One‐class classification using a support vector machine with a quasi‐linear kernel

Peifeng Liang; Weite Li; Hao Tian; Jinglu Hu

doi:10.1002/tee.22826

journal article Oct 17, 2018

One‐class classification using a support vector machine with a quasi‐linear kernel

Peifeng Liang

Weite Li Hao Tian

Jinglu Hu

IEEJ Transactions on Electrical and Electronic Engineering Vol. 14 No. 3 pp. 449-456 · Wiley

View at Publisher Save 10.1002/tee.22826

Abstract

This article proposes a novel method for one‐class classification based on a divide‐and‐conquer strategy to improve the one‐class support vector machine (SVM). The idea is to build a piecewise linear separation boundary in the feature space to separate the data points from the origin, which is expected to have a more compact region in the input space. For the purpose, the input space of the dataset is first divided into a group of partitions by using a partitioning mechanism of tops% winner‐take‐all autoencoder. A gated linear network is designed to implement a group of linear classifiers for each partition, in which the gate signals are generated from the autoencoder. By applying a one‐class SVM (OCSVM) formulation to optimize the parameter set of the gated linear network, the one‐class classifier is implemented in an exactly same way as a standard OCSVM with a quasi‐linear kernel composed using a base kernel with the gate signals. The proposed one‐class classification method is applied to different real‐world datasets, and simulation results show that it shows a better performance than a traditional OCSVM. © 2018 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

Topics

No keywords indexed for this article. Browse by subject →

References

35

[1]

KhanSS MaddenMG. A survey of recent trends in one class classification.Proceedings of the 18th Irish Conference on Artificial Intelligence and Cognitive Science Dublin Springer 2009;188–197. 10.1007/978-3-642-17080-5_21

[2]

TaxDMJ.One‐class classification PhD dissertation series number 65 Delft University of Technology 2001.

[3]

One-class classification: taxonomy of study and review of techniques

Shehroz S. Khan, Michael G. Madden

The Knowledge Engineering Review 10.1017/s026988891300043x

[4]

JanssensJ HM. Outlier selection and one‐class classification TiCC PhD Dissertation Series No. 27 Tilburg University 2013.

[5]

10.1109/tkde.2004.1264823

[6]

Cohen G "An application of one‐class support vector machines to nosocomial infection detection" Studies in health technology and informatics (2004)

[7]

10.1016/j.cie.2005.01.009

[8]

ZengZ FuY RoismanGI WenZ HuY HuangTS. One‐class classification for spontaneous facial expression analysis.Proceedings of 7th International Conference on Automatic Face and Gesture Recognition (FGR 2006) Southampton IEEE 2006;281–286.

[9]

Alashwal H "One‐class support vector machines for protein‐protein interactions prediction" International Journal of Bioengineering and Life Sciences (2007)

[10]

10.1016/j.patcog.2013.05.022

[11]

Robert P "On the choice of smoothing parameters for parzen estimators of probability density functions" IEEE Transactions on Computers (1976)

[12]

Cohen G "Novelty detection using one‐class parzen density estimator. An application to surveillance of nosocomial infections" Studies in Health Technology and Informatics (2008)

[13]

10.1007/s007780050006

[14]

10.1016/s0167-8655(00)00131-8

[15]

10.1016/j.neucom.2006.05.013

[16]

Estimating the Support of a High-Dimensional Distribution

Bernhard Schölkopf, John C. Platt, John Shawe-Taylor et al.

Neural Computation 10.1162/089976601750264965

[17]

10.1023/b:mach.0000008084.60811.49

[18]

PekalskaE TaxDM DuinR. One‐class LP classifiers for dissimilarity representations.Proceedings of Advances in Neural Information Processing Systems (NIPS) Vancouver 2003;777–784.

[19]

GhaouiLE JordanMI LanckrietGR. Robust novelty detection with single‐class mpm.Proceedings of Advances in Neural Information Processing Systems Vancouver 2003;929–936.

[20]

Manevitz LM "One‐class SVMs for document classification" Journal of Machine Learning Research (2001)

[21]

Yin S (2014)

[22]

Makhzani A (2015)

[23]

LiW LiangP HuJ. Non‐local information for a mixture of multiple linear classifiers 2017 IEEE International Joint Conference on Neural Networks (IJCNN2017) Anchorage IEEE 2017;3741–3746. 10.1109/ijcnn.2017.7966327

[24]

Vert J‐P "A primer on kernel methods" Kernel Methods in Computational Biology (2004) 10.7551/mitpress/4057.003.0004

[25]

10.1587/transfun.e99.a.2558

[26]

Reducing the Dimensionality of Data with Neural Networks

G. E. Hinton, R. R. Salakhutdinov

Science 10.1126/science.1127647

[27]

NgA. Sparse autoencoder. CS294A Lecture Notes 2011.

[28]

MakhzaniA FreyB. K‐sparse autoencoders. arXiv preprint arXiv:1312.5663 2013.

[29]

LadickyL TorrP. Locally linear support vector machines.Procedings of the 28th International Conference on Machine Learning (ICML 2011) Bellevue 2011;985–992.

[30]

GlorotX BordesA BengioY. Deep sparse rectifier neural networks.Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics Lauderdale 2011;315–323.

[31]

LIBSVM

Chih-Chung Chang, Chih-Jen Lin

ACM Transactions on Intelligent Systems and Techno... 10.1145/1961189.1961199

[32]

TaxDM MüllerK‐R. Feature extraction for one‐class classification.Proceedings of Joint International Conference on Artificial Neural Networks and Neural Information Processing (ICANN/ICONIP 2003) Istanbul Springer 2003;342–349. 10.1007/3-540-44989-2_41

[33]

TokuiS OonoK HidoS ClaytonJ. Chainer: A next‐generation open source framework for deep learning.Proceedings of the 29th Annual Conference on Neural Information Processing Systems (NIPS2015) Montreal 2015.

[34]

TaxD. Data description toolbox dd tools 2.1. 1 Delft University of Technology Delft The Netherlands Technical Report 2014.

[35]

The relationship between Precision-Recall and ROC curves

Jesse Davis, Mark Goadrich

Proceedings of the 23rd international conference o... 10.1145/1143844.1143874

Metrics

10

Citations

35

References

Details

Published: Oct 17, 2018
Vol/Issue: 14(3)
Pages: 449-456
License: View

Authors

P

Peifeng Liang

Graduate School of Information, Production and Systems Waseda University Kitakyushu‐shi 808‐0135 Japan

W

Weite Li

Graduate School of Information, Production and Systems Waseda University Kitakyushu‐shi 808‐0135 Japan

H

Hao Tian

School of Information Engineering Hubei University of Economics, No. 8, Yangqiaohu Avenue Jiangxia District Wuhan 430205 China

J

Jinglu Hu

Graduate School of Information, Production and Systems Waseda University Kitakyushu‐shi 808‐0135 Japan

Funding

Science Research Key Project of the Department of Education in Hubei Province, China Award: D20162202

Cite This Article

Peifeng Liang, Weite Li, Hao Tian, et al. (2018). One‐class classification using a support vector machine with a quasi‐linear kernel. IEEJ Transactions on Electrical and Electronic Engineering, 14(3), 449-456. https://doi.org/10.1002/tee.22826

One‐class classification using a support vector machine with a quasi‐linear kernel

You May Also Like