An Improved Support Vector Machine Classifier for EEG-Based Motor Imagery Classification

  • Hui Zhou
  • Qi Xu
  • Yongji Wang
  • Jian Huang
  • Jun Wu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5552)


Electroencephalogram (EEG) recordings during motor imagery tasks are often used as input signals for brain-computer interfaces (BCIs). We analyze the EEG signals with Daubechies order 4 (db4) wavelets in 10 Hz and 21Hz at C3 channel, and in 10 Hz and 20 Hz at C4 channel, for these frequencies are prominent in discrimination of left and right motor imagery tasks according to EEG frequency spectral. We apply the improved support vector machines (SVMs) for classifying motor imagery tasks. First, a SVM is trained on all the training samples, then removes the support vectors which contribute less to the decision function from the training samples, finally the SVM is re-trained on the remaining samples. The classification error rate of the presented approach was as low as 9.29 % and the mutual information could be 0.7 above based on the Graz BCI 2003 data set.


EEG Continuous wavelet transform (CWT) SVMs Leave-one-out (LOO) Mutual information (MI) 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Wolpaw, J.R., Birbaumer, N., McFarlanda, D.J., Pfurtschellere, G., Vaughan, T.M.: Brain–Computer Interfaces for Communication and Control. Clin. Neurophysiol. 113, 767–791 (2002)CrossRefGoogle Scholar
  2. 2.
    Burke, D.P., Kelly, S.P., Chazal, P.D., Reilly, R.B., Finucane, C.: A Parametric Feature Extraction and Classification Strategy for Brain–Computer Interfacing. IEEE Trans. Neural Syst. Rehab. Eng. 13(1), 12–17 (2005)CrossRefGoogle Scholar
  3. 3.
    Anderson, C.W., Stolz, E.A., Shamsunder, S.: Multivariate Autoregressive Models for Classification of Spontaneous Electroencephalographic Signals. IEEE Trans. Biomed. Eng. 45(3), 277–286 (1998)CrossRefGoogle Scholar
  4. 4.
    McFarland, D.J., McCane, L., Miner, L.A., Vaughan, T.M., Wolpaw, J.R.: EEG mu and beta Rhythm Topographies with Movement Imagery and Actual Movement. Society for Neuroscience Abstracts, 1277 (1997)Google Scholar
  5. 5.
    Wolpaw, J.R., McFarland, D.J., Neat, G.W., Forneris, C.A.: An EEG-Based Brain–Computer Interface for Cursor Control. Electroenceph Clin. Neurophysiol. 78(3), 252–259 (1991)CrossRefGoogle Scholar
  6. 6.
    Steven, L., Christin, S., Gabriel, C.: BCI Competition 2003—Data Set III: Probabilistic Modeling of Sensorimotor μ Rhythms for Classification of Imaginary Hand Movements. IEEE Transactions on Biomedical Engineering 51(6) (2004)Google Scholar
  7. 7.
    Belousov, A.I., Verzakov, S.A., Von, F.J.: A Flexible Classification Approach with Optimal Generalization Performance: Support Vector Machines. Chemometrics and Intelligent Laboratory Systems 64, 15–25 (2002)CrossRefGoogle Scholar
  8. 8.
    Guo, J., Norikazu, T., Tetsuo, N.: A Learning Algorithm for Improving the Classification Speed of Support Vector Machines. In: Proceedings of the 2005 European conference on Circuit Theory and Design, vol. 3, pp. 381–384 (2005)Google Scholar
  9. 9.
    Duda, R., Hart, P., Stock, D.: Pattern Classification, 2nd edn. Wiley, New York (2001)Google Scholar
  10. 10.
  11. 11.
    Pfurtscheller, G., LopesdaSilva, F.H.: Event-related EEG/MEG Synchronization and Desynchronization: Basic Principles. Clin. Neurophysiol. 110, 1842–1857 (1999)CrossRefGoogle Scholar
  12. 12.
    Torrence, C., Compo, G.: A Practical Guide to Wavelet Analysis. Bull. Amer. Meterol. 79, 61–78 (1998)CrossRefGoogle Scholar
  13. 13.
    Lottel, F., Congedo, M., Lécuyer, A., Lamarche, F., Arnaldi, B.: A Review of Classification Algorithms for EEG-based Brain–Computer Interfaces. J. Neural. Eng. 4, R1–R13 (2007)CrossRefGoogle Scholar
  14. 14.
    Chapelle, O., Vapnik, V., Bousquet, O., Mukerjee, S.: Choosing Multiple Parameters for Support Vector Machines. Machine Learning 46(1), 131–159 (2002)CrossRefzbMATHGoogle Scholar
  15. 15.
    Zhou, S.M., Gan, J.Q., Sepulveda, F.: Information Sciences 178, 1629–1640 (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Hui Zhou
    • 1
  • Qi Xu
    • 1
  • Yongji Wang
    • 1
  • Jian Huang
    • 1
  • Jun Wu
    • 1
  1. 1.Key Laboratory of Image Processing and Intelligent Control, Department of Control Science and EngineeringHuazhong University of Science and TechnologyWuhanChina

Personalised recommendations