN (Print): 0164-1212
Original language: English
ASJC Scopus subject areas: Software, Information Systems, Hardware and Architecture
Keywords: Machine learning, PMD rules, Pull requests

Bibliographical note

EXT="Lenarduzzi, Valentina"
INT=comp,"Nikkola, Vili"

Source: Scopus
Source ID: 85090024069

Research output: Contribution to journalArticleScientificpeer-review

Multimodal subspace support vector data description

In this paper, we propose a novel method for projecting data from multiple modalities to a new subspace optimized for one-class classification. The proposed method iteratively transforms the data from the original feature space of each modality to a new common feature space along with finding a joint compact description of data coming from all the modalities. For data in each modality, we define a separate transformation to map the data from the corresponding feature space to the new optimized subspace by exploiting the available information from the class of interest only. We also propose different regularization strategies for the proposed method and provide both linear and non-linear formulations. The proposed Multimodal Subspace Support Vector Data Description outperforms all the competing methods using data from a single modality or fusing data from all modalities in four out of five datasets.

General information

Publication status: E-pub ahead of print
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, Research group: Multimedia Research Group - MRG, Finnish Environment Institute, Aarhus Universitet
Contributors: Sohrab, F., Raitoharju, J., Iosifidis, A., Gabbouj, M.
Number of pages: 13
Publication date: 2020
Peer-reviewed: Yes

Publication information

Journal: Pattern Recognition
Volume: 110
Article number: 107648
ISSN (Print): 0031-3203
Original language: English
ASJC Scopus subject areas: Software, Signal Processing, Computer Vision and Pattern Recognition, Artificial Intelligence
Keywords: Feature transformation, Multimodal data, One-class classification, Subspace learning, Support vector data description

Bibliographical note

EXT="Iosifidis, Alexandros"

Source: Scopus
Source ID: 85090954677

Research output: Contribution to journalArticleScientificpeer-review

Bayesian receiver operating characteristic metric for linear classifiers

We propose a novel classifier accuracy metric: the Bayesian Area Under the Receiver Operating Characteristic Curve (CBAUC). The method estimates the area under the ROC curve and is related to the recently proposed Bayesian Error Estimator. The metric can assess the quality of a classifier using only the training dataset without the need for computationally expensive cross-validation. We derive a closed-form solution of the proposed accuracy metric for any linear binary classifier under the Gaussianity assumption, and study the accuracy of the proposed estimator using simulated and real-world data. These experiments confirm that the closed-form CBAUC is both faster and more accurate than conventional AUC estimators.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Research group: Computational Systems Biology, Computing Sciences, AI Virtanen Institute for Molecular Sciences, University of Eastern Finland
Contributors: Hassan, S. S., Huttunen, H., Niemi, J., Tohka, J.
Number of pages: 8
Pages: 52-59
Publication date: 1 Dec 2019
Peer-reviewed: Yes

Publication information

Journal: Pattern Recognition Letters
Volume: 128
ISSN (Print): 0167-8655
Ratings: 
  • Scopus rating (2019): CiteScore 6.3 SJR 0.848 SNIP 2.021
Original language: English
ASJC Scopus subject areas: Software, Signal Processing, Computer Vision and Pattern Recognition, Artificial Intelligence
Keywords: Bayesian error estimation, Classification, Receiver operating characteristic curve

Bibliographical note

EXT="Tohka, Jussi"

Source: Scopus
Source ID: 85071016385

Research output: Contribution to journalArticleScientificpeer-review

Software architecture design in global software development: An empirical study

In Global Software Development (GSD), the additional complexity caused by global distance requires processes to ease collaboration difficulties, reduce communication overhead, and improve control. How development tasks are broken down, shared and prioritized is key to project success. While the related literature provides some support for architects involved in GSD, guidelines are far from complete. This paper presents a GSD Architectural Practice Framework reflecting the views of software architects, all of whom are working in a distributed setting. In-depth interviews with architects from seven different GSD organizations revealed a complex set of challenges and practices. We found that designing software for distributed teams requires careful selection of practices that support understanding and adherence to defined architectural plans across sites. Teams used Scrum which aided communication, and Continuous Integration which helped solve synchronization issues. However, teams deviated from the design, causing conflicts. Furthermore, there needs to be a balance between the self-organizing Scrum team methodology and the need to impose architectural design decisions across distributed sites. The research presented provides an enhanced understanding of architectural practices in GSD companies. Our GSD Architectural Practice Framework gives practitioners a cohesive set of warnings, which for the most part, are matched by recommendations.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, Research area: Software engineering, University of Limerick
Contributors: Sievi-Korte, O., Richardson, I., Beecham, S.
Publication date: 1 Dec 2019
Peer-reviewed: Yes

Publication information

Journal: Journal of Systems and Software
Volume: 158
Article number: 110400
ISSN (Print): 0164-1212
Ratings: 
  • Scopus rating (2019): CiteScore 7.8 SJR 0.772 SNIP 2.387
Original language: English
ASJC Scopus subject areas: Software, Information Systems, Hardware and Architecture
Keywords: Empirical study, Global software development, GSD, GSE, Scrum, Software architecture
URLs: 
Source: Scopus
Source ID: 85072283236

Research output: Contribution to journalArticleScientificpeer-review

Programming languages for data-Intensive HPC applications: A systematic mapping study

A major challenge in modelling and simulation is the need to combine expertise in both software technologies and a given scientific domain. When High-Performance Computing (HPC) is required to solve a scientific problem, software development becomes a problematic issue. Considering the complexity of the software for HPC, it is useful to identify programming languages that can be used to alleviate this issue. Because the existing literature on the topic of HPC is very dispersed, we performed a Systematic Mapping Study (SMS) in the context of the European COST Action cHiPSet. This literature study maps characteristics of various programming languages for data-intensive HPC applications, including category, typical user profiles, effectiveness, and type of articles. We organised the SMS in two phases. In the first phase, relevant articles are identified employing an automated keyword-based search in eight digital libraries. This lead to an initial sample of 420 papers, which was then narrowed down in a second phase by human inspection of article abstracts, titles and keywords to 152 relevant articles published in the period 2006–2018. The analysis of these articles enabled us to identify 26 programming languages referred to in 33 of relevant articles. We compared the outcome of the mapping study with results of our questionnaire-based survey that involved 57 HPC experts. The mapping study and the survey revealed that the desired features of programming languages for data-intensive HPC applications are portability, performance and usability. Furthermore, we observed that the majority of the programming languages used in the context of data-intensive HPC applications are text-based general-purpose programming languages. Typically these have a steep learning curve, which makes them difficult to adopt. We believe that the outcome of this study will inspire future research and development in programming languages for data-intensive HPC applications.

General information

Publication status: E-pub ahead of print
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, Research group: MMDM, Universidade Nova de Lisboa, University of Torino, Der Technischen Universitat Wien Fakultät für Elektrotechnik und Informationstechnik, University of Stirling, Universidade de Lisboa, University of Latvia, NOVA University of Lisbon, University of Amsterdam, Aristotle University of Thessaloniki, Linköping University, Queen's University, Belfast, Northern Ireland, Linnaeus University, Kalmar, Instituto Superior de Engenharia de Lisboa
Contributors: Amaral, V., Norberto, B., Goulão, M., Aldinucci, M., Benkner, S., Bracciali, A., Carreira, P., Celms, E., Correia, L., Grelck, C., Karatza, H., Kessler, C., Kilpatrick, P., Martiniano, H., Mavridis, I., Pllana, S., Respício, A., Simão, J., Veiga, L., Visa, A.
Number of pages: 17
Publication date: 8 Nov 2019
Peer-reviewed: Yes

Publication information

Journal: Parallel Computing
Volume: 91
Article number: 102584
ISSN (Print): 0167-8191
Ratings: 
  • Scopus rating (2019): CiteScore 2.9 SJR 0.346 SNIP 1.104
Original language: English
ASJC Scopus subject areas: Software, Theoretical Computer Science, Hardware and Architecture, Computer Networks and Communications, Computer Graphics and Computer-Aided Design, Artificial Intelligence
Keywords: Big data, Data-intensive applications, Domain-Specific language (DSL), General-Purpose language (GPL), High performance computing (HPC), Programming languages, Systematic mapping study (SMS)
Source: Scopus
Source ID: 85076201522

Research output: Contribution to journalArticleScientificpeer-review

Feasibility of FPGA accelerated IPsec on cloud

Hardware acceleration for famous VPN solution, IPsec, has been widely researched already. Still it is not fully covered and the increasing latency, throughput, and feature requirements need further evaluation. We propose an IPsec accelerator architecture in an FPGA and explain the details that need to be considered for a production ready design. This research considers the IPsec packet processing without IKE to be offloaded on an FPGA in an SDN network. Related work performance rates in 64 byte packet size for throughput is 1–2 Gbps with 0.2 ms latency in software, and 1–4 Gbps with unknown latencies for hardware solutions. Our proposed architecture is capable to host 1000 concurrent tunnels and have 10 Gbps throughput with only 10 µs latency in our test network. Therefore the proposed design is efficient even with voice or video encryption. The architecture is especially designed for data centers and locations with vast number of concurrent IPsec tunnels. The research confirms that FPGA based hardware acceleration increases performance and is feasible to integrate with the other server infrastructure.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, Research area: Information security, Baseband ASIC R&D, Nokia Siemens Networks
Contributors: Vajaranta, M., Oinonen, A., Hämäläinen, T. D., Viitamäki, V., Markunmäki, J., Kulmala, A.
Publication date: 1 Nov 2019
Peer-reviewed: Yes

Publication information

Journal: Microprocessors and Microsystems
Volume: 71
Article number: 102861
ISSN (Print): 0141-9331
Ratings: 
  • Scopus rating (2019): CiteScore 3 SJR 0.303 SNIP 0.879
Original language: English
ASJC Scopus subject areas: Software, Hardware and Architecture, Computer Networks and Communications, Artificial Intelligence
Keywords: Accelerator, IPsec, Offloading, SDN

Bibliographical note

EXT="Viitamäki, Vili"
EXT="Kulmala, Ari"

Source: Scopus
Source ID: 85070320729

Research output: Contribution to journalArticleScientificpeer-review

Action-Oriented Programming Model: Collective Executions and Interactions in the Fog

Today's dominant design for the Internet of Things (IoT) is a Cloud-based system, where devices transfer their data to a back-end and in return receive instructions on how to act. This view is challenged when delays caused by communication with the back-end become an obstacle for IoT applications with, for example, stringent timing constraints. In contrast, Fog Computing approaches, where devices communicate and orchestrate their operations collectively and closer to the origin of data, lack adequate tools for programming secure interactions between humans and their proximate devices at the network edge. This paper fills the gap by applying Action-Oriented Programming (AcOP) model for this task. While originally the AcOP model was proposed for Cloud-based infrastructures, presently it is re-designed around the notion of coalescence and disintegration, which enable the devices to collectively and autonomously execute their operations in the Fog by serving humans in a peer-to-peer fashion. The Cloud's role has been minimized—it is being leveraged as a development and deployment platform.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, Electrical Engineering, Department of Computer Science, University of Helsinki, National Research University Higher School of Economics
Contributors: Mäkitalo, N., Aaltonen, T., Raatikainen, M., Ometov, A., Andreev, S., Koucheryavy, Y., Mikkonen, T.
Publication date: 1 Nov 2019
Peer-reviewed: Yes

Publication information

Journal: Journal of Systems and Software
Volume: 157
Article number: 110391
ISSN (Print): 0164-1212
Ratings: 
  • Scopus rating (2019): CiteScore 7.8 SJR 0.772 SNIP 2.387
Original language: English
ASJC Scopus subject areas: Software, Information Systems, Hardware and Architecture
Keywords: Edge computing, Fog Computing, Programming model, Proximity-based computing, Socio-technical systems
Electronic versions: 

Bibliographical note

EXT="Mäkitalo, Niko"
EXT="Mikkonen, Tommi"

Source: Scopus
Source ID: 85070882337

Research output: Contribution to journalArticleScientificpeer-review

An icon that everyone wants to click: How perceived aesthetic qualities predict app icon successfulness

Mobile app markets have been touted as fastest growing marketplaces in the world. Every day thousands of apps are published to join millions of others on app stores. The competition for top grossing apps and market visibility is fierce. The way an app is visually represented can greatly contribute to the amount of attention an icon receives and to its consequent commercial performance. Therefore, the icon of the app is of crucial importance as it is the first point of contact with the potential user/customer amidst the flood of information. Those apps that fail to arouse attention through their icons danger their commercial performance in the market where consumers browse past hundreds of icons daily. Using semantic differential scale (22 adjective pairs), we investigate the relationship between consumer perceptions of app icons and icon successfulness, measured by 1)overall evaluation of the icon, 2)willingness to click the icon, 3)willingness to download the imagined app and, 4)willingness to purchase the app. The study design was a vignette study with random participant (n = 569)assignment to evaluate 4 icons (n = 2276)from a total of pre-selected 68 game app icons across 4 categories (concrete, abstract, character and text). Results show that consumers are more likely to interact with app icons that are aesthetically pleasing and convey good quality. Particularly, app icons that are perceived unique, realistic and stimulating lead to more clicks, downloads and purchases.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, Gamification Group, Tampere University, University of Turku
Contributors: Jylhä, H., Hamari, J.
Number of pages: 13
Pages: 73-85
Publication date: 1 Oct 2019
Peer-reviewed: Yes

Publication information

Journal: International Journal of Human Computer Studies
Volume: 130
ISSN (Print): 1071-5819
Ratings: 
  • Scopus rating (2019): CiteScore 5.8 SJR 0.756 SNIP 2.163
Original language: English
ASJC Scopus subject areas: Software, Human Factors and Ergonomics, Education, Engineering(all), Human-Computer Interaction, Hardware and Architecture
Keywords: Aesthetics, Digital marketing, Graphical user interfaces, Iconography, Mobile apps, Semantic differential
Electronic versions: 
Source: Scopus
Source ID: 85067993498

Research output: Contribution to journalArticleScientificpeer-review

DevOps in practice: A multiple case study of five companies

Context: DevOps is considered important in the ability to frequently and reliably update a system in operational state. DevOps presumes cross-functional collaboration and automation between software development and operations. DevOps adoption and implementation in companies is non-trivial due to required changes in technical, organisational and cultural aspects. Objectives: This exploratory study presents detailed descriptions of how DevOps is implemented in practice. The context of our empirical investigation is web application and service development in small and medium sized companies. Method: A multiple-case study was conducted in five different development contexts with successful DevOps implementations since its benefits, such as quick releases and minimum deployment errors, were achieved. Data was mainly collected through interviews with 26 practitioners and observations made at the companies. Data was analysed by first coding each case individually using a set of predefined themes and thereafter perform a cross-case synthesis. Results: Our analysis yielded some of the following results: (i) software development team attaining ownership and responsibility to deploy software changes in production is crucial in DevOps. (ii) toolchain usage and support in deployment pipeline activities accelerates the delivery of software changes, bug fixes and handling of production incidents. (ii) the delivery speed to production is affected by context factors, such as manual approvals by the product owner (iii) steep learning curve for new skills is experienced by both software developers and operations staff, who also have to cope with working under pressure. Conclusion: Our findings contributes to the overall understanding of DevOps concept, practices and its perceived impacts, particularly in small and medium sized companies. We discuss two practical implications of the results.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, University of Oulu, Aalto University, University of Helsinki
Contributors: Lwakatare, L. E., Kilamo, T., Karvonen, T., Sauvola, T., Heikkilä, V., Itkonen, J., Kuvaja, P., Mikkonen, T., Oivo, M., Lassenius, C.
Number of pages: 14
Pages: 217-230
Publication date: 1 Oct 2019
Peer-reviewed: Yes

Publication information

Journal: Information and Software Technology
Volume: 114
ISSN (Print): 0950-5849
Ratings: 
  • Scopus rating (2019): CiteScore 7.6 SJR 0.781 SNIP 2.555
Original language: English
ASJC Scopus subject areas: Software, Information Systems, Computer Science Applications
Keywords: Agile, Continuous deployment, Development, DevOps, Operations

Bibliographical note

EXT="Mikkonen, Tommi"

Source: Scopus
Source ID: 85068546035

Research output: Contribution to journalArticleScientificpeer-review

Automatic word count estimation from daylong child-centered recordings in various language environments using language-independent syllabification of speech

Automatic word count estimation (WCE) from audio recordings can be used to quantify the amount of verbal communication in a recording environment. One key application of WCE is to measure language input heard by infants and toddlers in their natural environments, as captured by daylong recordings from microphones worn by the infants. Although WCE is nearly trivial for high-quality signals in high-resource languages, daylong recordings are substantially more challenging due to the unconstrained acoustic environments and the presence of near- and far-field speech. Moreover, many use cases of interest involve languages for which reliable ASR systems or even well-defined lexicons are not available. A good WCE system should also perform similarly for low- and high-resource languages in order to enable unbiased comparisons across different cultures and environments. Unfortunately, the current state-of-the-art solution, the LENA system, is based on proprietary software and has only been optimized for American English, limiting its applicability. In this paper, we build on existing work on WCE and present the steps we have taken towards a freely available system for WCE that can be adapted to different languages or dialects with a limited amount of orthographically transcribed speech data. Our system is based on language-independent syllabification of speech, followed by a language-dependent mapping from syllable counts (and a number of other acoustic features) to the corresponding word count estimates. We evaluate our system on samples from daylong infant recordings from six different corpora consisting of several languages and socioeconomic environments, all manually annotated with the same protocol to allow direct comparison. We compare a number of alternative techniques for the two key components in our system: speech activity detection and automatic syllabification of speech. As a result, we show that our system can reach relatively consistent WCE accuracy across multiple corpora and languages (with some limitations). In addition, the system outperforms LENA on three of the four corpora consisting of different varieties of English. We also demonstrate how an automatic neural network-based syllabifier, when trained on multiple languages, generalizes well to novel languages beyond the training data, outperforming two previously proposed unsupervised syllabifiers as a feature extractor for WCE.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, Aalto University, Laboratoire de Sciences Cognitives et Psycholinguistique, Carnegie Mellon University, University of Manitoba, Max Planck Institute for Psycholinguistics, CONICET, Duke University
Contributors: Räsänen, O., Seshadri, S., Karadayi, J., Riebling, E., Bunce, J., Cristia, A., Metze, F., Casillas, M., Rosemberg, C., Bergelson, E., Soderstrom, M.
Number of pages: 18
Pages: 63-80
Publication date: 1 Oct 2019
Peer-reviewed: Yes

Publication information

Journal: Speech Communication
Volume: 113
ISSN (Print): 0167-6393
Ratings: 
  • Scopus rating (2019): CiteScore 4.2 SJR 0.554 SNIP 1.297
Original language: English
ASJC Scopus subject areas: Software, Modelling and Simulation, Communication, Language and Linguistics, Linguistics and Language, Computer Vision and Pattern Recognition, Computer Science Applications
Keywords: Automatic syllabification, Daylong recordings, Language acquisition, Noise robustness, Word count estimation
Electronic versions: 
Source: Scopus
Source ID: 85070952723

Research output: Contribution to journalArticleScientificpeer-review

Tunable VVC Frame Partitioning based on Lightweight Machine Learning

Block partition structure is a critical module in video coding scheme to achieve significant gap of compression performance. Under the exploration of the future video coding standard, named Versatile Video Coding (VVC), a new Quad Tree Binary Tree (QTBT) block partition structure has been introduced. In addition to the QT block partitioning defined in High Efficiency Video Coding (HEVC) standard, new horizontal and vertical BT partitions are enabled, which drastically increases the encoding time compared to HEVC. In this paper, we propose a lightweight and tunable QTBT partitioning scheme based on a Machine Learning (ML) approach. The proposed solution uses Random Forest classifiers to determine for each coding block the most probable partition modes. To minimize the encoding loss induced by misclassification, risk intervals for classifier decisions are introduced in the proposed solution. By varying the size of risk intervals, tunable trade-off between encoding complexity reduction and coding loss is achieved. The proposed solution implemented in the JEM-7.0 software offers encoding complexity reductions ranging from 30average for only 0.7% to 3.0% Bjxntegaard Delta Rate (BDBR) increase in Random Access (RA) coding configuration, with very slight overhead induced by Random Forest. The proposed solution based on Random Forest classifiers is also efficient to reduce the complexity of the Multi-Type Tree (MTT) partitioning scheme under the VTM-5.0 software, with complexity reductions ranging from 25% to 61% in average for only 0.4% to 2.2% BD-BR increase.

General information

Publication status: E-pub ahead of print
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, UBL, HTE/STR/MMP Gennevilliers
Contributors: Amestoy, T., Mercat, A., Hamidouche, W., Menard, D., Bergeron, C.
Publication date: 6 Sep 2019
Peer-reviewed: Yes

Publication information

Journal: IEEE Transactions on Image Processing
ISSN (Print): 1057-7149
Ratings: 
  • Scopus rating (2019): CiteScore 15.6 SJR 2.893 SNIP 4.182
Original language: English
ASJC Scopus subject areas: Software, Computer Graphics and Computer-Aided Design
Keywords: Complexity Reduction, JEM, Machine Learning, QTBT, Random Forest, Video Compression, VTM, VVC
Source: Scopus
Source ID: 85072159338

Research output: Contribution to journalArticleScientificpeer-review

Model checking and validity in propositional and modal inclusion logics

Propositional and modal inclusion logic are formalisms that belong to the family of logics based on team semantics. This article investigates the model checking and validity problems of these logics. We identify complexity bounds for both problems, covering both lax and strict team semantics. By doing so, we come close to finalizing the programme that aims to completely classify the complexities of the basic reasoning problems for modal and propositional dependence, independence and inclusion logics.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, Tampere University, Leibniz Universität Hannover, University of Helsinki, Hasselt University
Contributors: Hella, L., Kuusisto, A., Meier, A., Virtema, J.
Number of pages: 26
Pages: 605-630
Publication date: 1 Sep 2019
Peer-reviewed: Yes

Publication information

Journal: JOURNAL OF LOGIC AND COMPUTATION
Volume: 29
Issue number: 5
ISSN (Print): 0955-792X
Ratings: 
  • Scopus rating (2019): CiteScore 2.8 SJR 0.786 SNIP 1.481
Original language: English
ASJC Scopus subject areas: Software, Theoretical Computer Science, Arts and Humanities (miscellaneous), Hardware and Architecture, Logic
Keywords: complexity, Inclusion logic, model checking, team semantics, validity problem
Source: Scopus
Source ID: 85080893187

Research output: Contribution to journalArticleScientificpeer-review

Performance analysis of single-query 6-DoF camera pose estimation in self-driving setups

In this work, we consider the problem of single-query 6-DoF camera pose estimation, i.e. estimating the position and orientation of a camera by using reference images and a point cloud. We perform a systematic comparison of three state-of-the-art strategies for 6-DoF camera pose estimation: feature-based, photometric-based and mutual-information-based approaches. Two standard datasets with self-driving setups are used for experiments, and the performance of the studied methods is evaluated in terms of success rate, translation error and maximum orientation error. Building on the analysis of the results, we evaluate a hybrid approach that combines feature-based and mutual-information-based pose estimation methods to benefit from their complementary properties for pose estimation. Experiments show that (1) in cases with large appearance change between query and reference, the hybrid approach outperforms feature-based and mutual-information-based approaches by an average increment of 9.4% and 8.7% in the success rate, respectively; (2) in cases where query and reference images are captured at similar imaging conditions, the hybrid approach performs similarly as the feature-based approach, but outperforms both photometric-based and mutual-information-based approaches with a clear margin; (3) the feature-based approach is consistently more accurate than mutual-information-based and photometric-based approaches when at least 4 consistent matching points are found between the query and reference images.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, Universidad Industrial de Santander, Czech Technical University in Prague
Contributors: Fu, J., Pertuz, S., Matas, J., Kämäräinen, J.
Pages: 58-73
Publication date: Sep 2019
Peer-reviewed: Yes

Publication information

Journal: Computer Vision and Image Understanding
Volume: 186
ISSN (Print): 1077-3142
Ratings: 
  • Scopus rating (2019): CiteScore 8.7 SJR 1.453 SNIP 2.255
Original language: English
ASJC Scopus subject areas: Software, Signal Processing, Computer Vision and Pattern Recognition
Keywords: 3D point cloud, Camera pose estimation, Hybrid method, Mutual information, Photometric matching, Self driving car

Bibliographical note

EXT="Matas, Jiri"

Source: Scopus
Source ID: 85067195521

Research output: Contribution to journalArticleScientificpeer-review

Are architectural smells independent from code smells? An empirical study

Background. Architectural smells and code smells are symptoms of bad code or design that can cause different quality problems, such as faults, technical debt, or difficulties with maintenance and evolution. Some studies show that code smells and architectural smells often appear together in the same file. The correlation between code smells and architectural smells, however, is not clear yet; some studies on a limited set of projects have claimed that architectural smells can be derived from code smells, while other studies claim the opposite. Objective. The goal of this work is to understand whether architectural smells are independent from code smells or can be derived from a code smell or from one category of them. Method. We conducted a case study analyzing the correlations among 19 code smells, six categories of code smells, and four architectural smells. Results. The results show that architectural smells are correlated with code smells only in a very low number of occurrences and therefore cannot be derived from code smells. Conclusion. Architectural smells are independent from code smells, and therefore deserve special attention by researchers, who should investigate their actual harmfulness, and practitioners, who should consider whether and when to remove them.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, University Milano-Bicocca, Alten Italia
Contributors: Arcelli Fontana, F., Lenarduzzi, V., Roveda, R., Taibi, D.
Number of pages: 18
Pages: 139-156
Publication date: 1 Aug 2019
Peer-reviewed: Yes

Publication information

Journal: Journal of Systems and Software
Volume: 154
ISSN (Print): 0164-1212
Ratings: 
  • Scopus rating (2019): CiteScore 7.8 SJR 0.772 SNIP 2.387
Original language: English
ASJC Scopus subject areas: Software, Information Systems, Hardware and Architecture
Keywords: Architectural smells, Code smells, Empirical analysis, Technical debt
Source: Scopus
Source ID: 85064869442

Research output: Contribution to journalArticleScientificpeer-review

Hermitian normalized Laplacian matrix for directed networks

In this paper, we extend and generalize the spectral theory of undirected networks towards directed networks by introducing the Hermitian normalized Laplacian matrix for directed networks. In order to start, we discuss the Courant–Fischer theorem for the eigenvalues of Hermitian normalized Laplacian matrix. Based on the Courant–Fischer theorem, we obtain a similar result towards the normalized Laplacian matrix of undirected networks: for each i ∈ {1, 2,…, n}, any eigenvalue of Hermitian normalized Laplacian matrix λ i ∈ [0, 2]. Moreover, we prove some special conditions if 0, or 2 is an eigenvalue of the Hermitian normalized Laplacian matrix L(X). On top of that, we investigate the symmetry of the eigenvalues of L(X)and the edge-version for the eigenvalue interlacing result. Finally we present two expressions for the coefficients of the characteristic polynomial of the Hermitian normalized Laplacian matrix. As an outlook, we sketch some novel and intriguing problems to which our apparatus could generally be applied.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, Research group: Predictive Society and Data Analytics (PSDA), Guizhou University of Finance and Economics, University of Applied Sciences Upper Austria, Nankai University, Hall in Tyrol, Institute of Biosciences and Medical Technology
Contributors: Yu, G., Dehmer, M., Emmert-Streib, F., Jodlbauer, H.
Number of pages: 10
Pages: 175-184
Publication date: 1 Aug 2019
Peer-reviewed: Yes

Publication information

Journal: Information Sciences
Volume: 495
ISSN (Print): 0020-0255
Ratings: 
  • Scopus rating (2019): CiteScore 11.3 SJR 1.723 SNIP 2.688
Original language: English
ASJC Scopus subject areas: Software, Control and Systems Engineering, Theoretical Computer Science, Computer Science Applications, Information Systems and Management, Artificial Intelligence
Keywords: Characteristic polynomial, Courant–Fischer theorem, Directed networks, Eigenvalue interlacing inequality, Hermitian normalized Laplacian matrix
Source: Scopus
Source ID: 85065248406

Research output: Contribution to journalArticleScientificpeer-review

High-performance SIMD implementation of the lattice-Boltzmann method on the Xeon Phi processor

We present a high-performance implementation of the lattice-Boltzmann method (LBM) on the Knights Landing generation of Xeon Phi. The Knights Landing architecture includes 16GB of high-speed memory (MCDRAM) with a reported bandwidth of over 400 GB/s, and a subset of the AVX-512 single instruction multiple data (SIMD) instruction set. We explain five critical implementation aspects for high performance on this architecture: (1) the choice of appropriate LBM algorithm, (2) suitable data layout, (3) vectorization of the computation, (4) data prefetching, and (5) running our LBM simulations exclusively from the MCDRAM. The effects of these implementation aspects on the computational performance are demonstrated with the lattice-Boltzmann scheme involving the D3Q19 discrete velocity set and the TRT collision operator. In our benchmark simulations of fluid flow through porous media, using double-precision floating-point arithmetic, the observed performance exceeds 960 million fluid lattice site updates per second.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Physics, CSC - IT center for science, Abo Akad Univ, Abo Akademi University, Dept Phys, Jyväskylän yliopisto
Contributors: Robertsén, F., Mattila, K., Westerholm, J.
Number of pages: 16
Publication date: 10 Jul 2019
Peer-reviewed: Yes

Publication information

Journal: Concurrency Computation
Volume: 31
Issue number: 13
Article number: e5072
ISSN (Print): 1532-0626
Ratings: 
  • Scopus rating (2019): CiteScore 3.4 SJR 0.341 SNIP 0.944
Original language: English
ASJC Scopus subject areas: Software, Theoretical Computer Science, Computer Science Applications, Computer Networks and Communications, Computational Theory and Mathematics
Keywords: Lattice Boltzmann, prefetching, SIMD, Xeon Phi
Source: Scopus
Source ID: 85056764195

Research output: Contribution to journalArticleScientificpeer-review

Challenges of Multi-Factor Authentication for Securing Advanced IoT Applications

The unprecedented proliferation of smart devices together with novel communication, computing, and control technologies have paved the way for A-IoT. This development involves new categories of capable devices, such as high-end wearables, smart vehicles, and consumer drones aiming to enable efficient and collaborative utilization within the smart city paradigm. While massive deployments of these objects may enrich people's lives, unauthorized access to said equipment is potentially dangerous. Hence, highly secure human authentication mechanisms have to be designed. At the same time, human beings desire comfortable interaction with the devices they own on a daily basis, thus demanding authentication procedures to be seamless and user-friendly, mindful of contemporary urban dynamics. In response to these unique challenges, this work advocates for the adoption of multi-factor authentication for A-IoT, such that multiple heterogeneous methods - both well established and emerging - are combined intelligently to grant or deny access reliably. We thus discuss the pros and cons of various solutions as well as introduce tools to combine the authentication factors, with an emphasis on challenging smart city environments. We finally outline the open questions to shape future research efforts in this emerging field.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Electrical Engineering, National Research University Higher School of Economics, ITMO University, Electrical Engineering Department, University of California, Los Angeles (UCLA)
Contributors: Ometov, A., Petrov, V., Bezzateev, S., Andreev, S., Koucheryavy, Y., Gerla, M.
Number of pages: 7
Pages: 82-88
Publication date: 1 Mar 2019
Peer-reviewed: Yes

Publication information

Journal: IEEE Network
Volume: 33
Issue number: 2
ISSN (Print): 0890-8044
Ratings: 
  • Scopus rating (2019): CiteScore 21.6 SJR 2.773 SNIP 3.323
Original language: English
ASJC Scopus subject areas: Software, Information Systems, Hardware and Architecture, Computer Networks and Communications
Source: Scopus
Source ID: 85063775257

Research output: Contribution to journalArticleScientificpeer-review

Convolutional low-resolution fine-grained classification

Successful fine-grained image classification methods learn subtle details between visually similar (sub-)classes, but the problem becomes significantly more challenging if the details are missing due to low resolution. Encouraged by the recent success of Convolutional Neural Network (CNN) architectures in image classification, we propose a novel resolution-aware deep model which combines convolutional image super-resolution and convolutional fine-grained classification into a single model in an end-to-end manner. Extensive experiments on multiple benchmarks demonstrate that the proposed model consistently performs better than conventional convolutional networks on classifying fine-grained object classes in low-resolution images.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Signal Processing, Research group: Vision
Contributors: Cai, D., Chen, K., Qian, Y., Kämäräinen, J.
Pages: 166-171
Publication date: Mar 2019
Peer-reviewed: Yes
Early online date: 2017

Publication information

Journal: Pattern Recognition Letters
Volume: 119
ISSN (Print): 0167-8655
Ratings: 
  • Scopus rating (2019): CiteScore 6.3 SJR 0.848 SNIP 2.021
Original language: English
ASJC Scopus subject areas: Software, Signal Processing, Computer Vision and Pattern Recognition, Artificial Intelligence
Keywords: Deep learning, Fine-grained image classification, Super resolution convoluational neural networks
Source: Scopus
Source ID: 85032974725

Research output: Contribution to journalArticleScientificpeer-review

Analysis of an efficient parallel implementation of active-set Newton algorithm

This paper presents an analysis of an efficient parallel implementation of the active-set Newton algorithm (ASNA), which is used to estimate the nonnegative weights of linear combinations of the atoms in a large-scale dictionary to approximate an observation vector by minimizing the Kullback–Leibler divergence between the observation vector and the approximation. The performance of ASNA has been proved in previous works against other state-of-the-art methods. The implementations analysed in this paper have been developed in C, using parallel programming techniques to obtain a better performance in multicore architectures than the original MATLAB implementation. Also a hardware analysis is performed to check the influence of CPU frequency and number of CPU cores in the different implementations proposed. The new implementations allow ASNA algorithm to tackle real-time problems due to the execution time reduction obtained.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Signal Processing, Research group: Audio research group - ARG, Universitat Politècnica de València
Contributors: San Juan Sebastián, P., Virtanen, T., Garcia-Molla, V. M., Vidal, A. M.
Number of pages: 12
Pages: 1298-1309
Publication date: Mar 2019
Peer-reviewed: Yes
Early online date: 19 May 2018

Publication information

Journal: Journal of Supercomputing
Volume: 75
Issue number: 3
ISSN (Print): 0920-8542
Ratings: 
  • Scopus rating (2019): CiteScore 3.9 SJR 0.432 SNIP 1.181
Original language: English
ASJC Scopus subject areas: Software, Theoretical Computer Science, Information Systems, Hardware and Architecture
Keywords: Convex optimization, Multicore, Newton algorithm, Parallel computing, Sparse representation
Source: Scopus
Source ID: 85047129085

Research output: Contribution to journalArticleScientificpeer-review

Challenges and recommended practices for software architecting in global software development

Context: Global software development (GSD), although now a norm in the software industry, carries with it enormous challenges mostly regarding communication and coordination. Aforementioned challenges are highlighted when there is a need to transfer knowledge between sites, particularly when software artifacts assigned to different sites depend on each other. The design of the software architecture and associated task dependencies play a major role in reducing some of these challenges. Objective: The current literature does not provide a cohesive picture of how the distributed nature of software development is taken into account during the design phase: what to avoid, and what works in practice. The objective of this paper is to gain an understanding of software architecting in the context of GSD, in order to develop a framework of challenges and solutions that can be applied in both research and practice. Method: We conducted a systematic literature review (SLR) that synthesises (i) challenges which GSD imposes on software architecture design, and (ii) recommended practices to alleviate these challenges. Results: We produced a comprehensive set of guidelines for performing software architecture design in GSD based on 55 selected studies. Our framework comprises nine key challenges with 28 related concerns, and nine recommended practices, with 22 related concerns for software architecture design in GSD. These challenges and practices were mapped to a thematic conceptual model with the following concepts: Organization (Structure and Resources), Ways of Working (Architecture Knowledge Management, Change Management and Quality Management), Design Practices, Modularity and Task Allocation. Conclusion: The synthesis of findings resulted in a thematic conceptual model of the problem area, a mapping of the key challenges to practices, and a concern framework providing concrete questions to aid the design process in a distributed setting. This is a first step in creating more concrete architecture design practices and guidelines.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Pervasive Computing, Research area: Software engineering, University of Limerick
Contributors: Sievi-Korte, O., Beecham, S., Richardson, I.
Number of pages: 20
Pages: 234-253
Publication date: 1 Feb 2019
Peer-reviewed: Yes
Early online date: 2018

