Skip to main content
SpringerLink
Log in

The stochastic approximation method for adaptive Bayesian classifiers: towards online brain–computer interfaces

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Recent developments of brain–computer interfaces (BCIs) bring forward some challenging problems to the machine learning community, of which classification of time-varying electrophysiological signals is a crucial one. Constructing adaptive classifiers is a promising approach to deal with this problem. In this paper, Bayesian classifiers with Gaussian mixture models (GMMs) are adopted to classify electroencephalogram (EEG) signals online. We propose to use the stochastic approximation method (SAM) as the specific gradient descent method for parameter update and systematically derive the instantaneous gradient formulas with respect to mean values and covariance matrices in the distributions of a GMM. With SAM, the parameters of mean values and covariance matrices embodied in the Bayesian classifiers can be simultaneously updated in a batch mode. The online simulation of EEG classification tasks in a BCI shows the effectiveness of the proposed SAM.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

References

  1. Nicolelis MAL (2001) Action from thoughts. Nature 409:403–407

    Article  Google Scholar 

  2. Ebrahimi T, Vesin JM, Garcia G (2003) Brain-computer interfaces in multimedia communication. IEEE Signal Process Mag 20:14–24

    Article  Google Scholar 

  3. Wickelgren I (2003) Tapping the mind. Science 299:496–499

    Article  Google Scholar 

  4. Wolpaw JR, Birbaumer N, McFarland DJ, Pfurtscheller G, Vaughan TM (2002) Brain-computer interfaces for communication and control. Clin Neurophysiol 113:767–791

    Article  Google Scholar 

  5. Wolpaw JR, Birbaumer N, Heetderks WJ, McFarland DJ et al (2000) Brain-computer interface technology: a review of the first international meeting. IEEE Trans Neural Syst Rehabil Eng 8:164–173

    Google Scholar 

  6. Vaughan TM, Heetderks WJ, Trejo LJ, Rymer WZ et al (2003) Brain-computer interface technology: a review of the second international meeting. IEEE Trans Neural Syst Rehabil Eng 11:94–109

    Article  Google Scholar 

  7. Blankertz B, Curio G, Müller KR (2002) Classifying single trial EEG: towards brain computer interfacing. Adv Neural Inf Process Syst 14:157–164

    Google Scholar 

  8. Lal TN, Hinterberger T, Widman G, Schröder M, Hill J, Rosenstiel W, Elger CE, Schölkpf B, Birbaumer N (2005) Methods towards invasive human brain computer interfaces. Adv Neural Inf Process Syst 17:737–744

    Google Scholar 

  9. Sun S, Zhang C (2006) An optimal kernel feature extractor and its application to EEG signal classification. Neurocomputing 69:1743–1748

    Article  Google Scholar 

  10. Sun S, Zhang C, Lu Y (2008) The random electrode selection ensemble for EEG signal classification. Pattern Recogn 41:1663–1675

    Article  MATH  Google Scholar 

  11. Millán JR (2004) On the need for on-line learning in brain-computer interfaces. In: Proceedings of International Joint Conferences Neural Networks, Budapest, Hungary, pp 2877–2882

  12. Anderson CW, Stolz EA, Shamsunder S (1998) Multivariate autoregressive models for classification of spontaneous electroencephalographic signals during mental tasks. IEEE Trans Biomed Eng 45:277–286

    Article  Google Scholar 

  13. Kaper M, Meinicke P, Grossekathoefer U, Lingner T, Ritter H (2004) BCI competition 2003-data set IIb: support vector machines for the P300 speller paradigm. IEEE Trans Biomed Eng 51:1073–1076

    Article  Google Scholar 

  14. Wang Y, Zhang Z, Li Y, Gao X, Gao S, Yang F (2004) BCI competition 2003-data set IV: an algorithm based on CSSD and FDA for classifying single-trial EEG. IEEE Trans Biomed Eng 51:1081–1086

    Article  Google Scholar 

  15. Zhong S, Ghosh J (2002) HMMs and coupled HMMs for multi-channel EEG classification. In: Proceedings International Joint Conference Neural Networks, Hawaii, USA, pp 1154–1159

  16. Millán JR, Renkens F, Mouriño J, Gerstner W (2004) Brain-actuated interaction. Artif Intell 159:241–259

    Article  Google Scholar 

  17. Millán JR, Renkens F, Mouriño J, Gerstner W (2004) Noninvasive brain-actuated control of a mobile robot by human EEG. IEEE Trans Biomed Eng 51:1026–1033

    Article  Google Scholar 

  18. Sun S (2006) Research on EEG signal classification for brain-computer interfaces based on machine learning methodologies. Ph.D. dissertation, Dept Automation, Tsinghua Univ, Beijing

  19. Mclachlan G, Peel D (2000) Finite mixture models. Wiley, New York

    Book  MATH  Google Scholar 

  20. Duda RO, Hart PE, Stork DG (2000) Pattern classification. 2nd edn. Wiley, New York

    Google Scholar 

  21. Kusner H, Yin G (1997) Stochastic approximation algorithms and applications. Springer, New York

    Google Scholar 

  22. Glentis GO, Berberidis K, Theodoridis S (1999) Efficient least squares adaptive algorithms for FIR transversal filtering. IEEE Signal Process Mag 16:13–41

    Article  Google Scholar 

  23. Zhang X (2004) Matrix analysis and applications. Tsinghua University Press, Beijing

    Google Scholar 

  24. Perrin R, Pernier J, Bertrand O, Echallier J (1989) Spherical spline for potential and current density mapping. Electroencephalogr Clin Neurophysiol 72:184–187

    Article  Google Scholar 

  25. Perrin R, Pernier J, Bertrand O, Echallier J (1990) Corrigendum EEG 02274. Electroencephalogr Clin Neurophysiol 76:565

    Article  Google Scholar 

  26. Chiappa S, Millán JR (2005) Data set V <mental imagery, multi-class>. Available via http://ida.first.fraunhofer.de/projects/bci/competition_iii/desc_V.html

Download references

Acknowledgments

The authors are thankful to the IDIAP Research Institute of Switzerland for providing the analyzed data. This work is supported by the National Natural Science Foundation of China under Projects 60703005 and 61075005.

Author information

Authors and Affiliations

  1. Department of Computer Science and Technology, East China Normal University, 500 Dongchuan Road, 200241, Shanghai, China

    Shiliang Sun & Yue Lu

  2. Computer Center, East China Normal University, Shanghai, China

    Youguang Chen

Authors
  1. Shiliang Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yue Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Youguang Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Shiliang Sun.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Sun, S., Lu, Y. & Chen, Y. The stochastic approximation method for adaptive Bayesian classifiers: towards online brain–computer interfaces. Neural Comput & Applic 20, 31–40 (2011). https://doi.org/10.1007/s00521-010-0472-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-010-0472-7

Keywords

Search

Navigation