Classifying Event-Related Desynchronization in EEG, ECoG and MEG Signals
We employed three different brain signal recording methods to perform Brain-Computer Interface studies on untrained subjects. In all cases, we aim to develop a system that could be used for fast, reliable preliminary screening in clinical BCI application, and we are interested in knowing how long screening sessions need to be. Good performance could be achieved, on average, after the first 200 trials in EEG, 75–100 trials in MEG, or 25–50 trials in ECoG. We compare the performance of Independent Component Analysis and the Common Spatial Pattern algorithm in each of the three sensor types, finding that spatial filtering does not help in MEG, helps a little in ECoG, and improves performance a great deal in EEG. In all cases the unsupervised ICA algorithm performed at least as well as the supervised CSP algorithm, which can suffer from poor generalization performance due to overfitting, particularly in ECoG and MEG.
KeywordsSupport Vector Machine Independent Component Analysis Motor Imagery Independent Component Analysis Brain Computer Interface
Unable to display preview. Download preview PDF.
- [Delorme and Makeig(2004)]
- [Dornhege et al(2004)Dornhege, Blankertz, Curio, and Müller]Dornhege, G., Blankertz, B., Curio, G., Müller, K.R.: Increase information transfer rates in bci by csp extension to multi-class. NIPS 16 (2004)Google Scholar
- [Dornhege et al(2006)Dornhege, Blankertz, Krauledat, Losch, Curio, and Müller]Dornhege, G., Blankertz, B., Krauledat, M., Losch, F., Curio, G., Müller, K.R.: Optimizing spatio-temporal filters for improving Brain-Computer Interfacing. NIPS 18 (2006)Google Scholar
- [Guyon et al(2002)Guyon, Weston, Barnhill, and Vapnik]
- [Koles et al(1990)Koles, Lazar, and Zhou]
- [Kübler et al(2005)Kübler, Nijboer, Mellinger, Vaughan, Pawelzik, Schalk, McFarland, Birbaumer, and Wolpaw]
- [Lal et al(2004)Lal, Schröder, Hinterberger, Weston, Bogdan, Birbaumer, and Schölkopf]Lal, T., Schröder, M., Hinterberger, T., Weston, J., Bogdan, M., Birbaumer, N., Schölkopf, B.: Support vector channel selection in BCI. IEEE TBME 51(6), 1003–1010 (2004)Google Scholar
- [Lal et al(2005a)Lal, Schröder, Hill, Hinterberger, Mellinger, Rosenstiel, Hofmann, Birbaumer, and Schölkopf]
- [Lal et al(2005b)Lal, Hinterberger, Widman, Schröder, Hill, Rosenstiel, Elger, Schölkopf, and Birbaumer]Lal, T.N., Hinterberger, T., Widman, G., Schröder, M., Hill, N.J., Rosenstiel, W., Elger, C.E., Schölkopf, B., Birbaumer, N.: Methods towards invasive human brain computer interfaces. NIPS 17 (2005b)Google Scholar
- [Lemm et al(2004)Lemm, Blankertz, Curio, and Müller]Lemm, S., Blankertz, B., Curio, G., Müller, K.R.: Spatio-spectral filters for robust classification of single trial EEG. IEEE TBME 52(9), 993–1002 (2004)Google Scholar
- [Müller et al(2003)Müller, Anderson, and Birch]Müller, K.R., Anderson, C.W., Birch, G.E.: Linear and nonlinear methods for brain-computer interfaces. IEEE TNSRE 11(2), 165–169 (2003)Google Scholar