Publication information

Journal: Information and Software Technology
Volume: 106
ISSN (Print): 0950-5849
Ratings: 
  • Scopus rating (2019): CiteScore 7.6 SJR 0.781 SNIP 2.555
Original language: English
ASJC Scopus subject areas: Software, Information Systems, Computer Science Applications
Keywords: Design practice, Global software development, Software architecture, Software design, Systematic literature review
Electronic versions: 
URLs: 
Source: Scopus
Source ID: 85055646041

Research output: Contribution to journalArticleScientificpeer-review

Towards detecting structural branching and cyclicity in graphs: A polynomial-based approach

Structural properties of graphs and networks have been investigated across scientific disciplines ranging from mathematics to structural chemistry. Structural branching, cyclicity and, more generally, connectedness are well-known examples of such properties. In particular, various graph measures for detecting structural branching and cyclicity have been investigated. These measures are of limited applicability since their interpretation relies heavily on a certain definition of structural branching. In this paper we define a related measure, taking an approach to measurement similar to that of Lovász and Pelikán (On the eigenvalues of trees, Periodica Mathematica Hungarica, Vol. 3 (1–2), 1973, 175–182). We define a complex valued polynomial which also has a unique positive root. Analytical and numerical results demonstrate that this measure can be interpreted as a structural branching and cyclicity measure for graphs. Our results generalize the work of Lovász and Pelikán since the measure we introduce is not restricted to trees.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Faculty of Biomedical Sciences and Engineering, Research group: Computational Medicine and Statistical Learning Laboratory (CMSL), Research group: Predictive Society and Data Analytics (PSDA), University of Applied Sciences Upper Austria, Nankai University, Hall in Tyrol, The City College of New York (CUNY), Shandong University at Weihai
Contributors: Dehmer, M., Chen, Z., Emmert-Streib, F., Mowshowitz, A., Shi, Y., Tripathi, S., Zhang, Y.
Number of pages: 10
Pages: 19-28
Publication date: 1 Jan 2019
Peer-reviewed: Yes
Early online date: 29 Aug 2018

Publication information

Journal: Information Sciences
Volume: 471
ISSN (Print): 0020-0255
Ratings: 
  • Scopus rating (2019): CiteScore 11.3 SJR 1.723 SNIP 2.688
Original language: English
ASJC Scopus subject areas: Software, Control and Systems Engineering, Theoretical Computer Science, Computer Science Applications, Information Systems and Management, Artificial Intelligence
Keywords: Data science, Graphs, Networks, Quantitative graph theory, Structural branching
Source: Scopus
Source ID: 85052883508

Research output: Contribution to journalArticleScientificpeer-review

Performance evaluation of bandwidth reservation for mmWave 5G NR systems

Introduction: In 3GPP New Radio (NR) systems, frequent radio propagation path blockages can lead to the disconnection of ongoing sessions already accepted into the system, reducing the quality of service in the network. Controlling access to system resource by prioritizing for the ongoing sessions can increase the session continuity. In this paper, we propose resource allocation with a reservation mechanism. Purpose: Development of a mathematical model for analyzing the effect of this mechanism on other system performance indicators - dropping probabilities for new and ongoing sessions and system utilization. The model takes into account the key features of the 3GPP NR technology, including the height of the interacting objects, the spatial distribution and mobility of the blockers, as well as the line-of-sight propagation properties between the transceivers for mmWave NR technology. Results: We analyzed the reservation mechanism with the help of a developed model in the form of a resource queueing system with signals, where the base station bandwidth corresponds to the resource, and the signals model a change in the line-of-sight conditions between the receiving and transmitting devices. Creating a priority for ongoing sessions whose service has not yet been completed provides a considerable flexibility for balancing the session continuity and dropping of a new session, with a slight decrease in the efficiency of the radio resource utility. With the developed model, we showed that reserving even a small bandwidth (less than 10% of the total resources) to maintain the ongoing sessions has a positive effect on their continuity, as it increases the probability of their successful completion. Practical relevance: The proposed mechanism works more efficiently in overload conditions and with sessions which have a high data transfer rate requirements. This increases the demand for the proposed mechanism in 5G NR communication systems.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Electrical Engineering, Research group: Emerging Technologies for Nano-Bio-Info-Cogno, Peoples’ Friendship University of Russia, Federal Research Center Computer Science and Control of the Russian Academy of Sciences
Contributors: Begishev, V. O., Sopin, E. S., Molchanov, D. A., Samouylov, A. K., Gaidamaka, Y. V., Samouylov, K. E.
Number of pages: 13
Pages: 51-63
Publication date: 1 Jan 2019
Peer-reviewed: Yes

Publication information

Journal: Informatsionno-Upravliaiushchie Sistemy
Issue number: 5
ISSN (Print): 1684-8853
Ratings: 
  • Scopus rating (2019): CiteScore 0.5 SJR 0.201 SNIP 0.507
Original language: English
ASJC Scopus subject areas: Software, Control and Systems Engineering, Information Systems, Human-Computer Interaction, Computer Science Applications, Control and Optimization
Keywords: 5G networks, Bandwidth reservation, Millimeter wave, New Radio, New session drop probability, Ongoing session drop probability, Session continuity, System resource utilization
Source: Scopus
Source ID: 85082424315

Research output: Contribution to journalArticleScientificpeer-review

Compatible natural gradient policy search

Trust-region methods have yielded state-of-the-art results in policy search. A common approach is to use KL-divergence to bound the region of trust resulting in a natural gradient policy update. We show that the natural gradient and trust region optimization are equivalent if we use the natural parameterization of a standard exponential policy distribution in combination with compatible value function approximation. Moreover, we show that standard natural gradient updates may reduce the entropy of the policy according to a wrong schedule leading to premature convergence. To control entropy reduction we introduce a new policy search method called compatible policy search (COPOS) which bounds entropy loss. The experimental results show that COPOS yields state-of-the-art results in challenging continuous control tasks and in discrete partially observable tasks.

General information

Publication status: E-pub ahead of print
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, Intelligent Autonomous Systems, Technical University Darmstadt, MPI for Intelligent Systems, University of Lincoln
Contributors: Pajarinen, J., Thai, H. L., Akrour, R., Peters, J., Neumann, G.
Publication date: 2019
Peer-reviewed: Yes

Publication information

Journal: Machine Learning
ISSN (Print): 0885-6125
Ratings: 
  • Scopus rating (2019): CiteScore 5 SJR 1.034 SNIP 1.941
Original language: English
ASJC Scopus subject areas: Software, Artificial Intelligence
Keywords: Policy search, Reinforcement learning
Electronic versions: 
Source: Scopus
Source ID: 85066145275

Research output: Contribution to journalArticleScientificpeer-review

PyGOP: A Python library for Generalized Operational Perceptron algorithms

PyGOP provides a reference implementation of existing algorithms using Generalized Operational Perceptron (GOP), a recently proposed artificial neuron model. The implementation adopts a user-friendly interface while allowing a high level of customization including user-defined operators, custom loss function, custom metric functions that requires full batch evaluation such as Precision, Recall or F1. Besides, PyGOP supports different computation environments (CPU/GPU) on both single machine and cluster using SLURM job scheduler. In addition, since training GOP-based algorithms might take days, PyGOP automatically saves checkpoints during computation and allows resuming to the last checkpoint in case the script got interfered in the middle during the progression.

General information

Publication status: Accepted/In press
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, Qatar University, Aarhus Universitet
Contributors: Tran, D. T., Kiranyaz, S., Gabbouj, M., Iosifidis, A.
Publication date: 2019
Peer-reviewed: Yes

Publication information

Journal: Knowledge-Based Systems
ISSN (Print): 0950-7051
Ratings: 
  • Scopus rating (2019): CiteScore 11.7 SJR 1.754 SNIP 2.902
Original language: English
ASJC Scopus subject areas: Software, Management Information Systems, Information Systems and Management, Artificial Intelligence
Keywords: Generalized Operational Perceptron (GOP), Heterogeneous Multilayer Generalized Operational Perceptron (HeMLGOP), Progressive Operational Perceptron (POP), Progressive Operational Perceptron with Memory (POPmem)

Bibliographical note

EXT="Kiranyaz, Serkan"
EXT="Iosifidis, Alexandros"

Source: Scopus
Source ID: 85066982487

Research output: Contribution to journalArticleScientificpeer-review

Institutional Perspectives on the Process of Enterprise Architecture Adoption

Organizations often adopt enterprise architecture (EA) when planning how best to develop their information technology (IT) or businesses, for strategic management, or generally for managing change initiatives. This variety of different uses affects many stakeholders within and between organizations. Because stakeholders have dissimilar backgrounds, positions, assumptions, and activities, they respond differently to changes and the potential problems that emerge from those changes. This situation creates contradictions and conflicts between stakeholders that may further influence project activities and ultimately determine how EA is adopted. In this paper, we examine how institutional pressures influence EA adoption. Based on a qualitative case study of two cases, we show how regulative, normative, and cognitive pressures influence stakeholders’ activities and behaviors during the process of EA adoption. Our contribution thus lies in identifying roles of institutional pressures in different phases during the process of EA adoption and how it changes overtime. The results provide insights into EA adoption and the process of institutionalization, which help to explain emergent challenges in EA adoption.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Information and Knowledge Management, Research group: Business Data Research Group, University of Vaasa (UVA)
Contributors: Dang, D., Pekkola, S.
Publication date: 2019
Peer-reviewed: Yes

Publication information

Journal: Information Systems Frontiers
ISSN (Print): 1387-3326
Ratings: 
  • Scopus rating (2019): CiteScore 6.7 SJR 1.02 SNIP 1.926
Original language: English
ASJC Scopus subject areas: Software, Theoretical Computer Science, Information Systems, Computer Networks and Communications
Keywords: EA adoption, Enterprise architecture, Institutional theory, Institutionalization process

Bibliographical note

EXT="Dang, Duong"

Source: Scopus
Source ID: 85069739091

Research output: Contribution to journalArticleScientificpeer-review

Zeffiro User Interface for Electromagnetic Brain Imaging: a GPU Accelerated FEM Tool for Forward and Inverse Computations in Matlab

This article introduces the Zeffiro interface (ZI) version 2.2 for brain imaging. ZI aims to provide a simple, accessible and multimodal open source platform for finite element method (FEM) based and graphics processing unit (GPU) accelerated forward and inverse computations in the Matlab environment. It allows one to (1) generate a given multi-compartment head model, (2) to evaluate a lead field matrix as well as (3) to invert and analyze a given set of measurements. GPU acceleration is applied in each of the processing stages (1)–(3). In its current configuration, ZI includes forward solvers for electro-/magnetoencephalography (EEG) and linearized electrical impedance tomography (EIT) as well as a set of inverse solvers based on the hierarchical Bayesian model (HBM). We report the results of EEG and EIT inversion tests performed with real and synthetic data, respectively, and demonstrate numerically how the inversion parameters affect the EEG inversion outcome in HBM. The GPU acceleration was found to be essential in the generation of the FE mesh and the LF matrix in order to achieve a reasonable computing time. The code package can be extended in the future based on the directions given in this article.

General information

Publication status: E-pub ahead of print
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences, Research group: Inverse Problems
Contributors: He, Q., Rezaei, A., Pursiainen, S.
Number of pages: 14
Publication date: 2019
Peer-reviewed: Yes

Publication information

Journal: Neuroinformatics
ISSN (Print): 1539-2791
Ratings: 
  • Scopus rating (2019): CiteScore 8.2 SJR 1.984 SNIP 2.238
Original language: English
ASJC Scopus subject areas: Software, Neuroscience(all), Information Systems
Keywords: Electrical Impedance Tomography (EIT), Electro-/Magnetoencephalography (EEG/MEG), Finite Element Method (FEM), Hierarchical Bayesian Model (HBM), Matlab Interface
Source: Scopus
Source ID: 85074501520

Research output: Contribution to journalArticleScientificpeer-review

Continuum approach to high-cycle fatigue. The finite life-time case with stochastic stress history

In this paper, we consider continuum approach for high-cycle fatigue in the case where life-time is finite. The method is based on differential equations and all basic concepts are explained. A stress history is assumed to be a stochastic process and this leads us to the theory of stochastic differential equations. The life-time is a quantity, which tells us when the breakdown of the material happens. In this method, it is naturally a random variable. The basic assumption is, that the distribution of the life-time is log-normal or Weibull. We give a numerical basic example to demonstrate the method.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Computing Sciences
Contributors: Orelma, H.
Number of pages: 12
Pages: 452-463
Publication date: 2019
Peer-reviewed: Yes

Publication information

Journal: Vestnik Samarskogo Gosudarstvennogo Tekhnicheskogo Universiteta, Seriya Fiziko-Matematicheskie Nauki
Volume: 23
Issue number: 3
ISSN (Print): 1991-8615
Ratings: 
  • Scopus rating (2019): CiteScore 0
Original language: English
ASJC Scopus subject areas: Mechanics of Materials, Condensed Matter Physics, Mathematical Physics, Modelling and Simulation, Analysis, Applied Mathematics, Software
Keywords: Evolution equation, High-cycle fatigue, Life-time
Source: Scopus
Source ID: 85079143163

Research output: Contribution to journalArticleScientificpeer-review

Power mitigation of a heterogeneous multicore architecture on FPGA/ASIC by DFS/DVFS techniques

This article presents an integrated self-aware computing model in a Heterogeneous Multicore Architecture (HMA) to mitigate the power dissipation of an Orthogonal Frequency-Division Multiplexing (OFDM) receiver. The proposed platform consists of template-based Coarse-Grained Reconfigurable Array (CGRA) devices connected through a Network-on-Chip (NoC) around a few Reduced Instruction-Set Computing (RISC) cores. The self-aware computing model exploits Feedback Control System (FCS) which constantly monitors the execution-time of each core and dynamically scales the operating frequency of each node of the NoC depending on the worst execution-time. Therefore, the performance of the overall system is equalized towards a desired level besides mitigating the power dissipation. Measurement results obtained from Field-Programmable Gate Array (FPGA) synthesis show up to 20.2% dynamic power dissipation and 16.8% total power dissipation savings. Since FCS technique can be employed for scaling the frequency and the voltage and on the other hand, voltage supply cannot be scaled on the FPGA-based prototyped platform, the implementation is also estimated in 28nm Ultra-Thin Body and Buried oxide (UTBB) Fully-Depleted Silicon-On-Insulator (FD-SOI) Application-Specific Integrated Circuit (ASIC) technology to scale voltage in addition to frequency and get more benefits in terms of dynamic power dissipation reduction. Subsequent to synthesizing the whole platform on ASIC and scaling the voltage and frequency simultaneously as a Dynamic Voltage and Frequency Scaling (DVFS) method, significant dynamic power dissipation savings by 5.97X against Dynamic Frequency Scaling (DFS) method were obtained.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Electronics and Communications Engineering, Research group: System-on-Chip for GNSS, Wireless Communications and Cyber-Physical Embedded Computing, University of Bologna
Contributors: Nouri, S., Rossi, D., Nurmi, J.
Number of pages: 10
Pages: 259-268
Publication date: 1 Nov 2018
Peer-reviewed: Yes

Publication information

Journal: Microprocessors and Microsystems
Volume: 63
ISSN (Print): 0141-9331
Ratings: 
  • Scopus rating (2018): CiteScore 2.5 SJR 0.264 SNIP 0.941
Original language: English
ASJC Scopus subject areas: Software, Hardware and Architecture, Computer Networks and Communications, Artificial Intelligence
Keywords: Accelerator, ASIC, CGRA, Channel estimation, DVFS, FCS, FFT, FPGA, Frequency offset estimation, Heterogeneous, Multicore, Network-on-Chip, OFDM, Power mitigation, Receiver, Reconfigurable, Time synchronization
Source: Scopus
Source ID: 85054428146

Research output: Contribution to journalArticleScientificpeer-review

Graph measures with high discrimination power revisited: A random polynomial approach

Finding graph measures with high discrimination power has been triggered by searching for so-called complete graph invariants. In a series of papers, we have already investigated highly discriminating measures to distinguish graphs (networks) based on their topology. In this paper, we propose an approach where the graph measures are based on the roots of random graph polynomials. The polynomial coefficients have been defined by utilizing information functionals which capture structural information of the underlying networks. Our numerical results obtained by employing exhaustively generated graphs reveal that the new approach outperforms earlier results in the literature.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Faculty of Biomedical Sciences and Engineering, Research group: Computational Medicine and Statistical Learning Laboratory (CMSL), Research group: Predictive Society and Data Analytics (PSDA), University of Applied Sciences Upper Austria, School of Management, Nankai University
Contributors: Dehmer, M., Chen, Z., Emmert-Streib, F., Shi, Y., Tripathi, S.
Number of pages: 8
Pages: 407-414
Publication date: 1 Oct 2018
Peer-reviewed: Yes

Publication information

Journal: Information Sciences
Volume: 467
ISSN (Print): 0020-0255
Ratings: 
  • Scopus rating (2018): CiteScore 10.4 SJR 1.62 SNIP 2.744
Original language: English
ASJC Scopus subject areas: Software, Control and Systems Engineering, Theoretical Computer Science, Computer Science Applications, Information Systems and Management, Artificial Intelligence
Keywords: Data science, Graphs, Networks, Quantitative graph theory, Statistics

Bibliographical note

EXT="Tripathi, Shailesh"

Source: Scopus
Source ID: 85051518614

Research output: Contribution to journalArticleScientificpeer-review

Reproducible Evaluation of System Efficiency with a Model of Architecture: From Theory to Practice

Current trends in high performance and embedded computing include design of increasingly complex hardware architectures with high parallelism, heterogeneous processing elements and non-uniform communication resources. In order to take hardware and software design decisions, early evaluations of the system non-functional properties are needed. These evaluations of system efficiency require Electronic System-Level (ESL) information on both the algorithms and the architecture. Contrary to algorithm models for which a major body of work has been conducted on defining formal Models of Computation (MoCs), architecture models from the literature are mostly empirical models from which reproducible experimentation requires the accompanying software. In this paper, a precise definition of a Model of Architecture (MoA) is proposed that focuses on reproducibility and abstraction and removes the overlap previously existing between the notions of MoA and MoC. A first MoA, called the Linear System-Level Architecture Model (LSLA), is presented. To demonstrate the generic nature of the proposed new architecture modeling concepts, we show that the LSLA Model can be integrated flexibly with different MoCs. LSLA is then used to model the energy consumption of a State-of-the-Art Multiprocessor System-on-Chip (MPSoC) when running an application described using the Synchronous Dataflow (SDF) MoC. A method to automatically learn LSLA model parameters from platform measurements is introduced. Despite the high complexity of the underlying hardware and software, a simple LSLA model is demonstrated to estimate the energy consumption of the MPSoC with a fidelity of 86%.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Pervasive Computing, UBL, Scuola Superiore sant'Anna, University of Maryland
Contributors: Pelcat, M., Mercat, A., Desnos, K., Maggiani, L., Liu, Y., Heulot, J., Nezan, J. F., Hamidouche, W., Menard, D., Bhattacharyya, S. S.
Pages: 2050-2063
Publication date: Oct 2018
Peer-reviewed: Yes
Early online date: 16 Nov 2017

Publication information

Journal: IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Volume: 37
Issue number: 10
ISSN (Print): 0278-0070
Ratings: 
  • Scopus rating (2018): CiteScore 4.6 SJR 0.476 SNIP 1.737
Original language: English
ASJC Scopus subject areas: Software, Computer Graphics and Computer-Aided Design, Electrical and Electronic Engineering
Keywords: Algorithm design and analysis, architecture, Complexity theory, Computational modeling, Computer architecture, design space exploration, Energy consumption, Hardware, hardware/software co-design, modeling, multiprocessor SoC, performance optimization, Ports (Computers), power modeling and estimation., system on chip
Source: Scopus
Source ID: 85035150836

Research output: Contribution to journalArticleScientificpeer-review

A quasi-virtual online analyser based on an artificial neural networks and offline measurements to predict purities of raffinate/extract in simulated moving bed processes

The quality control and optimization of Simulated Moving Bed processes are still a challenge. Among the main reasons for that, the real time measurement of its main properties can be highlighted. Further developments in this field are necessary in order to allow the development of better control and optimization systems of these units. In the present work, a system composed by two Artificial Neural Networks working concomitantly with an offline measurement system is proposed, named Quasi-Virtual Analyser (Q-VOA) system. The development of the Q-VOA is presented and the system is simulated in order to evaluate its efficiency. The methodology used to select the input variables for the Q-VOA is another contribution of this work. The results show that the Q-VOA is capable of reducing the system errors and keep the prediction closer to the process true responses, when compared with the simple VOA system, which is based solely on model predictions. Furthermore, the results show the efficiency of the measurement system even under the presence of non-measured perturbations.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Automation and Hydraulic Engineering, Univ Porto, Universidade do Porto, Fac Med, Dept Med Imaging, Federal Univ. of Bahia
Contributors: Nogueira, I. B., Ribeiro, A. M., Requião, R., Pontes, K. V., Koivisto, H., Rodrigues, A. E., Loureiro, J. M.
Number of pages: 19
Pages: 29-47
Publication date: 1 Jun 2018
Peer-reviewed: Yes

Publication information

Journal: Applied Soft Computing Journal
Volume: 67
ISSN (Print): 1568-4946
Ratings: 
  • Scopus rating (2018): CiteScore 8.9 SJR 1.216 SNIP 2.474
Original language: English
ASJC Scopus subject areas: Software
Keywords: Artificial neural network, Enantiomers separation, Purity measurement, Quasi-virtual analyser system, True moving bed
Source: Scopus
Source ID: 85043383206

Research output: Contribution to journalArticleScientificpeer-review

On the Definition of Microservice Bad Smells

Code smells and architectural smells (also called bad smells) are symptoms of poor design that can hinder code understandability and decrease maintainability. Several bad smells have been defined in the literature for both generic architectures and specific architectures. However, cloud-native applications based on microservices can be affected by other types of issues. In order to identify a set of microservice-specific bad smells, researchers collected evidence of bad practices by interviewing 72 developers with experience in developing systems based on microservices. Then, they classified the bad practices into a catalog of 11 microservice-specific bad smells frequently considered harmful by practitioners. The results can be used by practitioners and researchers as a guideline to avoid experiencing the same difficult situations in the systems they develop.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Pervasive Computing
Contributors: Taibi, D., Lenarduzzi, V.
Number of pages: 7
Pages: 56-62
Publication date: 1 May 2018
Peer-reviewed: Yes

Publication information

Journal: IEEE Software
Volume: 35
Issue number: 3
ISSN (Print): 0740-7459
Ratings: 
  • Scopus rating (2018): CiteScore 5.3 SJR 0.549 SNIP 2.444
Original language: English
ASJC Scopus subject areas: Software
Keywords: anti-pattern, antipattern, architectural smell, bad smell, cloud computing, code smell, microservice, software development, software engineering
Source: Scopus
Source ID: 85046708734

Research output: Contribution to journalArticleScientificpeer-review

Backshoring of production in the context of a small and open Nordic economy

Purpose – The purpose of this paper is to investigate the extent, drivers, and conditions underlying backshoring in the Finnish manufacturing industry, comparing the results to the wider ongoing relocation of production in the international context. Design/methodology/approach – The survey of 229 Finnish manufacturing firms reveals the background, drivers, and patterns of offshoring and backshoring. Findings – Companies that had transferred their production back to Finland were more commonly in industries with relatively higher technology intensity and they were typically larger than the no-movement companies, and with a higher number of plants. They also reported more commonly having a corporate-wide strategy for guiding production location decisions. Research limitations/implications – Backshoring activity in the small and open economy of Finland seems to be higher compared to earlier studies in larger countries. The findings suggest that there is a transformation in the manufacturing industries with some gradual replacement of labor-intensive and lower technology-intensive industries toward higher technology-intensive industries. Practical implications – Moving production across national borders is one option in the strategies of firms to stay competitive. Companies must carefully consider the relevance of various decision-making drivers when determining strategies for their production networks. Social implications – Manufacturing industries have traditionally been important for employment in the relatively small and open economies of the Nordic countries. From the social perspective, it is important to understand the ongoing transformation and its implications. Originality/value – There are few empirical studies available of the ongoing backshoring movement, utilizing data from company decision makers instead of macroeconomic factors.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Industrial and Information Management, Research group: Center for Research on Operations Projects and Services
Contributors: Heikkilä, J., Martinsuo, M., Nenonen, S.
Number of pages: 19
Pages: 658-675
Publication date: May 2018
Peer-reviewed: Yes
Early online date: 27 Nov 2017

Publication information

Journal: Journal of Manufacturing Technology Management
Volume: 29
Issue number: 4
ISSN (Print): 1741-038X
Ratings: 
  • Scopus rating (2018): CiteScore 4.8 SJR 0.954 SNIP 1.393
Original language: English
ASJC Scopus subject areas: Software, Control and Systems Engineering, Computer Science Applications, Strategy and Management, Industrial and Manufacturing Engineering
Keywords: Manufacturing, Manufacturing strategy, Production
Source: Scopus
Source ID: 85039840754

Research output: Contribution to journalArticleScientificpeer-review

Memory-Constrained vectorization and scheduling of dataflow graphs for hybrid CPU-GPU platforms

The increasing use of heterogeneous embedded systems with multi-core CPUs and Graphics Processing Units (GPUs) presents important challenges in effectively exploiting pipeline, task, and data-level parallelism to meet throughput requirements of digital signal processing applications. Moreover, in the presence of system-level memory constraints, hand optimization of code to satisfy these requirements is inefficient and error prone and can therefore, greatly slow down development time or result in highly underutilized processing resources. In this article, we present vectorization and scheduling methods to effectively exploit multiple forms of parallelism for throughput optimization on hybrid CPU-GPU platforms, while conforming to system-level memory constraints. The methods operate on synchronous dataflow representations, which are widely used in the design of embedded systems for signal and information processing. We show that our novel methods can significantly improve system throughput compared to previous vectorization and scheduling approaches under the same memory constraints. In addition, we present a practical case-study of applying our methods to significantly improve the throughput of an orthogonal frequency division multiplexing receiver system for wireless communications.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Pervasive Computing, University of Maryland, Department of Electrical and Computer Engineering
Contributors: Lin, S., Wu, J., Bhattacharyya, S. S.
Publication date: 1 Feb 2018
Peer-reviewed: Yes

Publication information

Journal: ACM Transactions on Embedded Computing Systems
Volume: 17
Issue number: 2
Article number: 50
ISSN (Print): 1539-9087
Ratings: 
  • Scopus rating (2018): CiteScore 3 SJR 0.326 SNIP 0.979
Original language: English
ASJC Scopus subject areas: Software, Hardware and Architecture
Keywords: Dataflow models, Design optimization, Heterogeneous computing, Signal processing systems, Software synthesis
Source: Scopus
Source ID: 85042527088

Research output: Contribution to journalArticleScientificpeer-review

Feature synthesis for image classification and retrieval via one-against-all perceptrons

Most existing content-based image retrieval and classification systems rely on low-level features which are automatically extracted from images. However, often these features lack the discrimination power needed for accurate description of the image content, and hence, they may lead to a poor retrieval or classification performance. We propose a novel technique to improve low-level features which uses parallel one-against-all perceptrons to synthesize new features with a higher discrimination power which in turn leads to improved classification and retrieval results. The proposed method can be applied on any database and low-level features as long as some ground-truth information is available. The main merits of the proposed technique are its simplicity and faster computation compared to existing feature synthesis methods. Extensive simulation results show a significant improvement in the features’ discrimination power.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Signal Processing, Research group: Video, Qatar University
Contributors: Raitoharju, J., Kiranyaz, S., Gabbouj, M.
Number of pages: 15
Pages: 943–957
Publication date: Feb 2018
Peer-reviewed: Yes
Early online date: 29 Jul 2016

Publication information

Journal: Neural Computing and Applications
Volume: 29
Issue number: 4
ISSN (Print): 0941-0643
Ratings: 
  • Scopus rating (2018): CiteScore 4.9 SJR 0.637 SNIP 1.521
Original language: English
ASJC Scopus subject areas: Artificial Intelligence, Software
Keywords: Content-based image retrieval and classification, Feature synthesis, Multi-dimensional particle swarm optimization, Multi-layer perceptrons

Bibliographical note

EXT="Kiranyaz, Serkan"

Source: Scopus
Source ID: 84979997953

Research output: Contribution to journalArticleScientificpeer-review

Is Texture Denoising Efficiency Predictable?

Images of different origin contain textures, and textural features in such regions are frequently employed in pattern recognition, image classification, information extraction, etc. Noise often present in analyzed images might prevent a proper solution of basic tasks in the aforementioned applications and is worth suppressing. This is not an easy task since even the most advanced denoising methods destroy texture in a more or less degree while removing noise. Thus, it is desirable to predict the filtering behavior before any denoising is applied. This paper studies the efficiency of texture image denoising for different noise intensities and several filter types under different visual quality criteria (quality metrics). It is demonstrated that the most efficient existing filters provide very similar results. From the obtained results, it is possible to generalize and employ the prediction strategy earlier proposed for denoising techniques based on the discrete cosine transform. Accuracy of such a prediction is studied and the ways to improve it are considered. Some practical recommendations concerning a decision to undertake whether it is worth applying a filter are given.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Signal Processing, Research group: Computational Imaging-CI
Contributors: Rubel, O., Lukin, V., Abramov, S., Vozel, B., Pogrebnyak, O., Egiazarian, K.
Publication date: 2018
Peer-reviewed: Yes

Publication information

Journal: International Journal of Pattern Recognition and Artificial Intelligence
Volume: 32
Issue number: 1
Article number: 1860005
ISSN (Print): 0218-0014
Ratings: 
  • Scopus rating (2018): CiteScore 2.2 SJR 0.304 SNIP 0.718
Original language: English
ASJC Scopus subject areas: Software, Computer Vision and Pattern Recognition, Artificial Intelligence
Keywords: image processing, noise suppression, Texture denoising, visual quality
Electronic versions: 
Source: Scopus
Source ID: 85025804856

Research output: Contribution to journalArticleScientificpeer-review

Mixed-integer linear programming approach for global discrete sizing optimization of frame structures

This paper focuses on discrete sizing optimization of frame structures using commercial profile catalogs. The optimization problem is formulated as a mixed-integer linear programming (MILP) problem by including the equations of structural analysis as constraints. The internal forces of the members are taken as continuous state variables. Binary variables are used for choosing the member profiles from a catalog. Both the displacement and stress constraints are formulated such that for each member limit values can be imposed at predefined locations along the member. A valuable feature of the formulation, lacking in most contemporary approaches, is that global optimality of the solution is guaranteed by solving the MILP using branch-and-bound techniques. The method is applied to three design problems: a portal frame, a two-story frame with three load cases and a multiple-bay multiple-story frame. Performance profiles are determined to compare the MILP reformulation method with a genetic algorithm.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Civil Engineering, KU Leuven
Contributors: van Mellaert, R., Mela, K., Tiainen, T., Heinisuo, M., Lombaert, G., Schevenels, M.
Number of pages: 15
Pages: 579–593
Publication date: 2018
Peer-reviewed: Yes

Publication information

Journal: Structural and Multidisciplinary Optimization
Volume: 57
Issue number: 2
ISSN (Print): 1615-147X
Ratings: 
  • Scopus rating (2018): CiteScore 5.1 SJR 1.835 SNIP 1.887
Original language: English
ASJC Scopus subject areas: Control and Systems Engineering, Software, Computer Science Applications, Computer Graphics and Computer-Aided Design, Control and Optimization
Keywords: Discrete optimization, Frame structures, Global optimization, Mixed-integer linear programming, Sizing optimization
Source: Scopus
Source ID: 85026724545

Research output: Contribution to journalArticleScientificpeer-review

Federated IoT services leveraging 5G technologies at the edge

The Internet of Things (IoT) ecosystem is evolving towards the deployment of integrated environments, wherein heterogeneous devices pool their capacities together to match wide-ranging user and service requirements. As a consequence, solutions for efficient and synergistic cooperation among objects acquire great relevance. Along this line, this paper focuses on the adoption of the promising MIFaaS (Mobile-IoT-Federation-as-a-Service) paradigm to support delay-sensitive applications for high-end IoT devices in next-to-come fifth generation (5G) environments. MIFaaS fosters the provisioning of IoT services and applications with low-latency requirements by leveraging cooperation among private/public clouds of IoT objects at the edge of the network. A performance assessment of the MIFaaS paradigm in a cellular 5G environment based on both Long Term Evolution (LTE) and the recent Narrowband IoT (NB-IoT) is presented. Obtained results demonstrate that the proposed solution outperforms classic approaches, highlighting significant benefits derived from the joint use of LTE and NB-IoT bandwidths in terms of increased number of successfully delivered IoT services.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Electronics and Communications Engineering, Universita degli Studi di Reggio Calabria, Peoples’ Friendship University of Russia
Contributors: Farris, I., Orsino, A., Militano, L., Iera, A., Araniti, G.
Pages: 58-69
Publication date: 2018
Peer-reviewed: Yes

Publication information

Journal: Ad Hoc Networks
Volume: 68
ISSN (Print): 1570-8705
Ratings: 
  • Scopus rating (2018): CiteScore 7.7 SJR 0.648 SNIP 2.03
Original language: English
ASJC Scopus subject areas: Software, Hardware and Architecture, Computer Networks and Communications
Keywords: 5G, IoT, Multi-access edge computing, Narrowband-IoT

Bibliographical note

INT=ELT, "Orsino, A."

