A New Hybrid Method with Biomimetic Pattern Recognition and Sparse Representation for EEG Classification

  • Yanbin Ge
  • Yan Wu
Part of the Communications in Computer and Information Science book series (CCIS, volume 304)


This paper presents a novel classification framework combining Biomimetic Pattern Recognition (BPR) with Sparse Representation (SR) for Brain Computer Interface based on motor imagery. This framework can work well when encountering the overlap coverage problem of BPR by introducing the idea of SR. Using Common Spatial Pattern to extract the rhythm features of EEG data, we evaluate the performance of the proposed method in the datasets from previous BCI Competitions. By making comparison with those of LDA, SVM and original BPR, our proposed method shows the better classification accuracy.


biomimetic pattern recognition hyper sausage neuron sparse representation brain-computer interface motor imagery 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Walpaw, J.R., Birbaumer, N., Heetderks, W.J.: Brain-Computer Interface Technology: A Review of the First International Meeting. IEEE Trans. Rehab. Eng. 8(2), 164–173 (2000)CrossRefGoogle Scholar
  2. 2.
    Graimann, B., Huggins, J.E., Schlogl, A.: Detection of Movement-related Desynchronization Patterns in Ongoing Single-channel Electrocorticogram. IEEE Trans. Neural Syst. Rehabil. Eng. 11(3), 276–281 (2003)CrossRefGoogle Scholar
  3. 3.
    Schlogl, A., Lee, F., Pfurtscheller, G.: Characterization of Four-class Motor Imagery EEG Data for the BCI-competition 2005. Journal of Neural Engineering 2(4), 14–22 (2005)CrossRefGoogle Scholar
  4. 4.
    Lotte, F., Congedo, M., Arnaldi, B.: A Review of Classification Algorithms for EEG-based Brain–Computer Interfaces. Journal of Neural Engineering 4(2), 1–13 (2007)CrossRefGoogle Scholar
  5. 5.
    Xu, K., Wu, Y.: Motor Imagery EEG Recognition Based on Biomimetic Pattern Recognition. In: The 3rd International Conference on Biomedical Engineering and Informatics (BMEI), pp. 955–959 (2010)Google Scholar
  6. 6.
    Wu, Y., Yao, X., Wang, S.J.: Relative Division of Overlapping Space Based Biomimetic Pattern Recognition. Pattern Recognition & Artificial Intelligence 21(3), 346–350 (2008)Google Scholar
  7. 7.
    Candes, E.J., Wakin, M.B.: An Introduction to Compressive Sampling. IEEE Signal Proc. Magazine 25(21), 21–30 (2008)CrossRefGoogle Scholar
  8. 8.
    Deng, Y., Dai, Q.H., Zhang, Z.K.: Graph Laplace for Occluded Face Completion and Recognition. IEEE Trans. on Image Processing 20(8), 2329–2338 (2011)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Yu, H.B., Lu, H.T., Ouyang, T., Liu, H.J., Lu, B.L.: Vigilance Detection Based on Sparse Representation of EEG. In: 32nd International Conference- IEEE/EMBS, pp. 2439–2442 (2010)Google Scholar
  10. 10.
    Younghak, S., Seungchan, L., Minkyu, A., Sung, C.J., Heung, L.: Motor Imagery based BCI Classification via Sparse Representation of EEG Signals. In: NFSI & ICBEM, Banff, Canada, pp. 93–97 (2011)Google Scholar
  11. 11.
    Wang, S.J., Lai, J.L.: Geometrical Learning, Descriptive Geometry, and Biomimetic Pattern Recognition. Neurocomputing 67(3), 9–28 (2005)Google Scholar
  12. 12.
    Yang, M., Zhang, L., Feng, X.C.: Fisher Discrimination on Dictionary Learning for Sparse Representation. In: 2011 IEEE ICCV, pp. 543–550 (2011)Google Scholar
  13. 13.
    Rubinstein, R., Bruckstein, A.M., Elad, M.: Dictionaries for Sparse Representation Modeling. Proceedings of the IEEE 98(6), 1045–1057 (2010)CrossRefGoogle Scholar
  14. 14.
    Cande‘s, E., Romberg, J., Tao, T.: Stable Signal Recovery from Incomplete and Inaccurate Measurements. Comm. Pure and Applied Math 59(8), 1207–1223 (2006)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Tropp, J.A., Gilbert, A.C.: Signal Recovery From Partial Information Via Orthogonal Matching Pursuit. IEEE Trans. Inf. Theory 53(12), 4655–4666 (2007)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Yanbin Ge
    • 1
  • Yan Wu
    • 1
  1. 1.Department of Computer Science and TechnologyTongji UniversityShanghaiChina

Personalised recommendations