DOI QR코드

DOI QR Code

Improving Classification Accuracy of Motion Imaginary Electroencephalogram Using Mutual Information and Rare Learning

상호 정보와 희소 학습을 이용하여 동작 상상 뇌파의 분류 정확도 향상

  • 이다빛 (가톨릭대학교 미디어공학과) ;
  • 박상훈 (가톨릭대학교 미디어공학과) ;
  • 이희재 (가톨릭대학교 미디어공학과) ;
  • 이상국 (가톨릭대학교 미디어기술콘텐츠학과)
  • Received : 2017.06.16
  • Accepted : 2017.07.20
  • Published : 2017.08.31

Abstract

Brain-computer interface (BCI) is a technology that directly connects a human brain and a computer to control and manipulate the computer through electroencephalogram. The common spatial pattern (CSP) is the most famous method for extracting discriminative features from BCI based on motor imagery electroencephalogram. However, CSP is sensitive to the operational frequency band, and this operational frequency band is subject-specific. In this paper, we propose a method to extract subject-specific features based on mutual information and sparse learning. The proposed method divides the 4~40Hz band into 17 sub-bands using a fifth order Butterworth filter. Then, CSP is applied to each sub-band to extract CSP features. Thereafter, mutual information is used to select the four most discriminating feature sets from the CSP features and sparse learning was used to eliminate redundancy in the four pairs of features selected. Finally, support vector machine was used for learning and classification. The performance of the proposed method was evaluated using formally available BCI Competition III and IV. The proposed method showed higher average classification accuracy than the results of CSP, FBCSP and SFBCSP.

뇌-컴퓨터 인터페이스(BCI, Brain-Computer Interface)는 인간의 두뇌와 컴퓨터를 직접 연결하여 뇌파를 통해 컴퓨터를 제어 조작하는 기술이다. 공통 공간 패턴(CSP, Common Spatial Pattern)은 동작 상상 뇌파를 기반으로 하는 BCI에서 식별적인 특징을 추출하는 방법 중 가장 유명하다. 하지만, CSP는 운영 주파수 대역에 민감하고, 이러한 운영 주파수 대역은 피실험자 마다 다르다. 이 논문에서는 상호 정보와 희소 학습을 기반으로 하여 피실험자에게 적합한 특징을 추출하는 방법을 제안한다. 제안한 방법은 5차 버터워스(Butterworth) 필터를 이용하여 4~40Hz 대역을 17개의 서브 밴드로 나눈다. 그리고 나서 각 서브 밴드에 CSP를 적용하여 특징들을 추출한다. 이후, 상호 정보를 이용하여 CSP 특징들로부터 가장 식별적인 4쌍의 특징 집합을 선택한다. 그리고 나서 선택된 4쌍의 특징 집합에 희소 학습을 적용하여 중복을 제거함으로써 가장 식별적인 특징들을 선택한다. 마지막으로 서포터 벡터 머신을 이용하여 분류한다. 제안한 방법의 성능은 공식적으로 이용할 수 있는 BCI Competition III와 IV를 사용하여 평가되었다. 제안한 방법은 CSP, FBCSP 그리고 SFBCSP 보다 높은 평균 분류 정확도를 보여주었다.

