The KIPS Transactions:PartB (정보처리학회논문지B)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Feature Analysis of Multi-Channel Time Series EEG Based on Incremental Model

점진적 모델에 기반한 다채널 시계열 데이터 EEG의 특징 분석

  • 김선희 (전남대학교 전산학과) ;
  • 양형정 (전남대학교 전자컴퓨터공학부) ;
  • ;
  • 정종문 (전남대학교 전자컴퓨터공학부)
  • Published : 2009.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

BCI technology is to control communication systems or machines by brain signal among biological signals followed by signal processing. For the implementation of BCI systems, it is required that the characteristics of brain signal are learned and analyzed in real-time and the learned characteristics are applied. In this paper, we detect feature vector of EEG signal on left and right hand movements based on incremental approach and dimension reduction using the detected feature vector. In addition, we show that the reduced dimension can improve the classification performance by removing unnecessary features. The processed data including sufficient features of input data can reduce the time of processing and boost performance of classification by removing unwanted features. Our experiments using K-NN classifier show the proposed approach 5% outperforms the PCA based dimension reduction.

BCI 기술은 생체신호인 뇌파를 수집하여 신호처리를 거친 후 실질적인 기기제어 및 통신 시스템 등을 제어하는 시스템 관련 기술이다. BCI 시스템 구현을 위해서는 뇌파의 특성을 실시간으로 분석하여 학습 시키고 학습된 뇌파의 특성을 적용하는 단계가 요구된다. 본 논문에서는 EEG 데이터를 효율적으로 분석하기 위해 점진적으로 갱신되는 주성분 분석을 이용하여 왼손/오른손 동작에 영향을 미치는 EEG 신호의 특징을 찾고, 이를 반영하여 데이터의 차원을 축소한다. 입력 자료의 특징을 충분히 포함하면서 낮은 차원을 가지는 데이터를 이용한다면 분류를 위한 계산량을 감소시킬 수 있을 뿐만 아니라 불필요한 특징을 제거함으로써 분류 성능을 향상 시킬 수 있다. 본 논문에서는 점진적으로 갱신되는 주성분 분석을 이용하여 데이터의 차원을 축소하고 이에 대한 효율성을 검증하기 위해 K-NN분류기를 이용하여 분류 정확도 측정을 수행하였다. 그 결과 주성분 분석을 이용하여 특징을 추출하고 분류율을 측정한 경우보다 평균 5% 높은 분류 정확율을 보였다.