Source: Scopus
Source ID: 85030565702

Research output: Contribution to journalArticleScientificpeer-review

Probabilistic saliency estimation

In this paper, we model the salient object detection problem under a probabilistic framework encoding the boundary connectivity saliency cue and smoothness constraints into an optimization problem. We show that this problem has a closed form global optimum solution, which estimates the salient object. We further show that along with the probabilistic framework, the proposed method also enjoys a wide range of interpretations, i.e. graph cut, diffusion maps and one-class classification. With an analysis according to these interpretations, we also find that our proposed method provides approximations to the global optimum to another criterion that integrates local/global contrast and large area saliency cues. The proposed unsupervised approach achieves mostly leading performance compared to the state-of-the-art unsupervised algorithms over a large set of salient object detection datasets including around 17k images for several evaluation metrics. Furthermore, the computational complexity of the proposed method is favorable/comparable to many state-of-the-art unsupervised techniques.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Signal Processing, Research group: Multimedia Research Group - MRG
Contributors: Aytekin, C., Iosifidis, A., Gabbouj, M.
Number of pages: 14
Pages: 359-372
Publication date: 2018
Peer-reviewed: Yes
Early online date: 20 Sep 2017

Publication information

Journal: Pattern Recognition
Volume: 74
ISSN (Print): 0031-3203
Ratings: 
  • Scopus rating (2018): CiteScore 10.4 SJR 1.363 SNIP 3.211
Original language: English
ASJC Scopus subject areas: Software, Signal Processing, Computer Vision and Pattern Recognition, Artificial Intelligence
Keywords: Diffusion maps, One-class classification, Probabilistic model, Saliency, Salient object detection, Spectral graph cut
Source: Scopus
Source ID: 85032271491

Research output: Contribution to journalArticleScientificpeer-review

A Dataset for Camera Independent Color Constancy

In this paper, we provide a novel dataset designed for camera independent color constancy research. Camera independence corresponds to the robustness of an algorithm’s performance when run on images of the same scene taken by different cameras. Accordingly, the images in our database correspond to several lab and field scenes each of which is captured by three different cameras with minimal registration errors. The lab scenes are also captured under five different illuminations. The spectral responses of cameras and the spectral power distributions of the lab light sources are also provided, as they may prove beneficial for training future algorithms to achieve color constancy. For a fair evaluation of future methods, we provide guidelines for supervised methods with indicated training, validation and testing partitions. Accordingly, we evaluate two recently proposed convolutional neural network based color constancy algorithms as baselines for future research. As a side contribution, this dataset also includes images taken by a mobile camera with color shading corrected and uncorrected results. This allows research on the effect of color shading as well.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Signal Processing, Research group: Multimedia Research Group - MRG, Intel Corporation
Contributors: Aytekin, C., Nikkanen, J., Gabbouj, M.
Pages: 530-544
Publication date: 2018
Peer-reviewed: Yes

Publication information

Journal: IEEE Transactions on Image Processing
Volume: 27
Issue number: 2
ISSN (Print): 1057-7149
Ratings: 
  • Scopus rating (2018): CiteScore 12.8 SJR 1.809 SNIP 4.285
Original language: English
ASJC Scopus subject areas: Software, Computer Graphics and Computer-Aided Design
Keywords: Cameras, Color constancy, color shading, illumination estimation, Image color analysis, Lighting, platform independence, Reflectivity, Robustness, Sensitivity, Training
Source: Scopus
Source ID: 85032268285

Research output: Contribution to journalArticleScientificpeer-review

How to design gamification? A method for engineering gamified software

Context: Since its inception around 2010, gamification has become one of the top technology and software trends. However, gamification has also been regarded as one of the most challenging areas of software engineering. Beyond traditional software design requirements, designing gamification requires the command of disciplines such as (motivational/behavioral) psychology, game design, and narratology, making the development of gamified software a challenge for traditional software developers. Gamification software inhabits a finely tuned niche of software engineering that seeks for both high functionality and engagement; beyond technical flawlessness, gamification has to motivate and affect users. Consequently, it has also been projected that most gamified software is doomed to fail. Objective: This paper seeks to advance the understanding of designing gamification and to provide a comprehensive method for developing gamified software. Method: We approach the research problem via a design science research approach; firstly, by synthesizing the current body of literature on gamification design methods and by interviewing 25 gamification experts, producing a comprehensive list of design principles for developing gamified software. Secondly, and more importantly, we develop a detailed method for engineering of gamified software based on the gathered knowledge and design principles. Finally, we conduct an evaluation of the artifacts via interviews of ten gamification experts and implementation of the engineering method in a gamification project. Results: As results of the study, we present the method and key design principles for engineering gamified software. Based on the empirical and expert evaluation, the developed method was deemed as comprehensive, implementable, complete, and useful. We deliver a comprehensive overview of gamification guidelines and shed novel insights into the nature of gamification development and design discourse. Conclusion: This paper takes first steps towards a comprehensive method for gamified software engineering.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Research group: TUT Game Lab, Pervasive Computing, University of Duisburg-Essen
Contributors: Morschheuser, B., Hassan, L., Werder, K., Hamari, J.
Pages: 219-237
Publication date: 2018
Peer-reviewed: Yes
Early online date: 2017

Publication information

Journal: Information and Software Technology
Volume: 95
ISSN (Print): 0950-5849
Ratings: 
  • Scopus rating (2018): CiteScore 7.9 SJR 0.615 SNIP 3.085
Original language: English
ASJC Scopus subject areas: Software, Information Systems, Computer Science Applications
Keywords: Design science research, Game design, Gameful design, Gamification, Persuasive technology, Playfulness, Software engineering
Source: Scopus
Source ID: 85035150495

Research output: Contribution to journalArticleScientificpeer-review

Fair testing and stubborn sets

Partial order methods alleviate state explosion by considering only a subset of actions in each constructed state. The choice of the subset depends on the properties that the method promises to preserve. Many methods have been developed ranging from deadlock-preserving to CTL(Formula presented.)-preserving and divergence-sensitive branching bisimilarity preserving. The less the method preserves, the smaller state spaces it constructs. Fair testing equivalence unifies deadlocks with livelocks that cannot be exited and ignores the other livelocks. It is the weakest congruence that preserves whether or not the system may enter a livelock that it cannot leave. We prove that a method that was designed for trace equivalence also preserves fair testing equivalence. We demonstrate its effectiveness on a protocol with a connection and data transfer phase. This is the first practical partial order method that deals with a practical fairness assumption.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Mathematics, University of Augsburg
Contributors: Valmari, A., Vogler, W.
Number of pages: 22
Pages: 589-610
Publication date: 2018
Peer-reviewed: Yes
Early online date: 11 Dec 2017

Publication information

Journal: International Journal on Software Tools for Technology Transfer
ISSN (Print): 1433-2779
Ratings: 
  • Scopus rating (2018): CiteScore 4.8 SJR 0.472 SNIP 1.693
Original language: English
ASJC Scopus subject areas: Software, Information Systems
Keywords: Fair testing equivalence, Fairness, Partial order methods, Progress, Stubborn sets
Electronic versions: 
URLs: 
Source: Scopus
Source ID: 85037686390

Research output: Contribution to journalArticleScientificpeer-review

Time-of-Flight Range Measurement in Low-sensing Environment: Noise Analysis and Complex-domain Non-local Denoising

In this work, we deal with the problem of denoising 3D scene range measurements acquired by Time-of-flight (ToF) range sensors and composed in the form of 2D image-like depth maps. We address the specific case of ToF low-sensing environment (LSE). Such environment is set by low-light sensing conditions, low-power hardware requirements, and low-reflectivity scenes. We demonstrate that data captured by a device in such mode can be effectively post-processed in order to reach the same measurement accuracy as if the device was working in normal operating mode. In order to achieve this, we first present an elaborated analysis of noise properties of ToF data sensed in LSE and verify the derived noise models by empirical measurements. Then, we develop a related novel non-local denoising approach working in complex domain and demonstrate its superiority against the state of the art for data acquired by an off-the-shelf ToF device.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Signal Processing, Research group: 3D MEDIA, Research group: 3D MEDIA
Contributors: Georgiev, M., Bregovic, R., Gotchev, A.
Publication date: 2018
Peer-reviewed: Yes
Early online date: 15 Feb 2018

Publication information

Journal: IEEE Transactions on Image Processing
Volume: 27
Issue number: 6
ISSN (Print): 1057-7149
Ratings: 
  • Scopus rating (2018): CiteScore 12.8 SJR 1.809 SNIP 4.285
Original language: English
ASJC Scopus subject areas: Software, Computer Graphics and Computer-Aided Design
Keywords: 3D, Delays, denoising, Filtering, Harmonic analysis, low-sensing environment, Noise measurement, noise model, Noise reduction, Phase measurement, phase-wrap, range sensing, Sensors, Time-of-Flight (ToF)
Source: Scopus
Source ID: 85042184733

Research output: Contribution to journalArticleScientificpeer-review

Multi-view predictive latent space learning

In unsupervised circumstances, multi-view learning seeks a shared latent representation by taking the consensus and complementary principles into account. However, most existing multi-view unsupervised learning approaches do not explicitly lay stress on the predictability of the latent space. In this paper, we propose a novel multi-view predictive latent space learning (MVP) model and apply it to multi-view clustering and unsupervised dimension reduction. The latent space is forced to be predictive by maximizing the correlation between the latent space and feature space of each view. By learning a multi-view graph with adaptive view-weight learning, MVP effectively combines the complementary information from multi-view data. Experimental results on benchmark datasets show that MVP outperforms the state-of-the-art multi-view clustering and unsupervised dimension reduction algorithms.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Signal Processing, Tianjin University
Contributors: Yuan, J., Gao, K., Zhu, P., Egiazarian, K.
Publication date: 2018
Peer-reviewed: Yes
Early online date: 2018

Publication information

Journal: Pattern Recognition Letters
ISSN (Print): 0167-8655
Ratings: 
  • Scopus rating (2018): CiteScore 5.8 SJR 0.662 SNIP 1.729
Original language: English
ASJC Scopus subject areas: Software, Signal Processing, Computer Vision and Pattern Recognition, Artificial Intelligence
Keywords: Multi-view learning, Predictive latent space learning, Unsupervised clustering, Unsupervised dimension reduction
Source: Scopus
Source ID: 85049094619

Research output: Contribution to journalArticleScientificpeer-review

Information Exchange Architecture for Collaborative Industrial Ecosystem

Due to the networked nature of modern industrial business, repeated information exchange activities are necessary. Unfortunately, information exchange is both laborious and expensive with the current communication media, which causes errors and delays. To increase the efficiency of communication, this study introduces an architecture to exchange information in a digitally processable manner in industrial ecosystems. The architecture builds upon commonly agreed business practices and data formats, and an open consortium and information mediators enable it. Following the architecture, a functional prototype has been implemented for a real industrial scenario. This study has its focus on the technical information of equipment, but the architecture concept can also be applied in financing and logistics. Therefore, the concept has potential to completely reform industrial communication.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Automation and Hydraulic Engineering, Research group: Automation and Systems Theory, Collaxion Oy
Contributors: Kannisto, P., Hästbacka, D., Marttinen, A.
Pages: 1-16
Publication date: 2018
Peer-reviewed: Yes
Early online date: 2018

Publication information

Journal: Information Systems Frontiers
ISSN (Print): 1387-3326
Ratings: 
  • Scopus rating (2018): CiteScore 7.6 SJR 0.797 SNIP 2.201
Original language: English
ASJC Scopus subject areas: Software, Theoretical Computer Science, Information Systems, Computer Networks and Communications
Keywords: Digital business ecosystem, Industrial information management, Lifecycle management, Multi-sided platform, Operations and maintenance, Systems integration
Source: Scopus
Source ID: 85052098014

Research output: Contribution to journalArticleScientificpeer-review

An algebraic approach to reducing the number of variables of incompletely defined discrete functions

In this paper, we consider incompletely defined discrete functions, i.e., Boolean and multiple-valued functions, f : S → {0, 1, . . . , q - 1} where S ⊆ {0, 1, . . . , q - 1}n i.e., the function value is specified only on a certain subset S of the domain of the corresponding completely defined function. We assume the function to be sparse i.e. |S| is 'small' relative to the cardinality of the domain. We show that by embedding the domain {0, 1, . . . , q - 1}n , where n is the number of variables and q is a prime power, in a suitable ring structure, the multiplicative structure of the ring can be used to construct a linear function {0, 1, . . . , q - 1}n → {0, 1, . . . , q - 1}m that is injective on S provided that m > 2 logq |S| + logq (n - 1). In this way we find a linear transform that reduces the number of variables from n to m, and can be used e.g. in implementation of an incompletely defined discrete function by using linear decomposition.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Signal Processing, Faculty of Electronics Niš
Contributors: Astola, J., Astola, P., Stanković, R., Tabus, I.
Number of pages: 15
Pages: 239-253
Publication date: 2018
Peer-reviewed: Yes

Publication information

Journal: Journal of Multiple-Valued Logic and Soft Computing
Volume: 31
Issue number: 3
ISSN (Print): 1542-3980
Ratings: 
  • Scopus rating (2018): CiteScore 1.2 SJR 0.224 SNIP 0.605
Original language: English
ASJC Scopus subject areas: Software, Theoretical Computer Science, Logic

Bibliographical note

EXT="Stanković, Radomir"

Source: Scopus
Source ID: 85055661435

Research output: Contribution to journalArticleScientificpeer-review

Reduction of variables of index generation functions using linear and quadratic transformations

In many applications in communication, data retrieval and processing, digital system design, and related areas, incompletely specified switching (Boolean or multiple-valued) functions are encountered. A particular class of highly incompletely specified functions are the so-called index generation functions, which being defined on a small fraction of input combinations, often do not require all the variables to be represented. Reducing the variables of index generation functions is an important task, since they are used mainly in real-time applications and compactness of their representations influences performances of related systems. One approach towards reducing the number of variables in index generation functions are linear transformations meaning that initial variables are replaced by their linear combinations. A drawback is that finding an optimal transformation can be difficult. Therefore, in this paper, we first formulate the problem of finding a good linear transformation by using linear subspaces. This formulation serves as a basis to propose non-linear (polynomial) transformations to reduce the number of variables in index generation functions.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Signal Processing, Faculty of Electronics
Contributors: Astola, H., Stanković, R., Astola, J.
Number of pages: 16
Pages: 255-270
Publication date: 2018
Peer-reviewed: Yes

Publication information

Journal: Journal of Multiple-Valued Logic and Soft Computing
Volume: 31
Issue number: 3
ISSN (Print): 1542-3980
Ratings: 
  • Scopus rating (2018): CiteScore 1.2 SJR 0.224 SNIP 0.605
Original language: English
ASJC Scopus subject areas: Software, Theoretical Computer Science, Logic
Keywords: Index generation function, Linear transformation, Non-linear transformation, Reed-Muller expression

Bibliographical note

EXT="Stanković, Radomir"

Source: Scopus
Source ID: 85055671990

Research output: Contribution to journalArticleScientificpeer-review

On the degeneracy of the Randić entropy and related graph measures

Numerous quantitative graph measures have been defined and applied in various disciplines. Such measures may be differentiated according to whether they are information-theoretic or non-information-theoretic. In this paper, we examine an important property of Randić entropy, an information-theoretic measure, and examine some related graph measures based on random roots. In particular, we investigate the degeneracy of these structural graph measures and discuss numerical results. Finally, we draw some conclusions about the measures’ applicability to deterministic and non-deterministic networks.

General information

Publication status: E-pub ahead of print
MoE publication type: A1 Journal article-refereed
Organisations: Faculty of Biomedical Sciences and Engineering, Research group: Computational Medicine and Statistical Learning Laboratory (CMSL), Research group: Predictive Society and Data Analytics (PSDA), University of Applied Sciences Upper Austria, School of Management, Nankai University, Hall in Tyrol, The City College of New York (CUNY), Production and Operations Management, Tianjin University of Technology
Contributors: Dehmer, M., Chen, Z., Mowshowitz, A., Jodlbauer, H., Emmert-Streib, F., Shi, Y., Tripathi, S., Xia, C.
Publication date: 2018
Peer-reviewed: Yes

Publication information

Journal: Information Sciences
ISSN (Print): 0020-0255
Ratings: 
  • Scopus rating (2018): CiteScore 10.4 SJR 1.62 SNIP 2.744
Original language: English
ASJC Scopus subject areas: Software, Control and Systems Engineering, Theoretical Computer Science, Computer Science Applications, Information Systems and Management, Artificial Intelligence
Keywords: Data science, Graphs, Networks, Quantitative graph theory, Structural graph measures, Structural network analysis

Bibliographical note

EXT="Tripathi, Shailesh"

Source: Scopus
Source ID: 85057760552

Research output: Contribution to journalArticleScientificpeer-review

Memory Tampering Attack on Binary GCD Based Inversion Algorithms

In the field of cryptography engineering, implementation-based attacks are a major concern due to their proven feasibility. Fault injection is one attack vector, nowadays a major research line. In this paper, we present how a memory tampering-based fault attack can be used to severely limit the output space of binary GCD based modular inversion algorithm implementations. We frame the proposed attack in the context of ECDSA showing how this approach allows recovering the private key from only one signature, independent of the key size. We analyze two memory tampering proposals, illustrating how this technique can be adapted to different implementations. Besides its application to ECDSA, it can be extended to other cryptographic schemes and countermeasures where binary GCD based modular inversion algorithms are employed. In addition, we describe how memory tampering-based fault attacks can be used to mount a previously proposed fault attack on scenarios that were initially discarded, showing the importance of including memory tampering attacks in the frameworks for analyzing fault attacks and their countermeasures.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Pervasive Computing, Research area: Information security, Universidad Tecnológica de la Habana José Antonio Echeverría, Universidad de Sevilla
Contributors: Aldaya, A. C., Brumley, B. B., Sarmiento, A. J., Sánchez-Solano, S.
Pages: 1-20
Publication date: 2018
Peer-reviewed: Yes
Early online date: 2018

Publication information

Journal: International Journal of Parallel Programming
ISSN (Print): 0885-7458
Ratings: 
  • Scopus rating (2018): CiteScore 2.4 SJR 0.289 SNIP 0.97
Original language: English
ASJC Scopus subject areas: Software, Theoretical Computer Science, Information Systems
Keywords: Binary GCD, Bitstream manipulation, ECDSA, Fault attacks, FPGA memory tampering
Electronic versions: 
URLs: 
Source: Scopus
Source ID: 85057616270

Research output: Contribution to journalArticleScientificpeer-review

Multisensor Time–Frequency Signal Processing MATLAB package: An analysis tool for multichannel non-stationary data

The Multisensor Time–FrequencySignal Processing (MTFSP) MATLAB package is an analysis tool for multichannel non-stationary signals collected from an array of sensors. By combining array signal processing for non-stationary signals and multichannel high resolution time–frequency methods, MTFSP enables applications such as cross-channel causality relationships, automated component separation and direction of arrival estimation, using multisensor time–frequency distributions (MTFDs). MTFSP can address old and new applications such as: abnormality detection in biomedical signals, source localization in wireless communications or condition monitoring and fault detection in industrial plants. It allows e.g. the reproduction of the results presented in Boashash and Aïssa-El-Bey (in press) [2].

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: University of Queensland
Contributors: Boashash, B., Aïssa-El-Bey, A., Al-Sa'd, M. F.
Pages: 53-58
Publication date: 2018
Peer-reviewed: Yes

Publication information

Journal: SoftwareX
Volume: 8
ISSN (Print): 2352-7110
Ratings: 
  • Scopus rating (2018): CiteScore 10.8 SJR 4.539 SNIP 5.206
Original language: English
ASJC Scopus subject areas: Software, Computer Science Applications
Keywords: Automated component separation, Blind source separation, Cross-channel causality analysis, Direction of arrival, Multisensor time–frequency analysis, Non-stationary array processing
Source: Scopus
Source ID: 85041238142

Research output: Contribution to journalArticleScientificpeer-review

Sparse approximations in complex domain based on BM3D modeling

In this paper the concept of sparsity for complex-valued variables is introduced in the following three types: directly in complex domain and for two real-valued pairs phase/amplitude and real/imaginary parts of complex variables. The nonlocal block-matching technique is used for sparsity implementation and filter design for each type of sparsity. These filters are complex domain generalizations of the Block Matching 3D collaborative (BM3D) filter based on the high-order singular value decomposition (HOSVD) in order to generate group-wise adaptive analysis/synthesis transforms. Complex domain denoising is developed and studied as a test-problem for comparison of the designed filters as well as the different types of sparsity modeling.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Signal Processing, Research group: Computational Imaging-CI
Contributors: Katkovnik, V., Ponomarenko, M., Egiazarian, K.
Number of pages: 13
Pages: 96-108
Publication date: 1 Dec 2017
Peer-reviewed: Yes

Publication information

Journal: Signal Processing
Volume: 141
ISSN (Print): 0165-1684
Ratings: 
  • Scopus rating (2017): CiteScore 7.1 SJR 0.94 SNIP 1.974
Original language: English
ASJC Scopus subject areas: Control and Systems Engineering, Software, Signal Processing, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering
Keywords: Block matching, Complex domain, Denoising, Elsevier article, Phase imaging, Sample document, Sparsity
Source: Scopus
Source ID: 85020311730

Research output: Contribution to journalArticleScientificpeer-review

Quantitative Graph Theory: A new branch of graph theory and network science

In this paper, we describe some highlights of the new branch QUANTITATIVE GRAPH THEORY and explain its significant different features compared to classical graph theory. The main goal of quantitative graph theory is the structural quantification of information contained in complex networks by employing a measurement approach based on numerical invariants and comparisons. Furthermore, the methods as well as the networks do not need to be deterministic but can be statistic. As such this complements the field of classical graph theory, which is descriptive and deterministic in nature. We provide examples of how quantitative graph theory can be used for novel applications in the context of the overarching concept network science.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Research group: Computational Medicine and Statistical Learning Laboratory (CMSL), Faculty of Biomedical Sciences and Engineering, BioMediTech, Research group: Predictive Society and Data Analytics (PSDA), Nankai University
Contributors: Dehmer, M., Emmert-Streib, F., Shi, Y.
Number of pages: 6
Pages: 575-580
Publication date: 1 Dec 2017
Peer-reviewed: Yes

Publication information

Journal: Information Sciences
Volume: 418-419
ISSN (Print): 0020-0255
Ratings: 
  • Scopus rating (2017): CiteScore 10 SJR 1.635 SNIP 2.304
Original language: English
ASJC Scopus subject areas: Control and Systems Engineering, Theoretical Computer Science, Software, Computer Science Applications, Information Systems and Management, Artificial Intelligence
Keywords: Data Science, Graphs, Networks, Quantitative Graph Theory, Statistics
Source: Scopus
Source ID: 85027400753

Research output: Contribution to journalArticleScientificpeer-review

Multilinear class-specific discriminant analysis

There has been a great effort to transfer linear discriminant techniques that operate on vector data to high-order data, generally referred to as Multilinear Discriminant Analysis (MDA) techniques. Many existing works focus on maximizing the inter-class variances to intra-class variances defined on tensor data representations. However, there has not been any attempt to employ class-specific discrimination criteria for the tensor data. In this paper, we propose a multilinear subspace learning technique suitable for applications requiring class-specific tensor models. The method maximizes the discrimination of each individual class in the feature space while retains the spatial structure of the input. We evaluate the efficiency of the proposed method on two problems, i.e. facial image analysis and stock price prediction based on limit order book data.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Signal Processing, Aarhus Universitet, Laboratory of Signal Processing
Contributors: Thanh Tran, D., Gabbouj, M., Iosifidis, A.
Number of pages: 6
Pages: 131-136
Publication date: 1 Dec 2017
Peer-reviewed: Yes

Publication information

Journal: Pattern Recognition Letters
Volume: 100
ISSN (Print): 0167-8655
Ratings: 
  • Scopus rating (2017): CiteScore 5.5 SJR 0.662 SNIP 1.605
Original language: English
ASJC Scopus subject areas: Software, Signal Processing, Computer Vision and Pattern Recognition, Artificial Intelligence
Keywords: Class-specific discriminant learning, Face verification, Multilinear discriminant analysis, Stock price prediction

Bibliographical note

INT=sgn,"Thanh Tran, Dat"

Source: Scopus
Source ID: 85032300703

Research output: Contribution to journalArticleScientificpeer-review

How developers perceive smells in source code: A replicated study

Context. In recent years, smells, also referred to as bad smells, have gained popularity among developers. However, it is still not clear how harmful they are perceived from the developers’ point of view. Many developers talk about them, but only few know what they really are, and even fewer really take care of them in their source code. Objective. The goal of this work is to understand the perceived criticality of code smells both in theory, when reading their description, and in practice. Method. We executed an empirical study as a differentiated external replication of two previous studies. The studies were conducted as surveys involving only highly experienced developers (63 in the first study and 41 in the second one). First the perceived criticality was analyzed by proposing the description of the smells, then different pieces of code infected by the smells were proposed, and finally their ability to identify the smells in the analyzed code was tested. Results. According to our knowledge, this is the largest study so far investigating the perception of code smells with professional software developers. The results show that developers are very concerned about code smells in theory, nearly always considering them as harmful or very harmful (17 out of 23 smells). However, when they were asked to analyze an infected piece of code, only few infected classes were considered harmful and even fewer were considered harmful because of the smell. Conclusions. The results confirm our initial hypotheses that code smells are perceived as more critical in theory but not as critical in practice.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Free University of Bolzano-Bozen, Free University of Bozen-Bolzano
Contributors: Taibi, D., Janes, A., Lenarduzzi, V.
Number of pages: 13
Pages: 223-235
Publication date: 1 Dec 2017
Peer-reviewed: Yes

Publication information

Journal: Information and Software Technology
Volume: 92
ISSN (Print): 0950-5849
Ratings: 
  • Scopus rating (2017): CiteScore 7.2 SJR 0.581 SNIP 2.913
Original language: English
ASJC Scopus subject areas: Software, Information Systems, Computer Science Applications
Keywords: Antipatterns, Bad smells, Code smells, Refactoring, Software maintenance
Source: Scopus
Source ID: 85028762206

Research output: Contribution to journalArticleScientificpeer-review

Big Media Data Analysis

In this editorial a short introduction to the special issue on Big Media Data Analysis is given. The scope of this Editorial is to briefly present methodologies, tasks and applications of big media data analysis and to introduce the papers of the special issue. The special issue includes six papers that span various media analysis application areas like generic image description, medical image and video analysis, distance calculation acceleration and data collection.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Signal Processing, Research group: Multimedia Research Group - MRG, Aarhus Universitet, University of Milan Bicocca, Department of Informatics, Aristotle University of Thessaloniki
Contributors: Iosifidis, A., Tefas, A., Pitas, I., Gabbouj, M.
Number of pages: 4
Pages: 105-108
Publication date: 1 Nov 2017
Peer-reviewed: Yes

Publication information

Journal: Signal Processing: Image Communication
Volume: 59
ISSN (Print): 0923-5965
Ratings: 
  • Scopus rating (2017): CiteScore 4.6 SJR 0.551 SNIP 1.512
Original language: English
ASJC Scopus subject areas: Software, Signal Processing, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering
Keywords: Big Media Data, Data analytics, Deep learning, Machine learning, Statistical learning

Bibliographical note

EXT="Tefas, Anastasios"

Source: Scopus
Source ID: 85033445526

Research output: Contribution to journalEditorialScientificpeer-review

Highly unique network descriptors based on the roots of the permanental polynomial

In this paper, we examine the zeros of permanental polynomials as highly unique network descriptors. We employ exhaustively generated networks and demonstrate that our defined graph measures based on the moduli of the zeros of permanental polynomials are quite efficient when distinguishing graphs structurally. In this work, we continue with a line of research that relates to the search of almost complete graph invariants. These highly unique network measures may serve as a powerful tool for tackling graph isomorphism.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Faculty of Biomedical Sciences and Engineering, Research group: Computational Medicine and Statistical Learning Laboratory (CMSL), BioMediTech, Research group: Predictive Society and Data Analytics (PSDA), Institute for Bioinformatics and Translational Research, Laboratory of Biosystem Dynamics, BioMediTech Institute and Faculty of Biomedical Sciences and Engineering, Universität der Bundeswehr München, Nankai University, Babes-Bolyai University
Contributors: Dehmer, M., Emmert-Streib, F., Hu, B., Shi, Y., Stefu, M., Tripathi, S.
Number of pages: 6
Pages: 176-181
Publication date: 1 Oct 2017
Peer-reviewed: Yes

Publication information

Journal: Information Sciences
Volume: 408
ISSN (Print): 0020-0255
Ratings: 
  • Scopus rating (2017): CiteScore 10 SJR 1.635 SNIP 2.304
Original language: English
ASJC Scopus subject areas: Control and Systems Engineering, Theoretical Computer Science, Software, Computer Science Applications, Information Systems and Management, Artificial Intelligence
Keywords: Data science, Graphs, Networks, Quantitative graph theory, Statistics
Source: Scopus
Source ID: 85018769218

Research output: Contribution to journalArticleScientificpeer-review

Gamified crowdsourcing: Conceptualization, literature review, and future agenda

Two parallel phenomena are gaining attention in human–computer interaction research: gamification and crowdsourcing. Because crowdsourcing's success depends on a mass of motivated crowdsourcees, crowdsourcing platforms have increasingly been imbued with motivational design features borrowed from games; a practice often called gamification. While the body of literature and knowledge of the phenomenon have begun to accumulate, we still lack a comprehensive and systematic understanding of conceptual foundations, knowledge of how gamification is used in crowdsourcing, and whether it is effective. We first provide a conceptual framework for gamified crowdsourcing systems in order to understand and conceptualize the key aspects of the phenomenon. The paper's main contributions are derived through a systematic literature review that investigates how gamification has been examined in different types of crowdsourcing in a variety of domains. This meticulous mapping, which focuses on all aspects in our framework, enables us to infer what kinds of gamification efforts are effective in different crowdsourcing approaches as well as to point to a number of research gaps and lay out future research directions for gamified crowdsourcing systems. Overall, the results indicate that gamification has been an effective approach for increasing crowdsourcing participation and the quality of the crowdsourced work; however, differences exist between different types of crowdsourcing: the research conducted in the context of crowdsourcing of homogenous tasks has most commonly used simple gamification implementations, such as points and leaderboards, whereas crowdsourcing implementations that seek diverse and creative contributions employ gamification with a richer set of mechanics.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Research group: TUT Game Lab, Pervasive Computing, Robert Bosch GmbH, Karlsruhe Institute of Technology, Insitute for Technical Physics, Germany, Gamification Group
Contributors: Morschheuser, B., Hamari, J., Koivisto, J., Maedche, A.
Number of pages: 18
Pages: 26-43
Publication date: 1 Oct 2017
Peer-reviewed: Yes

Publication information

Journal: International Journal of Human-Computer Studies
Volume: 106
ISSN (Print): 1071-5819
Ratings: 
  • Scopus rating (2017): CiteScore 5.9 SJR 0.605 SNIP 2.146
Original language: English
ASJC Scopus subject areas: Human Factors and Ergonomics, Software, Education, Engineering(all), Human-Computer Interaction, Hardware and Architecture
Keywords: Crowdsourcing, Gamification, Human computation, Literature review, Persuasive technology, Research agenda
Source: Scopus
Source ID: 85019568466

Research output: Contribution to journalArticleScientificpeer-review

Architecting liquid software

The Liquid Software metaphor refers to software that can operate seamlessly across multiple devices owned by one or multiple users. Liquid Software applications can take advantage of the computing, storage and communication resources available on all the devices owned by the user. Liquid Software applications can also dynamically migrate from one device to another, following the user’s attention and usage context. The key design goal in Liquid Software development is to minimize the additional efforts arising from multiple device ownership (e.g., installation, synchronization and general maintenance of personal computers, smartphones, tablets, home and car displays, and wearable devices), while keeping the users in full control of their devices, applications and data. In this paper we present the design space for Liquid Software, categorizing and discussing the most important architectural dimensions and technical choices. We also provide an introduction and comparison of two frameworks implementing Liquid Software capabilities in the context of the World Wide Web.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Pervasive Computing, Università della Svizzera Italiana, University of Helsinki, Nokia Technologies Oy
Contributors: Gallidabino, A., Pautasso, C., Mikkonen, T., Systä, K., Voutilainen, J., Taivalsaari, A.
Number of pages: 38
Pages: 433-470
Publication date: 1 Sep 2017
Peer-reviewed: Yes

Publication information

Journal: Journal of Web Engineering
Volume: 16
Issue number: 5-6
ISSN (Print): 1540-9589
Ratings: 
  • Scopus rating (2017): CiteScore 1.1 SJR 0.157 SNIP 0.455
Original language: English
ASJC Scopus subject areas: Software, Information Systems, Computer Networks and Communications
Keywords: Design space, Liquid software, Multi-device programming, Multiple device ownership, Software architecture

Bibliographical note

EXT="Mikkonen, Tommi"
EXT="Taivalsaari, Antero"

Source: Scopus
Source ID: 85020531917

Research output: Contribution to journalArticleScientificpeer-review

Hardware design methodology using lightweight dataflow and its integration with low power techniques

Dataflow models of computation are capable of providing high-level descriptions for hardware and software components and systems, facilitating efficient processes for system-level design. The modularity and parallelism of dataflow representations make them suitable for key aspects of design exploration and optimization, such as efficient scheduling, task synchronization, memory and power management. The lightweight dataflow (LWDF) programming methodology provides an abstract programming model that supports dataflow-based design of signal processing hardware and software components and systems. Due to its formulation in terms of abstract application programming interfaces, the LWDF methodology can be integrated with a wide variety of simulation- and implementation-oriented languages, and can be targeted across different platforms, which allows engineers to integrate dataflow modeling approaches relatively easily into existing design processes. Previous work on LWDF techniques has emphasized their application to DSP software implementation (e.g., through integration with C and CUDA). In this paper, we efficiently integrate the LWDF methodology with hardware description languages (HDLs), and we apply this HDL-integrated form of the methodology to develop efficient methods for low power DSP hardware implementation. The effectiveness of the proposed LWDF-based hardware design methodology is demonstrated through a case study of a deep neural network application for vehicle classification.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Pervasive Computing, Signal Processing, Research group: Vision, Research area: Computer engineering, Dept. of Electrical and Electronic Engineering, University of Maryland, PolComIng - Information Engineering Unit
Contributors: Fanni, T., Li, L., Viitanen, T., Sau, C., Xie, R., Palumbo, F., Raffo, L., Huttunen, H., Takala, J., Bhattacharyya, S. S.
Number of pages: 15
Pages: 15-29
Publication date: 1 Aug 2017
Peer-reviewed: Yes

Publication information

Journal: Journal of Systems Architecture
Volume: 78
ISSN (Print): 1383-7621
Ratings: 
  • Scopus rating (2017): CiteScore 3 SJR 0.255 SNIP 1.274
Original language: English
ASJC Scopus subject areas: Software, Hardware and Architecture
Keywords: Clock gating, Dataflow, Deep neural networks, Digital systems design, Globally asynchronous locally synchronous, Low power design, Signal processing

Bibliographical note

INT=tie,"Xie, Renjie"

Source: Scopus
Source ID: 85020917888

Research output: Contribution to journalArticleScientificpeer-review

A Mixed Finite Element Method to Solve the EEG Forward Problem

Finite element methods have been shown to achieve high accuracies in numerically solving the EEG forward problem and they enable the realistic modeling of complex geometries and important conductive features such as anisotropic conductivities. To date, most of the presented approaches rely on the same underlying formulation, the continuous Galerkin (CG)-FEM. In this article, a novel approach to solve the EEG forward problem based on a mixed finite element method (Mixed-FEM) is introduced. To obtain the Mixed-FEM formulation, the electric current is introduced as an additional unknown besides the electric potential. As a consequence of this derivation, the Mixed-FEM is, by construction, current preserving, in contrast to the CG-FEM. Consequently, a higher simulation accuracy can be achieved in certain scenarios, e.g., when the diameter of thin insulating structures, such as the skull, is in the range of the mesh resolution. A theoretical derivation of the Mixed-FEM approach for EEG forward simulations is presented, and the algorithms implemented for solving the resulting equation systems are described. Subsequently, first evaluations in both sphere and realistic head models are presented, and the results are compared to previously introduced CG-FEM approaches. Additional visualizations are shown to illustrate the current preserving property of the Mixed-FEM. Based on these results, it is concluded that the newly presented Mixed-FEM can at least complement and in some scenarios even outperform the established CG-FEM approaches, which motivates a further evaluation of the Mixed-FEM for applications in bioelectromagnetism.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Mathematics, Research group: Inverse Problems, University of Utah, Cluster of Excellence EXC, University of Münster
Contributors: Vorwerk, J., Engwer, C., Pursiainen, S., Wolters, C. H.
Number of pages: 12
Pages: 930-941
Publication date: 1 Apr 2017
Peer-reviewed: Yes

Publication information

Journal: IEEE Transactions on Medical Imaging
Volume: 36
Issue number: 4
Article number: 7731161
ISSN (Print): 0278-0062
Ratings: 
  • Scopus rating (2017): CiteScore 9.3 SJR 1.895 SNIP 2.904
Original language: English
ASJC Scopus subject areas: Software, Radiological and Ultrasound Technology, Computer Science Applications, Electrical and Electronic Engineering
Keywords: EEG, forward problem, mixed finite element method, realistic head modeling, source analysis
Source: Scopus
Source ID: 85017598893

Research output: Contribution to journalArticleScientificpeer-review

Stop it, and be stubborn!

