Journal of Institute of Control, Robotics and Systems (제어로봇시스템학회논문지)

Institute of Control, Robotics and Systems (제어로봇시스템학회)
권호 표지
DOI QR코드

DOI QR Code

HSA-based HMM Optimization Method for Analyzing EEG Pattern of Motor Imagery

운동심상 EEG 패턴분석을 위한 HSA 기반의 HMM 최적화 방법

  • 고광은 (중앙대학교 전자전기공학부) ;
  • 심귀보 (중앙대학교 전자전기공학부)
  • Received : 2011.05.20
  • Accepted : 2011.06.20
  • Published : 2011.08.01
Download PDF
⟨ Previous Next ⟩

Abstract

HMMs (Hidden Markov Models) are widely used for biological signal, such as EEG (electroencephalogram) sequence, analysis because of their ability to incorporate sequential information in their structure. A recent trends of research are going after the biological interpretable HMMs, and we need to control the complexity of the HMM so that it has good generalization performance. So, an automatic means of optimizing the structure of HMMs would be highly desirable. In this paper, we described a procedure of classification of motor imagery EEG signals using HMM. The motor imagery related EEG signals recorded from subjects performing left, right hand and foots motor imagery. And the proposed a method that was focus on the validation of the HSA (Harmony Search Algorithm) based optimization for HMM. Harmony search algorithm is sufficiently adaptable to allow incorporation of other techniques. A HMM training strategy using HSA is proposed, and it is tested on finding optimized structure for the pattern recognition of EEG sequence. The proposed HSA-HMM can performs global searching without initial parameter setting, local optima, and solution divergence.

Keywords

Acknowledgement

Supported by : 한국연구재단

References

  1. L. R. Rabiner, "A tutorial on hidden markov models and selected applications in speech recognition," Proc. IEEE, vol. 77, no. 2, pp. 257-285, 1989. https://doi.org/10.1109/5.18626
  2. K.-J. Won, A. Prűgel-Bennett, and A. Krogh, "Training HMM structure with genetic algorithm for biological sequence analysis," Bioinformatics, vol. 20, no. 18, pp. 3613-3619, Dec. 2004. https://doi.org/10.1093/bioinformatics/bth454
  3. C. W. Chau, S. Kwong, C. K. Diu, and W. R. Fahrner, "Optimization of HMM by a genetic algorithm," Proc. ICASSP-97, vol. 3, pp. 1727-1730, 1997.
  4. D. Obermaier, C. Guger, C. Neuper, and G. Pfurtscheller, "Hidden markov models for online classification of single trial EEG data," Pattern Recognition Letters, vol. 22, no. 12, pp. 1299-1309, 2001. https://doi.org/10.1016/S0167-8655(01)00075-7
  5. Z. W. Geem and K. B. Sim, "Parameter-setting-free harmony search algorithm," Applied Mathematics and Computation, vol. 217, pp. 3881-3889, 2010. https://doi.org/10.1016/j.amc.2010.09.049
  6. H. K. Lee and S. J. Choi, "PCA+HMM+SVM for EEG pattern classification," Proc. 7th Inter. Symp. on Signal Processing and its Applications, vol. 1, pp. 541-544, July 2003.
  7. B. Blankertz, G. Dornhege, M. Krauledat, K.-R. Műller, and G. Curio, "The non-invasive berlin brain-computer interface: fast acquisition of effective performance in untrained subjects," Neuroimage, vol. 37, no. 2, pp. 539-550, 2007 https://doi.org/10.1016/j.neuroimage.2007.01.051
  8. A. Delorme and S. Makeig, "EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics," Journal of Neuroscience Methods, vol. 134, pp. 9-21, 2004 https://doi.org/10.1016/j.jneumeth.2003.10.009
  9. H. K. Lee and S. J. Choi, "PCA+HMM+SVM for EEG pattern classification," Proc. of the 7th International Symposium in Signal Processing and Its Applications, pp. 541-544, 2003.
  10. C. H, Lee, J. W. Kwon, G. D. Kim, J. E. Hong, D. S. Shin, and D. H. Lee, "A study on EEG based concentration transmission and brain computer interface application," Journal of the Electrics Engineering of Korea, vol. 46, SC, no. 2, pp. 41-45, 2009.
  11. K. B. Sim, H. G. Yeom, and I. Y. Lee, "EEG signals measurement and analysis method for brain-computer interface," Journal of Korean Institute of Intelligent Systems (in Korean), vol. 18, no. 5, pp. 605-610, 2008. https://doi.org/10.5391/JKIIS.2008.18.5.605
  12. K. E. Ko and K. B. Sim, "Optimization of HMM structure with HSA for EEG sequence analysis," 2011 ICROS Annual Conference (in Korean), 2011.
  13. R. Durbin, S. Eddy, A. Krogh, and G. Mitchison, "Biological sequence analysis," Cambridge, UK: Cambridge University Press, 1998.
  14. W.-Y. Hsu and Y.-N. Sun, "EEG-based motor imagery analysis using weighted wavelet transform features," Journal of Neuroscience Methods, vol. 176, no. 2, pp. 310-318, 2009. https://doi.org/10.1016/j.jneumeth.2008.09.014
  15. W.-Y. Hsu, "EEG-based motor imagery classification using neuro-fuzzy prediction and wavelet fractal features," Journal of Neuroscience Methods, vol. 189, no. 2, pp. 295-302, 2010. https://doi.org/10.1016/j.jneumeth.2010.03.030
  16. W.-Y. Hsu, "EEG-based motor imagery classification using enhanced active segment selection and adaptive classifier," Computers in Biology and Medicine, In Press, Corrected Proof, Available online 17, 2011.
  17. C. H. Han, C. S. Oh, and B. W. Choi, "Recognition of fighting motion using a 3D-chain code and HMM," Journal of Institute of Control, Robotics, and Systems (in Korean), vol. 16, no. 8, pp. 756-760, 2010. https://doi.org/10.5302/J.ICROS.2010.16.8.756
  18. D. W. Lee, K. R, Cho, and S. W. Baek, "Fitness change of mission scheduling algorithm using genetic theory according to the control constants," Journal of Institute of Control, Robotics, and Systems (in Korean), vol. 16, no. 6, pp. 572-578, 2010. https://doi.org/10.5302/J.ICROS.2010.16.6.572

Cited by

  1. Parallel Model Feature Extraction to Improve Performance of a BCI System vol.19, pp.11, 2013, https://doi.org/10.5302/J.ICROS.2013.13.1930
  2. Practical Use Technology for Robot Control in BCI Environment based on Motor Imagery-P300 vol.19, pp.3, 2013, https://doi.org/10.5302/J.ICROS.2013.13.1866
  3. Brain Wave Characteristic Analysis by Multi-stimuli with EEG Channel Grouping based on Binary Harmony Search vol.19, pp.8, 2013, https://doi.org/10.5302/J.ICROS.2013.13.1915