Independent Component Analysis for EEG Data Preprocessing - Algorithms Comparison

  • Izabela Rejer
  • Paweł Górski
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8104)


Some scientific papers report that when Independent Component Analysis (ICA) is applied in the preprocessing step of designing a brain computer interface, the quality of this interface increases. At the same time, however, these papers do not provide information about the exact gain in classification precision obtained after applying different ICA algorithms. The aim of this paper is to compare three algorithms for Independent Component Analysis applied in the process of creating a brain computer interface in order to find out whether the choice of a specific ICA algorithm has an influence on the final classification precision of this interface. The comparison will be carried out with a set submitted to the second BCI Competition.


Brain Computer Interface BCI EEG preprocessing ICA Independent Component Analysis 


  1. 1.
    Wolpaw, J.R., Birbaumer, N., McFarland, D.J., Pfurtscheller, G., Vaughan, T.M.: Brain–computer interfaces for communication and control. Clinical Neurophysiology 113, 767–791 (2002)CrossRefGoogle Scholar
  2. 2.
    Wang, Y., Shangkai, G., Xiaorong, G.: Common Spatial Pattern Method for Channel Selection in Motor Imagery Based Brain-Computer Interface. In: Proceedings of the 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference (2005)Google Scholar
  3. 3.
    Oja, E., Yuan, Z.: The FastICA Algorithm Revisited: Convergence Analysis. IEEE Transaction on Neural Networks 17(6), 1370–1381 (2006)CrossRefGoogle Scholar
  4. 4.
    Augustyniak, P.: Adaptive Wavelet Discrimination of Muscular Noise in the ECG. In: Proc. Computers in Cardiology (IEEE-EMB), vol. 33, pp. 481–484 (2006)Google Scholar
  5. 5.
    Yang, R., Song, A., Xu, B.: Feature Extraction of Motor Imagery EEG Based on Wavelet Transform and Higher-Order Statistics. International Journal of Wavelets, Multiresolution and Information Processing 8(3), 373–384 (2010)MathSciNetCrossRefzbMATHGoogle Scholar
  6. 6.
    Müller-Putz, G.R., Kaiser, V., Solis-Escalante, T., Pfurtscheller, G.: Fast set-up asynchronous brain-switch based on detection of foot motor imagery in 1-channel EEG. Medical & Biological Engineering & Computing 48(3), 229–233 (2010)CrossRefGoogle Scholar
  7. 7.
    Koprinska, I.: Feature Selection for Brain-Computer Interfaces. In: Theeramunkong, T., Nattee, C., Adeodato, P.J.L., Chawla, N., Christen, P., Lenca, P., Poon, J., Williams, G. (eds.) PAKDD Workshops 2009. LNCS (LNAI), vol. 5669, pp. 106–117. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  8. 8.
    Rejer, I.: Genetic Algorithms in EEG Feature Selection for the Classification of Movements of the Left and Right Hand. In: Burduk, R., Jackowski, K., Kurzynski, M., Wozniak, M., Zolnierek, A. (eds.) CORES 2013. AISC, vol. 226, pp. 579–589. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  9. 9.
    Burduk, R.: Recognition Task with Feature Selection and Weighted Majority Voting Based on Interval-Valued Fuzzy Sets. In: Nguyen, N.-T., Hoang, K., Jedrzejowicz, P. (eds.) ICCCI 2012, Part I. LNCS, vol. 7653, pp. 204–209. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  10. 10.
    Pfurtscheller, G., Neuper, C., Schlögl, A., Lugger, K.: Separability of EEG Singals Recorded During Right and Left Motor Imagery Using Adaptive Autoregressive Parameters. IEEE Trans. on Rehabilitation Engineering 6(3) (September 1998)Google Scholar
  11. 11.