This publication discusses how automatic verification of concurrent systems can be made more efficient by focusing on always may-terminating systems. First, making a system always may-terminating is a method formeeting a modelling need that exists independently of this publication. It is illustrated that without doing so, non-progress errors may be lost. Second, state explosion is often alleviated with stubborn, ample, and persistent set methods. They use expensive cycle or terminal strong component conditions in many cases. It is proven that for many important classes of properties, if the systems are always may-terminating, then these conditions can be left out.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Mathematics, Research group: MAT Computer Science and Applied Logics
Contributors: Valmari, A.
Publication date: 1 Jan 2017
Peer-reviewed: Yes

Publication information

Journal: ACM Transactions on Embedded Computing Systems
Volume: 16
Issue number: 2
Article number: 46
ISSN (Print): 1539-9087
Ratings: 
  • Scopus rating (2017): CiteScore 2.5 SJR 0.32 SNIP 1.093
Original language: English
ASJC Scopus subject areas: Software, Hardware and Architecture
Keywords: Ignoring problem, Safety/progress/liveness properties, Stubborn set/ample set/persistent set/partial order methods
Source: Scopus
Source ID: 85011350059

Research output: Contribution to journalArticleScientificpeer-review

Urban 3D segmentation and modelling from street view images and LiDAR point clouds

3D urban maps with semantic labels and metric information are not only essential for the next generation robots such autonomous vehicles and city drones, but also help to visualize and augment local environment in mobile user applications. The machine vision challenge is to generate accurate urban maps from existing data with minimal manual annotation. In this work, we propose a novel methodology that takes GPS registered LiDAR (Light Detection And Ranging) point clouds and street view images as inputs and creates semantic labels for the 3D points clouds using a hybrid of rule-based parsing and learning-based labelling that combine point cloud and photometric features. The rule-based parsing boosts segmentation of simple and large structures such as street surfaces and building facades that span almost 75% of the point cloud data. For more complex structures, such as cars, trees and pedestrians, we adopt boosted decision trees that exploit both structure (LiDAR) and photometric (street view) features. We provide qualitative examples of our methodology in 3D visualization where we construct parametric graphical models from labelled data and in 2D image segmentation where 3D labels are back projected to the street view images. In quantitative evaluation we report classification accuracy and computing times and compare results to competing methods with three popular databases: NAVTEQ True, Paris-Rue-Madame and TLS (terrestrial laser scanned) Velodyne.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Signal Processing, Research group: Vision, Nokia
Contributors: Babahajiani, P., Fan, L., Kämäräinen, J., Gabbouj, M.
Number of pages: 16
Pages: 679–694
Publication date: 2017
Peer-reviewed: Yes

Publication information

Journal: Machine Vision and Applications
Volume: 28
Issue number: 7
ISSN (Print): 0932-8092
Ratings: 
  • Scopus rating (2017): CiteScore 5.3 SJR 0.485 SNIP 1.683
Original language: English
ASJC Scopus subject areas: Software, Hardware and Architecture, Computer Vision and Pattern Recognition, Computer Science Applications
Keywords: LiDAR, Point cloud, Robotics, Semantic segmentation, Street view, Urban 3D

Bibliographical note

EXT="Babahajiani, Pouria"

Source: Scopus
Source ID: 85019692066

Research output: Contribution to journalArticleScientificpeer-review

Method for Simulating Dose Reduction in Digital Breast Tomosynthesis

This work proposes a new method of simulating dose reduction in digital breast tomosynthesis (DBT), starting from a clinical image acquired with a standard radiation dose. It considers both signal-dependent quantum and signal-independent electronic noise. Furthermore, the method accounts for pixel crosstalk, which causes the noise to be frequency-dependent, thus increasing the simulation accuracy. For an objective assessment, simulated and real images were compared in terms of noise standard deviation, signal-to-noise ratio (SNR) and normalized noise power spectrum (NNPS). A two-alternative forced-choice (2-AFC) study investigated the similarity between the noise strength of low-dose simulated and real images. Six experienced medical physics specialists participated on the study, with a total of 2,160 readings. Objective assessment showed no relevant trends with the simulated noise. The relative error in the standard deviation of the simulated noise was less than 2% for every projection angle. The relative error of the SNR was less than 1.5%, and the NNPS of the simulated images had errors less than 2.5%. The 2-AFC human observer experiment yielded no statistically significant difference (p=0.84) in the perceived noise strength between simulated and real images. Furthermore, the observer study also allowed the estimation of a dose difference at which the observer perceived a just-noticeable difference (JND) in noise levels. The estimated JND value indicated that a change of 17% in the current-time product was sufficient to cause a noticeable difference in noise levels. The observed high accuracy, along with the flexible calibration, make this method an attractive tool for clinical image-based simulations of dose reduction.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Signal Processing, Research group: Signal and Image Restoration-RST
Contributors: Borges, L. R., Guerrero, I., Bakic, P. R., Foi, A., Maidment, A. D., Vieira, M. A.
Pages: 2331-2342
Publication date: 2017
Peer-reviewed: Yes

Publication information

Journal: IEEE Transactions on Medical Imaging
Volume: 36
Issue number: 11
ISSN (Print): 0278-0062
Ratings: 
  • Scopus rating (2017): CiteScore 9.3 SJR 1.895 SNIP 2.904
Original language: English
ASJC Scopus subject areas: Software, Radiological and Ultrasound Technology, Computer Science Applications, Electrical and Electronic Engineering
Keywords: Biomedical imaging, Breast, Calibration, digital breast tomosynthesis, dose reduction, Electronic noise, Estimation, Image reconstruction, quantum noise, Signal to noise ratio, Standards
Electronic versions: 
Source: Scopus
Source ID: 85023177059

Research output: Contribution to journalArticleScientificpeer-review

Data Rate Assessment on L2–L3 CPU Bus and Bus between CPU and RAM in Modern CPUs

In this paper, modern CPU architecture with several different cache levels is described and current CPU performance limitations such as frequency increase bounds are discussed. As changes to the currently existing architecture are usually proposed as a way of increasing CPU performance, data rates of the internal and external CPU interfaces must be known. This information would help to assess the applicability of proposed solutions and to optimize them. This paper is aimed at obtaining real values of traffic on an L2–L3 cache interface inside a CPU and a CPU–RAM bus load, as well as showing the dependences of the total traffic on the studied interfaces on the number of active cores, CPU frequency, and test type. A measurement methodology using an Intel Performance Counter Monitor is provided and the equations used to obtain data rates from the internal CPU counters are explained. Both real-life and synthetic tests are described. The dependence of total traffic on the number of active cores and the dependence of total traffic on CPU frequency are provided as plots. The dependence of total traffic on test type is provided as a bar plot for multiple CPU frequencies.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Electronics and Communications Engineering, Yaroslavl State University
Contributors: Komar, M. S.
Number of pages: 8
Pages: 701-708
Publication date: 2017
Peer-reviewed: Yes

Publication information

Journal: Automatic Control and Computer Sciences
Volume: 51
Issue number: 7
ISSN (Print): 0146-4116
Ratings: 
  • Scopus rating (2017): CiteScore 0.6 SJR 0.218 SNIP 0.613
Original language: English
ASJC Scopus subject areas: Software, Control and Systems Engineering, Signal Processing
Keywords: data rate assessment, multicore CPUs, Network-on-Chip, NoC, System-on-Chip, Wireless Network- on-Chip, WNoC

Bibliographical note

INT=elt,"Komar, M. S."

Source: Scopus
Source ID: 85042229432

Research output: Contribution to journalArticleScientificpeer-review

Improving the delivery cycle: A multiple-case study of the toolchains in Finnish software intensive enterprises

Context: Software companies seek to gain benefit from agile development approaches in order to meet evolving market needs without losing their innovative edge. Agile practices emphasize frequent releases with the help of an automated toolchain from code to delivery. Objective: We investigate, which tools are used in software delivery, what are the reasons omitting certain parts of the toolchain and what implications toolchains have on how rapidly software gets delivered to customers. Method: We present a multiple-case study of the toolchains currently in use in Finnish software-intensive organizations interested in improving their delivery frequency. We conducted qualitative semi-structured interviews in 18 case organizations from various software domains. The interviewees were key representatives of their organization, considering delivery activities. Results: Commodity tools, such as version control and continuous integration, were used in almost every organization. Modestly used tools, such as UI testing and performance testing, were more distinctly missing from some organizations. Uncommon tools, such as artifact repository and acceptance testing, were used only in a minority of the organizations. Tool usage is affected by the state of current workflows, manual work and relevancy of tools. Organizations whose toolchains were more automated and contained fewer manual steps were able to deploy software more rapidly. Conclusions: There is variety in the need for tool support in different development steps as there are domain-specific differences in the goals of the case organizations. Still, a well-founded toolchain supports speedy delivery of new software.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Pervasive Computing, Research area: Software engineering, University of Helsinki, Aalto University
Contributors: Mäkinen, S., Leppänen, M., Kilamo, T., Mattila, A., Laukkanen, E., Pagels, M., Männistö, T.
Number of pages: 13
Pages: 1339-1351
Publication date: 1 Dec 2016
Peer-reviewed: Yes

Publication information

Journal: Information and Software Technology
Volume: 80
ISSN (Print): 0950-5849
Ratings: 
  • Scopus rating (2016): CiteScore 6.1 SJR 0.801 SNIP 2.568
Original language: English
ASJC Scopus subject areas: Software, Information Systems, Computer Science Applications
Keywords: Agile software development, Continuous delivery, Continuous deployment, Deployment pipeline, Software development tools
Source: Scopus
Source ID: 84988001567

Research output: Contribution to journalArticleScientificpeer-review

Ensembles of dense and dense sampling descriptors for the HEp-2 cells classification problem

The classification of Human Epithelial (HEp-2) cells images, acquired through Indirect Immunofluorescence (IIF) microscopy, is an effective method to identify staining patterns in patient sera. Indeed it can be used for diagnostic purposes, in order to reveal autoimmune diseases. However, the automated classification of IIF HEp-2 cell patterns represents a challenging task, due to the large intra-class and the small inter-class variability. Consequently, recent HEp-2 cell classification contests have greatly spurred the development of new IIF image classification systems.Here we propose an approach for the automatic classification of IIF HEp-2 cell images by fusion of several texture descriptors by ensemble of support vector machines combined by sum rule. Its effectiveness is evaluated using the HEp-2 cells dataset used for the "Performance Evaluation of Indirect Immunofluorescence Image Analysis Systems" contest, hosted by the International Conference on Pattern Recognition in 2014: the accuracy on the testing set is 79.85%.The same dataset was used to test an ensemble of ternary-encoded local phase quantization descriptors, built by perturbation approaches: the accuracy on the training set is 84.16%. Finally, this ensemble was validated on 14 additional datasets, obtaining the best performance on 11 datasets.Our MATLAB code is available at https://www.dei.unipd.it/node/2357.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Electronics and Communications Engineering, Research group: Computational Biophysics and Imaging Group, BioMediTech, Integrated Technologies for Tissue Engineering Research (ITTE), Universita degli Studi di Padova, Italy, University of Bologna
Contributors: Nanni, L., Lumini, A., dos Santos, F. L. C., Paci, M., Hyttinen, J.
Pages: 28-35
Publication date: 15 Oct 2016
Peer-reviewed: Yes

Publication information

Journal: Pattern Recognition Letters
Volume: 82
ISSN (Print): 0167-8655
Ratings: 
  • Scopus rating (2016): CiteScore 5.2 SJR 0.729 SNIP 1.678
Original language: English
ASJC Scopus subject areas: Software, Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing
Keywords: Bag-of-features, Ensemble, HEp-2 cell classification, Machine learning, Support vector machine, Texture descriptors
URLs: 
Source: Scopus
Source ID: 84961195136

Research output: Contribution to journalArticleScientificpeer-review

Nyström-based approximate kernel subspace learning

In this paper, we describe a method for the determination of a subspace of the feature space in kernel methods, which is suited to large-scale learning problems. Linear model learning in the obtained space corresponds to a nonlinear model learning process in the input space. Since the obtained feature space is determined only by exploiting properties of the training data, this approach can be used for generic nonlinear pattern recognition. That is, nonlinear data mapping can be considered to be a pre-processing step exploiting nonlinear relationships between the training data. Linear techniques can be subsequently applied in the new feature space and, thus, they can model nonlinear properties of the problem at hand. In order to appropriately address the inherent problem of kernel learning methods related to their time and memory complexities, we follow an approximate learning approach. We show that the method can lead to considerable operation speed gains and achieve very good performance. Experimental results verify our analysis.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Signal Processing, Research group: Video, Research Community on Data-to-Decision (D2D)
Contributors: Iosifidis, A., Gabbouj, M.
Number of pages: 8
Pages: 190-197
Publication date: Sep 2016
Peer-reviewed: Yes

Publication information

Journal: Pattern Recognition
ISSN (Print): 0031-3203
Ratings: 
  • Scopus rating (2016): CiteScore 9 SJR 1.501 SNIP 3.005
Original language: English
ASJC Scopus subject areas: Software, Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing
Keywords: Kernel methods, Nonlinear pattern recognition, Nonlinear projection trick, Nyström approximation
Source: Scopus
Source ID: 85013223573

Research output: Contribution to journalArticleScientificpeer-review

SoftWater: Software-defined networking for next-generation underwater communication systems

Underwater communication systems have drawn the attention of the research community in the last 15 years. This growing interest can largely be attributed to new civil and military applications enabled by large-scale networks of underwater devices (e.g., underwater static sensors, unmanned autonomous vehicles (AUVs), and autonomous robots), which can retrieve information from the aquatic and marine environment, perform in-network processing on the extracted data, and transmit the collected information to remote locations. Currently underwater communication systems are inherently hardware-based and rely on closed and inflexible architectural design. This imposes significant challenges into adopting new underwater communication and networking technologies, prevent the provision of truly-differentiated services to highly diverse underwater applications, and induce great barriers to integrate heterogeneous underwater devices. Software-defined networking (SDN), recognized as the next-generation networking paradigm, relies on the highly flexible, programmable, and virtualizable network architecture to dramatically improve network resource utilization, simplify network management, reduce operating cost, and promote innovation and evolution. In this paper, a software-defined architecture, namely SoftWater, is first introduced to facilitate the development of the next-generation underwater communication systems. More specifically, by exploiting the network function virtualization (NFV) and network virtualization concepts, SoftWater architecture can easily incorporate new underwater communication solutions, accordingly maximize the network capacity, can achieve the network robustness and energy efficiency, as well as can provide truly differentiated and scalable networking services. Consequently, the SoftWater architecture can simultaneously support a variety of different underwater applications, and can enable the interoperability of underwater devices from different manufacturers that operate on different underwater communication technologies based on acoustic, optical, or radio waves. Moreover, the essential network management tools of SoftWater are discussed, including reconfigurable multi-controller placement, hybrid in-band and out-of-band control traffic balancing, and utility-optimal network virtualization. Furthermore, the major benefits of SoftWater architecture are demonstrated by introducing software-defined underwater networking solutions, including the throughput-optimal underwater routing, SDN-enhanced fault recovery, and software-defined underwater mobility management. The research challenges to realize the SoftWater are also discussed in detail.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Wireless Communications and Positioning (WICO), Georgia Institute of Technology, School of Electrical and Computer Engineering, Wichita State University
Contributors: Akyildiz, I. F., Wang, P., Lin, S. C.
Publication date: Aug 2016
Peer-reviewed: Yes

Publication information

Journal: Ad Hoc Networks
Volume: 46
ISSN (Print): 1570-8705
Ratings: 
  • Scopus rating (2016): CiteScore 6.1 SJR 0.648 SNIP 2.045
Original language: English
ASJC Scopus subject areas: Software, Hardware and Architecture, Computer Networks and Communications
Keywords: SDN, Underwater communications, Virtualization
Source: Scopus
Source ID: 84992306085

Research output: Contribution to journalArticleScientificpeer-review

Compressive Sensing Image Restoration Using Adaptive Curvelet Thresholding and Nonlocal Sparse Regularization

Compressive sensing (CS) is a recently emerging technique and an extensively studied problem in signal and image processing, which suggests a new framework for the simultaneous sampling and compression of sparse or compressible signals at a rate significantly below the Nyquist rate. Maybe, designing an effective regularization term reflecting the image sparse prior information plays a critical role in CS image restoration. Recently, both local smoothness and nonlocal self-similarity have led to superior sparsity prior for CS image restoration. In this paper, first, an adaptive curvelet thresholding criterion is developed, trying to adaptively remove the perturbations appeared in recovered images during CS recovery process, imposing sparsity. Furthermore, a new sparsity measure called joint adaptive sparsity regularization (JASR) is established, which enforces both local sparsity and nonlocal 3-D sparsity in transform domain, simultaneously. Then, a novel technique for high-fidelity CS image recovery via JASR is proposed - CS-JASR. To efficiently solve the proposed corresponding optimization problem, we employ the split Bregman iterations. Extensive experimental results are reported to attest the adequacy and effectiveness of the proposed method comparing with the current state-of-the-art methods in CS image restoration.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Signal Processing, Babol Noshirvani University of Technology
Contributors: Eslahi, N., Aghagolzadeh, A.
Number of pages: 15
Pages: 3126-3140
Publication date: 1 Jul 2016
Peer-reviewed: Yes

Publication information

Journal: IEEE Transactions on Image Processing
Volume: 25
Issue number: 7
ISSN (Print): 1057-7149
Ratings: 
  • Scopus rating (2016): CiteScore 10.2 SJR 1.749 SNIP 3.397
Original language: English
ASJC Scopus subject areas: Computer Graphics and Computer-Aided Design, Software
Keywords: adaptive curvelet thresholding, Compressive sensing, nonlocal self-similarity, sparse recovery
Source: Scopus
Source ID: 84973121940

Research output: Contribution to journalArticleScientificpeer-review

Emotional Reactions to Point-Light Display Animations

Emotional reactions to basic, artificial, yet carefully controllable point-light displays (PLDs) were investigated with ratings of valence, arousal, approachability and dominance. PLDs were varied by movement location (upper and lower) and intensity (10°, 20° and 30° angular change) for angular upward and downward movements. Half of participants (N =28) were told that PLDs were related to face while to other half nothing was hinted. Results showed that 20° and 30° angle lower location upward movements were rated as significantly more pleasant, relaxing and approachable than corresponding upper location downward movements. Informed participants rated 20° and 30° angle lower movements as significantly more controllable than corresponding upper movements. Results are important from many perspectives, like for understanding human perceptual mechanisms. When using PLDs only a small amount of information needs to be transmitted. This enables low bandwidth requirements. As PLD visualizations are simple, there is no need for high-definition displays.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Automation Science and Engineering, Nokia
Contributors: Venesvirta, H., Surakka, V., Gizatdinova, Y., Lylykangas, J., Špakov, O., Verho, J., Vetek, A., Lekkala, J.
Number of pages: 11
Pages: 521-531
Publication date: 16 Jun 2016
Peer-reviewed: Yes

Publication information

Journal: Interacting with Computers
Volume: 28
Issue number: 4
ISSN (Print): 0953-5438
Ratings: 
  • Scopus rating (2016): CiteScore 3.5 SJR 0.374 SNIP 1.128
Original language: English
ASJC Scopus subject areas: Human-Computer Interaction, Software
Keywords: biological movement, emotions, face perception, information visualization, point-light displays, psychology
Source: Scopus
Source ID: 84976499522

Research output: Contribution to journalArticleScientificpeer-review

Fifty years of graph matching, network alignment and network comparison

In this paper we survey methods for performing a comparative graph analysis and explain the history, foundations and differences of such techniques of the last 50 years. While surveying these methods, we introduce a novel classification scheme by distinguishing between methods for deterministic and random graphs. We believe that this scheme is useful for a better understanding of the methods, their challenges and, finally, for applying the methods efficiently in an interdisciplinary setting of data science to solve a particular problem involving comparative network analysis.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Signal Processing
Contributors: Emmert-Streib, F., Dehmer, M., Shi, Y.
Number of pages: 18
Pages: 180-197
Publication date: 10 Jun 2016
Peer-reviewed: Yes

Publication information

Journal: Information Sciences
Volume: 346-347
ISSN (Print): 0020-0255
Ratings: 
  • Scopus rating (2016): CiteScore 8.6 SJR 1.781 SNIP 2.515
Original language: English
ASJC Scopus subject areas: Artificial Intelligence, Software, Control and Systems Engineering, Theoretical Computer Science, Computer Science Applications, Information Systems and Management
Keywords: Biological networks, Computational graph theory, Graph matching, Network comparison, Network similarity, Quantitative graph theory
Source: Scopus
Source ID: 84964349574

Research output: Contribution to journalArticleScientificpeer-review

Exploring the role of ten universal values in using products and services

The aim of this research was to explore the role of Schwartz's ten universal human values in the context of using products and services. Seventy-five participants were asked to qualitatively describe a product or service especially well in line with their values and a product or service in conflict with their values, and to evaluate them on a number of rating scales. The scales included 30 statements (three statements per universal value) probing the presence of each value in user experiences related to products and services and 10 statements studying the perceived importance of each value. The results showed that all the ten universal values were relevant in the evaluations of products and services both in line with the users' values and in conflict with the users' values. In the current sample, hedonism and self-direction were rated as the values most frequently present and most important in the evaluations of products and services in line with values. Power was rated as a moderately important value for products in conflict with values, but significantly less important for products in line with values. Achievement values were frequently reported in the qualitative descriptions, but they were less prominent in the quantitative data. The results suggest that the model of ten universal values is promising in understanding the role of users' value preferences in using products and services, and it seems to have potential for complementing the psychological needs approach in understanding user experience.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Pervasive Computing, Department of Computer Science, Aalto University
Contributors: Partala, T., Kujala, S.
Number of pages: 21
Pages: 311-331
Publication date: 1 May 2016
Peer-reviewed: Yes

Publication information

Journal: Interacting with Computers
Volume: 28
Issue number: 3
ISSN (Print): 0953-5438
Ratings: 
  • Scopus rating (2016): CiteScore 3.5 SJR 0.374 SNIP 1.128
Original language: English
ASJC Scopus subject areas: Human-Computer Interaction, Software
Keywords: empirical studies in HCI, HCI design and evaluation methods, user experience, user values, value-sensitive design
Source: Scopus
Source ID: 84966359109

Research output: Contribution to journalArticleScientificpeer-review

Texture classification using dense micro-block difference

This paper is devoted to the problem of texture classification. Motivated by recent advancements in the field of compressive sensing and keypoints descriptors, a set of novel features called dense micro-block difference (DMD) is proposed. These features provide highly descriptive representation of image patches by densely capturing the granularities at multiple scales and orientations. Unlike most of the earlier work on local features, the DMD does not involve any quantization, thus retaining the complete information. We demonstrate that the DMD have dimensionality much lower than Scale Invariant Feature Transform (SIFT) and can be computed using integral image much faster than SIFT. The proposed features are encoded using the Fisher vector method to obtain an image descriptor, which considers high-order statistics. The proposed image representation is combined with the linear support vector machine classifier. Extensive experiments are conducted on five texture data sets (KTH-TIPS, UMD, KTH-TIPS-2a, Brodatz, and Curet) using standard protocols. The results demonstrate that our approach outperforms the state-of-the-art in texture classification.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Signal Processing, Research group: Computational Imaging-CI
Contributors: Mehta, R., Egiazarian, K.
Number of pages: 13
Pages: 1604-1616
Publication date: 1 Apr 2016
Peer-reviewed: Yes

Publication information

Journal: IEEE Transactions on Image Processing
Volume: 25
Issue number: 4
ISSN (Print): 1057-7149
Ratings: 
  • Scopus rating (2016): CiteScore 10.2 SJR 1.749 SNIP 3.397
Original language: English
ASJC Scopus subject areas: Computer Graphics and Computer-Aided Design, Software
Keywords: compressive sensing, descriptors, LBP, Scale Invariant Feature Transform, SVM, Texture classification
Source: Scopus
Source ID: 84963877958

Research output: Contribution to journalArticleScientificpeer-review

Detection of bubbles as concentric circular arrangements

The paper proposes a method for the detection of bubble-like transparent objects in a liquid. The detection problem is non-trivial since bubble appearance varies considerably due to different lighting conditions causing contrast reversal and multiple interreflections. We formulate the problem as the detection of concentric circular arrangements (CCA). The CCAs are recovered in a hypothesize-optimize-verify framework. The hypothesis generation is based on sampling from the partially linked components of the non-maximum suppressed responses of oriented ridge filters, and is followed by the CCA parameter estimation. Parameter optimization is carried out by minimizing a novel cost-function. The performance was tested on gas dispersion images of pulp suspension and oil dispersion images. The mean error of gas/oil volume estimation was used as a performance criterion due to the fact that the main goal of the applications driving the research was the bubble volume estimation. The method achieved 28 and 13 % of gas and oil volume estimation errors correspondingly outperforming the OpenCV Circular Hough Transform in both cases and the WaldBoost detector in gas volume estimation.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Signal Processing, Research group: Vision, Research Community on Data-to-Decision (D2D), Machine Vision and Pattern Recognition Laboratory, Lappeenranta University of Technology, Computer Vision Group, Czech Technical University in Prague, Monash University Malaysia
Contributors: Strokina, N., Matas, J., Eerola, T., Lensu, L., Kälviäinen, H.
Number of pages: 10
Pages: 387-396
Publication date: Apr 2016
Peer-reviewed: Yes
Early online date: 10 Feb 2016

Publication information

Journal: Machine Vision and Applications
Volume: 27
Issue number: 3
ISSN (Print): 0932-8092
Ratings: 
  • Scopus rating (2016): CiteScore 4.7 SJR 0.741 SNIP 1.433
Original language: English
ASJC Scopus subject areas: Hardware and Architecture, Computer Vision and Pattern Recognition, Software, Computer Science Applications
Keywords: Bubble detection, Circular arrangements, Image processing, Machine vision, Object segmentation
Source: Scopus
Source ID: 84957656160

Research output: Contribution to journalArticleScientificpeer-review

An Assessment of Errors and Their Reduction in Terrestrial Laser Scanner Measurements in Marmorean Surfaces

The need for accurate documentation for the preservation of cultural heritage has prompted the use of terrestrial laser scanner (TLS) in this discipline. Its study in the heritage context has been focused on opaque surfaces with lambertian reflectance, while translucent and anisotropic materials remain a major challenge. The use of TLS for the mentioned materials is subject to significant distortion in measure due to the optical properties under the laser stimulation. The distortion makes the measurement by range not suitable for digital modelling in a wide range of cases. The purpose of this paper is to illustrate and discuss the deficiencies and their resulting errors in marmorean surfaces documentation using TLS based on time-of-flight and phase-shift. Also proposed in this paper is the reduction of error in depth measurement by adjustment of the incidence laser beam. The analysis is conducted by controlled experiments.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: School of Architecture
Contributors: Garcia-Fernandez, J.
Number of pages: 11
Pages: 1-11
Publication date: 1 Mar 2016
Peer-reviewed: Yes

Publication information

Journal: 3D Research
Volume: 7
Issue number: 1
Article number: 2
ISSN (Print): 2092-6731
Ratings: 
  • Scopus rating (2016): CiteScore 1.3 SJR 0.166 SNIP 0.425
Original language: English
ASJC Scopus subject areas: Electrical and Electronic Engineering, Software
Keywords: Comparison, Experimental, Laser scanning, Marble, Measurement, Translucency
Source: Scopus
Source ID: 84955495304

Research output: Contribution to journalArticleScientificpeer-review

The influence of developer multi-homing on competition between software ecosystems

Having a large number of applications in the marketplace is considered a critical success factor for software ecosystems. The number of applications has been claimed to determine which ecosystems holds the greatest competitive advantage and will eventually dominate the market. This paper investigates the influence of developer multi-homing (i.e., participating in more than one ecosystem) in three leading mobile application ecosystems. Our results show that when regarded as a whole, mobile application ecosystems are single-homing markets. The results further show that 3% of all developers generate more than 80% of installed applications and that multi-homing is common among these developers. Finally, we demonstrate that the most installed content actually comprises only a small number of the potential value propositions. The results thus imply that attracting and maintaining developers of superstar applications is more critical for the survival of a mobile application ecosystem than the overall number of developers and applications. Hence, the mobile ecosystem is unlikely to become a monopoly. Since exclusive contracts between application developers and mobile application ecosystems are rare, multi-homing is a viable component of risk management and a publishing strategy. The study advances the theoretical understanding of the influence of multi-homing on competition in software ecosystems.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Information Technology, University of Turku, VTT Technical Research Centre of Finland
Contributors: Hyrynsalmi, S., Suominen, A., Mäntymäki, M.
Number of pages: 9
Pages: 119-127
Publication date: 1 Jan 2016
Peer-reviewed: Yes

Publication information

Journal: Journal of Systems and Software
Volume: 111
ISSN (Print): 0164-1212
Ratings: 
  • Scopus rating (2016): CiteScore 5.3 SJR 0.617 SNIP 2.139
Original language: English
ASJC Scopus subject areas: Hardware and Architecture, Software, Information Systems
Keywords: Multi-homing, Software ecosystem, Two-sided markets
Source: Scopus
Source ID: 84949783538

Research output: Contribution to journalArticleScientificpeer-review

Graph Embedded Extreme Learning Machine

In this paper, we propose a novel extension of the extreme learning machine (ELM) algorithm for single-hidden layer feedforward neural network training that is able to incorporate subspace learning (SL) criteria on the optimization process followed for the calculation of the network's output weights. The proposed graph embedded ELM (GEELM) algorithm is able to naturally exploit both intrinsic and penalty SL criteria that have been (or will be) designed under the graph embedding framework. In addition, we extend the proposed GEELM algorithm in order to be able to exploit SL criteria in arbitrary (even infinite) dimensional ELM spaces. We evaluate the proposed approach on eight standard classification problems and nine publicly available datasets designed for three problems related to human behavior analysis, i.e., the recognition of human face, facial expression, and activity. Experimental results denote the effectiveness of the proposed approach, since it outperforms other ELM-based classification schemes in all the cases.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Aristotle University of Thessaloniki, Department of Informatics
Contributors: Iosifidis, A., Tefas, A., Pitas, I.
Pages: 311 - 324
Publication date: 2016
Peer-reviewed: Yes

Publication information

Journal: IEEE Transactions on Cybernetics
Volume: 46
Issue number: 1
ISSN (Print): 2168-2267
Ratings: 
  • Scopus rating (2016): CiteScore 12 SJR 2.927 SNIP 3.301
Original language: English
ASJC Scopus subject areas: Computer Science Applications, Human-Computer Interaction, Information Systems, Software, Control and Systems Engineering, Electrical and Electronic Engineering

Research output: Contribution to journalArticleScientificpeer-review

Still image/video frame lossy compression providing a desired visual quality

The problem of how to automatically provide a desired (required) visual quality in lossy compression of still images and video frames is considered in this paper. The quality can be measured based on different conventional and visual quality metrics. In this paper, we mainly employ human visual system (HVS) based metrics PSNR-HVS-M and MSSIM since both of them take into account several important peculiarities of HVS. To provide a desired visual quality with high accuracy, iterative image compression procedures are proposed and analyzed. An experimental study is performed for a large number of grayscale test images. We demonstrate that there exist several coders for which the number of iterations can be essentially decreased using a reasonable selection of the starting value and the variation interval for the parameter controlling compression (PCC). PCC values attained at the end of the iterative procedure may heavily depend upon the coder used and the complexity of the image. Similarly, the compression ratio also considerably depends on the above factors. We show that for some modern coders that take HVS into consideration it is possible to give practical recommendations on setting a fixed PCC to provide a desired visual quality in a non-iterative manner. The case when original images are corrupted by visible noise is also briefly studied.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Signal Processing, Research group: Computational Imaging-CI, National Aerospace University
Contributors: Zemliachenko, A., Lukin, V., Ponomarenko, N., Egiazarian, K., Astola, J.
Pages: 697-718
Publication date: 2016
Peer-reviewed: Yes

Publication information

Journal: Multidimensional Systems and Signal Processing
Volume: 27
Issue number: 3
ISSN (Print): 0923-6082
Ratings: 
  • Scopus rating (2016): CiteScore 3.4 SJR 0.424 SNIP 1.109
Original language: English
ASJC Scopus subject areas: Computer Science Applications, Information Systems, Signal Processing, Software, Artificial Intelligence, Hardware and Architecture, Applied Mathematics
Keywords: Compression ratio, Lossy compression, Required quality, Visual quality metrics
Source: Scopus
Source ID: 84930357751

Research output: Contribution to journalArticleScientificpeer-review

Analysis of a receiver-based reliable broadcast approach for vehicular networks

The Intelligent Transportation Systems concept provides the ground to enable a wide range of applications to improve traffic safety and efficiency. Innovative communication systems must be proposed taking into account, on the one hand, unstable characteristics of vehicular communications and, on the other hand, different requirements of applications. In this paper a reliable (geo-)broadcasting scheme for vehicular ad-hoc networks is proposed and analyzed. This receiver-based technique aims at fulfilling the received message integrity yet keeping the overhead at a reasonably low level. The results are compared to simulation studies carried out in the Network Simulator-3 (NS-3) simulation environment demonstrating good agreement with each other. The analysis shows that in a single-hop scenario, receiver-based reliable broadcasting can provide good reliability, while giving very little overhead for high number of receivers.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Electronics and Communications Engineering, Research group: Emerging Technologies for Nano-Bio-Info-Cogno, University of Twente
Contributors: Gholibeigi, M., Heijenk, G., Moltchanov, D., Koucheryavy, Y.
Number of pages: 13
Pages: 63-75
Publication date: 2016
Peer-reviewed: Yes

Publication information

Journal: Ad Hoc Networks
Volume: 37
ISSN (Print): 1570-8705
Ratings: 
  • Scopus rating (2016): CiteScore 6.1 SJR 0.648 SNIP 2.045
Original language: English
ASJC Scopus subject areas: Computer Networks and Communications, Hardware and Architecture, Software
Keywords: (Geo)Broadcast, Performance modeling, Reliability, Vehicular ad hoc networks
Source: Scopus
Source ID: 84947868264

Research output: Contribution to journalArticleScientificpeer-review

Dominant Rotated Local Binary Patterns (DRLBP) for texture classification

In this paper, we present a novel rotation-invariant and computationally efficient texture descriptor called Dominant Rotated Local Binary Pattern (DRLBP). A rotation invariance is achieved by computing the descriptor with respect to a reference in a local neighborhood. A reference is fast to compute maintaining the computational simplicity of the Local Binary Patterns (LBP). The proposed approach not only retains the complete structural information extracted by LBP, but it also captures the complimentary information by utilizing the magnitude information, thereby achieving more discriminative power. For feature selection, we learn a dictionary of the most frequently occurring patterns from the training images, and discard redundant and non-informative features. To evaluate the performance we conduct experiments on three standard texture datasets: Outex12, Outex 10 and KTH-TIPS. The performance is compared with the state-of-the-art rotation invariant texture descriptors and results show that the proposed method is superior to other approaches.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Signal Processing, Research group: Computational Imaging-CI
Contributors: Mehta, R., Egiazarian, K.
Number of pages: 7
Pages: 16-22
Publication date: 2016
Peer-reviewed: Yes
Early online date: 30 Nov 2015

Publication information

Journal: Pattern Recognition Letters
Volume: 71
ISSN (Print): 0167-8655
Ratings: 
  • Scopus rating (2016): CiteScore 5.2 SJR 0.729 SNIP 1.678
Original language: English
ASJC Scopus subject areas: Software, Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing
Keywords: Feature Selection, KTH-TIPS, Local Binary Pattern (LBP), Outex, Rotation Invariance, Texture Classification
Source: Scopus
Source ID: 84951106920

Research output: Contribution to journalArticleScientificpeer-review

Comparison of Feature Selection Techniques in Machine Learning for Anatomical Brain MRI in Dementia

We present a comparative split-half resampling analysis of various data driven feature selection and classification methods for the whole brain voxel-based classification analysis of anatomical magnetic resonance images. We compared support vector machines (SVMs), with or without filter based feature selection, several embedded feature selection methods and stability selection. While comparisons of the accuracy of various classification methods have been reported previously, the variability of the out-of-training sample classification accuracy and the set of selected features due to independent training and test sets have not been previously addressed in a brain imaging context. We studied two classification problems: 1) Alzheimer’s disease (AD) vs. normal control (NC) and 2) mild cognitive impairment (MCI) vs. NC classification. In AD vs. NC classification, the variability in the test accuracy due to the subject sample did not vary between different methods and exceeded the variability due to different classifiers. In MCI vs. NC classification, particularly with a large training set, embedded feature selection methods outperformed SVM-based ones with the difference in the test accuracy exceeding the test accuracy variability due to the subject sample. The filter and embedded methods produced divergent feature patterns for MCI vs. NC classification that suggests the utility of the embedded feature selection for this problem when linked with the good generalization performance. The stability of the feature sets was strongly correlated with the number of features selected, weakly correlated with the stability of classification accuracy, and uncorrelated with the average classification accuracy.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Signal Processing, Research group: Vision, Department of Bioengineering and Aerospace Engineering, Universidad Carlos III de Madrid, Instituto de Investigación Sanitaria Gregorio Marañon
Contributors: Tohka, J., Moradi, E., Huttunen, H., Alzheimer’s Disease Neuroimaging Initiative, Alzheimer’s Disease Neuroimaging Initiative 2
Number of pages: 18
Pages: 279-296
Publication date: 2016
Peer-reviewed: Yes

