DOI QR코드

DOI QR Code

Application of CSP Filter to Differentiate EEG Output with Variation of Muscle Activity in the Left and Right Arms

좌우 양팔의 근육 활성도 변화에 따른 EEG 출력 구분을 위한 CSP 필터의 적용

  • Kang, Byung-Jun (School of Electrical, Electronics and Communication Engineering, KOREATECH) ;
  • Jeon, Bu-Il (School of Electrical, Electronics and Communication Engineering, KOREATECH) ;
  • Cho, Hyun-Chan (School of Electrical, Electronics and Communication Engineering, KOREATECH)
  • Received : 2020.05.29
  • Accepted : 2020.06.29
  • Published : 2020.06.30

Abstract

Through the output of brain waves during muscle operation, this paper checks whether it is possible to find characteristic vectors of brain waves that are capable of dividing left and right movements by extracting brain waves in specific areas of muscle signal output that include the motion of the left and right muscles or the will of the user within EEG signals, where uncertainties exist considerably. A typical surface EMG and noninvasive brain wave extraction method does not exist to distinguish whether the signal is a motion through the degree of ionization by internal neurotransmitter and the magnitude of electrical conductivity. In the case of joint and motor control through normal robot control systems or electrical signals, signals that can be controlled by the transmission and feedback control of specific signals can be identified. However, the human body lacks evidence to find the exact protocols between the brain and the muscles. Therefore, in this paper, efficiency is verified by utilizing the results of application of CSP (Common Spatial Pattern) filter to verify that the left-hand and right-hand signals can be extracted through brainwave analysis when the subject's behavior is performed. In addition, we propose ways to obtain data through experimental design for verification, to verify the change in results with or without filter application, and to increase the accuracy of the classification.

본 논문은 근육 동작시의 뇌파의 출력을 통해 불확실성이 상당히 존재하는 EEG 신호 안에서 좌우완 근육의 동작이나 사용자의 의지가 포함된 근육 신호 출력 시의 특정 부위 뇌파를 추출하여 좌우 동작 구분이 가능한 뇌파의 특징 벡터를 찾아낼 수 있는지를 확인한다. 일반적인 표면 근전도와 비침습적인 방식의 뇌파 추출 방법으로는 내부 신경 전달에 의한 이온화 정도와 전기 전도도의 크기를 통해서 그 동작 신호인지 구분할 수 있는 방법이 존재하지 않는다. 일반 로봇 제어 시스템이나 전기 신호를 통한 관절 및 모터 제어의 경우는 특정 신호의 전달 및 피드백 제어를 통해 관절 및 로봇 제어기를 제어할 수 있는 신호를 확인할 수 있지만, 인간의 인체는 정확한 뇌와 근육간의 프로토콜을 찾을 근거가 부족하다. 따라서 본 논문에서는 피험자의 동작이 이루어질 경우의 뇌파 분석을 통해 좌완의 신호와 우완의 신호를 특정할 만한 근거 신호 또는 특징 벡터를 추출할 수 있는지 확인하기 위해 CSP(Common Spatial Pattern) 필터의 적용 결과 활용하여 효율성을 검증한다. 더불어 검증을 위한 실험 설계를 통해 데이터를 획득하고, 필터 적용 유무에 따른 결과의 변화가 어떠한지 검증하며 구분 정확도를 높일 수 있는 방법을 제안한다.

Keywords

References

  1. SUK, Ji-A., et al. "Neural Correlates and Electrodermal Activity Produced by Humor and Joy," In: Proceedings of the Korean Institute of Intelligent Systems Conference. Korean Institute of Intelligent Systems, pp.373-376, 2005.
  2. ROBINSON, Neethu, et al. "EEG-based classification of fast and slow hand movements using wavelet-CSP algorithm," IEEE Transactions on Biomedical Engineering, Vol.60, No.8, pp.2123-2132, 2013. DOI: 10.1109/TBME.2013.2248153
  3. LI, Shufang, et al. "Feature extraction and recognition of ictal EEG using EMD and SVM," Computers in biology and medicine, Vol.43, No.7, pp.807-816, 2013. DOI: 10.1016/j.compbiomed.2013.04.002
  4. KUO, Bor-Chen, et al. "A kernel-based feature selection method for SVM with RBF kernel for hyperspectral image classification," IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol.7, No.1, pp.317-326, 2013. DOI: 10.1109/JSTARS.2013.2262926
  5. TRIBA, Mohamed N., et al. "PLS/OPLS models in metabolomics: the impact of permutation of dataset rows on the K-fold cross-validation quality parameters," Molecular BioSystems, Vol.11, NO.1 pp.13-19, 2015. DOI: 10.1039/C4MB00414K
  6. JEON, Bu Il, et al. "Motion Recognition and an Accuracy Comparison of Left and Right Arms by EEG Signal Analysis," Applied Sciences, Vol.9, No.22, p.4885, 2019. DOI: 10.3390/app9224885