    Bobrowski, L., Topczewska, M.: Separable Linearization of Learning Sets by Ranked Layer of Radial Binary Classifiers. In: Burduk, R., Jackowski, K., Kurzynski, M., Wozniak, M., Zolnierek, A. (eds.) CORES 2013. AISC, vol. 226, pp. 131–140. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  12. 12.
    Wozniak, M., Krawczyk, B.: Combined classifier based on feature space partitioning. Applied Mathematics and Computer Science 22(4), 855–866 (2012)MathSciNetGoogle Scholar
  13. 13.
    Chen, X., Wang, L., Xu, Y.: A symmetric orthogonal FastICA algorithm and applications in EEG. In: Fifth International Conference on Natural Computation, ICNC 2009, vol. 2 (2009)Google Scholar
  14. 14.
    Peterson, D.A., Knight, J.N., Kirby, M.J., Anderson, C.W., Thaut, M.H.: Feature Selection and Blind Source Separation in an EEG-Based Brain-Computer Interface. EURASIP Journal on Applied Signal Processing 19, 3128–3140 (2005)CrossRefzbMATHGoogle Scholar
  15. 15.
    Boord, P., Craig, A., Tran, Y., Nguyen, H.: Discrimination of left and right leg motor imagery for brain–computer interfaces. Medical & Biological Engineering & Computing 48(4), 343–350 (2010)CrossRefGoogle Scholar
  16. 16.
    Park, H.M., Oh, S.H., Lee, S.Y.: A modified infomax algorithm for blind signal separation. Science Direct. Neurocomputing 70, 229–240 (2006)CrossRefGoogle Scholar
  17. 17.
    Stone, J.V.: Independent component analysis: an introduction. TRENDS in Cognitive Sciences 6(2), 59–64 (2002)CrossRefGoogle Scholar
  18. 18.
    Langlois, D., Chartier, S., Gosselin, D.: An Introduction to Independent Component Analysis: InfoMax and FastICA algorithms. Tutorials in Quantitative Methods for Psychology 6, 31–38 (2010)Google Scholar
  19. 19.
    Hyvärinen, A., Oja, E.: Independent Component Analysis: Algorithms and Applications. Neural Networks 13(4-5), 411–430 (2000)CrossRefGoogle Scholar
  20. 20.
    Tichavský, P., Koldovský, Z., Oja, E.: Performance Analysis of the FastICA Algorithm and Cramér–Rao Bounds for Linear Independent Component Analysis. IEEE Transactions on Signal Processing 54(4), 1189–1203 (2006)CrossRefGoogle Scholar
  21. 21.
    Naik, G., Kumar, D.: An Overview of Independent Component Analysis and Its Applications. Informatykica, 63–81 (2011)Google Scholar
  22. 22.
    Fan, C., Wang, B., Ju, H.: A New FastICA Algorithm with Symmetric Orthogonalization, pp. 2058–2061. IEEE (2006)Google Scholar
  23. 23.
    Linsker, R.: Self-Organization in a Perceptual Network. Computer 21, 105–117 (1988)CrossRefGoogle Scholar
  24. 24.
    Bell, A.J., Sejnowski, T.J.: An information-maximisation approach to blind separation and blind deconvolution. Journal Neural Computation 7, 1129–1159 (1995)CrossRefGoogle Scholar
  25. 25.
    Raimondo, F., Kamienkowski, J.E., Sigman, M., Slezak, D.F.: CUDAICA: GPU Optimization of Infomax-ICA EEG Analysis. Computational Intelligence and Neuroscience 2012 (2012)Google Scholar
  26. 26.
    Karhunen, J.: Neural approaches to independent component analysis and source separation. In: Proc 4th European Symposium on Artificial Neural Networks, ESANN 1996 (1996)Google Scholar
  27. 27.
    Data set III, II BCI Competition, motor imaginary,
  28. 28.
    Raudys, S.J., Jain, A.K.: Small sample size effects in statistical pattern recognition: Recommendations for practitioners. IEEE Transactions on Pattern Analysis and Machine Intelligence 13(3), 252–264 (1991)CrossRefGoogle Scholar

Copyright information

© IFIP International Federation for Information Processing 2013

Authors and Affiliations

  • Izabela Rejer
    • 1
  • Paweł Górski
    • 1
  1. 1.Faculty of Computer ScienceWest Pomeranian University of Technology, SzczecinSzczecinPoland

Personalised recommendations