Publication information

Journal: Neuroinformatics
Volume: 14
Issue number: 3
ISSN (Print): 1539-2791
Ratings: 
  • Scopus rating (2016): CiteScore 5.4 SJR 1.358 SNIP 1.047
Original language: English
ASJC Scopus subject areas: Neuroscience(all), Information Systems, Software
Keywords: Alzheimer’s Disease, Classification, Feature selection, Machine Learning, Magnetic Resonance Imaging, Multivariate pattern analysis

Bibliographical note

EXT="Tohka, Jussi"

Source: Scopus
Source ID: 84955306208

Research output: Contribution to journalArticleScientificpeer-review

Foveated Nonlocal Self-Similarity

When we gaze a scene, our visual acuity is maximal at the fixation point (imaged by the fovea, the central part of the retina) and decreases rapidly towards the periphery of the visual field. This phenomenon is known as foveation. We investigate the role of foveation in nonlocal image filtering, installing a different form of self-similarity: the foveated self-similarity. We consider the image denoising problem as a simple means of assessing the effectiveness of descriptive models for natural images and we show that, in nonlocal image filtering, the foveated self-similarity is far more effective than the conventional windowed self-similarity. To facilitate the use of foveation in nonlocal imaging algorithms, we develop a general framework for designing foveation operators for patches by means of spatially variant blur. Within this framework, we construct several parametrized families of operators, including anisotropic ones. Strikingly, the foveation operators enabling the best denoising performance are the radial ones, in complete agreement with the orientation preference of the human visual system.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Signal Processing, Research area: Signal and Information Processing, Research group: Signal and Image Restoration-RST, Dipartimento di Elettronica, Politecnico di Milano
Contributors: Foi, A., Boracchi, G.
Number of pages: 33
Pages: 78–110
Publication date: 2016
Peer-reviewed: Yes
Early online date: 9 Mar 2016

Publication information

Journal: International Journal of Computer Vision
Volume: 120
Issue number: 1
ISSN (Print): 0920-5691
Ratings: 
  • Scopus rating (2016): CiteScore 17.4 SJR 6.779 SNIP 5.171
Original language: English
ASJC Scopus subject areas: Software, Artificial Intelligence, Computer Vision and Pattern Recognition
Electronic versions: 
URLs: 

Bibliographical note

EXT="Boracchi, Giacomo"

Source: Scopus
Source ID: 84960153979

Research output: Contribution to journalArticleScientificpeer-review

HTML5-based mobile agents for Web-of-Things

Systems and services utilizing Internet-of-Things can benefit from dynamically updated software in a significant way. In this paper we show how the most advanced variant of moving code, mobile agents, can be used for operating and managing Internet-connected systems composed of gadgets, sensors and actuators. We believe that the use of mobile agents brings several benefits, for example, mobile agents help to reduce the network load, overcome network latency, and encapsulate protocols. In addition, they can perform autonomous tasks that would otherwise require extensive configuration. The need for moving agents is even more significant if the applications and other factors of the over experience should follow the user to new contexts. When multiple agents are used to provide the user with services, some mechanisms to manage the agents are needed. In the context of Internet-of-Things such management should reflect the physical spaces and other relevant contexts. In this paper we describe the technical solutions used in implementation of the mobile agents, describe two proof concepts and we also compare our solution to related work. We also describe our visions of the future work.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Pervasive Computing, Research area: Software engineering
Contributors: Voutilainen, J. P., Mattila, A. L., Systä, K., Mikkonen, T.
Number of pages: 9
Pages: 43-51
Publication date: 2016
Peer-reviewed: Yes

Publication information

Journal: Informatica
Volume: 40
Issue number: 1
ISSN (Print): 0350-5596
Ratings: 
  • Scopus rating (2016): CiteScore 1.2 SJR 0.136 SNIP 0.461
Original language: English
ASJC Scopus subject areas: Computer Science Applications, Software, Artificial Intelligence, Theoretical Computer Science
Keywords: Html5, Internet-of-things, Javascript, Mobile agents, Web applications, Web-of-things
Source: Scopus
Source ID: 84963719558

Research output: Contribution to journalArticleScientificpeer-review

Gravity gradient routing for information delivery in fog Wireless Sensor Networks

Fog Computing is a new paradigm that has been proposed by CISCO to take full advantage of the ever growing computational capacity of the near-user or edge devices (e.g., wireless gateways and sensors). The paradigm proposes an architecture that enables the devices to host functionality of various user-centric services. While the prospects of Fog Computing promise numerous advantages, development of Fog Services remains under-investigated. This article considers an opportunity of Fog implementation for Alert Services on top of Wireless Sensor Network (WSN) technology. In particular, we focus on targeted WSN-alert delivery based on spontaneous interaction between a WSN and hand-held devices of its users. For the alert delivery, we propose a Gravity Routing concept that prioritizes the areas of high user-presence within the network. Based on the concept, we develop a routing protocol, namely the Gradient Gravity Routing (GGR) that combines targeted delivery and resilience to potential sensor-load heterogeneity within the network. The protocol has been compared against a set of state-of-the-art solutions via a series of simulations. The evaluation has shown the ability of GGR to match the performance of the compared solutions in terms of alert delivery ratio, while minimizing the overall energy consumption of the network.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Electronics and Communications Engineering, Research group: Emerging Technologies for Nano-Bio-Info-Cogno
Contributors: Ivanov, S., Balasubramaniam, S., Botvich, D., Akan, O. B.
Pages: 61-74
Publication date: 2016
Peer-reviewed: Yes

Publication information

Journal: Ad Hoc Networks
Volume: 46
ISSN (Print): 1570-8705
Ratings: 
  • Scopus rating (2016): CiteScore 6.1 SJR 0.648 SNIP 2.045
Original language: English
ASJC Scopus subject areas: Computer Networks and Communications, Hardware and Architecture, Software
Keywords: Fog Computing, User-awareness, Wireless sensor networks
Source: Scopus
Source ID: 84964329276

Research output: Contribution to journalArticleScientificpeer-review

One-Class Classification based on Extreme Learning and Geometric Class Information

In this paper, we propose an extreme learning machine (ELM)-based one-class classification method that exploits geometric class information. We formulate the proposed method to exploit data representations in the feature space determined by the network hidden layer outputs, as well as in ELM spaces of arbitrary dimensions. We show that the exploitation of geometric class information enhances performance. We evaluate the proposed approach in publicly available datasets and compare its performance with the recently proposed one-class extreme learning machine algorithm, as well as with standard and recently proposed one-class classifiers. Experimental results show that the proposed method consistently outperforms the remaining approaches.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Signal Processing, Aristotle University of Thessaloniki, Aristotle University of Thessaloniki, Department of Informatics
Contributors: Iosifidis, A., Mygdalis, V., Tefas, A., Pitas, I.
Number of pages: 16
Pages: 1-16
Publication date: 2016
Peer-reviewed: Yes

Publication information

Journal: Neural Processing Letters
ISSN (Print): 1370-4621
Ratings: 
  • Scopus rating (2016): CiteScore 2.6 SJR 0.399 SNIP 0.777
Original language: English
ASJC Scopus subject areas: Software, Neuroscience(all), Computer Networks and Communications, Artificial Intelligence
Keywords: Big data, Extreme learning machine, Novelty detection, One-class classification

Bibliographical note

EXT="Tefas, Anastasios"

Source: Scopus
Source ID: 84982810055

Research output: Contribution to journalArticleScientificpeer-review

Software Startups - A Research Agenda

Software startup companies develop innovative, software-intensive products within limited time frames and with few resources, searching for sustainable and scalable business models. Software startups are quite distinct from traditional mature software companies, but also from micro-, small-, and medium-sized enterprises, introducing new challenges relevant for software engineering research. This paper's research agenda focuses on software engineering in startups, identifying, in particular, 70+ research questions in the areas of supporting startup engineering activities, startup evolution models and patterns, ecosystems and innovation hubs, human aspects in software startups, applying startup concepts in non-startup environments, and methodologies and theories for startup research. We connect and motivate this research agenda with past studies in software startup research, while pointing out possible future directions. While all authors of this research agenda have their main background in Software Engineering or Computer Science, their interest in software startups broadens the perspective to the challenges, but also to the opportunities that emerge from multi-disciplinary research. Our audience is therefore primarily software engineering researchers, even though we aim at stimulating collaborations and research that crosses disciplinary boundaries. We believe that with this research agenda we cover a wide spectrum of the software startup industry current needs.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Pervasive Computing, Research area: User experience, Blekinge Institute of Technology, Norwegian Univ. of Sci. and Technol., Free University of Bolzano-Bozen, SICS, Lake Constance University, Natl. University of Ireland, Galway, Universidad Politecnica de Madrid, Department of Applied Physics, University of Cagliari, National University of Ireland Maynooth, Univ of Oulu, Hochschule Konstanz
Contributors: Unterkalmsteiner, M., Abrahamsson, P., Wang, X. F., Nguyen-Duc, A., Shah, S., Bajwa, S. S., Baltes, G. H., Conboy, K., Cullina, E., Dennehy, D., Edison, H., Fernandez-Sanchez, C., Garbajosa, J., Gorschek, T., Klotins, E., Hokkanen, L., Kon, F., Lunesu, I., Marchesi, M., Morgan, L., Oivo, M., Selig, C., Seppänen, P., Sweetman, R., Tyrväinen, P., Ungerer, C., Yagüe, A.
Number of pages: 35
Pages: 89-123
Publication date: 2016
Peer-reviewed: Yes

Publication information

Journal: e-Informatica Software Engineering Journal
Volume: 10
Issue number: 1
ISSN (Print): 1897-7979
Ratings: 
  • Scopus rating (2016): CiteScore 1.3 SJR 0.136 SNIP 0.743
Original language: English
ASJC Scopus subject areas: Software
Keywords: Research agenda, Software startup, Software-intensive systems

Bibliographical note

EXT="Shah, Syed"

Source: Scopus
Source ID: 84994056890

Research output: Contribution to journalArticleScientificpeer-review

Generative part-based Gabor object detector

Discriminative part-based models have become the approach for visual object detection. The models learn from a large number of positive and negative examples with annotated class labels and location (bounding box). In contrast, we propose a part-based generative model that learns from a small number of positive examples. This is achieved by utilizing "privileged information", sparse class-specific landmarks with semantic meaning. Our method uses bio-inspired complex-valued Gabor features to describe local parts. Gabor features are transformed to part probabilities by unsupervised Gaussian Mixture Model (GMM). GMM estimation is robustified for a small amount of data by a randomization procedure inspired by random forests. The GMM framework is also used to construct a probabilistic spatial model of part configurations. Our detector is invariant to translation, rotation and scaling. On part level invariance is achieved by pose quantization which is more efficient than previously proposed feature transformations. In the spatial model, invariance is achieved by mapping parts to an "aligned object space". Using a small number of positive examples our generative method performs comparably to the state-of-the-art discriminative method.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Signal Processing, Research group: Vision, Field robotics for efficient work sites (FIRE), Prostate cancer research center (PCRC), Lappeenranta University of Technology
Contributors: Riabchenko, E., Kämäräinen, J.
Number of pages: 8
Pages: 1-8
Publication date: 15 Dec 2015
Peer-reviewed: Yes

Publication information

Journal: Pattern Recognition Letters
Volume: 68
Issue number: P1
ISSN (Print): 0167-8655
Ratings: 
  • Scopus rating (2015): CiteScore 5.1 SJR 0.95 SNIP 2.002
Original language: English
ASJC Scopus subject areas: Software, Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing
Keywords: Gabor feature, Gaussian mixture model, Generative learning, Object detection, Visual classification

Bibliographical note

EXT="Riabchenko, Ekaterina"

Source: Scopus
Source ID: 84941570575

Research output: Contribution to journalArticleScientificpeer-review

Time series trends in software evolution

Background The laws of software evolution were formulated to describe time series trends in software over time. Objective Building on econometrics, the paper relates the laws theoretically to the concept of stationarity. The theoretical argumentation builds on the fact that in a stationary time series, the mean and variance remain constant. The concept is further elaborated with different statistical types of time series trends. These provide the objective for the empirical experiment that evaluates whether software size measures in a typical software evolution dataset are stationary. Method The time series analysis is based on conventional statistical tests for the evaluation of stationarity. Results The empirical dataset contains time series extracted from the version control systems used in Vaadin and Tomcat between circa 2006 and 2013. The results establish that the observed time series are neither stationary nor follow simple mathematical functions that would translate into stationarity. Conclusion The testing framework presented in the paper allows evaluating the stationarity of software evolution time series. The results can be interpreted theoretically against the laws of software evolution. These methodological and theoretical contributions improve the foundations of predictive time series modeling of software evolution problems.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Managing digital industrial transformation (mDIT), University of Turku, Department of Management and Entrepreneurship, Turun Kauppakorkeakoulu
Contributors: Ruohonen, J., Hyrynsalmi, S., Leppänen, V.
Number of pages: 26
Pages: 990-1015
Publication date: 1 Dec 2015
Peer-reviewed: Yes

Publication information

Journal: Journal of Software: Evolution and Process
Volume: 27
Issue number: 12
ISSN (Print): 2047-7473
Original language: English
ASJC Scopus subject areas: Software
Keywords: dynamic regression, software evolution, stationarity, time series analysis, unit roots
Source: Scopus
Source ID: 84955628781

Research output: Contribution to journalArticleScientificpeer-review

Sparse extreme learning machine classifier exploiting intrinsic graphs

This paper presents an analysis of the recently proposed sparse extreme learning machine (S-ELM) classifier and describes an optimization scheme that can be used to calculate the network output weights. This optimization scheme exploits intrinsic graph structures in order to describe geometric data relationships in the so-called ELM space. Kernel formulations of the approach operating in ELM spaces of arbitrary dimensions are also provided. It is shown that the application of the optimization scheme exploiting geometric data relationships in the original ELM space is equivalent to the application of the original S-ELM to a transformed ELM space. The experimental results show that the incorporation of geometric data relationships in S-ELM can lead to enhanced performance.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Signal Processing, Research Community on Data-to-Decision (D2D), Aristotle University of Thessaloniki, Department of Informatics, Aristotle University of Thessaloniki
Contributors: Iosifidis, A., Tefas, A., Pitas, I.
Number of pages: 5
Pages: 192-196
Publication date: 1 Nov 2015
Peer-reviewed: Yes

Publication information

Journal: Pattern Recognition Letters
Volume: 65
ISSN (Print): 0167-8655
Ratings: 
  • Scopus rating (2015): CiteScore 5.1 SJR 0.95 SNIP 2.002
Original language: English
ASJC Scopus subject areas: Software, Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing
Keywords: Intrinsic graphs, Single-hidden layer neural networks, Sparse extreme learning machine
Source: Scopus
Source ID: 84940388000

Research output: Contribution to journalArticleScientificpeer-review

Model selection for linear classifiers using Bayesian error estimation

Regularized linear models are important classification methods for high dimensional problems, where regularized linear classifiers are often preferred due to their ability to avoid overfitting. The degree of freedom of the model dis determined by a regularization parameter, which is typically selected using counting based approaches, such as K-fold cross-validation. For large data, this can be very time consuming, and, for small sample sizes, the accuracy of the model selection is limited by the large variance of CV error estimates. In this paper, we study the applicability of a recently proposed Bayesian error estimator for the selection of the best model along the regularization path. We also propose an extension of the estimator that allows model selection in multiclass cases and study its efficiency with L-1 regularized logistic regression and L-2 regularized linear support vector machine. The model selection by the new Bayesian error estimator is experimentally shown to improve the classification accuracy, especially in small sample-size situations, and is able to avoid the excess variability inherent to traditional cross-validation approaches. Moreover, the method has significantly smaller computational complexity than cross-validation. (C) 2015 Elsevier Ltd. All rights reserved.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Signal Processing, Research group: Vision, Research Community on Data-to-Decision (D2D), Universidad Carlos III de Madrid
Contributors: Huttunen, H., Tohka, J.
Number of pages: 10
Pages: 3739-3748
Publication date: Nov 2015
Peer-reviewed: Yes

Publication information

Journal: Pattern Recognition
Volume: 48
Issue number: 11
ISSN (Print): 0031-3203
Ratings: 
  • Scopus rating (2015): CiteScore 8.6 SJR 1.579 SNIP 2.996
Original language: English
ASJC Scopus subject areas: Software, Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing
Keywords: Logistic regression, Support vector machine, Regularization, Bayesian error estimator, Linear classifier, MULTINOMIAL LOGISTIC-REGRESSION, SUPPORT VECTOR MACHINES, CLASSIFICATION, PERFORMANCE, BOUNDS

Bibliographical note

EXT="Tohka, Jussi"

Source: Scopus
Source ID: 84937812363

Research output: Contribution to journalArticleScientificpeer-review

Automatic image-based detection and inspection of paper fibres for grasping

An automatic computer vision algorithm that detects individual paper fibres from an image, assesses the possibility of grasping the detected fibres with microgrippers and detects the suitable grasping points is presented. The goal of the algorithm is to enable automatic fibre manipulation for mechanical characterisation, which has traditionally been slow manual work. The algorithm classifies the objects in images based on their morphology, and detects the proper grasp points from the individual fibres by applying given geometrical constraints. The authors test the ability of the algorithm to detect the individual fibres with 35 images containing more than 500 fibres in total, and also compare the graspability analysis and the calculated grasp points with the results of an experienced human operator with 15 images that contain a total of almost 200 fibres. The detection results are outstanding, with fewer than 1% of fibres missed. The graspability analysis gives sensitivity of 0.83 and specificity of 0.92, and the average distance between the grasp points of the human and the algorithm is 220 μm. Also, the choices made by the algorithm are much more consistent than the human choices.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Automation Science and Engineering, Integrated Technologies for Tissue Engineering Research (ITTE)
Contributors: Hirvonen, J., Kallio, P.
Number of pages: 7
Pages: 588-594
Publication date: 1 Aug 2015
Peer-reviewed: Yes

Publication information

Journal: IET Computer Vision
Volume: 9
Issue number: 4
ISSN (Print): 1751-9632
Ratings: 
  • Scopus rating (2015): CiteScore 2.3 SJR 0.3 SNIP 1.218
Original language: English
ASJC Scopus subject areas: Computer Vision and Pattern Recognition, Software
Electronic versions: 
Source: Scopus
Source ID: 84938530267

Research output: Contribution to journalArticleScientificpeer-review

Railway fastener inspection by real-time machine vision

In this paper, a real-time railway fastener detection system using a high-speed laser range finder camera is presented. First, an extensive analysis of various methods based on pixel-wise and histogram similarities are conducted on a specific railway route. Then, a fusing stage is introduced which combines least correlated approaches also considering the performance upgrade after fusing. Then, the resulting method is tested on a larger database collected from a different railway route. After observing repeated successes, the method is implemented on NI LabVIEW and run real-time with a high-speed 3-D camera placed under a railway carriage designed for railway quality inspection.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Signal Processing, Research group: Video, Middle East Technical University, Electrical and Electronics Engineering Department
Contributors: Aytekin, C., Rezaeitabar, Y., Dogru, S., Ulusoy, I.
Number of pages: 7
Pages: 1101-1107
Publication date: 1 Jul 2015
Peer-reviewed: Yes

Publication information

Journal: IEEE Transactions on Systems, Man, and Cybernetics: Systems
Volume: 45
Issue number: 7
ISSN (Print): 1083-4427
Ratings: 
  • Scopus rating (2015): CiteScore 6.1 SJR 1.273 SNIP 2.189
Original language: English
ASJC Scopus subject areas: Computer Science Applications, Human-Computer Interaction, Software, Control and Systems Engineering, Electrical and Electronic Engineering
Keywords: High-speed laser range finder, railway fastener detection, railway inspection
Source: Scopus
Source ID: 84932638036

Research output: Contribution to journalArticleScientificpeer-review

Information retrieval approach to meta-visualization

Visualization is crucial in the first steps of data analysis. In visual data exploration with scatter plots, no single plot is sufficient to analyze complicated high-dimensional data sets. Given numerous visualizations created with different features or methods, meta-visualization is needed to analyze the visualizations together. We solve how to arrange numerous visualizations onto a meta-visualization display, so that their similarities and differences can be analyzed. Visualization has recently been formalized as an information retrieval task; we extend this approach, and formalize meta-visualization as an information retrieval task whose performance can be rigorously quantified and optimized. We introduce a machine learning approach to optimize the meta-visualization, based on an information retrieval perspective: two visualizations are similar if the analyst would retrieve similar neighborhoods between data samples from either visualization. Based on the approach, we introduce a nonlinear embedding method for meta-visualization: it optimizes locations of visualizations on a display, so that visualizations giving similar information about data are close to each other. In experiments we show such meta-visualization outperforms alternatives, and yields insight into data in several case studies.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Research Community on Data-to-Decision (D2D), Aalto University
Contributors: Peltonen, J., Lin, Z.
Number of pages: 41
Pages: 189-229
Publication date: 1 May 2015
Peer-reviewed: Yes

Publication information

Journal: Machine Learning
Volume: 99
Issue number: 2
ISSN (Print): 0885-6125
Ratings: 
  • Scopus rating (2015): CiteScore 5.2 SJR 1.257 SNIP 2.054
Original language: English
ASJC Scopus subject areas: Software, Artificial Intelligence
Keywords: Meta-visualization, Neighbor embedding, Nonlinear dimensionality reduction
Source: Scopus
Source ID: 84939887799

Research output: Contribution to journalArticleScientificpeer-review

On the kernel Extreme Learning Machine classifier

In this paper, we discuss the connection of the kernel versions of the ELM classifier with infinite Single-hidden Layer Feedforward Neural networks and show that the original ELM kernel definition can be adopted for the calculation of the ELM kernel matrix for two of the most common activation functions, i.e., the RBF and the sigmoid functions. In addition, we show that a low-rank decomposition of the kernel matrix defined on the input training data can be exploited in order to determine an appropriate ELM space for input data mapping. The ELM space determined from this process can be subsequently used for network training using the original ELM formulation. Experimental results denote that the adoption of the low-rank decomposition-based ELM space determination leads to enhanced performance, when compared to the standard choice, i.e., random input weights generation.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Research Community on Data-to-Decision (D2D), Aristotle University of Thessaloniki, Department of Informatics
Contributors: Iosifidis, A., Tefas, A., Pitas, I.
Number of pages: 7
Pages: 11-17
Publication date: 1 Mar 2015
Peer-reviewed: Yes

Publication information

Journal: Pattern Recognition Letters
Volume: 54
ISSN (Print): 0167-8655
Ratings: 
  • Scopus rating (2015): CiteScore 5.1 SJR 0.95 SNIP 2.002
Original language: English
ASJC Scopus subject areas: Software, Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing
Keywords: Extreme learning machine, Infinite networks, Single-hidden layer networks
Source: Scopus
Source ID: 84920068822

Research output: Contribution to journalArticleScientificpeer-review

The MOBISERV-AIIA eating and drinking multi-view database for vision-based assisted living

Assisted living has a particular social importance in most developed societies, due to the increased life expectancy of the general population and the ensuing ageing problems. It has also importance for the provision of improved home care in cases of disabled persons or persons suffering from certain diseases that have high social impact. In this context, the development of computer vision systems capable to identify human eating and drinking activity can be really useful in order to prevent undernourishment/malnutrition and dehydration in a smart home environment targeting to extend independent living of older persons in the early stage of dementia. In this paper, we first describe the human centered interface specifications and implementations for such a system, which can be supported by ambient intelligence and robotic technologies. We, subsequently, describe a multi-view eating and drinking activity recognition database that has been created in order to facilitate research towards this direction. The database has been created by using four cameras in order to produce multi-view videos, each depicting one of twelve persons having a meal, resulting to a database size equal to 59.68 hours in total. Various types of meals have been recorded, i.e., breakfast, lunch and fast food. Moreover, the persons have different sizes, clothing and are of different sex. The database has been annotated in a frame base in terms of person ID and activity class. We hope that such a database will serve as a benchmark data set for computer vision researchers in order to devise methods targeting to this important application.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Research Community on Data-to-Decision (D2D), School of Dentistry, Aristotle University of Thessaloniki, Department of Informatics
Contributors: Iosifidis, A., Marami, E., Tefas, A., Pitas, I., Lyroudia, K.
Number of pages: 20
Pages: 254-273
Publication date: 1 Mar 2015
Peer-reviewed: Yes

Publication information

Journal: Journal of Information Hiding and Multimedia Signal Processing
Volume: 6
Issue number: 2
ISSN (Print): 2073-4212
Ratings: 
  • Scopus rating (2015): CiteScore 2.6 SJR 0.414 SNIP 1.483
Original language: English
ASJC Scopus subject areas: Computer Vision and Pattern Recognition, Software
Keywords: Activity recognition, Multiview video database, Nutrition assistance, Smart home environment
Source: Scopus
Source ID: 84911457722

Research output: Contribution to journalArticleScientificpeer-review

The highways and country roads to continuous deployment

As part of a Finnish research program, researchers interviewed 15 information and communications technology companies to determine the extent to which the companies adopted continuous deployment. They also aimed to find out why continuous deployment is considered beneficial and what the obstacles are to its full adoption. The benefits mentioned the most often were the ability to get faster feedback, the ability to deploy more often to keep customers satisfied, and improved quality and productivity. Despite understanding the benefits, none of the companies adopted a fully automatic deployment pipeline. The companies also had higher continuous-deployment capability than what they practiced. In many cases, they consciously chose to not aim for full continuous deployment. Obstacles to full adoption included domain-imposed restrictions, resistance to change, customer desires, and developers' skill and confidence.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Pervasive Computing, Research area: Software engineering, Aalto University, University of Helsinki
Contributors: Leppänen, M., Mäkinen, S., Pagels, M., Eloranta, V., Itkonen, J., Mäntylä, M. V., Männistö, T.
Number of pages: 9
Pages: 64-72
Publication date: 1 Mar 2015
Peer-reviewed: Yes

Publication information

Journal: IEEE Software
Volume: 32
Issue number: 2
ISSN (Print): 0740-7459
Ratings: 
  • Scopus rating (2015): CiteScore 3.5 SJR 0.528 SNIP 1.762
Original language: English
ASJC Scopus subject areas: Software
Keywords: continuous delivery, continuous deployment, continuous integration, software development, software engineering, thematic analysis
Source: Scopus
Source ID: 84925158464

Research output: Contribution to journalArticleScientificpeer-review

Fault tolerant control architecture design for mobile manipulation in scientific facilities

This paper describes one of the challenging issues implied by scientific infrastructures on a mobile robot cognition architecture. For a generally applicable cognition architecture, we study the dependencies and logical relations between several tasks and subsystems. The overall view of the software modules is described, including their relationship with a fault management module that monitors the consistency of the data flow among the modules. The fault management module is the solution of the deliberative architecture for the single point failures, and the safety anchor is the reactive solution for the faults by redundant equipment. In addition, a hardware architecture is proposed to ensure safe robot movement as a redundancy for the cognition of the robot. The method is designed for a four-wheel steerable (4WS) mobile manipulator (iMoro) as a case study.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Intelligent Hydraulics and Automation, Research group: Mobile manipulation, Research group: Field robotics and control, Field robotics for efficient work sites (FIRE)
Contributors: M. Aref, M., Oftadeh, R., Ghabcheloo, R., Mattila, J.
Publication date: 29 Jan 2015
Peer-reviewed: Yes

Publication information

Journal: international Journal of Advanced Robotic Systems
Volume: 12
Issue number: 4
ISSN (Print): 1729-8806
Ratings: 
  • Scopus rating (2015): CiteScore 2.1 SJR 0.346 SNIP 0.932
Original language: English
ASJC Scopus subject areas: Software, Artificial Intelligence, Computer Science Applications
Keywords: Architecture design, Autonomous vehicle drive, Cognition, Mobile robot, Remote handling
Source: Scopus
Source ID: 84923377541

Research output: Contribution to journalArticleScientificpeer-review

Image database TID2013: Peculiarities, results and perspectives

This paper describes a recently created image database, TID2013, intended for evaluation of full-reference visual quality assessment metrics. With respect to TID2008, the new database contains a larger number (3000) of test images obtained from 25 reference images, 24 types of distortions for each reference image, and 5 levels for each type of distortion. Motivations for introducing 7 new types of distortions and one additional level of distortions are given; examples of distorted images are presented. Mean opinion scores (MOS) for the new database have been collected by performing 985 subjective experiments with volunteers (observers) from five countries (Finland, France, Italy, Ukraine, and USA). The availability of MOS allows the use of the designed database as a fundamental tool for assessing the effectiveness of visual quality. Furthermore, existing visual quality metrics have been tested with the proposed database and the collected results have been analyzed using rank order correlation coefficients between MOS and considered metrics. These correlation indices have been obtained both considering the full set of distorted images and specific image subsets, for highlighting advantages and drawbacks of existing, state of the art, quality metrics. Approaches to thorough performance analysis for a given metric are presented to detect practical situations or distortion types for which this metric is not adequate enough to human perception. The created image database and the collected MOS values are freely available for downloading and utilization for scientific purposes.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Signal Processing, Research group: Computational Imaging-CI, Research group: Algebraic and Algorithmic Methods in Signal Processing AAMSP, Signal Processing Research Community (SPRC), National Aerospace University, Dept of Transmitters, Receivers and Signal Processing, University of Rennes 1 - IETR, Media Communications Lab, USC Viterbi School of Engineering
Contributors: Ponomarenko, N., Jin, L., Ieremeiev, O., Lukin, V., Egiazarian, K., Astola, J., Vozel, B., Chehdi, K., Carli, M., Battisti, F., Jay Kuo, C. C.
Number of pages: 21
Pages: 57-77
Publication date: 1 Jan 2015
Peer-reviewed: Yes

Publication information

Journal: Signal Processing: Image Communication
Volume: 30
ISSN (Print): 0923-5965
Ratings: 
  • Scopus rating (2015): CiteScore 4 SJR 0.532 SNIP 1.413
Original language: English
ASJC Scopus subject areas: Computer Vision and Pattern Recognition, Signal Processing, Software, Electrical and Electronic Engineering
Keywords: Image denoising, Image lossy compression, Image visual quality metrics
Source: Scopus
Source ID: 84919839405

Research output: Contribution to journalArticleScientificpeer-review

Social behavior in bacterial nanonetworks: Challenges and opportunities

Molecular communication holds the promise to enable communication between nanomachines with a view to increasing their functionalities and opening up new possible applications. Due to some of the biological properties, bacteria have been proposed as a possible information carrier for molecular communication, and the corresponding communication networks are known as bacterial nanonetworks. The biological properties include the ability for bacteria to mobilize between locations and carry the information encoded in deoxyribonucleic acid molecules. However, similar to most organisms, bacteria have complex social properties that govern their colony. These social characteristics enable the bacteria to evolve through various fluctuating environmental conditions by utilizing cooperative and non-cooperative behaviors. This article provides an overview of the different types of cooperative and non-cooperative social behavior of bacteria. The challenges (due to non-cooperation) and the opportunities (due to cooperation) these behaviors can bring to the reliability of communication in bacterial nanonetworks are also discussed. Finally, simulation results on the impact of bacterial cooperative social behavior on the end-to-end reliability of a single-link bacterial nanonetwork are presented. The article concludes by highlighting the potential future research opportunities in this emerging field.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Electronics and Communications Engineering, Research group: Emerging Technologies for Nano-Bio-Info-Cogno, Wireless Communications and Positioning (WICO), University of Manitoba
Contributors: Hasan, M., Hossain, E., Balasubramaniam, S., Koucheryavy, Y.
Number of pages: 9
Pages: 26-34
Publication date: 1 Jan 2015
Peer-reviewed: Yes

Publication information

Journal: IEEE Network
Volume: 29
Issue number: 1
Article number: 7018200
ISSN (Print): 0890-8044
Ratings: 
  • Scopus rating (2015): CiteScore 7.9 SJR 1.107 SNIP 2.903
Original language: English
ASJC Scopus subject areas: Computer Networks and Communications, Hardware and Architecture, Information Systems, Software
Source: Scopus
Source ID: 84921862364

Research output: Contribution to journalArticleScientificpeer-review

Distant speech separation using predicted time-frequency masks from spatial features

Speech separation algorithms are faced with a difficult task of producing high degree of separation without containing unwanted artifacts. The time-frequency (T-F) masking technique applies a real-valued (or binary) mask on top of the signal's spectrum to filter out unwanted components. The practical difficulty lies in the mask estimation. Often, using efficient masks engineered for separation performance leads to presence of unwanted musical noise artifacts in the separated signal. This lowers the perceptual quality and intelligibility of the output. Microphone arrays have been long studied for processing of distant speech. This work uses a feed-forward neural network for mapping microphone array's spatial features into a T-F mask. Wiener filter is used as a desired mask for training the neural network using speech examples in simulated setting. The T-F masks predicted by the neural network are combined to obtain an enhanced separation mask that exploits the information regarding interference between all sources. The final mask is applied to the delay-and-sum beamformer (DSB) output. The algorithm's objective separation capability in conjunction with the separated speech intelligibility is tested with recorded speech from distant talkers in two rooms from two distances. The results show improvement in instrumental measure for intelligibility and frequency-weighted SNR over complex-valued non-negative matrix factorization (CNMF) source separation approach, spatial sound source separation, and conventional beamforming methods such as the DSB and minimum variance distortionless response (MVDR).

