Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

A Bayesian approach for adaptive BCI classification

: Kawanabe, M.; Krauledat, M.; Blankertz, B.

Fulltext (PDF; )

Müller-Putz, G.R. ; TU Graz, Laboratory of Brain-Computer Interface:
3rd International Brain-Computer Interface Workshop and Training Course 2006. Proceedings : September 21-24 2006, Graz University of Technology, Austria
Graz: Verlag der TU Graz, 2006
ISBN: 3-902465-46-8
ISBN: 978-3-902465-46-7
International Brain-Computer Interface Workshop and Training Course <3, 2006, Graz>
Conference Paper, Electronic Publication
Fraunhofer FIRST ()

In this article, we present an adaptive classifier for BCI based on a mixture of Gaussian (moG) model of the features and a dynamical Bayesian model of the class means. We apply this approach to feedback data from the Berlin Brain-
Computer Interface (BBCI). The proposed model can improve the classification performance by compensating for substantial changes of EEG signals between training and feedback sessions as well as for gradual nonstationarity in the feedback sessions.