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

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

DOI QR Code

Parallel Model Feature Extraction to Improve Performance of a BCI System

BCI 시스템의 성능 개선을 위한 병렬 모델 특징 추출

  • Chum, Pharino (School of Electrical and Electronics Engineering, Chung-Ang University) ;
  • Park, Seung-Min (School of Electrical and Electronics Engineering, Chung-Ang University) ;
  • Sim, Kwee-Bo (School of Electrical and Electronics Engineering, Chung-Ang University)
  • ;
  • 박승민 (중앙대학교 전자전기공학부) ;
  • 심귀보 (중앙대학교 전자전기공학부)
  • Received : 2013.06.11
  • Accepted : 2013.08.19
  • Published : 2013.11.01
Download PDF
⟨ Previous Next ⟩

Abstract

It is well knowns that based on the CSP (Common Spatial Pattern) algorithm, the linear projection of an EEG (Electroencephalography) signal can be made to spaces that optimize the discriminant between two patterns. Sharing disadvantages from linear time invariant systems, CSP suffers from the non-stationary nature of EEGs causing the performance of the classification in a BCI (Brain-Computer Interface) system to drop significantly when comparing the training data and test data. The author has suggested a simple idea based on the parallel model of CSP filters to improve the performance of BCI systems. The model was tested with a simple CSP algorithm (without any elaborate regularizing methods) and a perceptron learning algorithm as a classifier to determine the improvement of the system. The simulation showed that the parallel model could improve classification performance by over 10% compared to conventional CSP methods.

Keywords

References

  1. G. Pfurtscheller and C. Neuper, "Motor imagery and direct brain-computer communication," Proc. of the IEEE, vol. 89, pp. 1123-1134, 2001. https://doi.org/10.1109/5.939829
  2. B. Blankertz and R. Tomioka, "Optimizing spatial filters for robust EEG single-trial analysis," IEEE Signal Processing Magazine, vol. 25, pp. 41-56, 2008.
  3. F. Lotte and C. Guan, "Regularizing common spatial patterns to improve BCI designs: unified theory and new Algorithm," IEEE Transaction on Bio-medical Engineering, vol. 58, no. 2, pp. 255-362, 2011.
  4. G. Pfurtscheller, C. Brunner, A. Schlogl, and F. H. "Lopes da Silva, Mu rhythm (de)synchronization and EEG single-trial classification of different motor imagery tasks," NeuroImage, vol. 31, pp. 153-159, 2006. https://doi.org/10.1016/j.neuroimage.2005.12.003
  5. G. Dornhenge, B. Blankertz, G. Curio, and K. Muller, "Boosting bit rates in noninvasive EEG single-trail classification by feature combination and multiclass paradigm," IEEE Transaction on Bio-Medical Engineering, vol. 51, pp. 992-1002, 2004.
  6. J. Sim and C. Wright, "The Kappa statistic in realizability studies: use, interpretation, and sample size requirements," Physical Therapy, vol. 85, pp. 257-268, 2005.
  7. Y. H. Kim, K. E. Ko, S. M. Park, and K. B. Sim, "Practical use technology for robot control in BCI environment based on motor imagery-P300," Journal of Institute of Control, Robotics and Systems (in Korean), vol. 19, no. 3, pp. 227-232, 2013. https://doi.org/10.5302/J.ICROS.2013.13.1866
  8. K. E. Ko and K. B. Sim, "HSA-based HMM optimization method for analyzing EEG pattern of motor imagery," Journal of Institute of Control, Robotics and Systems (in Korean), vol. 17, no. 8, pp. 747-752, 2011. https://doi.org/10.5302/J.ICROS.2011.17.8.747