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Signal Processing, Research group: Audio research group
Contributors: Pertilä, P., Nikunen, J.
Number of pages: 10
Pages: 97-106
Publication date: 2015
Peer-reviewed: Yes

Publication information

Journal: Speech Communication
Volume: 68
ISSN (Print): 0167-6393
Ratings: 
  • Scopus rating (2015): CiteScore 4.1 SJR 0.49 SNIP 1.612
Original language: English
ASJC Scopus subject areas: Modelling and Simulation, Computer Science Applications, Computer Vision and Pattern Recognition, Software, Communication, Linguistics and Language, Language and Linguistics
Keywords: Beamforming, Microphone arrays, Neural networks, Speech separation, Time-frequency masking
Source: Scopus
Source ID: 84923277715

Research output: Contribution to journalArticleScientificpeer-review

Analytical model in discrete time for cross-layer video communication over LTE

Since video traffic is resource intensive, it is a challenging issue to stream video over low bandwidth networks, whereas video communication over LTE becomes an open research topic nowadays due to LTE’s high throughput capabilities. Indeed, video transmission requires low delay, and wireless channel is time-varying, which result in a scenario when a layer-separated design is replaced by a Cross-Layer Adaptation (CLA) principle. In this paper an efficient analytical model that evaluates the behavior of the downlink LTE channel with CLA is presented. To the best of our knowledge, this is the first time an analytical model using CLA principle has been devised that covers both the transmission process from the eNB to the User Equipment (UE) at the first phase and video decoding process at the UE at the second phase. In order to ensure the cross-layer adaptation in the model, the arrival rate varies based on the received video request, whereas the service probability changes according to the channel quality indicator sent from the UE. In the experimental part the analysis of the main performance measures found from the stationary distribution is conducted.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Signal Processing, Research group: Video, Research Community on Data-to-Decision (D2D), Department of Telecommunication Systems, Peoples’ Friendship University of Russia
Contributors: Efimushkina, T., Gabbouj, M., Samuylov, K.
Number of pages: 13
Pages: 345-357
Publication date: 2015
Peer-reviewed: Yes

Publication information

Journal: Automatic Control and Computer Sciences
Volume: 48
Issue number: 6
ISSN (Print): 0146-4116
Ratings: 
  • Scopus rating (2015): CiteScore 0.4 SJR 0.184 SNIP 0.561
Original language: English
ASJC Scopus subject areas: Signal Processing, Software, Control and Systems Engineering
Keywords: cross-layer adaptation, DASH, downlink, LTE, OFDMA, queuing system, stationary distribution
Source: Scopus
Source ID: 84920176216

Research output: Contribution to journalArticleScientificpeer-review

Cultural influence on online community use: A cross-cultural study on online exercise diary users of three nationalities

This study investigates the influence of culture on the use of a website intended for tracking exercise activities. The data was collected using an online survey with 258 respondents from three national backgrounds: Germany, the USA and Spain. In the analysis, the focus was on determining whether users' cultural background impacts their use and perception of the site, especially as concerns social networking and the sharing of content. The Spanish were most interested in social networking, collaboration and sharing content with others, whereas the German participants were the least interested in these activities. The applicability of Hofstede's cultural theory in the explanation of differences between national cultures in online community use is discussed.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Pervasive Computing, University of Tampere
Contributors: Malinen, S., Nurkka, P.
Number of pages: 17
Pages: 153-169
Publication date: 2015
Peer-reviewed: Yes

Publication information

Journal: International Journal of Web Based Communities
Volume: 11
Issue number: 2
ISSN (Print): 1477-8394
Ratings: 
  • Scopus rating (2015): CiteScore 1.4 SJR 0.268 SNIP 0.406
Original language: English
ASJC Scopus subject areas: Computer Networks and Communications, Software, Education, Communication
Keywords: Cross-cultural research, Health and wellness applications, Online communities, SNSs, Social network sites

Bibliographical note

EXT="Malinen, Sanna"

Source: Scopus
Source ID: 84927129737

Research output: Contribution to journalArticleScientificpeer-review

Quality measures for improving technology trees

The quality of technology trees in digital games can be improved by adjusting their structural and quantitative properties. Therefore, there is a demand for recognizing and measuring such properties. Part of the process can be automated; there are properties measurable by computers, and analyses based on the results (and visualizations of them) may help to produce significantly better technology trees, even practically without extra workload for humans. In this paper, we introduce useful technology tree properties and novel measuring features implemented into our sofware tool for manipulating technology trees.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Mathematics, Research group: MAT Computer Science and Applied Logics
Contributors: Heinimäki, T. J., Elomaa, T.
Number of pages: 10
Publication date: 2015
Peer-reviewed: Yes

Publication information

Journal: International Journal of Computer Games Technology
Volume: 2015
Article number: 975371
ISSN (Print): 1687-7047
Ratings: 
  • Scopus rating (2015): CiteScore 1 SJR 0.204 SNIP 0.366
Original language: English
ASJC Scopus subject areas: Human-Computer Interaction, Software, Computer Graphics and Computer-Aided Design
Source: Scopus
Source ID: 84929378426

Research output: Contribution to journalArticleScientificpeer-review

Subjective evaluation of Super Multi-View compressed contents on high-end light-field 3D displays

Super Multi-View (SMV) video content is composed of tens or hundreds of views that provide a light-field representation of a scene. This representation allows a glass-free visualization and eliminates many causes of discomfort existing in current available 3D video technologies. Efficient video compression of SMV content is a key factor for enabling future 3D video services. This paper first compares several coding configurations for SMV content and several inter-view prediction structures are also tested and compared. The experiments mainly suggest that large differences in coding efficiency can be observed from one configuration to another. Several ratios for the number of coded and synthesized views are compared, both objectively and subjectively. It is reported that view synthesis significantly affects the coding scheme. The amount of views to skip highly depends on the sequence and on the quality of the associated depth maps. Reported ranges of bitrates required to obtain a good quality for the tested SMV content are realistic and coherent with future 4. K/8. K needs. The reliability of the PSNR metric for SMV content is also studied. Objective and subjective results show that PSNR is able to reflect increase or decrease in subjective quality even in the presence of synthesized views. However, depending on the ratio of coded and synthesized views, the order of magnitude of the effective quality variation is biased by PSNR. Results indicate that PSNR is less tolerant to view synthesis artifacts than human viewers. Finally, preliminary observations are initiated. First, the light-field conversion step does not seem to alter the objective results for compression. Secondly, the motion parallax does not seem to be impacted by specific compression artifacts. The perception of the motion parallax is only altered by variations of the typical compression artifacts along the viewing angle, in cases where the subjective image quality is already low. To the best of our knowledge, this paper is the first to carry out subjective experiments and to report results of SMV compression for light-field 3D displays. It provides first results showing that improvement of compression efficiency is required, as well as depth estimation and view synthesis algorithms improvement, but that the use of SMV appears realistic according to next generation compression technology requirements.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Signal Processing, Orange Labs, Holografika Kft., Pamany Peter Katolikus Egyetem
Contributors: Dricot, A., Jung, J., Cagnazzo, M., Pesquet, B., Dufaux, F., Kovács, P., Adhikarla, V. K.
Pages: 369–385
Publication date: 2015
Peer-reviewed: Yes

Publication information

Journal: Signal Processing: Image Communication
Volume: 39
Issue number: Part B
ISSN (Print): 0923-5965
Ratings: 
  • Scopus rating (2015): CiteScore 4 SJR 0.532 SNIP 1.413
Original language: English
ASJC Scopus subject areas: Computer Vision and Pattern Recognition, Signal Processing, Software, Electrical and Electronic Engineering
Keywords: 3D, Light-field, Subjective evaluation, Super Multi-View, Video coding, Video compression
Source: Scopus
Source ID: 84947865722

Research output: Contribution to journalArticleScientificpeer-review

On constructibility and unconstructibility of LTS operators from other LTS operators

An LTS operator can be constructed from a set of LTS operators up to an equivalence if and only if there is an LTS expression that only contains operators from the set and whose result is equivalent to the result of the operator. In this publication this idea is made precise in the context where each LTS has an alphabet of its own and the operators may depend on the alphabets. Then the extent to which LTS operators are constructible is studied. Most, if not all, established LTS operators have the property that each trace of the result arises from the execution of no more than one trace of each of its argument LTSs, and similarly for infinite traces. All LTS operators that have this property and satisfy some other rather weak regularity properties can be constructed from parallel composition and hiding up to the equivalence that compares the alphabets, traces, and infinite traces of the LTSs. Furthermore, a collection of other miscellaneous constructibility and unconstructibility results is presented.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Mathematics, Regulation of learning and active learning methods (REALMEE)
Contributors: Valmari, A.
Number of pages: 28
Pages: 207-234
Publication date: 2015
Peer-reviewed: Yes

Publication information

Journal: Acta Informatica
Volume: 52
Issue number: 2-3
ISSN (Print): 0001-5903
Ratings: 
  • Scopus rating (2015): CiteScore 1.7 SJR 0.421 SNIP 0.736
Original language: English
ASJC Scopus subject areas: Computer Networks and Communications, Information Systems, Software
Electronic versions: 
Source: Scopus
Source ID: 84925463574

Research output: Contribution to journalArticleScientificpeer-review

Dynamic text presentation in print interpreting - An eye movement study of reading behaviour

Print interpreting supports people with a hearing disability by giving them access to spoken language. In print interpreting, the interpreter types the spoken text in real time for the hard-of-hearing client to read. This results in dynamic text presentation. An eye movement study was conducted to compare two types of dynamic text presentation formats in print interpreting: letter-by-letter and word-by-word. Gaze path analysis with 20 hearing participants showed different types of reading behaviour during reading of two pieces of text in these two presentation formats. Our analysis revealed that the text presentation format has a significant effect on reading behaviour. Rereading and regressions occurred significantly more often with the word-by-word format than with the letter-by-letter format. We also found a significant difference between the number of regressions starting at the words that end a sentence and that of regressions starting at all other words. The frequency of rereading was significantly higher for incorrectly typed or abbreviated words than for the other words. Analysis of the post-test questionnaire found almost equal acceptance of the word-by-word and letter-by-letter formats by the participants. A follow-up study with 18 hard-of-hearing participants showed a similar trend in results. The findings of this study highlight the importance of developing print interpreting tools that allow the interpreter and the client to choose the options that best facilitate the communication. They also bring up the need to develop new eye movement metrics for analysing the reading of dynamic text, and provide first results on a new dynamic presentation context.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Augmented Human Activities (AHA), School of Management (JKK)
Contributors: Sharmin, S., Špakov, O., Räihä, K. J.
Number of pages: 14
Pages: 17-30
Publication date: 2015
Peer-reviewed: Yes

Publication information

Journal: International Journal of Human-Computer Studies
Volume: 78
ISSN (Print): 1071-5819
Ratings: 
  • Scopus rating (2015): CiteScore 4.4 SJR 0.666 SNIP 1.739
Original language: English
ASJC Scopus subject areas: Human Factors and Ergonomics, Software, Education, Engineering(all), Human-Computer Interaction, Hardware and Architecture
Keywords: Dynamic text presentation, Eye movements, Print interpreting, Reading, Regressions
Source: Scopus
Source ID: 84923618729

Research output: Contribution to journalArticleScientificpeer-review

Majorization-minimization for manifold embedding

Nonlinear dimensionality reduction by manifold embedding has become a popular and powerful approach both for visualization and as preprocessing for predictive tasks, but more efficient optimization algorithms are still crucially needed. Majorization-Minimization (MM) is a promising approach that monotonically decreases the cost function, but it remains unknown how to tightly majorize the manifold embedding objective functions such that the resulting MM algorithms are efficient and robust. We propose a new MM procedure that yields fast MM algorithms for a wide variety of manifold embedding problems. In our majorization step, two parts of the cost function are respectively upper bounded by quadratic and Lipschitz surrogates, and the resulting upper bound can be minimized in closed form. For cost functions amenable to such QL-majorization, the MM yields monotonic improvement and is efficient: In experiments, the newly developed MM algorithms outperformed five state-ofthe-art optimization approaches in manifold embedding tasks.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Research Community on Data-to-Decision (D2D), Aalto University
Contributors: Yang, Z., Peltonen, J., Kaski, S.
Number of pages: 10
Pages: 1088-1097
Publication date: 2015
Peer-reviewed: Yes

Publication information

Journal: Journal of Machine Learning Research
Volume: 38
ISSN (Print): 1532-4435
Ratings: 
  • Scopus rating (2015): CiteScore 4.5 SJR 1.431 SNIP 2.032
Original language: English
ASJC Scopus subject areas: Control and Systems Engineering, Software, Statistics and Probability, Artificial Intelligence
Source: Scopus
Source ID: 84954311496

Research output: Contribution to journalArticleScientificpeer-review

Schoolchildren's user experiences on a physical exercise game utilizing lighting and audio

Motivated by the troubling news on decreased exercise amount and increased obesity among children and adolescents, we investigated the possibilities of interactive lighting technology in encouraging children to participate in physical exercise in schools. We have created a story-driven physical exercise game based on light and sound utilizing a reasonably priced technological setup. The game has been evaluated with several groups of schoolchildren during physical education classes. The results show that a physical exercise game enhanced with lighting and audio keeps schoolchildren motivated both mentally and physically even after several playtimes. In subjective evaluations, participants still found the story of the game interesting after three playtimes, and were eager to exercise this way again.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Augmented Human Activities (AHA), Mathematical modelling with wide societal impact (MathImpact), University of Tampere
Contributors: Keskinen, T., Hakulinen, J., Turunen, M., Heimonen, T., Sand, A., Paavilainen, J., Parviainen, J., Yrjänäinen, S., Mäyrä, F., Okkonen, J., Raisamo, R.
Number of pages: 10
Pages: 475-484
Publication date: 1 Dec 2014
Peer-reviewed: Yes

Publication information

Journal: Entertainment Computing
Volume: 5
Issue number: 4
ISSN (Print): 1875-9521
Ratings: 
  • Scopus rating (2014): CiteScore 2.2 SJR 0.404 SNIP 1.424
Original language: English
ASJC Scopus subject areas: Software, Human-Computer Interaction
Keywords: Exergaming, Interactive lighting, Physical education, Schoolchildren, Storytelling, User experience
Source: Scopus
Source ID: 84912526011

Research output: Contribution to journalArticleScientificpeer-review

Kernel reference discriminant analysis

Linear Discriminant Analysis (LDA) and its nonlinear version Kernel Discriminant Analysis (KDA) are well-known and widely used techniques for supervised feature extraction and dimensionality reduction. They determine an optimal discriminant space for (non)linear data projection based on certain assumptions, e.g. on using normal distributions (either on the input or in the kernel space) for each class and employing class representation by the corresponding class mean vectors. However, there might be other vectors that can be used for classes representation, in order to increase class discrimination in the resulted feature space. In this paper, we propose an optimization scheme aiming at the optimal class representation, in terms of Fisher ratio maximization, for nonlinear data projection. Compared to the standard approach, the proposed optimization scheme increases class discrimination in the reduced-dimensionality feature space and achieves higher classification rates in publicly available data sets.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Research Community on Data-to-Decision (D2D), Aristotle University of Thessaloniki, Department of Informatics
Contributors: Iosifidis, A., Tefas, A., Pitas, I.
Number of pages: 7
Pages: 85-91
Publication date: 1 Nov 2014
Peer-reviewed: Yes

Publication information

Journal: Pattern Recognition Letters
Volume: 49
ISSN (Print): 0167-8655
Ratings: 
  • Scopus rating (2014): CiteScore 4.3 SJR 0.73 SNIP 2.131
Original language: English
ASJC Scopus subject areas: Software, Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing
Keywords: Kernel Discriminant Analysis, Kernel Spectral Regression, Optimized class representation
Source: Scopus
Source ID: 84904957982

Research output: Contribution to journalArticleScientificpeer-review

Discriminant Bag of Words based representation for human action recognition

In this paper we propose a novel framework for human action recognition based on Bag of Words (BoWs) action representation, that unifies discriminative codebook generation and discriminant subspace learning. The proposed framework is able to, naturally, incorporate several (linear or non-linear) discrimination criteria for discriminant BoWs-based action representation. An iterative optimization scheme is proposed for sequential discriminant BoWs-based action representation and codebook adaptation based on action discrimination in a reduced dimensionality feature space where action classes are better discriminated. Experiments on five publicly available data sets aiming at different application scenarios demonstrate that the proposed unified approach increases the codebook discriminative ability providing enhanced action classification performance.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Research Community on Data-to-Decision (D2D), Aristotle University of Thessaloniki, Department of Informatics
Contributors: Iosifidis, A., Tefas, A., Pitas, I.
Number of pages: 8
Pages: 185-192
Publication date: 1 Nov 2014
Peer-reviewed: Yes

Publication information

Journal: Pattern Recognition Letters
Volume: 49
ISSN (Print): 0167-8655
Ratings: 
  • Scopus rating (2014): CiteScore 4.3 SJR 0.73 SNIP 2.131
Original language: English
ASJC Scopus subject areas: Software, Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing
Keywords: Bag of Words, Codebook learning, Discriminant learning
Source: Scopus
Source ID: 84907347636

Research output: Contribution to journalArticleScientificpeer-review

Prediction models and techniques for Open Source Software projects: A systematic literature review

Open Source Software (OSS) is currently a widely adopted approach to developing and distributing software. For effective adoption of OSS, fundamental knowledge of project development is needed. This often calls for reliable prediction models to simulate project evolution and to envision project future. These models provide help in supporting preventive maintenance and building quality software. This paper reports on a systematic literature survey aimed at the identification and structuring of research that offer prediction models and techniques in analyzing OSS projects. In this review, we systematically selected and reviewed 52 peer reviewed articles that were published between January, 2000 and March, 2013. The study outcome provides insight in what constitutes the main contributions of the field, identifies gaps and opportunities, and distills several important future research directions.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Pervasive Computing, Chalmers and University of Gothenburg
Contributors: Syeed, M. M. M., Hammouda, I., Systä, T.
Number of pages: 39
Pages: 1-39
Publication date: 1 Apr 2014
Peer-reviewed: Yes

Publication information

Journal: International Journal of Open Source Software and Processes
Volume: 5
Issue number: 2
ISSN (Print): 1942-3926
Ratings: 
  • Scopus rating (2014): CiteScore 0.8 SJR 0.28 SNIP 0.291
Original language: English
ASJC Scopus subject areas: Software
Keywords: Fault prediction, Open Source Software, OSS community, Prediction, Systematic literature review

Bibliographical note

EXT="Hammouda, Imed"

Source: Scopus
Source ID: 84924346193

Research output: Contribution to journalArticleScientificpeer-review

Optimizing spatial and temporal reuse in wireless networks by decentralized partially observable markov decision processes

The performance of medium access control (MAC) depends on both spatial locations and traffic patterns of wireless agents. In contrast to conventional MAC policies, we propose a MAC solution that adapts to the prevailing spatial and temporal opportunities. The proposed solution is based on a decentralized partially observable Markov decision process (DEC-POMDP), which is able to handle wireless network dynamics described by a Markov model. A DEC-POMDP takes both sensor noise and partial observations into account, and yields MAC policies that are optimal for the network dynamics model. The DEC-POMDP MAC policies can be optimized for a freely chosen goal, such as maximal throughput or minimal latency, with the same algorithm. We make approximate optimization efficient by exploiting problem structure: the policies are optimized by a factored DEC-POMDP method, yielding highly compact state machine representations for MAC policies. Experiments show that our approach yields higher throughput and lower latency than CSMA/CA based comparison methods adapted to the current wireless network configuration.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Research Community on Data-to-Decision (D2D), Aalto University, Asparrow Ltd, Helsinki Institute for Information Technology
Contributors: Pajarinen, J., Hottinen, A., Peltonen, J.
Number of pages: 14
Pages: 866-879
Publication date: Apr 2014
Peer-reviewed: Yes

Publication information

Journal: IEEE Transactions on Mobile Computing
Volume: 13
Issue number: 4
Article number: 6482133
ISSN (Print): 1536-1233
Ratings: 
  • Scopus rating (2014): CiteScore 7.5 SJR 1.192 SNIP 3.51
Original language: English
ASJC Scopus subject areas: Software, Computer Networks and Communications, Electrical and Electronic Engineering
Keywords: decentralized POMDP, medium access control, multi-agent planning, Spatial reuse, wireless network
Source: Scopus
Source ID: 84897873909

Research output: Contribution to journalArticleScientificpeer-review

System integration for real-time mobile manipulation

Mobile manipulators are one of the most complicated types of mechatronics systems. The performance of these robots in performing complex manipulation tasks is highly correlated with the synchronization and integration of their low-level components. This paper discusses in detail the mechatronics design of a four wheel steered mobile manipulator. It presents the manipulator's mechanical structure and electrical interfaces, designs low-level software architecture based on embedded PC-based controls, and proposes a systematic solution based on code generation products of MATLAB and Simulink. The remote development environment described here is used to develop real-time controller software and modules for the mobile manipulator under a POSIX-compliant, real-time Linux operating system. Our approach enables developers to reliably design controller modules that meet the hard real-time constraints of the entire low-level system architecture. Moreover, it provides a systematic framework for the development and integration of hardware devices with various communication mediums and protocols, which facilitates the development and integration process of the software controller. © 2014 The Author(s). Licensee InTech.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Tampere University of Technology, Department of Intelligent Hydraulics and Automation, Research group: Mobile manipulation, Research group: Field robotics and control, Field robotics for efficient work sites (FIRE)
Contributors: Oftadeh, R., Aref, M. M., Ghabcheloo, R., Mattila, J.
Publication date: 28 Mar 2014
Peer-reviewed: Yes

Publication information

Journal: international Journal of Advanced Robotic Systems
Volume: 11
Issue number: 1
Article number: 51
ISSN (Print): 1729-8806
Ratings: 
  • Scopus rating (2014): CiteScore 1.4 SJR 0.297 SNIP 0.768
Original language: English
ASJC Scopus subject areas: Software, Artificial Intelligence, Computer Science Applications
Keywords: Autonomous vehicles, Mechatronic design, Mobile manipulators, Real-time systems

Bibliographical note

Contribution: organisation=iha,FACT1=1<br/>Portfolio EDEND: 2014-05-30<br/>Publisher name: InTech Open Access Publisher

Source: researchoutputwizard
Source ID: 1179

Research output: Contribution to journalArticleScientificpeer-review

A computational approach to construct a multivariate complete graph invariant

In this paper, we present a computational approach for finding complete graph invariants. Specifically, we generate exhaustive sets of connected, non-isomorphic graphs with 9 and 10 vertices and demonstrate that a 97-dimensional multivariate graph invariant is capable to distinguish each of the non-isomorphic graphs. Furthermore, in order to tame the computational complexity of the problem caused by the vast number of graphs, e.g., involving over 10 million networks with 10 vertices, we suggest a low-dimensional, iterative procedure that is based on highly discriminative individual graph invariants. We show that also this computational approach leads to a perfect discrimination. Overall, our numerical results prove the existence of such graph invariants for networks with 9 and 10 vertices. Furthermore, we show that our iterative approach has a polynomial time complexity.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Research Community on Data-to-Decision (D2D), 6060 Hall in Tyrol, Computational Biology and Machine Learning, Queen's University, Belfast, Northern Ireland
Contributors: Dehmer, M., Emmert-Streib, F., Grabner, M.
Number of pages: 9
Pages: 200-208
Publication date: 1 Mar 2014
Peer-reviewed: Yes

Publication information

Journal: Information Sciences
Volume: 260
ISSN (Print): 0020-0255
Ratings: 
  • Scopus rating (2014): CiteScore 7.4 SJR 2.226 SNIP 3.198
Original language: English
ASJC Scopus subject areas: Artificial Intelligence, Software, Control and Systems Engineering, Theoretical Computer Science, Computer Science Applications, Information Systems and Management
Keywords: Information inequality, Quantitative graph theory, Random network model, Statistics
Source: Scopus
Source ID: 84891738883

Research output: Contribution to journalArticleScientificpeer-review

Head movement and facial expressions as game input

This study aimed to develop and test a hands-free video game that utilizes information on the player's real-time face position and facial expressions as intrinsic elements of a gameplay. Special focus was given to investigating the user's subjective experiences in utilizing computer vision input in the game interaction. The player's goal was to steer a drunken character home as quickly as possible by moving their head. Additionally, the player could influence the behavior of game characters by using the facial expressions of frowning and smiling. The participants played the game with computer vision and a conventional joystick and rated the functionality of the control methods and their emotional and game experiences. The results showed that although the functionality of the joystick steering was rated higher than that of the computer vision method, the use of head movements and facial expressions enhanced the experiences of game playing in many ways. The participants rated playing with the computer vision technique as more entertaining, interesting, challenging, immersive, and arousing than doing so with a joystick. The results suggested that a high level of experienced arousal in the case of computer vision-based interaction may be a key factor for better experiences of game playing.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Augmented Human Activities (AHA)
Contributors: Ilves, M., Gizatdinova, Y., Surakka, V., Vankka, E.
Number of pages: 10
Pages: 147-156
Publication date: 2014
Peer-reviewed: Yes

Publication information

Journal: Entertainment Computing
Volume: 5
Issue number: 3
ISSN (Print): 1875-9521
Ratings: 
  • Scopus rating (2014): CiteScore 2.2 SJR 0.404 SNIP 1.424
Original language: English
ASJC Scopus subject areas: Software, Human-Computer Interaction
Keywords: Camera-based video game, Computer vision, Emotion, Face detection and tracking, Facial expression classification, Gameplay experience
Source: Scopus
Source ID: 84901983211

Research output: Contribution to journalArticleScientificpeer-review

Low-Power Reconfigurable Miniature Sensor Nodes for Condition Monitoring

Wireless sensor networks (WSNs) are being deployed at an escalating rate for various application fields. The ever growing number of application areas requires a diverse set of algorithms with disparate processing needs. WSNs also need to adapt to prevailing energy conditions and processing requirements. The preceding reasons rule out the use of a single fixed design. Instead, a general purpose design that can rapidly be adapted to different conditions and requirements is desired. In lieu of the traditional inflexible wireless sensor node consisting of a separate micro-controller, radio transceiver, sensor array and energy storage, we propose a unified rapidly reconfigurable miniature sensor node, implemented with a transport triggered architecture processor on a low-power Flash FPGA. To our knowledge, this is the first study of its kind. The proposed approach does not solely concentrate on energy efficiency but a high emphasis is also put on the ease of development perspective. Power consumption and silicon area usage comparison based on solutions implemented using our novel rapid design approach for wireless sensor nodes are performed. The comparison is performed between 16-bit fixed point, 16-bit floating point and 32-bit floating point implementations. The implemented processors and algorithms are intended for rolling bearing condition monitoring, but can be fully extended for other applications as well.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Signal Processing Research Community (SPRC), Univ of Oulu, Dept. of Computer Science and Engineering
Contributors: Nyländen, T., Boutellier, J., Nikunen, K., Hannuksela, J., Silvén, O.
Number of pages: 21
Pages: 3-23
Publication date: 2014
Peer-reviewed: Yes

Publication information

Journal: International Journal of Parallel Programming
Volume: 43
Issue number: 1
ISSN (Print): 0885-7458
Ratings: 
  • Scopus rating (2014): CiteScore 1.5 SJR 0.256 SNIP 1.046
Original language: English
ASJC Scopus subject areas: Theoretical Computer Science, Software, Information Systems
Keywords: Application specific processors, Transport triggered architecture, Wireless sensor networks
Source: Scopus
Source ID: 84921701379

Research output: Contribution to journalArticleScientificpeer-review

Automated design of networks of transport-triggered architecture processors using dynamic dataflow programs

Modern embedded systems show a clear trend towards the use of Multiprocessor System-on-Chip (MPSoC) architectures in order to handle the performance and power consumption constraints. However, the design and validation of dedicated MPSoCs is an extremely hard and expensive task due to their complexity. Thus, the development of automated design processes is of highest importance to satisfy the time-to-market pressure of embedded systems. This paper proposes an automated co-design flow based on the high-level language-based approach of the Reconfigurable Video Coding framework. The designer provides the application description in the RVC-CAL dataflow language, after which the presented co-design flow automatically generates a network of heterogeneous processors that can be synthesized on FPGA chips. The synthesized processors are Very Long Instruction Word-style processors. Such a methodology permits the rapid design of a many-core signal processing system which can take advantage of all levels of parallelism. The toolchain functionality has been demonstrated by synthesizing an MPEG-4 Simple Profile video decoder to two different FPGA boards. The decoder is realized into 18 processors that decode QCIF resolution video at 45 frames per second on a 50 MHz FPGA clock frequency. The results show that the given application can take advantage of every level of parallelism.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Signal Processing Research Community (SPRC), Universite de Rennes, CSE Department, Univ of Oulu, UBL
Contributors: Yviquel, H., Boutellier, J., Raulet, M., Casseau, E.
Number of pages: 8
Pages: 1295-1302
Publication date: Nov 2013
Peer-reviewed: Yes

Publication information

Journal: Signal Processing: Image Communication
Volume: 28
Issue number: 10
ISSN (Print): 0923-5965
Ratings: 
  • Scopus rating (2013): CiteScore 3.2 SJR 0.407 SNIP 1.301
Original language: English
ASJC Scopus subject areas: Software, Signal Processing, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering
Keywords: Co-design, Dataflow programming, Multi-Processor System-on-Chip (MPSoC), Reconfigurable Video Coding (RVC), Transport-Trigger Architecture (TTA)
Source: Scopus
Source ID: 84888203042

Research output: Contribution to journalArticleScientificpeer-review

Multi-view action recognition based on action volumes, fuzzy distances and cluster discriminant analysis

In this paper, we present a view-independent action recognition method exploiting a low computational-cost volumetric action representation. Binary images depicting the human body during action execution are accumulated in order to produce the so-called action volumes. A novel time-invariant action representation is obtained by exploiting the circular shift invariance property of the magnitudes of the Discrete Fourier Transform coefficients. The similarity of an action volume with representative action volumes is exploited in order to map it to a lower-dimensional feature space that preserves the action class properties. Discriminant learning is, subsequently, employed for further dimensionality reduction and action class discrimination. By using such an action representation, the proposed approach performs fast action recognition. By combining action recognition results coming from different view angles, high recognition rates are obtained. The proposed method is extended to interaction recognition, i.e., to human action recognition involving two persons. The proposed approach is evaluated on a publicly available action recognition database using experimental settings simulating situations that may appear in real-life applications, as well as on a new nutrition support action recognition database.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Research Community on Data-to-Decision (D2D), Aristotle University of Thessaloniki, Department of Informatics
Contributors: Iosifidis, A., Tefas, A., Pitas, I.
Number of pages: 13
Pages: 1445-1457
Publication date: Jun 2013
Peer-reviewed: Yes

Publication information

Journal: Signal Processing
Volume: 93
Issue number: 6
ISSN (Print): 0165-1684
Ratings: 
  • Scopus rating (2013): CiteScore 5.1 SJR 0.909 SNIP 2.244
Original language: English
ASJC Scopus subject areas: Electrical and Electronic Engineering, Control and Systems Engineering, Software, Signal Processing, Computer Vision and Pattern Recognition
Keywords: Action recognition, Action volumes, Cluster discriminant analysis, Fuzzy vector quantization
Source: Scopus
Source ID: 84875267100

Research output: Contribution to journalArticleScientificpeer-review

An evaluation of the virtual curvature with the StickGrip haptic device: A case study

Dynamic simulation of distance to the physical surface could promote the development of new inexpensive tools for blind and visually impaired users. The StickGrip is a haptic device comprised of the Wacom pen input device added with a motorized penholder. The goal of the research presented in this paper was to assess the accuracy and usefulness of the new pen-based interaction technique when the position and displacement of the penholder in relation to the pen tip provided haptic feedback to the user about the distance to the physical or virtual surface of interaction. The aim was to examine how accurately people are able (1) to align the randomly deformed virtual surfaces to the flat surface and (2) to adjust the number of surface samples having a randomly assigned curvature to the template having the given curvature and kept fixed. These questions were approached by measuring both the values of the adjusted parameters and the parameters of the human performance, such as a ratio between inspection time and control time spent by the participants to complete the matching task with the use of the StickGrip device. The test of the pen-based interaction technique was conducted in the absence of visual feedback when the subject could rely on the proprioception and kinesthetic sense. The results are expected to be useful for alternative visualization and interaction with complex topographic and mathematical surfaces, artwork, and modeling.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Augmented Human Activities (AHA)
Contributors: Evreinova, T. V., Evreinov, G., Raisamo, R.
Number of pages: 13
Pages: 161-173
Publication date: Jun 2013
Peer-reviewed: Yes

Publication information

Journal: Universal Access in the Information Society
Volume: 12
Issue number: 2
ISSN (Print): 1615-5289
Ratings: 
  • Scopus rating (2013): CiteScore 2.6 SJR 0.513 SNIP 1.516
Original language: English
ASJC Scopus subject areas: Software, Information Systems, Computer Networks and Communications, Human-Computer Interaction
Keywords: Curved surface, Kinesthetic feedback, Pen-based interaction, StickGrip haptic device
Source: Scopus
Source ID: 84878407340

Research output: Contribution to journalArticleScientificpeer-review

Indirect measurement of the vascular endothelial glycocalyx layer thickness in human submucosal capillaries with a plug-in for ImageJ

Background: The thickness of vascular endothelial glycocalyx layer can be measured indirectly during a spontaneous leukocyte passage from oral submucosal capillaries in humans. The subsequent differences in red blood cell (RBC) column widths, before a spontaneous white blood cell passage (pre-WBC) and after a spontaneous WBC passage (post-WBC) can be used in off-line analysis to measure glycocalyx thickness: [pre-WBC width - post-WBC width]/2. We created and validated a semi-automatic plug-in for ImageJ to measure the endothelial glycocalyx layer thickness. Methods: Video clips presenting human sublingual microvasculature were created with a side-stream dark field imaging device. Spontaneous leukocyte passages in capillaries were analyzed from video clips with ImageJ. The capillary glycocalyx layer thickness was measured by the indirect approach with two manual and two semi-automatic methods. Results: There were no statistically significant differences between glycocalyx layer thicknesses measured with different methods, even though small inter-method differences in RBC column thicknesses could be detected. Inter-rater differences were systematically smaller with both semi-automatic methods. Intra-rater coefficient of variation [CV] (95% CI) was largest when measurements were made completely manually [9.2% (8.4-10.0)], but improved significantly with automatic image enhancement prior to manual measurement [7.2% (6.4-8.0)]. CV could be improved further when using semi-automatic analysis with an in-frame median filter radius of 1 pixel [5.8% (5.0-6.6)], or a median filter radius of 2 pixels [4.3% (3.5-5.1)]. Conclusions: Semi-automatic analysis of glycocalyx decreased the intra-rater CV and the inter-rater differences compared to the manual method. On average, each of the four methods yielded equal results for the glycocalyx thickness. Being the only feasible bed side method in most clinical scenarios, indirect measurement of glycocalyx thickness with orthogonal polarization spectral imaging or side-stream dark field imaging device and our plug-in can advance the study of glycocalyx layer pathology in man.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Integrated Technologies for Tissue Engineering Research (ITTE), Helsinki University Central Hospital, University of Helsinki, Uppsala University, Tampere University Hospital
Contributors: Liuhanen, S., Sallisalmi, M., Pettilä, V., Oksala, N., Tenhunen, J.
Number of pages: 10
Pages: 38-47
Publication date: Apr 2013
Peer-reviewed: Yes

Publication information

Journal: Computer Methods and Programs in Biomedicine
Volume: 110
Issue number: 1
ISSN (Print): 0169-2607
Ratings: 
  • Scopus rating (2013): CiteScore 3.4 SJR 0.628 SNIP 1.459
Original language: English
ASJC Scopus subject areas: Computer Science Applications, Software, Health Informatics
Keywords: Endothelial surface layer, Glycocalyx, Imagej, Open source, Side-stream dark field
Source: Scopus
Source ID: 84875094399

Research output: Contribution to journalArticleScientificpeer-review

High-performance and low-energy buffer mapping method for multiprocessor DSP systems

When implementing digital signal processing (DSP) applications onto multiprocessor systems, one significant problem in the viewpoints of performance is the memory wall. In this paper, to help alleviate the memory wall problem, we propose a novel, high-performance buffer mapping policy for SDF-represented DSP applications on bus-based multiprocessor systems that support the shared-memory programming model. The proposed policy exploits the bank concurrency of the DRAM main memory system according to the analysis of hierarchical parallelism. Energy consumption is also a critical parameter, especially in battery-based embedded computing systems. In this paper, we apply a synchronization back-off scheme on the top of the proposed high-performance buffer mapping policy to reduce energy consumption. The energy saving is attained by minimizing the number of non-essential synchronization transactions. We measure throughput and energy consumption on both synthetic and real benchmarks. The simulation results show that the proposed buffer mapping policy is very useful in terms of performance, especially in memory-intensive applications where the total execution time of computational tasks is relatively small compared to that of memory operations. In addition, the proposed synchronization back-off scheme provides a reduction in the number of synchronization transactions without degrading performance, which results in system energy saving.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Signal Processing Research Community (SPRC), Georgia Institute of Technology, Department of ECE and Institute for Advanced Computer Studies, University of Maryland
Contributors: Lee, D., Wolf, M., Bhattacharyya, S. S.
Publication date: Mar 2013
Peer-reviewed: Yes

Publication information

Journal: ACM Transactions on Embedded Computing Systems
Volume: 12
Issue number: 3
Article number: 82
ISSN (Print): 1539-9087
Ratings: 
  • Scopus rating (2013): CiteScore 1.7 SJR 0.307 SNIP 0.982
Original language: English
ASJC Scopus subject areas: Software, Hardware and Architecture
Keywords: Bank concurrency, DRAM main memory systems, Multiprocessor DSP systems, SDF
Source: Scopus
Source ID: 84878495064

Research output: Contribution to journalArticleScientificpeer-review

On the optimal class representation in linear discriminant analysis

Linear discriminant analysis (LDA) is a widely used technique for supervised feature extraction and dimensionality reduction. LDA determines an optimal discriminant space for linear data projection based on certain assumptions, e.g., on using normal distributions for each class and employing class representation by the mean class vectors. However, there might be other vectors that can represent each class, to increase class discrimination. In this brief, we propose an optimization scheme aiming at the optimal class representation, in terms of Fisher ratio maximization, for LDA-based data projection. Compared with the standard LDA approach, the proposed optimization scheme increases class discrimination in the reduced dimensionality space and achieves higher classification rates in publicly available data sets.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Research Community on Data-to-Decision (D2D), Aristotle University of Thessaloniki, Department of Informatics
Contributors: Iosifidis, A., Tefas, A., Pitas, I.
Number of pages: 7
Pages: 1491-1497
Publication date: 2013
Peer-reviewed: Yes

