Advertisement

Classifying Event-Related Desynchronization in EEG, ECoG and MEG Signals

  • N. Jeremy Hill
  • Thomas Navin Lal
  • Michael Schröder
  • Thilo Hinterberger
  • Guido Widman
  • Christian E. Elger
  • Bernhard Schölkopf
  • Niels Birbaumer
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4174)

Abstract

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.

Keywords

Support Vector Machine Independent Component Analysis Motor Imagery Independent Component Analysis Brain Computer Interface 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [Delorme and Makeig(2004)]
    Delorme, A., Makeig, S.: EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics. Journal of Neuroscience Methods 134, 9–21 (2004)CrossRefGoogle Scholar
  2. [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
  3. [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
  4. [Guyon et al(2002)Guyon, Weston, Barnhill, and Vapnik]
    Guyon, I., Weston, J., Barnhill, S., Vapnik, V.: Gene selection for cancer classification using support vector machines. Machine Learning 46, 389–422 (2002)zbMATHCrossRefGoogle Scholar
  5. [Koles et al(1990)Koles, Lazar, and Zhou]
    Koles, Z.J., Lazar, M.S., Zhou, S.Z.: Spatial patterns underlying population differences in the background EEG. Brain Topography 2(4), 275–284 (1990)CrossRefGoogle Scholar
  6. [Kübler et al(2005)Kübler, Nijboer, Mellinger, Vaughan, Pawelzik, Schalk, McFarland, Birbaumer, and Wolpaw]
    Kübler, A., Nijboer, F., Mellinger, J., Vaughan, T., Pawelzik, H., Schalk, G., McFarland, D., Birbaumer, N., Wolpaw, J.: Patients with ALS can use sensorimotor rhythms to operate a braincomputer interface. Neurology 64, 1775–1777 (2005)CrossRefGoogle Scholar
  7. [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
  8. [Lal et al(2005a)Lal, Schröder, Hill, Hinterberger, Mellinger, Rosenstiel, Hofmann, Birbaumer, and Schölkopf]
    Lal, T., Schröder, M., Hill, N., Hinterberger, T., Mellinger, J., Rosenstiel, W., Hofmann, T., Birbaumer, N., Schölkopf, B.: A brain computer interface with online feedback based on magnetoencephalography. ICML 22, 465–472 (2005a)CrossRefGoogle Scholar
  9. [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
  10. [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
  11. [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

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • N. Jeremy Hill
    • 1
  • Thomas Navin Lal
    • 1
  • Michael Schröder
    • 2
  • Thilo Hinterberger
    • 3
  • Guido Widman
    • 4
  • Christian E. Elger
    • 4
  • Bernhard Schölkopf
    • 1
  • Niels Birbaumer
    • 3
    • 5
  1. 1.MPI for Biological CyberneticsTübingen
  2. 2.Fraunhofer FIRST IDA groupBerlin
  3. 3.Inst. of Medical Psychology and Behavioral NeurobiologyUniversity of Tübingen 
  4. 4.Department of EpileptologyUniversity of Bonn 
  5. 5.NIH Human Cortical Physiology UnitBethesdaUSA

Personalised recommendations