Multiclass Support Matrix Machines by Maximizing the Inter-Class Margin for Single Trial EEG Classification

Razzak, I; Blumenstein, M; Xu, G

Multiclass Support Matrix Machines by Maximizing the Inter-Class Margin for Single Trial EEG Classification

Razzak, I

Blumenstein, M

Xu, G

Permalink

Publication Type:: Journal Article
Citation:: IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2019, 27 (6), pp. 1117 - 1127
Issue Date:: 2019-06-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published VersionAdobe PDF (547.05 kB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Razzak, I https://orcid.org/0000-0002-3930-6600	en_US
dc.contributor.author	Blumenstein, M https://orcid.org/0000-0002-9908-3744	en_US
dc.contributor.author	Xu, G https://orcid.org/0000-0003-4493-6663	en_US
dc.date.available	2021-08-12T19:00:56Z
dc.date.issued	2019-06-01	en_US
dc.identifier.citation	IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2019, 27 (6), pp. 1117 - 1127	en_US
dc.identifier.issn	1534-4320	en_US
dc.identifier.uri	http://hdl.handle.net/10453/134906
dc.description.abstract	© 2001-2011 IEEE. Accurate classification of Electroencephalogram (EEG) signals plays an important role in diagnoses of different type of mental activities. One of the most important challenges, associated with classification of EEG signals is how to design an efficient classifier consisting of strong generalization capability. Aiming to improve the classification performance, in this paper, we propose a novel multiclass support matrix machine (M-SMM) from the perspective of maximizing the inter-class margins. The objective function is a combination of binary hinge loss that works on C matrices and spectral elastic net penalty as regularization term. This regularization term is a combination of Frobenius and nuclear norm, which promotes structural sparsity and shares similar sparsity patterns across multiple predictors. It also maximizes the inter-class margin that helps to deal with complex high dimensional noisy data. The extensive experiment results supported by theoretical analysis and statistical tests show the effectiveness of the M-SMM for solving the problem of classifying EEG signals associated with motor imagery in brain-computer interface applications.	en_US
dc.relation	http://purl.org/au-research/grants/arc/LP170100891
dc.relation.ispartof	IEEE Transactions on Neural Systems and Rehabilitation Engineering	en_US
dc.relation.isbasedon	10.1109/TNSRE.2019.2913142	en_US
dc.rights	info:eu-repo/semantics/embargoedAccess
dc.subject.classification	Biomedical Engineering	en_US
dc.title	Multiclass Support Matrix Machines by Maximizing the Inter-Class Margin for Single Trial EEG Classification	en_US
dc.type	Journal Article
utslib.citation.volume	6	en_US
utslib.citation.volume	27	en_US
utslib.for	0903 Biomedical Engineering	en_US
utslib.for	0906 Electrical and Electronic Engineering	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
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
pubs.organisational-group	/University of Technology Sydney/Strength - AAI - Advanced Analytics Institute Research Centre
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
pubs.organisational-group	/University of Technology Sydney/Strength - QSI - Centre for Quantum Software and Information
pubs.organisational-group	/University of Technology Sydney/Students
utslib.copyright.status	open_access	*
pubs.issue	6	en_US
pubs.publication-status	Published	en_US
pubs.volume	27	en_US

Abstract:

© 2001-2011 IEEE. Accurate classification of Electroencephalogram (EEG) signals plays an important role in diagnoses of different type of mental activities. One of the most important challenges, associated with classification of EEG signals is how to design an efficient classifier consisting of strong generalization capability. Aiming to improve the classification performance, in this paper, we propose a novel multiclass support matrix machine (M-SMM) from the perspective of maximizing the inter-class margins. The objective function is a combination of binary hinge loss that works on C matrices and spectral elastic net penalty as regularization term. This regularization term is a combination of Frobenius and nuclear norm, which promotes structural sparsity and shares similar sparsity patterns across multiple predictors. It also maximizes the inter-class margin that helps to deal with complex high dimensional noisy data. The extensive experiment results supported by theoretical analysis and statistical tests show the effectiveness of the M-SMM for solving the problem of classifying EEG signals associated with motor imagery in brain-computer interface applications.

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

http://hdl.handle.net/10453/134906