Publication information

Journal: IEEE Transactions on Neural Networks and Learning Systems
Volume: 24
Issue number: 9
ISSN (Print): 2162-237X
Ratings: 
  • Scopus rating (2013): CiteScore 9.4 SJR 2.33 SNIP 3.576
Original language: English
ASJC Scopus subject areas: Artificial Intelligence, Computer Networks and Communications, Computer Science Applications, Software
Keywords: Class representation, data projection, linear discriminant analysis (LDA), subspace learning
Source: Scopus
Source ID: 84882899597

Research output: Contribution to journalArticleScientificpeer-review

Dynamic action recognition based on dynemes and Extreme Learning Machine

In this paper, we propose a novel method that performs dynamic action classification by exploiting the effectiveness of the Extreme Learning Machine (ELM) algorithm for single hidden layer feedforward neural networks training. It involves data grouping and ELM based data projection in multiple levels. Given a test action instance, a neural network is trained by using labeled action instances forming the groups that reside to the test sample's neighborhood. The action instances involved in this procedure are, subsequently, mapped to a new feature space, determined by the trained network outputs. This procedure is performed multiple times, which are determined by the test action instance at hand, until only a single class is retained. Experimental results denote the effectiveness of the dynamic classification approach, compared to the static one, as well as the effectiveness of the ELM in the proposed dynamic classification setting.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Research Community on Data-to-Decision (D2D), Aristotle University of Thessaloniki, Department of Informatics
Contributors: Iosifidis, A., Tefas, A., Pitas, I.
Number of pages: 9
Pages: 1890-1898
Publication date: 2013
Peer-reviewed: Yes

Publication information

Journal: Pattern Recognition Letters
Volume: 34
Issue number: 15
ISSN (Print): 0167-8655
Ratings: 
  • Scopus rating (2013): CiteScore 4.8 SJR 0.768 SNIP 2.474
Original language: English
ASJC Scopus subject areas: Software, Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing
Keywords: Activity recognition, Dynamic classification, Extreme Learning Machine, Fuzzy vector quantization
Source: Scopus
Source ID: 84885069818

Research output: Contribution to journalArticleScientificpeer-review

Guest editorial

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Research group: System-on-Chip for GNSS, Wireless Communications and Cyber-Physical Embedded Computing, Department of Electronics and Communications Engineering
Contributors: Ellervee, P., Nurmi, J.
Number of pages: 2
Pages: 430-431
Publication date: 2013
Peer-reviewed: Yes

Publication information

Journal: Microprocessors and Microsystems
Volume: 37
Issue number: 4-5
ISSN (Print): 0141-9331
Ratings: 
  • Scopus rating (2013): CiteScore 1.6 SJR 0.225 SNIP 1.194
Original language: English
ASJC Scopus subject areas: Computer Networks and Communications, Hardware and Architecture, Software, Artificial Intelligence
Source: Scopus
Source ID: 84878614529

Research output: Contribution to journalArticleScientificpeer-review

Touch gestures in communicating emotional intention via vibrotactile stimulation

Remote communication between people typically relies on audio and vision although current mobile devices are increasingly based on detecting different touch gestures such as swiping. These gestures could be adapted to interpersonal communication by using tactile technology capable of producing touch stimulation to a user's hand. It has been suggested that such mediated social touch would allow for new forms of emotional communication. The aim was to study whether vibrotactile stimulation that imitates human touch can convey intended emotions from one person to another. For this purpose, devices were used that converted touch gestures of squeeze and finger touch to vibrotactile stimulation. When one user squeezed his device or touched it with finger(s), another user felt corresponding vibrotactile stimulation on her device via four vibrating actuators. In an experiment, participant dyads comprising a sender and receiver were to communicate variations in the affective dimensions of valence and arousal using the devices. The sender's task was to create stimulation that would convey unpleasant, pleasant, relaxed, or aroused emotional intention to the receiver. Both the sender and receiver rated the stimulation using scales for valence and arousal so that the match between sender's intended emotions and receiver's interpretations could be measured. The results showed that squeeze was better at communicating unpleasant and aroused emotional intention, while finger touch was better at communicating pleasant and relaxed emotional intention. The results can be used in developing technology that enables people to communicate via touch by choosing touch gesture that matches the desired emotion.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Augmented Human Activities (AHA), Field robotics for efficient work sites (FIRE)
Contributors: Rantala, J., Salminen, K., Raisamo, R., Surakka, V.
Number of pages: 12
Pages: 679-690
Publication date: 2013
Peer-reviewed: Yes

Publication information

Journal: International Journal of Human-Computer Studies
Volume: 71
Issue number: 6
ISSN (Print): 1071-5819
Ratings: 
  • Scopus rating (2013): CiteScore 4.6 SJR 0.861 SNIP 2.378
Original language: English
ASJC Scopus subject areas: Human Factors and Ergonomics, Software, Education, Engineering(all), Human-Computer Interaction, Hardware and Architecture
Keywords: Affective interaction, Emotions, Haptics, Mediated social touch, Mobile devices, Tactile communication
Source: Scopus
Source ID: 84876589281

Research output: Contribution to journalArticleScientificpeer-review

Information retrieval perspective to meta-visualization

In visual data exploration with scatter plots, no single plot is sufficient to analyze complicated high-dimensional data sets. Given numerous visualizations created with different features or methods, meta-visualization is needed to analyze the visualizations together. We solve how to arrange numerous visualizations onto a meta-visualization display, so that their similarities and differences can be analyzed. We introduce a machine learning approach to optimize the meta-visualization, based on an information retrieval perspective: Two visualizations are similar if the analyst would retrieve similar neighborhoods between data samples from either visualization. Based on the approach, we introduce a nonlinear embedding method for meta-visualization: it optimizes locations of visualizations on a display, so that visualizations giving similar information about data are close to each other.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Research Community on Data-to-Decision (D2D), Aalto University
Contributors: Peltonen, J., Lin, Z.
Number of pages: 16
Pages: 165-180
Publication date: 2013
Peer-reviewed: Yes

Publication information

Journal: Journal of Machine Learning Research
Volume: 29
ISSN (Print): 1532-4435
Ratings: 
  • Scopus rating (2013): CiteScore 6.2 SJR 1.235 SNIP 2.293
Original language: English
ASJC Scopus subject areas: Artificial Intelligence, Software, Control and Systems Engineering, Statistics and Probability
Keywords: Meta-visualization, Neighbor embedding, Nonlinear dimensionality reduction
Source: Scopus
Source ID: 84908485499

Research output: Contribution to journalArticleScientificpeer-review

Focused multi-task learning in a Gaussian process framework

Multi-task learning, learning of a set of tasks together, can improve performance in the individual learning tasks. Gaussian process models have been applied to learning a set of tasks on different data sets, by constructing joint priors for functions underlying the tasks. In these previous Gaussian process models, the setting has been symmetric in the sense that all the tasks have been assumed to be equally important, whereas in settings such as transfer learning the goal is asymmetric, to enhance performance in a target task given the other tasks. We propose a focused Gaussian process model which introduces an "explaining away" model for each of the additional tasks to model their non-related variation, in order to focus the transfer to the task-of-interest. This focusing helps reduce the key problem of negative transfer, which may cause performance to even decrease if the tasks are not related closely enough. In experiments, our model improves performance compared to single-task learning, symmetric multi-task learning using hierarchical Dirichlet processes, transfer learning based on predictive structure learning, and symmetric multi-task learning with Gaussian processes.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Research Community on Data-to-Decision (D2D), deCODE Genetics, Aalto University, University of Helsinki
Contributors: Leen, G., Peltonen, J., Kaski, S.
Number of pages: 26
Pages: 157-182
Publication date: Oct 2012
Peer-reviewed: Yes

Publication information

Journal: Machine Learning
Volume: 89
Issue number: 1-2
ISSN (Print): 0885-6125
Ratings: 
  • Scopus rating (2012): CiteScore 6.3 SJR 1.148 SNIP 3.203
Original language: English
ASJC Scopus subject areas: Artificial Intelligence, Software
Keywords: Gaussian processes, Multi-task learning, Negative transfer, Transfer learning
Source: Scopus
Source ID: 84865229433

Research output: Contribution to journalArticleScientificpeer-review

Elastic image registration for guiding focal laser ablation of prostate cancer: Preliminary results

Purpose: To guide ultrasound-driven prostate photodynamic therapy using information from MRI-based treatment planning. Methods: Robust points matching (RPM) and thin plate splines (TPS) are used to solve correspondences and to map optimally positioned landmarks from MR images to transrectal ultrasound (TRUS) images. The algorithm uses a reduced number of anatomical markers that are initialized on the images. Results: Both phantom and patient data were used to evaluate precision and robustness of the method. Mean registration error (±standard deviation) was of 2.18. ±. 0.25. mm and 1.55. ±. 0.31. mm for patient prostate and urethra, respectively. Repeated tests with different markers initialization conditions showed that the quality of registration was neither influenced by the number of markers nor to the human observer. Conclusion: This method allows for satisfyingly accurate and robust non rigid registration of MRI and TRUS and provides practitioners with substantial help in mapping treatment planning from pre-operative MRI to interventional TRUS.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Frontier Photonics, Univ Paris 06, Centre National de la Recherche Scientifique (CNRS), Pierre & Marie Curie University - Paris 6, Institut de Recherche pour le Developpement (IRD), Inria, Institut National de la Sante et de la Recherche Medicale (Inserm), Univ Sorbonne, CNRS,ICM,UMR S 1127,UMR 7225,U1127, INSERM,Inria Paris Rocquencourt,Inst Cerveau & Mo, Lille University Hospital - CHRU, CHU Angers, Univ Lille Nord de France
Contributors: Makni, N., Puech, P., Colin, P., Azzouzi, A., Mordon, S., Betrouni, N.
Number of pages: 11
Pages: 213-223
Publication date: Oct 2012
Peer-reviewed: Yes

Publication information

Journal: Computer Methods and Programs in Biomedicine
Volume: 108
Issue number: 1
ISSN (Print): 0169-2607
Ratings: 
  • Scopus rating (2012): CiteScore 3.1 SJR 0.489 SNIP 1.52
Original language: English
ASJC Scopus subject areas: Computer Science Applications, Software, Health Informatics
Keywords: Image-guided interventions, Magnetic resonance imaging, Non rigid registration, PDT, Prostate cancer, Transrectal ultrasound imaging
Source: Scopus
Source ID: 84865711653

Research output: Contribution to journalArticleScientificpeer-review

SymbolChat: A flexible picture-based communication platform for users with intellectual disabilities

Persons with intellectual disabilities benefit from participating in the modern information society, especially the World Wide Web, social media and Internet-mediated communication services. Although several computer-based prototypes and commercial systems have been introduced for accessible in-person communication, currently few applications and services exist to support synchronous remote communication for this user group. We introduce SymbolChat, a software platform that supports the creation of multimodal communication applications utilizing picture-based instant messaging. End users and their support personnel can customize the input and output features of the application based on their individual needs and abilities. The interaction is based on touchscreen input and speech output using speech synthesis technology. The SymbolChat platform was developed together with the prospective end users and practitioners in the field of special needs care. We evaluated the prototype application in a field study with nine users with varying degrees of intellectual and other disabilities. The results clearly indicate that the participants were able to express themselves in spontaneous communication using a large-scale picture-based vocabulary (around 2000 symbols) even without prior training in the use of symbols. This finding was supported in the constructive feedback gathered from professionals working in the area. We also successfully applied methodology from other settings, such as child-computer interaction to evaluate interaction in this challenging context. Overall, the results show that social inclusion for people with intellectual disabilities can be improved with customizable communication tools. The implemented communication platform forms a solid basis for further improvements and new communication services. In addition, we found that users with motor impairments would greatly benefit from alternative input and output methods for symbol browsing and selection.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Augmented Human Activities (AHA), Laurea University of Applied Sciences
Contributors: Keskinen, T., Heimonen, T., Turunen, M., Rajaniemi, J. P., Kauppinen, S.
Number of pages: 13
Pages: 374-386
Publication date: Sep 2012
Peer-reviewed: Yes

Publication information

Journal: Interacting with Computers
Volume: 24
Issue number: 5
ISSN (Print): 0953-5438
Ratings: 
  • Scopus rating (2012): CiteScore 4.9 SJR 0.669 SNIP 1.982
Original language: English
ASJC Scopus subject areas: Human-Computer Interaction, Software
Keywords: Augmentative and alternative communication, Instant messaging, Picture-based communication, User-centered design
Source: Scopus
Source ID: 84866739334

Research output: Contribution to journalArticleScientificpeer-review

Barriers to task-based information access in molecular medicine

We analyze barriers to task-based information access in molecular medicine, focusing on research tasks, which provide task performance sessions of varying complexity. Molecular medicine is a relevant domain because it offers thousands of digital resources as the information environment. Data were collected through shadowing of real work tasks. Thirty work task sessions were analyzed and barriers in these identified. The barriers were classified by their character (conceptual, syntactic, and technological) and by their context of appearance (work task, system integration, or system). Also, work task sessions were grouped into three complexity classes and the frequency of barriers of varying types across task complexity levels were analyzed. Our findings indicate that although most of the barriers are on system level, there is a quantum of barriers in integration and work task contexts. These barriers might be overcome through attention to the integrated use of multiple systems at least for the most frequent uses. This can be done by means of standardization and harmonization of the data and by taking the requirements of the work tasks into account in system design and development, because information access is seldom an end itself, but rather serves to reach the goals of work tasks.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Tampere Research Center for Information and Media
Contributors: Kumpulainen, S., Järvelin, K.
Number of pages: 12
Pages: 86-97
Publication date: Jan 2012
Peer-reviewed: Yes

Publication information

Journal: JOURNAL OF THE ASSOCIATION FOR INFORMATION SCIENCE AND TECHNOLOGY
Volume: 63
Issue number: 1
ISSN (Print): 2330-1635
Ratings: 
  • Scopus rating (2012): CiteScore 5.5 SJR 1.398 SNIP 2.283
Original language: English
ASJC Scopus subject areas: Software, Artificial Intelligence, Information Systems, Human-Computer Interaction, Computer Networks and Communications
Source: Scopus
Source ID: 83655163751

Research output: Contribution to journalArticleScientificpeer-review

Novel approaches to crawling important pages early

Web crawlers are essential to many Web applications, such as Web search engines, Web archives, and Web directories, which maintain Web pages in their local repositories. In this paper, we study the problem of crawl scheduling that biases crawl ordering toward important pages. We propose a set of crawling algorithms for effective and efficient crawl ordering by prioritizing important pages with the well-known PageRank as the importance metric. In order to score URLs, the proposed algorithms utilize various features, including partial link structure, inter-host links, page titles, and topic relevance. We conduct a large-scale experiment using publicly available data sets to examine the effect of each feature on crawl ordering and evaluate the performance of many algorithms. The experimental results verify the efficacy of our schemes. In particular, compared with the representative RankMass crawler, the FPR-title-host algorithm reduces computational overhead by a factor as great as three in running time while improving effectiveness by 5% in cumulative PageRank.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Research Community on Data-to-Decision (D2D), Korea University
Contributors: Alam, M. H., Ha, J. W., Lee, S. K.
Number of pages: 28
Pages: 707-734
Publication date: 2012
Peer-reviewed: Yes

Publication information

Journal: Knowledge and Information Systems
Volume: 33
Issue number: 3
ISSN (Print): 0219-1377
Ratings: 
  • Scopus rating (2012): CiteScore 4.2 SJR 1.111 SNIP 2.008
Original language: English
ASJC Scopus subject areas: Software, Information Systems, Human-Computer Interaction, Hardware and Architecture, Artificial Intelligence
Keywords: Crawl ordering, Fractional PageRank, PageRank, Web crawler
Source: Scopus
Source ID: 84869092092

Research output: Contribution to journalArticleScientificpeer-review

On the definition of dynamic software measures

The quantification of several software attributes (e.g., size, complexity, cohesion, coupling) is usually carried out in a static fashion, and several hundreds of measures have been defined to this end. However, static measurement may only be an approximation for the measurement of these attributes during software use. The paper proposes a theoretical framework based on Axiomatic Approaches for the definition of sensible dynamic software measures that can dynamically capture these attributes. Dynamic measures based on this framework are defined for dynamically quantifying size and coupling. In this paper, we also compare dynamic measures of size and coupling against well-known static measures by correlating them with fault-pronenesses of four case studies.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Università degli Studi Dell'Insubria, Former organisation of the author
Contributors: Lavazza, L., Morasca, S., Taibi, D., Tosi, D.
Number of pages: 10
Pages: 39-48
Publication date: 2012
Peer-reviewed: Yes

Publication information

Journal: International Symposium on Empirical Software Engineering and Measurement
ISSN (Print): 1949-3770
Original language: English
ASJC Scopus subject areas: Computer Science Applications, Software
Keywords: Code coverage, Dynamic coupling, Dynamic measures, Dynamic size
Source: Scopus
Source ID: 84867570388

Research output: Contribution to journalArticleScientificpeer-review

Managing concern knowledge in software systems

Knowledge representation, acquisition, and sharing in software development projects is challenging due to the involvement of different kinds of stakeholders and large heterogeneous repositories of artifacts. In this paper, we argue that the concept of a concern can be used to facilitate the management of knowledge concerning the various system artifacts. Concerns represent pieces of knowledge pertaining to various viewpoints and interests of the stakeholders. In order to represent concerns, we propose the use of a non-intrusive role-based mechanism called a fragment. Using this mechanism, tacit knowledge can be made explicit by mapping stakeholders interests to artifact repositories, concern-based queries can be addressed to the repositories, and concerns can be combined to produce new knowledge. A concern-based prototype tool environment for knowledge management has been built and used for evaluating the approach in the context of industrial case studies.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Department of Pervasive Computing, Managing digital industrial transformation (mDIT)
Contributors: Hammouda, I., Koskimies, K., Mikkonen, T.
Number of pages: 31
Pages: 957-987
Publication date: Nov 2011
Peer-reviewed: Yes

Publication information

Journal: INTERNATIONAL JOURNAL OF SOFTWARE ENGINEERING AND KNOWLEDGE ENGINEERING
Volume: 21
Issue number: 7
ISSN (Print): 0218-1940
Ratings: 
  • Scopus rating (2011): CiteScore 1 SJR 0.19 SNIP 0.482
Original language: English
ASJC Scopus subject areas: Software, Artificial Intelligence, Computer Graphics and Computer-Aided Design, Computer Networks and Communications
Keywords: Knowledge management, Separation of concerns, Software development tools, Software repositories
Source: Scopus
Source ID: 84856103523

Research output: Contribution to journalArticleScientificpeer-review

Interaction strategies for an affective conversational agent

The development of embodied conversational agents (ECA) as companions brings several challenges for both affective and conversational dialogue. These include challenges in generating appropriate affective responses, selecting the overall shape of the dialogue, providing prompt system response times, and handling interruptions. We present an implementation of such a companion showing the development of individual modules that attempt to address these challenges. Further, to resolve resulting conflicts, we present encompassing interaction strategies that attempt to balance the competing requirements along with dialogues from our working prototype to illustrate these interaction strategies in operation. Finally, we provide the results of an evaluation of the companion using an evaluation methodology created for conversational dialogue and including analysis using appropriateness annotation.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Augmented Human Activities (AHA), School of Computing Teesside University Middlesbrough, University of Oxford, Telefonica, School of Management (JKK), School of Computing Edinburgh Napier University Edinburgh, SICS SE-164 29 Kista, ILS Institute SUNY Albany Albany
Contributors: Smith, C., Crook, N., Dobnik, S., Charlton, D., Boye, J., Pulman, S., Santos de la Camara, R., Turunen, M., Benyon, D., Bradley, J., Gambäck, B., Hansen, P., Mival, O., Webb, N., Cavazza, M.
Number of pages: 17
Pages: 395-411
Publication date: Oct 2011
Peer-reviewed: Yes

Publication information

Journal: Presence: Teleoperators and Virtual Environments
Volume: 20
Issue number: 5
ISSN (Print): 1054-7460
Ratings: 
  • Scopus rating (2011): CiteScore 3 SJR 0.354 SNIP 1.141
Original language: English
ASJC Scopus subject areas: Control and Systems Engineering, Software, Human-Computer Interaction, Computer Vision and Pattern Recognition
Source: Scopus
Source ID: 84863122938

Research output: Contribution to journalArticleScientificpeer-review

A survey on open source software trustworthiness

Trustworthiness is a crucial characteristic when it comes to evaluating any product, even more so for open source software, which is now becoming widely used. The authors conducted a survey to identify the reasons and motivations that lead software companies to adopt or reject open source software; they then ranked, according to importance, the specific trust factors used when selecting an open source software component or product. The motivations and importance ranking of factors might be useful for both developers of open source software (to make their products and components more useful for other stakeholders) and to future prospective open source software users.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Università degli Studi Dell'Insubria, Uni-versità Degli Studi dell'Insubria in Como, Universita' degli Studi dell'Insubria
Contributors: Del Bianco, V., Lavazza, L., Morasca, S., Taibi, D.
Number of pages: 9
Pages: 67-75
Publication date: Sep 2011
Peer-reviewed: Yes

Publication information

Journal: IEEE Software
Volume: 28
Issue number: 5
ISSN (Print): 0740-7459
Ratings: 
  • Scopus rating (2011): CiteScore 3.2 SJR 0.701 SNIP 2.255
Original language: English
ASJC Scopus subject areas: Software
Keywords: external software qualities, internal software qualities, open source software, pragmatic software engineering, trustworthiness
Source: Scopus
Source ID: 80051758696

Research output: Contribution to journalArticleScientificpeer-review

Multimodal and mobile conversational Health and Fitness Companions

Multimodal conversational spoken dialogues using physical and virtual agents provide a potential interface to motivate and support users in the domain of health and fitness. This paper describes how such multimodal conversational Companions can be implemented to support their owners in various pervasive and mobile settings. We present concrete system architectures, virtual, physical and mobile multimodal interfaces, and interaction management techniques for such Companions. In particular how knowledge representation and separation of low-level interaction modelling from high-level reasoning at the domain level makes it possible to implement distributed, but still coherent, interaction with Companions. The distribution is enabled by using a dialogue plan to communicate information from domain level planner to dialogue management and from there to a separate mobile interface. The model enables each part of the system to handle the same information from its own perspective without containing overlapping logic, and makes it possible to separate task-specific and conversational dialogue management from each other. In addition to technical descriptions, results from the first evaluations of the Companions interfaces are presented.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Augmented Human Activities (AHA), SICS, Norwegian Univ. of Sci. and Technol., Telefonica, School of Computing Teesside University Middlesbrough
Contributors: Turunen, M., Hakulinen, J., Ståhl, O., Gambäck, B., Hansen, P., Rodríguez Gancedo, M. C., De La Cámara, R. S., Smith, C., Charlton, D., Cavazza, M.
Number of pages: 18
Pages: 192-209
Publication date: Apr 2011
Peer-reviewed: Yes

Publication information

Journal: Computer Speech and Language
Volume: 25
Issue number: 2
ISSN (Print): 0885-2308
Ratings: 
  • Scopus rating (2011): CiteScore 4.2 SJR 0.586 SNIP 1.9
Original language: English
ASJC Scopus subject areas: Theoretical Computer Science, Software, Human-Computer Interaction
Keywords: Cognitive modelling, Companions, Conversational spoken dialogue systems, Dialogue management, Embodied conversational agents, Mobile interfaces
Source: Scopus
Source ID: 78049527811

Research output: Contribution to journalArticleScientificpeer-review

Guidelines for improving the testing process of open source software

Open Source Software (OSS) products do not usually follow traditional software engineering development paradigms. Specifically, testing activities in OSS development may be quite different from those carried out in Closed Source Software (CSS) development. As testing and verification require a good deal of resources in OSS, it is necessary to have ways to assess and improve OSS testing processes. This paper provides a set of testing guidelines and issues that OSS developers can use to decide which testing techniques make most sense for their OSS products. This paper 1) provides a checklist that helps OSS developers identify the most useful testing techniques according to the main characteristics of their products, and 2) outlines a proposal for a method that helps assess the maturity of OSS testing processes. The method is a proposal of a Maturity Model for testing processes (called OSS-TMM). To show its usefulness, the authors apply the method to seven real-life projects. Specifically, the authors apply the method to BusyBox, Apache Httpd, and Eclipse Test & Performance Tools Platform to show how the checklist supports and guides the testing process of these OSS products.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Università degli Studi Dell'Insubria
Contributors: Morasca, S., Taibi, D., Tosi, D.
Number of pages: 22
Pages: 1-22
Publication date: Apr 2011
Peer-reviewed: Yes

Publication information

Journal: International Journal of Open Source Software and Processes
Volume: 3
Issue number: 2
ISSN (Print): 1942-3926
Ratings: 
  • Scopus rating (2011): CiteScore 0.5 SJR 0.141 SNIP 0.777
Original language: English
ASJC Scopus subject areas: Software
Keywords: Open Source Software (OSS) Quality, Survey, Testing Process, Testing Quality Assessment, Trustworthiness
Source: Scopus
Source ID: 84860503937

Research output: Contribution to journalArticleScientificpeer-review

Generative modeling for maximizing precision and recall in information visualization

Information visualization has recently been formulated as an information retrieval problem, where the goal is to find similar data points based on the visualized nonlinear projection, and the visualization is optimized to maximize a compromise between (smoothed) precision and recall. We turn the visualization into a generative modeling task where a simple user model parameterized by the data coordinates is optimized, neighborhood relations are the observed data, and straightforward maximum likelihood estimation corresponds to Stochastic Neighbor Embedding (SNE). While SNE maximizes pure recall, adding a mixture component that "explains away" misses allows our generative model to focus on maximizing precision as well. The resulting model is a generative solution to maximizing tradeoffs between precision and recall. The model outperforms earlier models in terms of precision and recall and in external validation by unsupervised classification.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Research Community on Data-to-Decision (D2D), Aalto University, University of Helsinki
Contributors: Peltonen, J., Kaski, S.
Number of pages: 9
Pages: 579-587
Publication date: 2011
Peer-reviewed: Yes

Publication information

Journal: Journal of Machine Learning Research
Volume: 15
ISSN (Print): 1532-4435
Ratings: 
  • Scopus rating (2011): CiteScore 7.7 SJR 1.18 SNIP 2.912
Original language: English
ASJC Scopus subject areas: Artificial Intelligence, Software, Control and Systems Engineering, Statistics and Probability
Source: Scopus
Source ID: 84862299625

Research output: Contribution to journalArticleScientificpeer-review

Conversion algorithms and implementations for koblitz curve cryptography

In this paper, we discuss conversions between integers and \tau-adic expansions and we provide efficient algorithms and hardware architectures for these conversions. The results have significance in elliptic curve cryptography using Koblitz curves, a family of elliptic curves offering faster computation than general elliptic curves. However, in order to enable these faster computations, scalars need to be reduced and represented using a special base-τ expansion. Hence, efficient conversion algorithms and implementations are necessary. Existing conversion algorithms require several complicated operations, such as multiprecision multiplications and computations with large rationals, resulting in slow and large implementations in hardware and microcontrollers with limited instruction sets. Our algorithms are designed to utilize only simple operations, such as additions and shifts, which are easily implementable on practically all platforms. We demonstrate the practicability of the new algorithms by implementing them on Altera Stratix ∥ FPGAs. The implementations considerably improve both computation speed and required area compared to the existing solutions.

General information

Publication status: Published
MoE publication type: A1 Journal article-refereed
Organisations: Pervasive Computing, Aalto University
Contributors: Brumley, B. B., Jarvinen, K. U.
Number of pages: 12
Pages: 81-92
Publication date: 4 Jan 2010
Peer-reviewed: Yes

Publication information

Journal: IEEE Transactions on Computers
Volume: 59
Issue number: 1
Article number: 5255226
ISSN (Print): 0018-9340
Ratings: 
  • Scopus rating (2010): SJR 0.584 SNIP 1.868
Original language: English
ASJC Scopus subject areas: Software, Theoretical Computer Science, Hardware and Architecture, Computational Theory and Mathematics
Keywords: Elliptic curve cryptography, Field-programmable gate arrays, Koblitz curves, Public-key cryptosystems
Source: Scopus
Source ID: 72949120592

Research output: Contribution to journalArticleScientificpeer-review

Tailored gamification: A review of literature

Gamification is increasingly becoming a pertinent aspect of any UI and UX design. However, a canonical dearth in research and application of gamification has been related to the role of individual differences in susceptibility to gamification and its varied designs. To address this gap, this study reviews the extant corpus of research on tailored gamification (42 studies). The findings of the review indicate that most studies on the field are mostly focused on user modeling for a future personalization, adaptation, or recommendation of game elements. This user model usually contains the users’ preferences of play (i.e., player types), and is mostly applied in educational settings. The main contributions of this paper are a standardized terminology of the game elements used in tailored gamification, the discussion on the most suitable game elements for each users’ characteristic, and a research agenda including dynamic modeling, exploring multiple characteristics simultaneously, and understanding the effects of other aspects of the interaction on user experience.

General information

Publication status: Published
MoE publication type: A2 Review article in a scientific journal
Organisations: Computing Sciences, Tampere University, Federal University of Rio Grande do Sul, State University of Santa Catarina
Contributors: Klock, A. C. T., Gasparini, I., Pimenta, M. S., Hamari, J.
Publication date: 1 Dec 2020
Peer-reviewed: Yes

Publication information

Journal: International Journal of Human Computer Studies
Volume: 144
Article number: 102495
ISSN (Print): 1071-5819
Original language: English
ASJC Scopus subject areas: Software, Human Factors and Ergonomics, Education, Engineering(all), Human-Computer Interaction, Hardware and Architecture
Keywords: Adaptation, Gamification, Personalization, Recommendation, Systematic review, Tailoring
Electronic versions: 
Source: Scopus
Source ID: 85086582163

Research output: Contribution to journalReview ArticleScientificpeer-review

Does migrating a monolithic system to microservices decrease the technical debt?

Background: The migration from a monolithic system to microservices requires a deep refactoring of the system. Therefore, such a migration usually has a big economic impact and companies tend to postpone several activities during this process, mainly to speed up the migration itself, but also because of the demand for releasing new features.

Objective: We monitored the technical debt of an SME while it migrated from a legacy monolithic system to an ecosystem of microservices. Our goal was to analyze changes in the code technical debt before and after the migration to microservices.

Method: We conducted a case study analyzing more than four years of the history of a twelve-year-old project (280K Lines of Code) where two teams extracted five business processes from the monolithic system as microservices. For the study, we first analyzed the technical debt with SonarQube and then performed a qualitative study with company members to understand the perceived quality of the system and the motivation for possibly postponed activities.

Results: The migration to microservices helped to reduce the technical debt in the long run. Despite an initial spike in the technical debt due to the development of the new microservice, after a relatively short period of time the technical debt tended to grow slower than in the monolithic system.

General information

Publication status: Published
MoE publication type: A2 Review article in a scientific journal
Organisations: Computing Sciences, LUT University
Contributors: Lenarduzzi, V., Lomio, F., Saarimäki, N., Taibi, D.
Number of pages: 16
Publication date: 2020
Peer-reviewed: Yes

Publication information

Journal: Journal of Systems and Software
Volume: 169
Article number: 110710
ISSN (Print): 0164-1212
Original language: English
ASJC Scopus subject areas: Software, Information Systems, Hardware and Architecture
Keywords: Architectural debt, Code quality, Microservices, Refactoring, Technical debt

Bibliographical note

EXT="Lenarduzzi, Valentina"

Source: Scopus
Source ID: 85087383887

Research output: Contribution to journalReview ArticleScientificpeer-review

On the arity gap of finite functions: Results and applications

Let A be a finite set and B an arbitrary set with at least two elements. The arity gap of a function f : An → B is the minimum decrease in the number of essential variables when essential variables of f are identified. A non- Trivial fact is that the arity gap of such B-valued functions on A is at most |A|. Even less trivial to verify is the fact that the arity gap of B-valued functions on A with more than |A| essential variables is at most 2. These facts ask for a classification of B-valued functions on A in terms of their arity gap. In this paper, we survey what is known about this problem. We present a general characterization of the arity gap of B-valued functions on A and provide explicit classifications of the arity gap of Boolean and pseudo-Boolean functions. Moreover, we reveal unsettled questions related to this topic, and discuss links and possible applications of some results to other subjects of research.

General information

Publication status: Published
MoE publication type: A2 Review article in a scientific journal
Organisations: Department of Mathematics, Université de Lorraine, Department of Combinatorics and Optimization, University of Waterloo, Computer Science and Communications Research Unit, University of Luxembourg
Contributors: Couceiro, M., Lehtonen, E.
Number of pages: 15
Pages: 193-207
Publication date: 2016
Peer-reviewed: Yes

Publication information

Journal: Journal of Multiple-Valued Logic and Soft Computing
Volume: 27
Issue number: 2-3
ISSN (Print): 1542-3980
Ratings: 
  • Scopus rating (2016): CiteScore 0.9 SJR 0.26 SNIP 0.571
Original language: English
ASJC Scopus subject areas: Software, Logic, Theoretical Computer Science
Source: Scopus
Source ID: 84979953947

Research output: Contribution to journalReview ArticleScientificpeer-review

Some background on dialogue management and conversational speech for dialogue systems

Several dialogue management (DM) architectures and conversational speech for dialogue systems are presented. Basic types of DM systems include dialogue grammars and frames, plan-based and collaborative systems, and conversational games theory. DM architectures include SmartKom, Trindi, WITAS, CONVERSE, COMIC, agent-based dialogue management, and DM and automatic speech recognition (ASR) language modeling. All data collection tasks should be tailored for the conversational scenario under consideration as each scenario can present different properties. It is shown in the multimodal dialogue system that turn taking can usually be achieved by a fusion of gesture, gaze, and intonation. Intonation within the speech signal informs the dialogue manager when new information is introduced into the current conversation. By placing established emotion detection methods within the recursive nature of conversation we can consider discourse as the exploitation of the shared set of interaction affordances.

General information

Publication status: Published
MoE publication type: A2 Review article in a scientific journal
Organisations: Augmented Human Activities (AHA), University of Oxford, University of Sheffield
Contributors: Wilks, Y., Catizone, R., Worgan, S., Turunen, M.
Number of pages: 12
Pages: 128-139
Publication date: Apr 2011
Peer-reviewed: Yes

Publication information

Journal: Computer Speech and Language
Volume: 25
Issue number: 2
ISSN (Print): 0885-2308
Ratings: 
  • Scopus rating (2011): CiteScore 4.2 SJR 0.586 SNIP 1.9
Original language: English
ASJC Scopus subject areas: Theoretical Computer Science, Software, Human-Computer Interaction
Keywords: Dialogue architectures, Dialogue management, Dialogue systems, Emotion detection, Human-computer interaction
Source: Scopus
Source ID: 78049527943

Research output: Contribution to journalReview ArticleScientificpeer-review

Modeling and estimation of signal-dependent and correlated noise

The additive white Gaussian noise (AWGN) model is ubiquitous in signal processing. This model is often justified by central-limit theorem (CLT) arguments. However, whereas the CLT may support a Gaussian distribution for the random errors, it does not provide any justification for the assumed additivity and whiteness. As a matter of fact, data acquired in real applications can seldom be described with good approximation by the AWGN model, especially because errors are typically correlated and not additive. Failure to model accurately the noise leads to inaccurate analysis, ineffective filtering, and distortion or even failure in the estimation. This chapter provides an introduction to both signal-dependent and correlated noise and to the relevant models and basic methods for the analysis and estimation of these types of noise. Generic one-parameter families of distributions are used as the essential mathematical setting for the observed signals. The distribution families covered as leading examples include Poisson, mixed Poisson–Gaussian, various forms of signal-dependent Gaussian noise (including multiplicative families and approximations of the Poisson family), as well as doubly censored heteroskedastic Gaussian distributions. We also consider various forms of noise correlation, encompassing pixel and readout cross-talk, fixed-pattern noise, column/row noise, etc., as well as related issues like photo-response and gain nonuniformity. The introduced models and methods are applicable to several important imaging scenarios and technologies, such as raw data from digital camera sensors, various types of radiation imaging relevant to security and to biomedical imaging.

