Brain-Computer Interface: Common Tensor Discriminant Analysis Classifier Evaluation

0365748 - ÚI 2012 RIV US eng C - Conference Paper (international conference)
Frolov, A. - Húsek, Dušan - Bobrov, P.
Brain-Computer Interface: Common Tensor Discriminant Analysis Classifier Evaluation.
Nature and Biologically Inspired Computing. Piscataway: IEEE, 2011 - (Abraham, A.; Corchado, E.; Berwick, R.; de Carvalho, A.; Zomaya, A.; Yager, R.), s. 614-620. ISBN 978-1-4577-1122-0.
[NaBIC 2011. World Congress on Nature and Biologically Inspired Computing /3./. Salamanca (ES), 19.10.2011-21.10.2011]
R&D Projects: GA ČR GAP202/10/0262; GA ČR GA205/09/1079; GA MŠMT(CZ) 1M0567
Grant - others:GA MŠk(CZ) ED1.1.00/02.0070
Program: ED
Institutional research plan: CEZ:AV0Z10300504
Keywords : human computer interface * motor imagery * EEG signal classification * Bayesian classification * Common Spatial Patterns * Common Tensor Discriminant Analysis
Subject RIV: IN - Informatics, Computer Science

The performance of the Common Tensor Discriminant Analysis CTDA method for Brain-Computer Interface EEG pattern classification is compared with three other classifiers. The classifiers are designed with the aim to distinguish EEG patterns appearing as a result of performance of several mental tasks. Classifier comparison has yielded quite similar results as regards our experimental imagery movement data set as well as for BCI Competition IV data set. The Bayesian and Multiclass Common Spatial Patterns classifiers, which use solely interchannel covariance as input, are shown to be comparable in performance, while lagging behind the Multiclass Common Spatial Patterns classifier and the CTDA classifier, that is classifiers which additionally account for EEG frequency structure. It is shown that the CTDA classifier and the Multiclass Common Spatial Patterns classifier provide significantly better classification than other two methods but at a higher computational cost.
Permanent Link: http://hdl.handle.net/11104/0200917