TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

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

Tutkimustuotosvertaisarvioitu

Standard

One-Class Classification based on Extreme Learning and Geometric Class Information. / Iosifidis, Alexandros; Mygdalis, Vasileios; Tefas, Anastasios; Pitas, Ioannis.

julkaisussa: Neural Processing Letters, 2016, s. 1-16.

Tutkimustuotosvertaisarvioitu

Harvard

Iosifidis, A, Mygdalis, V, Tefas, A & Pitas, I 2016, 'One-Class Classification based on Extreme Learning and Geometric Class Information', Neural Processing Letters, Sivut 1-16. https://doi.org/10.1007/s11063-016-9541-y

APA

Iosifidis, A., Mygdalis, V., Tefas, A., & Pitas, I. (2016). One-Class Classification based on Extreme Learning and Geometric Class Information. Neural Processing Letters, 1-16. https://doi.org/10.1007/s11063-016-9541-y

Vancouver

Iosifidis A, Mygdalis V, Tefas A, Pitas I. One-Class Classification based on Extreme Learning and Geometric Class Information. Neural Processing Letters. 2016;1-16. https://doi.org/10.1007/s11063-016-9541-y

Author

Iosifidis, Alexandros ; Mygdalis, Vasileios ; Tefas, Anastasios ; Pitas, Ioannis. / One-Class Classification based on Extreme Learning and Geometric Class Information. Julkaisussa: Neural Processing Letters. 2016 ; Sivut 1-16.

Bibtex - Lataa

@article{c9d1bbe656de44089fdd9b8ad3553fbd,
title = "One-Class Classification based on Extreme Learning and Geometric Class Information",
abstract = "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.",
keywords = "Big data, Extreme learning machine, Novelty detection, One-class classification",
author = "Alexandros Iosifidis and Vasileios Mygdalis and Anastasios Tefas and Ioannis Pitas",
note = "EXT={"}Tefas, Anastasios{"}",
year = "2016",
doi = "10.1007/s11063-016-9541-y",
language = "English",
pages = "1--16",
journal = "Neural Processing Letters",
issn = "1370-4621",
publisher = "Springer Verlag",

}

RIS (suitable for import to EndNote) - Lataa

TY - JOUR

T1 - One-Class Classification based on Extreme Learning and Geometric Class Information

AU - Iosifidis, Alexandros

AU - Mygdalis, Vasileios

AU - Tefas, Anastasios

AU - Pitas, Ioannis

N1 - EXT="Tefas, Anastasios"

PY - 2016

Y1 - 2016

N2 - 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.

AB - 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.

KW - Big data

KW - Extreme learning machine

KW - Novelty detection

KW - One-class classification

U2 - 10.1007/s11063-016-9541-y

DO - 10.1007/s11063-016-9541-y

M3 - Article

SP - 1

EP - 16

JO - Neural Processing Letters

JF - Neural Processing Letters

SN - 1370-4621

ER -