TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Semantic Labeling of Places based on Phone Usage Features using Supervised Learning

Tutkimustuotosvertaisarvioitu

Standard

Semantic Labeling of Places based on Phone Usage Features using Supervised Learning. / Rivero Rodriguez, Alejandro; Leppäkoski, Helena; Piché, Robert.

2014 Ubiquitous Positioning Indoor Navigation and Location Based Service, UPINLBS 2014 - Conference Proceedings. Piscataway, NJ, USA : IEEE, 2015. s. 97-102 7033715.

Tutkimustuotosvertaisarvioitu

Harvard

Rivero Rodriguez, A, Leppäkoski, H & Piché, R 2015, Semantic Labeling of Places based on Phone Usage Features using Supervised Learning. julkaisussa 2014 Ubiquitous Positioning Indoor Navigation and Location Based Service, UPINLBS 2014 - Conference Proceedings., 7033715, IEEE, Piscataway, NJ, USA, Sivut 97-102, Ubiquitous Positioning, Indoor Navigation and Location-Based Service, 1/01/15. https://doi.org/10.1109/UPINLBS.2014.7033715

APA

Rivero Rodriguez, A., Leppäkoski, H., & Piché, R. (2015). Semantic Labeling of Places based on Phone Usage Features using Supervised Learning. teoksessa 2014 Ubiquitous Positioning Indoor Navigation and Location Based Service, UPINLBS 2014 - Conference Proceedings (Sivut 97-102). [7033715] Piscataway, NJ, USA: IEEE. https://doi.org/10.1109/UPINLBS.2014.7033715

Vancouver

Rivero Rodriguez A, Leppäkoski H, Piché R. Semantic Labeling of Places based on Phone Usage Features using Supervised Learning. julkaisussa 2014 Ubiquitous Positioning Indoor Navigation and Location Based Service, UPINLBS 2014 - Conference Proceedings. Piscataway, NJ, USA: IEEE. 2015. s. 97-102. 7033715 https://doi.org/10.1109/UPINLBS.2014.7033715

Author

Rivero Rodriguez, Alejandro ; Leppäkoski, Helena ; Piché, Robert. / Semantic Labeling of Places based on Phone Usage Features using Supervised Learning. 2014 Ubiquitous Positioning Indoor Navigation and Location Based Service, UPINLBS 2014 - Conference Proceedings. Piscataway, NJ, USA : IEEE, 2015. Sivut 97-102

Bibtex - Lataa

@inproceedings{3ab18a2054d34f4fa1dbddec3d58e0d9,
title = "Semantic Labeling of Places based on Phone Usage Features using Supervised Learning",
abstract = "Nowadays mobile applications demand higher context awareness. The applications aim to understand the user's context (e.g., home or at work) and provide services tailored to the users. The algorithms responsible for inferring the user's context are the so-called context inference algorithms, the place detection being a particular case. Our hypothesis is that people use mobile phones differently when they are located in different places (e.g. longer calls at home than at work). Therefore, the usage of the mobile phones could be an indicator of the users' current context. The objective of the work is to develop a system that can estimate the user's place label (home, work, etc.), based on phone usage. As training and validation set, we use a database containing phone usage information of 200 users over several months including phone call and SMS logs, multimedia usage, accelerometer, GPS, network information and system information. The data was split into visits, i.e., periods of uninterrupted time that the user has been in a certain place (Home, Work, Leisure, etc.). The data include information about the phone usage during the visits, and the semantic label of the place visited (Home, Work, etc.). We consider two approaches to represent this data: the first approach (so-called visits approach) saves each visit separately; the second approach (so-called places approach) combines all visits of one user to a certain place and creates place-specific information. For place detection, we used five popular classification methods, Na{\"i}ve Bayes, Decision Tree, Bagged Tree, Neural Network and K-Nearest Neighbors, in both representation approaches. We evaluated their classification rates and found that: 1) Bagged Tree outperforms the other methods; 2) the places data-representation gives better results than the visits data-representation.",
keywords = "Context Inference, Location and positioning services, Place detection, Semantic positioning",
author = "{Rivero Rodriguez}, Alejandro and Helena Lepp{\"a}koski and Robert Pich{\'e}",
note = "ORG=mat,0.6 ORG=ase,0.4 Portfolio EDEND: 2015-01-14 <br /> publication_forum:72750",
year = "2015",
month = "2",
day = "5",
doi = "10.1109/UPINLBS.2014.7033715",
language = "English",
isbn = "9781479960040",
pages = "97--102",
booktitle = "2014 Ubiquitous Positioning Indoor Navigation and Location Based Service, UPINLBS 2014 - Conference Proceedings",
publisher = "IEEE",

