Classification Methods for Brain-Computer Interface

0364124 - ÚI 2012 CZ eng K - Conference Paper (Czech conference)
Bobrov, P. - Frolov, A. A. - Húsek, Dušan
Classification Methods for Brain-Computer Interface.
WOFEX 2011. Ostrava: VŠB - Technical University, 2011 - (Krátký, P.; Dvorský, J.; Moravec, P.), s. 314-319. ISBN 978-80-248-2449-9.
[WOFEX 2011. Annual Workshop /9./. Ostrava (CZ), 08.09.2011-09.09.2011]
Institutional research plan: CEZ:AV0Z10300504
Keywords : brain computer interface * BCI * EEG * Bayesian classifier * common spatial patterns * CSP * common tensor discriminant analysis * CTDA * classification accuracy
Subject RIV: IN - Informatics, Computer Science

The performance of four classifiers for Brain Computer Interface (BCI) systems based on multichannel EEG recordings is tested in this work. The classifiers are designed to distinguish EEG patterns corresponding to performance of several mental tasks. It is shown that relatively simple classifiers based on the Bayesian approach are comparable in classification accuracy with more sophisticated classifiers based on Common Spatial Patterns and Common Tensor Discriminant Analysis
Permanent Link: http://hdl.handle.net/11104/0199687