Keywords

References

  1. Akrami A, Solhjoo S, Motie-Nasrabadi A and Hashemi-Golpayegani M.R, “EEG-Based Mental Task Classification: Linear and Nonlinear Classification of Movement Imagery,” Annual International Conference of the IEEE, pp.4626-4629, 2005 https://doi.org/10.1109/IEMBS.2005.1615501
  2. Arthur P., Danil V.P., Richard H., Richard D. and Donald C.W., “Recurrent neural network based prediction of epileptic seizures in intra- and extracranial EEG,” Neurocomputing pp.201-218, 2000 https://doi.org/10.1016/S0925-2312(99)00126-5
  3. Costa EJ and Cabral EF Jr, “EEG-based discrimination between imagination of left and right hand movements using Adaptive Gaussian Representation,” Med Eng Phys, pp.345-348, 2000 https://doi.org/10.1016/S1350-4533(00)00051-5
  4. Dharwarkar G.S and Basir O, “Enhancing Temporal Classification of AAR Parameters in EEG single-trial analysis for Brain-Computer Interfacing,” IEEE-Engineering in Medicine and Biology Society, pp.5358-5361, 2005 https://doi.org/10.1109/IEMBS.2005.1615692
  5. Folkers A, Mosch F, Malina T and Hofmann U.G, “Realtime bioelectrical data acquisition and processing from 128 channels utilizing the wavelet-transformation,” Neurocomputing, pp.247-254, 2003 https://doi.org/10.1016/S0925-2312(02)00763-4
  6. Gasser B, Toussant M, Luthringer R, Macher J.P and Cerf R, “Wave Separation versus Bandpass Filtering: a Comparative Non-linear Analysis of Brain ${\alpha}$-EEG Signals with and without Psychotropic Drug Treatment,” Journal of Biological Physics, pp.209-225, 1996 https://doi.org/10.1007/BF00401874
  7. Harner P.K and Sannit T, “A review of the international ten-twenty system of electrode placement,” Quincy, MA: Grass Instrument, 1974
  8. Li Y and Zhang S, “Apply wavelet transform to analyse EEG signal,” Annual International Conference of the IEEE, pp. 1007-1008, 1996 https://doi.org/10.1109/IEMBS.1996.652683
  9. Lindsay I Smith, “A tutorial on Principal Components Analysis,” 2002
  10. Lee H and Choi S, “PCA-based linear dynamical systems for multichannel EEG classification,” Neural Information Processing, pp.745-749, 2002 https://doi.org/10.1109/ICONIP.2002.1198157
  11. Michael D and Houchin J. “Automatic EEG analysis: a segmentation procedure based on the autocorrelation function,” Electroencephalogr Clin Neurophysiol, pp.232-5, 1979 https://doi.org/10.1016/0013-4694(79)90075-0
  12. Neep H, Jean Z.C, Ah C.T and Alex S, “Classification of EEG signals using the wavelet transform,” Signal Processing, pp.61-72, 1997 https://doi.org/10.1016/S0165-1684(97)00038-8
  13. Pari J, Vassilis K and Kenneth R, “EEG Signal Classification Using Wavelet Feature Extraction and Neural Networks,” IEEE John Vincent Atanasoff 2006 International Symposium on Modern Computing, pp.120-124, 2006 https://doi.org/10.1109/JVA.2006.17
  14. Scott M, Anthony J.B, Tzyy-Ping J and Terrence JS, “Independent Component Analysis of Electroencephalographic Data,” Advances in Neural Information Processing Systems, pp.145-151, 1996
  15. Spiros P, Jimeng S and Christos F, “Streaming pattern discovery in multiple time-series,” Proceeding of the 31st VLDB Conference, pp.697-708, 2005
  16. Shaker M.M, “EEG waves classifier using wavelet transform and Fourier transform,” IJBS pp.85-90, 2006
  17. Walter D.O and Leuchter A.F, “A Tourial on Classical computer analysis of EEGs: Spectra and Cohereneces in analysis of the Electrical Activity of the Brain,” By Angeleri R, Butler S, Giaquinto S, Majkowski J. Wiley & Sons, pp.105-124.1997
  18. Yong L, Xiaorong G, Hesheng L and Shangkai G, “Classification of single-trial electroencephalogram during finger movement,” IEEE- Biomedical Engineering, pp.1019-1025, 2004 https://doi.org/10.1109/TBME.2004.826688
  19. Zarjam P and Mesbah M, “Discrete wavelet transform based seizure detection in newborns EEG signals,” Signal Processing and Its Applications, pp.459-462, 2003 https://doi.org/10.1109/ISSPA.2003.1224913
  20. Zhang Q and Benveniste A, “Wavelet Networks,” IEEE Trans, Neural Networks, pp.889-898, 1992 https://doi.org/10.1109/72.165591
  21. 임성길, 박찬호, 이현수, “웨이블릿 신경망을 이용한 패턴 분류 시스템 설계 및 EEG 신호 분류에 대한 연구”, 전자공학회논문지-CI 제39권 3호 pp.32-43, 2002
  22. 이혜경, 최승진, “다채널 뇌파 분류를 위한 주성분 분석 기반 선형동적시스템”, 한국뇌학회지, Vol.2, No.1, pp.53-59, 2002
  23. http://ida.first.fraunhofer.de/