One-Class Classification Using Quasi-Linear Support Vector Machine

Peifeng Liang, Weite Li, Yudong Wang, Takayuki Furuzuki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper proposes a novel method for one-class classification by using support vector machine (SVM) based on a divide-and-conquer strategy. An s% winner-take-all autoencoder is applied to realize a sophisticated partitioning which divides the dataset into many clusters. For each cluster, data points are separated from the origin in the feature space like a traditional one-class SVM (OCSVM). By designing a gated linear network, and generating the gate signal from the autoencoder, the proposed OCSVM is implemented in an exact same way as a standard OCSVM with a quasi-linear kernel composed by using a base kernel with the gate signals. Comparing to a traditional OCSVM, the proposed quasi-linear OCSVM is expected to capture a more compact region in the input space. The compact region will decrease the probability of outlier objects falling inside the domain of classifier, which give a better performance. The proposed quasi-linear OCSVM method is applied to different real-world datasets, and simulation results confirm the effectiveness of the proposed method.

Original languageEnglish
Title of host publicationProceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages662-667
Number of pages6
ISBN (Electronic)9781538666500
DOIs
Publication statusPublished - 2019 Jan 16
Event2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018 - Miyazaki, Japan
Duration: 2018 Oct 72018 Oct 10

Publication series

NameProceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018

Conference

Conference2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018
CountryJapan
CityMiyazaki
Period18/10/718/10/10

Fingerprint

Support vector machines
Linear networks
Classifiers
Support Vector Machine
Support vector machine
Datasets

ASJC Scopus subject areas

  • Information Systems
  • Information Systems and Management
  • Health Informatics
  • Artificial Intelligence
  • Computer Networks and Communications
  • Human-Computer Interaction

Cite this

Liang, P., Li, W., Wang, Y., & Furuzuki, T. (2019). One-Class Classification Using Quasi-Linear Support Vector Machine. In Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018 (pp. 662-667). [8616117] (Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SMC.2018.00121

One-Class Classification Using Quasi-Linear Support Vector Machine. / Liang, Peifeng; Li, Weite; Wang, Yudong; Furuzuki, Takayuki.

Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018. Institute of Electrical and Electronics Engineers Inc., 2019. p. 662-667 8616117 (Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Liang, P, Li, W, Wang, Y & Furuzuki, T 2019, One-Class Classification Using Quasi-Linear Support Vector Machine. in Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018., 8616117, Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018, Institute of Electrical and Electronics Engineers Inc., pp. 662-667, 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018, Miyazaki, Japan, 18/10/7. https://doi.org/10.1109/SMC.2018.00121
Liang P, Li W, Wang Y, Furuzuki T. One-Class Classification Using Quasi-Linear Support Vector Machine. In Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 662-667. 8616117. (Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018). https://doi.org/10.1109/SMC.2018.00121
Liang, Peifeng ; Li, Weite ; Wang, Yudong ; Furuzuki, Takayuki. / One-Class Classification Using Quasi-Linear Support Vector Machine. Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 662-667 (Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018).
@inproceedings{ae32eea5415f451c979224aa557337eb,
title = "One-Class Classification Using Quasi-Linear Support Vector Machine",
abstract = "This paper proposes a novel method for one-class classification by using support vector machine (SVM) based on a divide-and-conquer strategy. An s{\%} winner-take-all autoencoder is applied to realize a sophisticated partitioning which divides the dataset into many clusters. For each cluster, data points are separated from the origin in the feature space like a traditional one-class SVM (OCSVM). By designing a gated linear network, and generating the gate signal from the autoencoder, the proposed OCSVM is implemented in an exact same way as a standard OCSVM with a quasi-linear kernel composed by using a base kernel with the gate signals. Comparing to a traditional OCSVM, the proposed quasi-linear OCSVM is expected to capture a more compact region in the input space. The compact region will decrease the probability of outlier objects falling inside the domain of classifier, which give a better performance. The proposed quasi-linear OCSVM method is applied to different real-world datasets, and simulation results confirm the effectiveness of the proposed method.",
author = "Peifeng Liang and Weite Li and Yudong Wang and Takayuki Furuzuki",
year = "2019",
month = "1",
day = "16",
doi = "10.1109/SMC.2018.00121",
language = "English",
series = "Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "662--667",
booktitle = "Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018",

}

TY - GEN

T1 - One-Class Classification Using Quasi-Linear Support Vector Machine

AU - Liang, Peifeng

AU - Li, Weite

AU - Wang, Yudong

AU - Furuzuki, Takayuki

PY - 2019/1/16

Y1 - 2019/1/16

N2 - This paper proposes a novel method for one-class classification by using support vector machine (SVM) based on a divide-and-conquer strategy. An s% winner-take-all autoencoder is applied to realize a sophisticated partitioning which divides the dataset into many clusters. For each cluster, data points are separated from the origin in the feature space like a traditional one-class SVM (OCSVM). By designing a gated linear network, and generating the gate signal from the autoencoder, the proposed OCSVM is implemented in an exact same way as a standard OCSVM with a quasi-linear kernel composed by using a base kernel with the gate signals. Comparing to a traditional OCSVM, the proposed quasi-linear OCSVM is expected to capture a more compact region in the input space. The compact region will decrease the probability of outlier objects falling inside the domain of classifier, which give a better performance. The proposed quasi-linear OCSVM method is applied to different real-world datasets, and simulation results confirm the effectiveness of the proposed method.

AB - This paper proposes a novel method for one-class classification by using support vector machine (SVM) based on a divide-and-conquer strategy. An s% winner-take-all autoencoder is applied to realize a sophisticated partitioning which divides the dataset into many clusters. For each cluster, data points are separated from the origin in the feature space like a traditional one-class SVM (OCSVM). By designing a gated linear network, and generating the gate signal from the autoencoder, the proposed OCSVM is implemented in an exact same way as a standard OCSVM with a quasi-linear kernel composed by using a base kernel with the gate signals. Comparing to a traditional OCSVM, the proposed quasi-linear OCSVM is expected to capture a more compact region in the input space. The compact region will decrease the probability of outlier objects falling inside the domain of classifier, which give a better performance. The proposed quasi-linear OCSVM method is applied to different real-world datasets, and simulation results confirm the effectiveness of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=85062217803&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062217803&partnerID=8YFLogxK

U2 - 10.1109/SMC.2018.00121

DO - 10.1109/SMC.2018.00121

M3 - Conference contribution

T3 - Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018

SP - 662

EP - 667

BT - Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -