Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

A maxmin approach to optimize spatial filters for EEG single-trial classification

: Kawanabe, M.; Vidaurre, C.; Blankertz, B.; Müller, K.-R.


Cabestany, J.:
10th International Work-Conference on Artificial Neural Networks 2009. Vol.1: Bio-inspired systems: Computational and ambient intelligence : Salamanca, Spain, June 10-12, 2009 ; proceedings
Berlin: Springer, 2009 (Lecture Notes in Computer Science 5517)
ISBN: 3-642-02477-7
ISBN: 978-3-642-02477-1
ISSN: 0302-9743
International Work Conference on Artificial Neural Networks (IWANN) <10, 2009, Salamanca>
Conference Paper
Fraunhofer FIRST ()

Electroencephalographic single-trial analysis requires methods that are robust with respect to noise, artifacts and non-stationarity among other problems. This work contributes by developing a maxmin approach to robustify the common spatial patterns (CSP) algorithm. By optimizing the worst-case objective function within a prefixed set of the covariance matrices, we can transform the respective complex mathematical program into a simple generalized eigen-value problem and thus obtain robust spatial filters very efficiently. We test our maxmin CSP method with real world brain-computer interface (BCI) data sets in which we expect substantial fluctuations caused by day-to-day or paradigm-to-paradigm variability or different forms of stimuli. The results clearly show that the proposed method significantly improves the classical CSP approach in multiple BCI scenarios.