Keywords

References

  1. W. Y. Hsu, "Embedded prediction in feature extraction: application to single-trial EEG discrimination", Clinical EEG and Neuroscience, Vol. 44, No. 1, pp. 31-38, 2013. https://doi.org/10.1177/1550059412456094
  2. D. Lee and S. G. Lee, "The Study on Movement Imagery EEG Classification using GMM and SVM", Journal of KIIT, Vol. 11, No. 7, pp. 67-75, Jul. 2013.
  3. G. Pfurtscheller and F. H. L. da Silva, "Event-related EEG/MEG synchronization and desynchronization: basic principles", Clinical Neurophysiology, Vol. 110, No. 11, pp. 1842-1857, Nov. 1999. https://doi.org/10.1016/S1388-2457(99)00141-8
  4. Z. J. Koles, M. S. Lazaret, and S. Z. Zhou, "Spatial patterns underlying population differences in the background EEG", Brain topography, Vol. 2, No. 4, pp. 275-284, Jun. 1990. https://doi.org/10.1007/BF01129656
  5. S. Lemm, B. Blankertz, G. Curio, and K. Muller, "Spatio-spectral filters for improving the classification of single trial EEG", IEEE Transactions on Biomedical Engineering Vol. 52, No. 9 pp. 1541-1548, Aug. 2005. https://doi.org/10.1109/TBME.2005.851521
  6. G. Dornhege, B. Blankertz, M. Krauledat, F. Losch, G. Curio, and K. Muller., "Combined optimization of spatial and temporal filters for improving brain-computer interfacing", IEEE Transactions on Biomedical Engineering, Vol. 53, No. 11, pp. 2274-2281, Oct. 2006. https://doi.org/10.1109/TBME.2006.883649
  7. K. Thomas, C. Guan, C. Lau, A. Vinod, and K. Ang, "A new discriminative common spatial pat-tern method for motor imagery brain-computer interfaces", IEEE Transactions on Biomedical Engineering, Vol. 56, No. 11, pp. 2730-2073, Nov. 2009. https://doi.org/10.1109/TBME.2009.2026181
  8. Q. Novi, C. Guan, T. H. Dat, and P. Xue, "Sub band common spatial pattern for brain-computer interface", In: 2007 3rd International IEEE/EMBS Conference on Neural Engineering, pp. 204-207, May 2007.
  9. K. Ang, Z. Chin, H. Zhang, and C. Guan, "Filter bank common spatial pattern (FBCSP) in brain-computer interface", In: IEEE International Joint Conference on Neural Networks (IJCNN 2008), Hong Kong, pp. 2390-2397, Jun. 2008
  10. K. K. Ang, Z. Y. Chin, H. Zhang, and C. Guan, "Filter Bank Common Spatial Pattern (FBCSP) in Brain-Computer Interface," 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), Hong Kong, 2008, pp. 2390-2397.
  11. Y. Zhang, G. Zhou, J. Jin, X. Wang, and A. Cichocki, "Optimizing spatial patterns with sparse filter bands for motor-imagery based brain- computer interface", Journal of Neuroscience Methods, Vol. 255, pp. 85-91, Nov. 2015. https://doi.org/10.1016/j.jneumeth.2015.08.004
  12. H. Ramoser, J. Muller-Gerking, and G. Pfurtscheller, "Optimal spatial filtering of single trial EEG during imagined hand movement", IEEE Transactions on Rehabilitation Engineering, Vol. 8, No. 4, pp. 441-446, Dec. 2000. https://doi.org/10.1109/86.895946
  13. K. K. Ang and C. Quek, "Rough set-based neuro-fuzzy system", in Proceedings of the IEEE International Joint Conference on Neural Networks, Vancouver, BC, pp. 742-749, Jul. 2006.
  14. A. K. Jain, R. P. W. Duin, and M. Jianchang, "Statistical pattern recognition: a review", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 22, No. 1, pp. 4-37, Jan. 2000. https://doi.org/10.1109/34.824819
  15. K. K. Ang, Z. Y. Chin, H. Zhang, and C. Guan, "Filter Bank Common Spatial Pattern (FBCSP) algorithm using online adaptive and semisupervised learning", The 2011 International Joint Conference on Neural Networks, San Jose, CA, pp. 392-396, Jul. 2011.
  16. R. Tibshirani. "Regression shrinkage and selection via the lasso", Journal of the Royal Statistical Society, Series B, Vol. 58, No. 1, pp. 267-288, 1996.
  17. S. Zhang, M. Zong, K. Sun, Y. Liu, and D. Cheng, "Efficient kNN algorithm based on graph sparse reconstruction", In : Advanced Data Mining and Applications, Guilin, China, pp. 356-369, 2014.
  18. M.. Law, "A Simple Introduction to Support Vector Machines", https://www.cise.ufl.edu/class/cis 4930sp11dtm/notes/intro_svm_new.pdf, 2006. [Accessed: Jul. 15. 2017]
  19. B. Blankertz, K. R. Müller, D. J. Krusienski, G. Schalk, J. R. Wolpaw, A. Schlogl, and N. Birbaumer, "The BCI competition III: Validating alternative approaches to actual BCI problems", IEEE Transactions on Neural Systems and Rehabilitation Engineering, Vol. 14, No. 2, pp. 153-159, Jun. 2006. https://doi.org/10.1109/TNSRE.2006.875642
  20. http://www.bbci.de/competition/iv/desc_2b.pdf [Accessed: Jul. 17. 2017]
  21. C. C. Chang and C. J. Lin, "LIBSVM : a library for support vector machines", ACM Transactions on Intelligent Systems and Technology, Vol. 2, pp. 27:1-27:27, May 2011.