DOI QR코드

DOI QR Code

Optimal EEG Channel Selection using BPSO with Channel Impact Factor

Channel Impact Factor 접목한 BPSO 기반 최적의 EEG 채널 선택 기법

  • Kim, Jun-Yeup (School of Electrical and Electronics Engineering, Chung-Ang University) ;
  • Park, Seung-Min (School of Electrical and Electronics Engineering, Chung-Ang University) ;
  • Ko, Kwang-Eun (School of Electrical and Electronics Engineering, Chung-Ang University) ;
  • Sim, Kwee-Bo (School of Electrical and Electronics Engineering, Chung-Ang University)
  • 김준엽 (중앙대학교 전자전기공학부) ;
  • 박승민 (중앙대학교 전자전기공학부) ;
  • 고광은 (중앙대학교 전자전기공학부) ;
  • 심귀보 (중앙대학교 전자전기공학부)
  • Received : 2012.11.10
  • Accepted : 2012.12.03
  • Published : 2012.12.25

Abstract

Brain-computer interface based on motor imagery is a system that transforms a subject's intention into a control signal by classifying EEG signals obtained from the imagination of movement of a subject's limbs. For the new paradigm, we do not know which positions are activated or not. A simple approach is to use as many channels as possible. The problem is that using many channels causes other problems. When applying a common spatial pattern (CSP), which is an EEG extraction method, many channels cause an overfit problem, in addition there is difficulty using this technique for medical analysis. To overcome these problems, we suggest a binary particle swarm optimization with channel impact factor in order to select channels close to the most important channels as channel selection method. This paper examines whether or not channel impact factor can improve accuracy by Support Vector Machine(SVM).

본 논문은 brain-computer interface (BCI)를 통해 움직임 상상 시 측정된 뇌-활동전위신호(EEG)에 내포된 행동의도의 패턴을 보다 정확하게 분류하기 위한 최적 EEG 채널 선택 기법을 제안한다. 기존의 EEG 측정실험에서는 실험 설계자에 의해 대뇌 기능적 피질 분류를 이용하여 인위적으로 선별된 채널을 활용하거나 측정기기가 수용 가능한 전체 채널을 사용해왔으며, 일정 수준의 패턴분류 정확도를 얻을 수 있었지만 다수의 채널로 인해 Common Spatial Pattern (CSP) 등의 패턴특징 추출 시 overfit 및 계산 복잡도 증가의 문제가 발생되었다. 이를 극복하기 위하여 방안으로 본 논문에서는 binary particle swarm optimization (BPSO)을 기반으로 다수의 채널 중 최적 채널을 자동으로 선택하고, 각각의 채널에 대한 impact factor를 부여함으로써 중요 채널 부근의 채널들에 가중치를 부여하는 선택방법을 제안하였으며, Support Vector Machine (SVM)을 이용하여 다수의 채널을 사용 하였을 때의 정확도와 channel impact factor를 고려한 BPSO를 적용시켰을 때의 정확도를 비교, 분석하였다.

Keywords

References

  1. J. Wolpaw, N. Birbaumer, W. Heetderks, D. McFarland, P. Peckham, G. Schalk, E. Donchin, L. Quatrano, C. Robinson, T. Vaughan, "Brain-Computer Interface Technology : A review of the First International Meeting," IEEE Trans. Rehab. Eng., vol. 8, no. 2, pp. 164-173, 2000. https://doi.org/10.1109/TRE.2000.847807
  2. H. Ramoser, J. M. Gerking, and G. Pfurtscheller, "Optimal spatial filtering of single trial EEG during imagined hand movement," IEEE Trans. Rehab. Ebg., vol. 8, no. 4, pp. 441-446, 1998.
  3. C.J.C. Burges, "A tutorial on support vector machines for pattern recognition," Data mining and knowledge discovery, vol. 2, pp. 121-167, 1998. https://doi.org/10.1023/A:1009715923555
  4. J. Kennedy and R. C. Eberhart, "Particle swarm optimization," Proceedings of IEEE International Conference on Neural Networks, Piscataway, NJ. pp. 1942-1948, 1995.
  5. J. Kennedy and R. C. Eberhart, "A discrete binary version of the particle swarm algorithm," IEEE Int. Conf. On Systems, Man and Cybernetics, vol. 5, pp. 4104-4108, 1997.
  6. C. Guger, R. Leeb, D. Friedman, V. Vinayagamoorthy, G. Edlinger and M. Slater, "Controlling Virtual Environments by Thoughts," Clinical Neurophysiology, vol. 118. no. 4, pp. e36, 2007.
  7. A. Schlogl, F. Lee, H. Bischof, G. Pfurtscheller, "Characterization of four-class motor imagery EEG data for the BCI-competition 2005," Neural Engineering, vol. 2, pp. 14-22, 2005. https://doi.org/10.1088/1741-2560/2/4/L02
  8. J. Y. Kim, S. M. Park, K. E. Ko and K. B. Sim, "Optimal EEG Channel Selection using BPSO with Channel Impact Factor," Proceedings of KIIS Fall Conference, vol. 22, no .2, pp.35-36, 2012.
  9. Blankertz, B., Dornhege, G., Krauledat, M., Muller, K.-R., Curio, G., 2007a, "The non-invasive Berlin Brain-Computer Interface: fast acquisition of effective performancein untrained subjects," Neuroimage, vol. 37, no. 2, pp. 539-550, 2007. https://doi.org/10.1016/j.neuroimage.2007.01.051
  10. J. Y. Kim, S. M. Park, K. E. Ko and K. B. Sim, "PSO Based Optimal EEG Channel Selection Method for Motor Imagery BCI System," Proceedings of KIIS Spring Conference, vol. 22, no. 1, pp. 113-114, 2012.