Tensor Based Simultaneous Feature Extraction and Sample Weighting for EEG Classification

  • Yoshikazu Washizawa
  • Hiroshi Higashi
  • Tomasz Rutkowski
  • Toshihisa Tanaka
  • Andrzej Cichocki
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6444)

Abstract

In this paper we propose a Multi-linear Principal Component Analysis (MPCA) which is a new feature extraction and sample weighting method for classification of EEG signals using tensor decomposition. The method has been successfully applied to Motor-Imagery Brain Computer Interface (MI-BCI) paradigm. The performance of the proposed approach has been compared with standard Common Spatial Pattern (CSP) as well with a combination of PCA and CSP methods. We have achieved an average accuracy improvement of two classes classification in a range from 4 to 14 percents.

Keywords

Feature extraction classification tensor decomposition multi-linear PCA 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Cichocki, A., Zdunek, R., Phan, A.H., Amari, S.: Nonnegative Matrix Factorization and Tensor Factorizations. John Wiley and Sons, Chichester (2009)CrossRefMATHGoogle Scholar
  2. 2.
    Lu, H., Plataniotis, K.N., Venetsanopoulos, A.N.: MPCA: Multilinear principal component analysis of tensor objects. IEEE Trans. Neural Network 19(1), 18–39 (2008)CrossRefGoogle Scholar
  3. 3.
    Lathauwer, L.D., Moor, B.D., Vandewalle, J.: A multilinear singular value decomposition. SIAM Journal of Matrix Analysis and Application 21(4), 1253–1278 (2001)MathSciNetCrossRefMATHGoogle Scholar
  4. 4.
    Phan, A.H., Cichocki, A.: Tensor Decompositions for Feature Extraction and Classification of High Dimensional Datasets. IEICE NOLTA E93-N(10) (October 2010)Google Scholar
  5. 5.
    Ramoser, H., Mueller-Gerking, J., Pfurtscheller, G.: Optimal spatial filtering of single trial EEG during imagined hand movement. IEEE Trans. Rehabilitation Engineering 8(4), 441–446 (2000)CrossRefGoogle Scholar
  6. 6.
    Dornhege, G., Blankertz, B., Curio, G., Müller, K.-R.: Boosting bit rates in noninvasive EEG single-trial classifications by feature combination and multiclass paradigms. IEEE Trans. Biomedical Engineering 51(6), 993–1002 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Yoshikazu Washizawa
    • 1
  • Hiroshi Higashi
    • 2
    • 1
  • Tomasz Rutkowski
    • 1
  • Toshihisa Tanaka
    • 2
    • 1
  • Andrzej Cichocki
    • 1
  1. 1.RIKEN Brain Science InstituteJapan
  2. 2.Department of Electrical and Electronic EngineeringTokyo University of Agriculture and TechnologyJapan

Personalised recommendations