Robust L<inf>1</inf>-norm multi-weight vector projection support vector machine with efficient algorithm

Chen, WJ; Li, CN; Shao, YH; Zhang, J; Deng, NY

Robust L<inf>1</inf>-norm multi-weight vector projection support vector machine with efficient algorithm

Chen, WJ

Li, CN Shao, YH Zhang, J Deng, NY

Permalink

Publication Type:: Journal Article
Citation:: Neurocomputing, 2018, 315 pp. 345 - 361
Issue Date:: 2018-11-13

Closed Access

	Filename	Description	Size
	1-s2.0-S0925231218308622-main.pdf	Published Version	2.95 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Chen, WJ https://orcid.org/0000-0001-5186-0279	en_US
dc.contributor.author	Li, CN	en_US
dc.contributor.author	Shao, YH	en_US
dc.contributor.author	Zhang, J	en_US
dc.contributor.author	Deng, NY	en_US
dc.date.issued	2018-11-13	en_US
dc.identifier.citation	Neurocomputing, 2018, 315 pp. 345 - 361	en_US
dc.identifier.issn	0925-2312	en_US
dc.identifier.uri	http://hdl.handle.net/10453/134339
dc.description.abstract	© 2018 Elsevier B.V. The recently proposed multi-weight vector projection support vector machine (EMVSVM) is an excellent multi-projections classifier. However, the formulation of MVSVM is based on the L2-norm criterion, which makes it prone to be affected by outliers. To alleviate this issue, in this paper, we propose a robust L1-norm MVSVM method, termed as MVSVML1. Specifically, our MVSVML1 aims to seek a pair of multiple projections such that, for each class, it maximizes the ratio of the L1-norm between-class dispersion and the L1-norm within-class dispersion. To optimize such L1-norm ratio problem, a simple but efficient iterative algorithm is further presented. The convergence of the algorithm is also analyzed theoretically. Extensive experimental results on both synthetic and real-world datasets confirm the feasibility and effectiveness of the proposed MVSVML1.	en_US
dc.relation.ispartof	Neurocomputing	en_US
dc.relation.isbasedon	10.1016/j.neucom.2018.04.083	en_US
dc.subject.classification	Artificial Intelligence & Image Processing	en_US
dc.title	Robust L<inf>1</inf>-norm multi-weight vector projection support vector machine with efficient algorithm	en_US
dc.type	Journal Article
utslib.citation.volume	315	en_US
utslib.for	0803 Computer Software	en_US
utslib.for	08 Information and Computing Sciences	en_US
utslib.for	09 Engineering	en_US
utslib.for	17 Psychology and Cognitive Sciences	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US
pubs.volume	315	en_US

Abstract:

© 2018 Elsevier B.V. The recently proposed multi-weight vector projection support vector machine (EMVSVM) is an excellent multi-projections classifier. However, the formulation of MVSVM is based on the L2-norm criterion, which makes it prone to be affected by outliers. To alleviate this issue, in this paper, we propose a robust L1-norm MVSVM method, termed as MVSVML1. Specifically, our MVSVML1 aims to seek a pair of multiple projections such that, for each class, it maximizes the ratio of the L1-norm between-class dispersion and the L1-norm within-class dispersion. To optimize such L1-norm ratio problem, a simple but efficient iterative algorithm is further presented. The convergence of the algorithm is also analyzed theoretically. Extensive experimental results on both synthetic and real-world datasets confirm the feasibility and effectiveness of the proposed MVSVML1.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/134339