Optimal Frequency Band Selection Based on Filter Banks and Wavelet Packet Decomposition in Multi-class Brain–Computer Interfaces

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 238)

Abstract

To address the problem of low system recognition rate in multi-class brain–computer interface (BCI), many ideas have been proposed. Among them frequency optimization is a good option because the performance of BCI systems depends largely on the operational frequency band of electroencephalography (EEG) signals. In this chapter, feature selection method was utilized to select frequency bands for classification in multi-class BCI systems. The procedures of the proposed algorithm are as follows: Firstly, all single-trial EEG signals are divided into some subband signals by two different methods. One is wavelet packet decomposition and the other is filter bank based on coefficient decimation. Secondly, a multi-class common spatial pattern algorithm based on approximate joint diagonalization is used to extract features of EEG signals on each subband. Finally, optimal subband features are selected for classification. In offline analysis, the proposed method yielded relatively better cross-validated classification accuracies.

Keywords

Attenuation Covariance 

Notes

Acknowledgment

This study was funded by National Natural Science Foundation of China (# 60965004).

References

  1. 1.
    Wolpaw JR, Birbaumer N, McFarland DJ et al (2002) Brain-computer interface for communication and control. Clin Neurophysiol 113:767–791CrossRefGoogle Scholar
  2. 2.
    Pfurtscheeler G, Brunner A, Schlogl A (2006) Mu rhythm (de) synchronization and EEG single-trial classification of different motor imagery tasks. Neuroimages 31(1):153–159CrossRefGoogle Scholar
  3. 3.
    Pfurtscheller G, Stancak A, Edlinger G (1997) On the existence of different types of central beta rhythms below 30Hz. Electroencephalogr Clin Neurophysiol 102(4):316–325CrossRefGoogle Scholar
  4. 4.
    Blankertz B, Tomioka R, Lemm S et al (2008) Optimizing spatial filters for robust EEG single-trial analysis. IEEE Signal Process Mag 25(1):41–56CrossRefGoogle Scholar
  5. 5.
    Mahesh R, Vinod AP (2008) Coefficient decimation approach for realizing reconfigurable finite impulse response filters. In: Proceedings of IEEE ISCAS, pp 81–84Google Scholar
  6. 6.
    Chen K, Wei Q, Ma Y (2010) An unweighted exhaustive diagonalization based multi-class common spatial pattern algorithm in brain-computer interfaces. 2nd international conference on information engineering and computer science, Wuhan, China, pp 25–26Google Scholar
  7. 7.
    Tichavsky P, Yeredor A, Nielsen J (2008) A fast approximate joint diagonalization algorithm using a criterion with a block diagonal weight matrix. In: Proceedings of IEEE ICASSP, pp 3321–3324Google Scholar
  8. 8.
    Tichavsky P, Yeredor A (2009) Fast approximate joint diagonalization incorporating weight matrices. IEEE Trans Signal Process 57(3):878–891MathSciNetCrossRefGoogle Scholar
  9. 9.
    Grosse-Wentrup M, Buss M (2008) Multi-class common spatial patterns and information theoretic feature extraction. IEEE Trans Biomed Eng 55(8):1991–2000CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2014

Authors and Affiliations

  1. 1.Department of Electronic EngineeringNanchang UniversityNanchangChina

Personalised recommendations