}

RIS (suitable for import to EndNote) - Lataa

TY - GEN

T1 - Semantic Labeling of Places based on Phone Usage Features using Supervised Learning

AU - Rivero Rodriguez, Alejandro

AU - Leppäkoski, Helena

AU - Piché, Robert

N1 - ORG=mat,0.6 ORG=ase,0.4 Portfolio EDEND: 2015-01-14 <br /> publication_forum:72750

PY - 2015/2/5

Y1 - 2015/2/5

N2 - Nowadays mobile applications demand higher context awareness. The applications aim to understand the user's context (e.g., home or at work) and provide services tailored to the users. The algorithms responsible for inferring the user's context are the so-called context inference algorithms, the place detection being a particular case. Our hypothesis is that people use mobile phones differently when they are located in different places (e.g. longer calls at home than at work). Therefore, the usage of the mobile phones could be an indicator of the users' current context. The objective of the work is to develop a system that can estimate the user's place label (home, work, etc.), based on phone usage. As training and validation set, we use a database containing phone usage information of 200 users over several months including phone call and SMS logs, multimedia usage, accelerometer, GPS, network information and system information. The data was split into visits, i.e., periods of uninterrupted time that the user has been in a certain place (Home, Work, Leisure, etc.). The data include information about the phone usage during the visits, and the semantic label of the place visited (Home, Work, etc.). We consider two approaches to represent this data: the first approach (so-called visits approach) saves each visit separately; the second approach (so-called places approach) combines all visits of one user to a certain place and creates place-specific information. For place detection, we used five popular classification methods, Naïve Bayes, Decision Tree, Bagged Tree, Neural Network and K-Nearest Neighbors, in both representation approaches. We evaluated their classification rates and found that: 1) Bagged Tree outperforms the other methods; 2) the places data-representation gives better results than the visits data-representation.

AB - Nowadays mobile applications demand higher context awareness. The applications aim to understand the user's context (e.g., home or at work) and provide services tailored to the users. The algorithms responsible for inferring the user's context are the so-called context inference algorithms, the place detection being a particular case. Our hypothesis is that people use mobile phones differently when they are located in different places (e.g. longer calls at home than at work). Therefore, the usage of the mobile phones could be an indicator of the users' current context. The objective of the work is to develop a system that can estimate the user's place label (home, work, etc.), based on phone usage. As training and validation set, we use a database containing phone usage information of 200 users over several months including phone call and SMS logs, multimedia usage, accelerometer, GPS, network information and system information. The data was split into visits, i.e., periods of uninterrupted time that the user has been in a certain place (Home, Work, Leisure, etc.). The data include information about the phone usage during the visits, and the semantic label of the place visited (Home, Work, etc.). We consider two approaches to represent this data: the first approach (so-called visits approach) saves each visit separately; the second approach (so-called places approach) combines all visits of one user to a certain place and creates place-specific information. For place detection, we used five popular classification methods, Naïve Bayes, Decision Tree, Bagged Tree, Neural Network and K-Nearest Neighbors, in both representation approaches. We evaluated their classification rates and found that: 1) Bagged Tree outperforms the other methods; 2) the places data-representation gives better results than the visits data-representation.

KW - Context Inference

KW - Location and positioning services

KW - Place detection

KW - Semantic positioning

U2 - 10.1109/UPINLBS.2014.7033715

DO - 10.1109/UPINLBS.2014.7033715

M3 - Conference contribution

SN - 9781479960040

SP - 97

EP - 102

BT - 2014 Ubiquitous Positioning Indoor Navigation and Location Based Service, UPINLBS 2014 - Conference Proceedings

PB - IEEE

CY - Piscataway, NJ, USA

ER -