Improving Classification Performance of BCIs by Using Stationary Common Spatial Patterns and Unsupervised Bias Adaptation

  • Wojciech Wojcikiewicz
  • Carmen Vidaurre
  • Motoaki Kawanabe
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6679)

Abstract

Non-stationarities in EEG signals coming from electrode artefacts, muscular activity or changes of task involvement can negatively affect the classification accuracy of Brain-Computer Interface (BCI) systems. In this paper we investigate three methods to alleviate this: (1) Regularization of Common Spatial Patterns (CSP) towards stationary subspaces in order to reduce the influence of artefacts. (2) Unsupervised adaptation of the classifier bias with the goal to account for systematic shifts of the features occurring for example in the transition from calibration to feedback session or with increasing fatigue of the subject. (3) Decomposition of the CSP projection matrix into a whitening and a rotation part and adaptation of the whitening matrix in order to reduce the influence of non-task related changes. We study all three approaches on a data set of 80 subjects and show that stationary features with bias adaptation significantly outperforms the other combinations.

Keywords

Brain-Computer Interface Common Spatial Patterns stationary features adaptive classification 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Blankertz, B., Tomioka, R., Lemm, S., Kawanabe, M., Müller, K.-R.: Optimizing spatial filters for robust eeg single-trial analysis. IEEE Signal Proc. Magazine, 581–607 (2008)Google Scholar
  2. 2.
    Blankertz, B., Kawanabe, M., Tomioka, R., Hohlefeld, F.U., Nikulin, V., Müller, K.-R.: Invariant common spatial patterns: Alleviating nonstationarities in brain-computer interfacing. Ad. in NIPS 20 (2008)Google Scholar
  3. 3.
    Blankertz, B., Sannelli, C., Halder, S., Hammer, E.M., Kübler, A., Müller, K.-R., Curio, G., Dickhaus, T.: Neurophysiological Predictor of SMR-Based BCI Performance. NeuroImage 51(4), 1303–1309 (2010)CrossRefGoogle Scholar
  4. 4.
    Dornhege, G., Millán, J.d.R., Hinterberger, T., McFarland, D., Müller, K.-R.: Toward Brain-Computer Interfacing. MIT Press, Cambridge (2007)Google Scholar
  5. 5.
    Li, Y., Kambara, H., Koike, Y., Sugiyama, M.: Application of covariate shift adaptation techniques in brain-computer interfaces. IEEE Trans. Biomed. Eng. 57(6), 1318–1324 (2010)CrossRefGoogle Scholar
  6. 6.
    Mika, S., Rätsch, G., Weston, J., Schölkopf, B., Smola, A., Müller, K.-R.: Invariant feature extraction and classification in kernel spaces. Ad. in NIPS 12, 526–532 (2000)Google Scholar
  7. 7.
    Ramoser, H., Müller-Gerking, J., Pfurtscheller, G.: Optimal spatial filtering of single trial EEG during imagined hand movement. IEEE Trans. Rehab. Eng. 8, 441–446 (1998)CrossRefGoogle Scholar
  8. 8.
    Tomioka, R., Hill, J.N., Blankertz, B., Aihara, K.: Adapting Spatial Filter Methods for Nonstationary BCIs. In: Proc. of Workshop on Information-Based Induction Sciences (IBIS), pp. 65–70 (2006)Google Scholar
  9. 9.
    Vidaurre, C., Kawanabe, M., von Bünau, P., Blankertz, B., Müller, K.-R.: Toward an unsupervised adaptation of LDA for Brain-Computer Interfaces. IEEE Trans. Biomed. Eng. (2010) (in press)Google Scholar
  10. 10.
    Vidaurre, C., Sannelli, C., Müller, K.-R., Blankertz, B.: Machine-learning based co-adaptive calibration. Neural Comput. (2010) (in press)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Wojciech Wojcikiewicz
    • 1
    • 2
    • 3
  • Carmen Vidaurre
    • 1
  • Motoaki Kawanabe
    • 2
    • 1
  1. 1.Technical University of BerlinBerlinGermany
  2. 2.Fraunhofer Institute FIRSTBerlinGermany
  3. 3.Bernstein Center for Computational NeuroscienceBerlinGermany

Personalised recommendations