General information

Publication status: Published
MoE publication type: A3 Part of a book or another research book
Organisations: Signal Processing, Research group: Signal and Image Restoration-RST, University of São Paulo
Contributors: Azzari, L., Borges, L. R., Foi, A.
Number of pages: 36
Pages: 1-36
Publication date: 2018

Host publication information

Title of host publication: Denoising of Photographic Images and Video : Fundamentals, Open Challenges and New Trends
Publisher: SPRINGER-VERLAG LONDON LTD
ISBN (Print): 978-3-319-96028-9

Publication series

Name: Advances in Computer Vision and Pattern Recognition
ISSN (Print): 2191-6586
ISSN (Electronic): 2191-6594
ASJC Scopus subject areas: Software, Signal Processing, Computer Vision and Pattern Recognition, Artificial Intelligence
URLs: 
Source: Scopus
Source ID: 85053409603

Research output: Chapter in Book/Report/Conference proceedingChapterScientificpeer-review

Data-driven stream mining systems for computer vision

In this chapter, we discuss the state of the art and future challenges in adaptive stream mining systems for computer vision. Adaptive stream mining in this context involves the extraction of knowledge from image and video streams in real-time, and from sources that are possibly distributed and heterogeneous. With advances in sensor and digital processing technologies, we are able to deploy networks involving large numbers of cameras that acquire increasing volumes of image data for diverse applications in monitoring and surveillance. However, to exploit the potential of such extensive networks for image acquisition, important challenges must be addressed in efficient communication and analysis of such data under constraints on power consumption, communication bandwidth, and end-to-end latency. We discuss these challenges in this chapter, and we also discuss important directions for research in addressing such challenges using dynamic, data-driven methodologies.

General information

Publication status: Published
MoE publication type: A3 Part of a book or another research book
Organisations: Signal Processing Research Community (SPRC), University of Maryland, Electrical Engineering Department, University of California, Los Angeles (UCLA)
Contributors: Bhattacharyya, S. S., Van Der Schaar, M., Atan, O., Tekin, C., Sudusinghe, K.
Number of pages: 16
Pages: 249-264
Publication date: 2014

Host publication information

Title of host publication: Advances in Computer Vision and Pattern Recognition
Volume: 68
Publisher: SPRINGER-VERLAG LONDON LTD

Publication series

Name: Advances in Computer Vision and Pattern Recognition
Volume: 68
ISSN (Print): 21916586
ISSN (Electronic): 21916594
ASJC Scopus subject areas: Software, Signal Processing, Computer Vision and Pattern Recognition, Artificial Intelligence
Source: Scopus
Source ID: 84984919867

Research output: Chapter in Book/Report/Conference proceedingChapterScientificpeer-review

Flow-bounded trajectory-scaling algorithm for hydraulic robotic manipulators

On-line methods for trajectory scaling have focused on torque or acceleration bounded minimum time trajectories, while other system constraints have received little attention. For hydraulic systems, volumetric flow rate of the supply unit establishes a critical constraint, that has been neglected in control design. Consequently, commercial solutions for robotic control of hydraulic manipulators are typically limited to a compromise of a slower constant endpoint velocity, that can be achieved in any operating point without violating the constrained flow rate. However, with real-time analysis of the required volumetric flow rate, the desired trajectories can be executed much faster without violating the flow rate constraint or losing control accuracy. This study proposes an on-line method for trajectory scaling to perform predetermined trajectories in minimum time. Essentially, the method scales velocity along the trajectory to maintain achievable velocity at all times. The proposed method is capable of enforcing a global volumetric flow limit, whether it is constant or time-varying. The method is validated with simulations and experiments with a real hydraulic robotic manipulator. Experimental results show a very significant improvement in the trajectory tracking control, where the tracking error is reduced from 461 mm to 73 mm on a square trajectory.

General information

Publication status: Published
MoE publication type: A4 Article in a conference publication
Organisations: Automation Technology and Mechanical Engineering, Rambooms Oy
Contributors: Lampinen, S., Niemi, J., Mattila, J.
Number of pages: 6
Pages: 619-624
Publication date: 1 Jul 2020

Host publication information

Title of host publication: 2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2020
Publisher: IEEE
ISBN (Electronic): 9781728167947

Publication series

Name: IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM
ISSN (Electronic): 2159-6255
ASJC Scopus subject areas: Electrical and Electronic Engineering, Control and Systems Engineering, Computer Science Applications, Software
Electronic versions: 

Bibliographical note

jufoid=73592

Source: Scopus
Source ID: 85090380825

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Kvazaar 2.0: Fast and efficient open-source HEVC inter encoder

High Efficiency Video Coding (HEVC) is the key to economic video transmission and storage in the current multimedia applications but tackling its inherent computational complexity requires powerful video codec implementations. This paper presents Kvazaar 2.0 HEVC encoder that is the new release of our academic open-source software (github.com/ultravideo/kvazaar). Kvazaar 2.0 introduces novel inter coding functionality that is built on advanced rate-distortion optimization (RDO) scheme and speeded up with several early termination mechanisms, SIMD-optimized coding tools, and parallelization strategies. Our experimental results show that the proposed coding scheme makes Kvazaar 125 times as fast as the HEVC reference software HM on the Intel Xeon E5-2699 v4 22-core processor at the additional coding cost of only 2.4% on average. In constant quantization parameter (QP) coding, Kvazaar is also 3 times as fast as the respective preset of the well-known practical x265 HEVC encoder and is still able to attain 10.7% lower average bit rate than x265 for the same objective visual quality. These results indicate that Kvazaar has become one of the leading open-source HEVC encoders in practical high-efficiency video coding.

General information

Publication status: Published
MoE publication type: A4 Article in a conference publication
Organisations: Computing Sciences, Research area: Computer engineering
Contributors: Lemmetti, A., Viitanen, M., Mercat, A., Vanne, J.
Number of pages: 6
Pages: 237-242
Publication date: 27 May 2020

Host publication information

Title of host publication: MMSys 2020 - Proceedings of the 2020 Multimedia Systems Conference
Publisher: ACM
ISBN (Electronic): 9781450368452
ASJC Scopus subject areas: Computer Graphics and Computer-Aided Design, Human-Computer Interaction, Software
Keywords: high efficiency video coding (HEVC), inter coding, Kvazaar HEVC encoder, open-source, rate-distortion optimization (RDO)
Source: Scopus
Source ID: 85086766655

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Adaptive Normalization for Forecasting Limit Order Book Data Using Convolutional Neural Networks

Deep learning models are capable of achieving state-of-the-art performance on a wide range of time series analysis tasks. However, their performance crucially depends on the employed normalization scheme, while they are usually unable to efficiently handle non-stationary features without first appropriately pre-processing them. These limitations impact the performance of deep learning models, especially when used for forecasting financial time series, due to their non-stationary and multimodal nature. In this paper we propose a data-driven adaptive normalization layer which is capable of learning the most appropriate normalization scheme that should be applied on the data. To this end, the proposed method first identifies the distribution from which the data were generated and then it dynamically shifts and scales them in order to facilitate the task at hand. The proposed nor-malization scheme is fully differentiable and it is trained in an end-to-end fashion along with the rest of the parameters of the model. The proposed method leads to significant performance improvements over several competitive normalization approaches, as demonstrated using a large-scale limit order book dataset.

General information

Publication status: Published
MoE publication type: A4 Article in a conference publication
Organisations: Computing Sciences, Research group: Multimedia Research Group - MRG, Aristotle University of Thessaloniki, Aarhus Universitet
Contributors: Passalis, N., Tefas, A., Kanniainen, J., Gabbouj, M., Iosifidis, A.
Number of pages: 5
Pages: 1713-1717
Publication date: 1 May 2020

Host publication information

Title of host publication: 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings
Publisher: IEEE
ISBN (Electronic): 9781509066315

Publication series

Name: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume: 2020-May
ISSN (Print): 1520-6149
ASJC Scopus subject areas: Software, Signal Processing, Electrical and Electronic Engineering

Bibliographical note

EXT="Tefas, Anastasios"
EXT="Iosifidis, Alexandros"

Source: Scopus
Source ID: 85089240342

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Peer to Peer Offloading with Delayed Feedback: An Adversary Bandit Approach

Fog computing brings computation and services to the edge of networks enabling real time applications. In order to provide satisfactory quality of experience, the latency of fog networks needs to be minimized. In this paper, we consider a peer computation offloading problem for a fog network with unknown dynamics. Peer competition occurs when different fog nodes offload tasks to the same peer FN. In this paper, the computation offloading problem is modeled as a sequential FN selection problem with delayed feedback. We construct an online learning policy based on the adversary multi-arm bandit framework to deal with peer competition and delayed feedback. Simulation results validate the effectiveness of the proposed policy.

General information

Publication status: Published
MoE publication type: A4 Article in a conference publication
Organisations: Electrical Engineering, Research group: Wireless Communications and Positioning, Shanghai Advanced Research Institute, Chinese Academy of Sciences, ShanghaiTech University, Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences, Peoples’ Friendship University of Russia
Contributors: Yang, M., Zhu, H., Wang, H., Koucheryavy, Y., Samouylov, K., Qian, H.
Number of pages: 5
Pages: 5035-5039
Publication date: 1 May 2020

Host publication information

Title of host publication: 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings
Publisher: IEEE
ISBN (Electronic): 9781509066315

Publication series

Name: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume: 2020-May
ISSN (Print): 1520-6149
ASJC Scopus subject areas: Software, Signal Processing, Electrical and Electronic Engineering
Keywords: adversary multi-arm bandit, delayed feed-back, Fog computing, reinforcement learning, task offloading
Source: Scopus
Source ID: 85089215773

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

SeCon-NG: Implementing a lightweight cryptographic library based on ECDH and ECDSA for the development of secure and privacy-preserving protocols in contiki-NG

There is no doubt that the Internet of Things (IoT) has the power to change our world and drive us to a complete social evolution. In business and industry, there are thousands of IoT use cases and real-life IoT deployments across a variety of sectors (e.g. industry 4.0 and smart factories, smart cities, etc.). However, due to the vastly resource constrained nature of the devices used in IoT, implementing secure and privacy-preserving services, using for example standard asymmetric cryptographic algorithms, has been a real challenge. The majority of IoT devices on the market currently employ the use of various forms of symmetric cryptography such as key pre-distribution. The overall efficiency of such implementations correlate directly to the size of the IoT environment and the deployment method. In this paper, we implement a lightweight cryptographic library that can be used to secure communication protocols between multiple communicating nodes without the need for external trusted entities or a server. Our implementation is based on modifying the Elliptic-Curve Diffie-Hillman (ECDH) and Elliptic Curve Digital Signature Algorithm (ECDSA) components of the Tinycrypt cryptographic library. This work focuses on extending the functionalities of the User Datagram Protocol (UDP) broadcast application on the Contiki-NG Operating System (OS) platform.

General information

Publication status: Published
MoE publication type: A4 Article in a conference publication
Organisations: Computing Sciences
Contributors: Frimpong, E., Michalas, A.
Number of pages: 3
Pages: 767-769
Publication date: 30 Mar 2020

Host publication information

Title of host publication: 35th Annual ACM Symposium on Applied Computing, SAC 2020
Publisher: ACM
ISBN (Electronic): 9781450368667
ASJC Scopus subject areas: Software
Keywords: Contiki-NG, Elliptic curve cryptography, Key distribution, Lightweight cryptography, Privacy, Wireless sensor networks
Source: Scopus
Source ID: 85083040552

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Serverless: What it Is, What to Do and What Not to Do

Serverless, the new buzzword, has been gaining a lot of attention from the developers and industry. Cloud vendors such as AWS and Microsoft have hyped the architecture almost everywhere, from practitioners' conferences to local events, to blog posts. In this work, we introduce serverless functions (also known as Function-as-a-Service or FaaS), together with on bad practices experienced by practitioners, members of the Tampere Serverless Meetup group.

General information

Publication status: Published
MoE publication type: A4 Article in a conference publication
Organisations: Computing Sciences, Gofore Plc
Contributors: Nupponen, J., Taibi, D.
Number of pages: 2
Pages: 49-50
Publication date: 1 Mar 2020

Host publication information

Title of host publication: 2020 IEEE International Conference on Software Architecture Companion, ICSA-C 2020
Publisher: IEEE
ISBN (Electronic): 9781728174150
ASJC Scopus subject areas: Computer Science Applications, Hardware and Architecture, Software, Information Systems and Management
Keywords: FaaS, Function-as-a-service, Serverless
Source: Scopus
Source ID: 85085749334

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Are SonarQube Rules Inducing Bugs?

The popularity of tools for analyzing Technical Debt, and particularly the popularity of SonarQube, is increasing rapidly. SonarQube proposes a set of coding rules, which represent something wrong in the code that will soon be reflected in a fault or will increase maintenance effort. However, our local companies were not confident in the usefulness of the rules proposed by SonarQube and contracted us to investigate the fault-proneness of these rules. In this work we aim at understanding which SonarQube rules are actually fault-prone and to understand which machine learning models can be adopted to accurately identify fault-prone rules. We designed and conducted an empirical study on 21 well-known mature open-source projects. We applied the SZZ algorithm to label the fault-inducing commits. We analyzed the fault-proneness by comparing the classification power of seven machine learning models. Among the 202 rules defined for Java by SonarQube, only 25 can be considered to have relatively low fault-proneness. Moreover, violations considered as 'bugs' by SonarQube were generally not fault-prone and, consequently, the fault-prediction power of the model proposed by SonarQube is extremely low. The rules applied by SonarQube for calculating technical debt should be thoroughly investigated and their harmfulness needs to be further confirmed. Therefore, companies should carefully consider which rules they really need to apply, especially if their goal is to reduce fault-proneness.

General information

Publication status: Published
MoE publication type: A4 Article in a conference publication
Organisations: Computing Sciences, Lappeenranta University of Technology
Contributors: Lenarduzzi, V., Lomio, F., Huttunen, H., Taibi, D.
Number of pages: 11
Pages: 501-511
Publication date: 1 Feb 2020

Host publication information

Title of host publication: SANER 2020 - Proceedings of the 2020 IEEE 27th International Conference on Software Analysis, Evolution, and Reengineering
Publisher: IEEE
Editors: Kontogiannis, K., Khomh, F., Chatzigeorgiou, A., Fokaefs, M., Zhou, M.
ISBN (Electronic): 9781728151434
ASJC Scopus subject areas: Organizational Behavior and Human Resource Management, Hardware and Architecture, Software, Safety, Risk, Reliability and Quality, Computer Networks and Communications
Keywords: architectural smells, code smells, coding style, machine learning, SonarQube, static analysis, Technical Debt

Bibliographical note

EXT="Lenarduzzi, Valentina"

Source: Scopus
Source ID: 85083565109

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

"The superhero of the university": Experience-driven design and field study of the university guidance robot

Robots have recently gained popularity in customer service. Especially social robots are nowadays utilized in healthcare, elderly homes and schools. Although it is crucial to design social robots according to well-defined user experience goals, research related to experience-driven design of social robots is still scarce. Experience-Driven Design (EDD) is a framework to design interaction for technology based on certain goals, known as experience goals. In this paper, we present the design and evaluation of the university guidance robot based on the user experience goals defined in previous research. The experience goals are nurture, fellowship and recreation. We designed applications, interaction, and robot's behavior to support the fulfillment of the experience goals. The social robot Pepper served as a platform for the university guidance robot. The evaluation was conducted as a field study in a university campus with 32 university students during the orientation week. According to our findings, the university guide robot successfully evoked nurture, fellowship and recreation among participants.

General information

Publication status: Published
MoE publication type: A4 Article in a conference publication
Organisations: Computing Sciences
Contributors: Chowdhury, A., Ahtinen, A., Kaipainen, K.
Number of pages: 9
Pages: 1-9
Publication date: 29 Jan 2020

Host publication information

Title of host publication: AcademicMindtrek 2020 - Proceedings of the 23rd International Academic Mindtrek Conference : January 2020, Tampere
Publisher: ACM
ISBN (Electronic): 9781450377744
ASJC Scopus subject areas: Software, Human-Computer Interaction, Computer Vision and Pattern Recognition, Computer Networks and Communications
Keywords: experience-driven design, social robots, user experience
Source: Scopus
Source ID: 85080943314

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

A preliminary network analysis on steam game tags: Another way of understanding game genres

Video game genre classification has long been a focusing perspective in game studies domain. Despite the commonly acknowledged usefulness of genre classification, scholars in the game studies domain are yet to reach consensus on the game genre classification. On the other hand, Steam, a popular video game distribution platform, adopts the user-generated tag feature enabling players to describe and annotate video games based on their own understanding of genres. Despite the concern of the quality, the user-generated tags (game tags) provide an opportunity towards an alternative way of understanding video game genres based on the players' collective intelligence. Hence, in this study, we construct a network of game tags based on the co-occurrence of tags in games on Steam platform and analyze the structure of the network via centrality analysis and community detection. Such analysis shall provide an intuitive presentation on the distribution and connections of the game tags, which furthermore suggests a potential way of understanding the important tags that are commonly adopted and the main genres of video games.

General information

Publication status: Published
MoE publication type: A4 Article in a conference publication
Organisations: Communication Sciences
Contributors: Li, X., Zhang, B.
Number of pages: 9
Pages: 65-73
Publication date: 29 Jan 2020

Host publication information

Title of host publication: AcademicMindtrek 2020 - Proceedings of the 23rd International Academic Mindtrek Conference : January 29-30, 2020, Tampere, Finland
Publisher: ACM
ISBN (Electronic): 9781450377744
ASJC Scopus subject areas: Software, Human-Computer Interaction, Computer Vision and Pattern Recognition, Computer Networks and Communications
Keywords: centrality, community detection, game tag, genre, modularity, network, steam, video game

Bibliographical note

INT=coms,"Li, Xiaozhou"

Source: Scopus
Source ID: 85080924784

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Color game: A collaborative social robotic game for icebreaking; Towards the design of robotic ambiences as part of smart building services

Social robots are entering our workplaces, homes, medical and educational systems in assistive and collaborative roles. In our research, we have investigated the use of a social robot Pepper as an interactive icebreaker host to create a positive atmosphere at events. This paper presents two user studies (total n=43) in which we evaluated two interactive prototypes of playful applications on Pepper, with the overall aim of providing a personal and entertaining service for event attendees. Data about users' experiences and attitudes were collected with semi-structured interviews, surveys, and observations. The results of the studies suggest that the majority of the participants had pleasurable and positive experiences with the robot and its applications. Moreover, their positive encounters led them to accept social robots as icebreaker hosts to connect with strangers. Based on our findings, we present a list of design implications to help the future design of social robots used to facilitate social connectedness, and to aid in the development of social robots as intelligent agents performing tasks as integrated parts of smart spaces.

General information

Publication status: Published
MoE publication type: A4 Article in a conference publication
Organisations: Computing Sciences, Civil Engineering, Research group: Digitalization in the real estate and construction sector
Contributors: Beheshtian, N., Kaipainen, K., Kähkönen, K., Ahtinen, A.
Number of pages: 10
Pages: 10-19
Publication date: 29 Jan 2020

Host publication information

Title of host publication: AcademicMindtrek 2020 - Proceedings of the 23rd International Academic Mindtrek Conference : January 2020, Tampere
Publisher: ACM
ISBN (Electronic): 9781450377744
ASJC Scopus subject areas: Software, Human-Computer Interaction, Computer Vision and Pattern Recognition, Computer Networks and Communications
Keywords: human robot interaction, ice breaking, smart building, social connectedness, social robots, user experience
Source: Scopus
Source ID: 85080911326

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Demographic differences in accumulated types of capital in massively multiplayer online role-playing games

This paper examines how the demographic attributes and extra-game habits of players of a Massively Multiplayer Online Role-Playing Game (MMORPG) predict the accumulated capital of their avatars. An online survey (N=905) was conducted amidst the players of Final Fantasy XIV (FFXIV). Four types of capital were measured to map out the concrete and intangible resources of the avatars; social, economic, cultural and symbolic. The results show that weekly time spent playing the game is the strongest predictor of avatar capital and was associated with all types of capital. Time subscribed to the game was associated with cultural, economic, symbolic and bonding social capital. Social capital was found to be highest amongst both young and female players. Forum activity was associated with symbolic capital.

General information

Publication status: Published
MoE publication type: A4 Article in a conference publication
Organisations: Communication Sciences, Research group: TUT Game Lab, Computing Sciences, Turun yliopisto
Contributors: Korkeila, H., Koivisto, J., Hamari, J.
Number of pages: 9
Pages: 74-82
Publication date: 29 Jan 2020

Host publication information

Title of host publication: AcademicMindtrek 2020 - Proceedings of the 23rd International Academic Mindtrek Conference : January 2020, Tampere
Publisher: ACM
ISBN (Electronic): 9781450377744
ASJC Scopus subject areas: Software, Human-Computer Interaction, Computer Vision and Pattern Recognition, Computer Networks and Communications
Keywords: avatar, capital, demographics, MMORPG
Source: Scopus
Source ID: 85080910780

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Satisfaction and willingness to consume immersive journalism: Experiment of differences between VR, 360 video, and article

Immersive journalism has been touted to revolutionize journalism due to its ability to afford a multi-modal engrossing experience. However, hardly any experiments have been conducted whether consumers' satisfaction and consequent intentions to use immersive journalistic media may differ from traditional forms of journalistic content. Therefore, in this study, we investigate the differences in satisfaction and continued use intentions between article, 360 video and VR-based interaction with content. The data was collected via a randomized controlled laboratory experiment with between-subjects design (N = 87). Participants were randomly assigned to reading a written article based on the video (article) and watching the video on a computer screen (2D 360) or in mobile VR (VR 360). The collected data consisted of demographics (age and gender) and reported satisfaction and intention to continue use. Results suggest that those who were assigned to VR 360 had higher intentions to continue use, but not greater satisfaction than those in the other two conditions. However, the intention was predicted to an extent by satisfaction as suggested by previous literature. Finally, age and gender did not predict continued use. These findings imply that users prefer the new media technology for consuming journalism content and support previous findings of the relationship between satisfaction and intention to continue use. Finally, avenues for further research are presented.

General information

Publication status: Published
MoE publication type: A4 Article in a conference publication
Organisations: Computing Sciences, Research group: TUT Game Lab
Contributors: Bujic, M., Hamari, J.
Number of pages: 6
Pages: 120-125
Publication date: 29 Jan 2020

Host publication information

Title of host publication: AcademicMindtrek 2020 - Proceedings of the 23rd International Academic Mindtrek Conference : January 2020, Tampere
Publisher: ACM
ISBN (Electronic): 9781450377744
ASJC Scopus subject areas: Software, Human-Computer Interaction, Computer Vision and Pattern Recognition, Computer Networks and Communications
Keywords: 360-degree video, age, gender, immersive journalism, intention to continue use, satisfaction, virtual reality
Source: Scopus
Source ID: 85080895604

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Innovation challenges as a novel multidisciplinary learning platform

Innovation Challenges is a new course offered for the whole Tampere university community by Y-kampus entrepreneurship and innovation services, for the first time in fall 2019. Innovation Challenges offers practice-based cases that allow students to develop their creativity and problem-solving skills in a team. Learning is anchored in team coaching pedagogy, learning-by-doing attitude and entrepreneurial mindset. In this paper, we first describe the evolution that created a course called Innovation Challenges. Then, we describe course organization and the six challenges that student teams are currently solving.

General information

Publication status: Published
MoE publication type: A4 Article in a conference publication
Organisations: Information and Knowledge Management, Research group: Business Data Research Group, Tampere Uni. of Applied Sci., Tampere University
Contributors: Jokiniemi, S., Myllärniemi, J., Poranen, T., Vuorenmaa, M.
Number of pages: 4
Pages: 145-148
Publication date: 29 Jan 2020

Host publication information

Title of host publication: AcademicMindtrek 2020 - Proceedings of the 23rd International Academic Mindtrek Conference : January 2020, Tampere
Publisher: ACM
ISBN (Electronic): 9781450377744
ASJC Scopus subject areas: Software, Human-Computer Interaction, Computer Vision and Pattern Recognition, Computer Networks and Communications
Keywords: innovation, learning platform, multidisciplinary projects

Bibliographical note

INT=comp,"Poranen, Timo"

Source: Scopus
Source ID: 85080863203

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

User experience of stereo and spatial audio in 360° live music videos

360° music videos are becoming prevalent in music entertainment. Still, academic studies of the 360° live music experience covering both audio and visual experience are scarce. In this paper, we present a study of user experience of stereo and spatial audio in a 360° live music video setting with two different display types. The research was conducted in the form of a laboratory experiment, in which 20 participants watched and evaluated stereo and spatial audio versions of the same music video using a flat computer display and a head-mounted display (HMD). Based on the results, spatial audio combined with HMD scored highest in the quantitative metrics of perceived audio quality, presence, and overall listening experience. However, qualitative findings reveal that this combination does not fit well with users' listening habits. While nine participants preferred to use headphones to listen to music, thirteen participants viewed music listening as a secondary task-making the use of HMDs less suitable.

General information

Publication status: Published
MoE publication type: A4 Article in a conference publication
Organisations: Computing Sciences, Tampere University, Tampere University of Applied Sciences
Contributors: Holm, J., Väänänen, K., Battah, A.
Number of pages: 8
Pages: 134-141
Publication date: 2020

Host publication information

Title of host publication: AcademicMindtrek 2020 - Proceedings of the 23rd International Academic Mindtrek Conference : January 2020, Tampere
Publisher: ACM
ISBN (Electronic): 9781450377744
ASJC Scopus subject areas: Software, Human-Computer Interaction, Computer Vision and Pattern Recognition, Computer Networks and Communications
Keywords: 360° video, ambisonics, head-mounted display, music video, spatial audio, stereo, user experience, virtual reality

Bibliographical note

EXT="Holm, Jukka"
INT=comp,"Battah, Anas"

Source: Scopus
Source ID: 85080964162

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Exploration and exploitation of sensorimotor contingencies for a cognitive embodied agent

The modelling of cognition is playing a major role in robotics. Indeed, robots need to learn, adapt and plan their actions in order to interact with their environment. To do so, approaches like embodiment and enactivism propose to ground sensorimotor experience in the robot's body to shape the development of cognition. In this work, we focus on the role of memory during learning in a closed loop. As sensorimotor contingencies, we consider a robot arm that moves a baby mobile toy to get visual reward. First, the robot explores the continuous sensorimotor space by associating visual stimuli to motor actions through motor babbling. After exploration, the robot uses the experience from its memory and exploits it, thus optimizing its motion to perceive more visual stimuli. The proposed approach uses Dynamic Field Theory and is integrated in the GummiArm, a 3D printed humanoid robot arm. The results indicate a higher visual neural activation after motion learning and show the benefits of an embodied babbling strategy.

General information

Publication status: Published
MoE publication type: A4 Article in a conference publication
Organisations: Automation Technology and Mechanical Engineering, Research group: Robotics and Automation
Contributors: Houbre, Q., Angleraud, A., Pieters, R.
Number of pages: 9
Pages: 546-554
Publication date: 2020

Host publication information

Title of host publication: ICAART 2020 - Proceedings of the 12th International Conference on Agents and Artificial Intelligence
Volume: 2
Publisher: SCITEPRESS
Editors: Rocha, A., Steels, L., van den Herik, J.
ISBN (Electronic): 9789897583957
ASJC Scopus subject areas: Artificial Intelligence, Software
Keywords: Cognitive Robotics, Dynamic Neural Fields, Embodiment, Sensorimotor Contingencies

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Patterns for serverless functions (Function-as-a-Service): A multivocal literature review

[Context] Serverless is a recent technology that enables companies to reduce the overhead for provisioning, scaling and in general managing the infrastructure. Companies are increasingly adopting Serverless, by migrating existing applications to this new paradigm. Different practitioners proposed patterns for composing and managing serverless functions. However, some of these patterns offer different solutions to solve the same problem, which makes it hard to select the most suitable solution for each problem. [Goal] In this work, we aim at supporting practitioners in understanding the different patterns, by classifying them and reporting possible benefits and issues. [Method]We adopted a multivocal literature review process, surveying peer-reviewed and grey literature and classifying patterns (common solutions to solve common problems), together with benefits and issues. [Results] Among 24 selected works, we identified 32 patterns that we classified as orchestration, aggregation, event-management, availability, communication, and authorization. [Conclusion] Practitioners proposed a list of fairly consistent patterns, even if a small number of patterns proposed different solutions to similar problems. Some patterns emerged to circumvent some serverless limitations, while others for some classical technical problems (e.g. publisher/subscriber).

General information

Publication status: Published
MoE publication type: A4 Article in a conference publication
Organisations: Computing Sciences, Free University of Bolzano-Bozen
Contributors: Taibi, D., El Ioini, N., Pahl, C., Niederkofler, J. R. S.
Number of pages: 12
Pages: 181-192
Publication date: 2020

Host publication information

Title of host publication: CLOSER 2020 - Proceedings of the 10th International Conference on Cloud Computing and Services Science
Volume: 1
Publisher: SCITEPRESS
Editors: Ferguson, D., Helfert, M., Pahl, C.
ISBN (Electronic): 9789897584244
ASJC Scopus subject areas: Computer Science (miscellaneous), Computer Science Applications, Software
Keywords: Cloud, Function as a Service, Serverless, Serverless Functions
Source: Scopus
Source ID: 85088373702

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

IoT-CryptoDiet: Implementing a lightweight cryptographic library based on ecdh and ecdsa for the development of secure and rivacy-preserving protocols in contiki-ng

Even though the idea of transforming basic objects to smart objects with the aid sensors is not new, it is only now that we have started seeing the incredible impact of this digital transformation in our societies. There is no doubt that the Internet of Things (IoT) has the power to change our world and drive us to a complete social evolution. This is something that has been well understood by the research and industrial communities that have been investing significant resources in the field of IoT. In business and industry, there are thousands of IoT use cases and real-life IoT deployments across a variety of sectors (e.g. industry 4.0 and smart factories, smart cities, etc.). However, due to the vastly resource-constrained nature of the devices used in IoT, implementing secure and privacy-preserving services, using, for example, standard asymmetric cryptographic algorithms, has been a real challenge. The majority of IoT devices on the market currently employ the use of various forms of symmetric cryptography such as key pre-distribution. The overall efficiency of such implementations correlates directly to the size of the IoT environment and the deployment method. In this paper, we implement a lightweight cryptographic library that can be used to secure communication protocols between multiple communicating nodes without the need for external trusted entities or a server. Our work focuses on extending the functionalities of the User Datagram Protocol (UDP) broadcast application on the Contiki-NG Operating System (OS) platform.

General information

Publication status: Published
MoE publication type: A4 Article in a conference publication
Organisations: Computing Sciences
Contributors: Frimpong, E., Michalas, A.
Number of pages: 11
Pages: 101-111
Publication date: 2020

Host publication information

Title of host publication: IoTBDS 2020 - Proceedings of the 5th International Conference on Internet of Things, Big Data and Security
Publisher: SCITEPRESS
Editors: Wills, G., Kacsuk, P., Chang, V.
ISBN (Electronic): 9789897584268
ASJC Scopus subject areas: Software, Computer Networks and Communications
Keywords: Contiki-NG, Elliptic Curve Cryptography, Key Distribution, Privacy, Wireless Sensor Networks.
Electronic versions: 
Source: Scopus
Source ID: 85089469229

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Redundancy-based visual tool center point pose estimation for long-reach manipulators

In this paper, we study a visual sensing scheme for 6 degree-of-freedom (DOF) tool center point (TCP) pose estimation of large-scale, long-reach manipulators. A sensor system is proposed, designed especially for mining manipulators, comprising a stereo camera running a simultaneous localization and mapping (SLAM) algorithm near the TCP and multiple cameras that track a fiducial marker attached near the stereo camera. In essence, the TCP pose is formulated using two different routes in a co-operative (eye-in-hand/eye-to-hand) manner using data fusion, with the goal of increasing the system's fault tolerance and robustness via sensor redundancy. The system is studied in offline data analysis based on real-world measurements recorded using a hydraulic 6 DOF robotic manipulator with a 5 m reach. The SLAM pose trajectory is obtained using the open source ORB-SLAM2 Stereo algorithm, whereas marker-based tracking is realized with a high-end motion capture system. For reference measurements, the pose trajectory is also formulated using joint encoders and a kinematic model of the manipulator. Results of the 6 DOF pose estimation using the proposed sensor system are presented, with future work and key challenges also highlighted.

General information

Publication status: Published
MoE publication type: A4 Article in a conference publication
Organisations: Automation Technology and Mechanical Engineering, Research group: Innovative Hydraulic Automation, Sandvik Mining and Construction Oy
Contributors: Mäkinen, P., Mustalahti, P., Launis, S., Mattila, J.
Number of pages: 7
Pages: 1387-1393
Publication date: 2020

Host publication information

Title of host publication: 2020 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2020
Publisher: IEEE
ISBN (Print): 978-1-7281-6795-4
ISBN (Electronic): 9781728167947

Publication series

Name: IEEE/ASME International Conference on Advanced Intelligent Mechatronics
ISSN (Print): 2159-6247
ISSN (Electronic): 2159-6255
ASJC Scopus subject areas: Electrical and Electronic Engineering, Control and Systems Engineering, Computer Science Applications, Software

Bibliographical note

EXT="Launis, Sirpa"
JUFOID=73592

Source: Scopus
Source ID: 85090392663

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Promoting local culture and enriching airport experiences through interactive storytelling

Experiences in airports may shape future travel plans and contribute to tourism destination development. However, a chaotic environment and time-consuming procedural routines in airports may result in negative associations towards the host country and its culture. Despite the existence of assistive airport applications, little attention is given to facilitating travelers’ engagement with cultural exploration. This paper introduces a concept of interactive personalized storytelling that provides both a cultural learning adventure and connection to local retailing. Our application generates an imaginative Finnish storyline unique to every user to guide them through local shops in the airport. A field evaluation was conducted with 15 travelers of different nationalities. Travelers perceived the interactive storytelling experience as an interesting and unique way to spend waiting time at the airport while increasing cultural exposure. Moreover, we found this method to be effective in persuading travelers to explore local products at the airport. Further, our results give insight to designing storytelling applications for large public places.

General information

Publication status: Published
MoE publication type: A4 Article in a conference publication
Organisations: Computing Sciences, Lapland University of Applied Sciences, Tampere University, Tampere University, Tampere University
Contributors: Burova, A., Kelling, C., Keskinen, T., Hakulinen, J., Kallioniemi, P., Väätäjä, H., Turunen, M.
Number of pages: 7
Publication date: 26 Nov 2019

Host publication information

Title of host publication: MUM 2019 - 18th International Conference on Mobile and Ubiquitous Multimedia, Proceedings
Publisher: Association for Computing Machinery
Editors: Jacucci, G., Paterno, F., Rohs, M., Santoro, C.
Article number: 3365640
ISBN (Electronic): 9781450376242

Publication series

Name: ACM International Conference Proceeding Series
ASJC Scopus subject areas: Human-Computer Interaction, Computer Networks and Communications, Computer Vision and Pattern Recognition, Software
Keywords: Airport experience, Digital storytelling, Field study, Mobile application

Bibliographical note

EXT="Väätäjä, Heli"

Source: Scopus
Source ID: 85076809996

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

The Double Shadowed κ-μ Fading Model

In this paper, we introduce a new fading model which is capable of characterizing both the shadowing of the dominant component and composite shadowing which may exist in wireless channels. More precisely, this new model assumes a κ-μ envelope where the dominant component is fluctuated by a Nakagami-m random variable (RV) which is preceded (or succeeded) by a secondary round of shadowing brought about by an inverse Nakagami-m RV. We conveniently refer to this as the double shadowed κ-μ fading model. In this context, novel closed-form and analytical expressions are developed for a range of channel related statistics, such as the probability density function, cumulative distribution function, and moments. All of the derived expressions have been validated through Monte-Carlo simulations and reduction to a number of well-known special cases. It is worth highlig