재활복지공학회논문지 (Journal of rehabilitation welfare engineering & assistive technology)

한국재활복지공학회 (Rehabilitation Engineering And Assistive Technology Society of Korea)
권호 표지
DOI QR코드

DOI QR Code

원형 근전도 센서 어레이 시스템의 센서 틀어짐에 강인한 손 제스쳐 인식

Hand Gesture Recognition Regardless of Sensor Misplacement for Circular EMG Sensor Array System

  • 주성수 (한양대학교 생체의공학과) ;
  • 박훈기 (한양대학교병원 가정의학과) ;
  • 김인영 (한양대학교 의공학교실) ;
  • 이종실 (한양대학교 의공학연구소)
  • 투고 : 2017.11.20
  • 심사 : 2017.11.29
  • 발행 : 2017.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서는 원형 근전도 시스템 장비를 사용하여 근전도 패턴인식을 할 때, 장비의 센서 위치와 무관하게 패턴 인식이 가능한 알고리즘을 제안한다. 6가지 동작의 8채널 근전도 신호를 1초간 측정한 데이터를 이용하여 14개의 특징점을 추출하였다. 또한 8개의 채널에서 추출된 112개의 특징점을 나열하여 주성분분석을 하고 영향력이 높은 데이터만을 추려내어 8개의 입력 신호로 줄였다. 모든 실험은 k-NN 분류기를 이용하여 데이터를 학습시키고 5-fold 교차 검증을 사용하여 데이터를 검증하였다. 기계학습에서 데이터를 학습시킬 때, 어떤 데이터를 학습하느냐에 따라 그 결과가 크게 달라진다. 기존의 연구들에서 사용하는 학습 데이터를 사용 할 경우 99.3%의 정확도를 확인하였다. 그러나 센서의 위치가 22.5도 정도만 틀어지더라도 67.28%의 정확도로 명확하게 떨어짐을 보았다. 본 논문에서 제안하는 학습 방법을 사용 할 경우 98%의 정확도를 보이고 장비의 센서의 위치가 바뀌더라도 98% 근처의 정확도를 유지함을 보였다. 이러한 결과를 사용하여 원형 근전도 시스템을 사용하는 사용자들의 편의성을 크게 증대시켜 줄 수 있을 것으로 보인다.

In this paper, we propose an algorithm that can recognize the pattern regardless of the sensor position when performing EMG pattern recognition using circular EMG system equipment. Fourteen features were extracted by using the data obtained by measuring the eight channel EMG signals of six motions for 1 second. In addition, 112 features extracted from 8 channels were analyzed to perform principal component analysis, and only the data with high influence was cut out to 8 input signals. All experiments were performed using k-NN classifier and data was verified using 5-fold cross validation. When learning data in machine learning, the results vary greatly depending on what data is learned. EMG Accuracy of 99.3% was confirmed when using the learning data used in the previous studies. However, even if the position of the sensor was changed by only 22.5 degrees, it was clearly dropped to 67.28% accuracy. The accuracy of the proposed method is 98% and the accuracy of the proposed method is about 98% even if the sensor position is changed. Using these results, it is expected that the convenience of the users using the circular EMG system can be greatly increased.

키워드

참고문헌

  1. Ahsan, Md Rezwanul, Muhammad I. Ibrahimy, and Othman O. Khalifa. "EMG signal classification for human computer interaction: a review.", European Journal of Scientific Research, vol 33, no. 3, pp. 480-501, 2009.
  2. Abreu, Teixeira and Figueiredo, "Evaluating Sign Language Recognition Using the Myo Armband." XVIII Symposium on Virtual and Augmented Reality(SVR) on IEEE, 2016.
  3. W Geng, Y Du and W Jin, "Gesture recognition by instantaneous surface EMG images." Scientific reports, 6, 36571, 2016. https://doi.org/10.1038/srep36571
  4. E. C. Jeong, S. J. Kim, Y. R. Song, S, M, Lee. "Artificial Neural Network based Motion Classification Algorithm using Surface Electromyogram", Rehabilitation Engineering & Assistive Technology Society of Korea, vol. 6, no. 1, pp. 67-74, 2012.
  5. Khushaba, Rami N. et al., "Combined influence of forearm orientation and muscular contraction on EMG pattern recognition.", Expert Systems with Applications, vol. 61, pp. 154-161, 2016. https://doi.org/10.1016/j.eswa.2016.05.031
  6. Sathiyanarayanan, Mithileysh, and Sharanya Rajan., "MYO Armband for physiotherapy healthcare: A case study using gesture recognition application.", Communication Systems and Networks, 8th International Conference on. IEEE, 2016.
  7. Phinyomark, Angkoon and Pornchai Phukpattaranont, and Chusak Limsakul, "Feature reduction and selection for EMG signal classification." Expert Systems with Applications, vol. 39, no. 8, pp. 7420-7431, 2012. https://doi.org/10.1016/j.eswa.2012.01.102
  8. Caesarendra and Wahyu, "A classification method of hand EMG signals based on principal component analysis and artificial neural network." International Conference on Instrumentation, Control and Automation (ICA), Bandung, Indonesia, August, 2016.
  9. Purushothaman, Geethanjali, and K. K. Ray. "EMG based man-machine interaction-A pattern recognition research platform." Robotics and Autonomous Systems, vol. 62, no. 6, pp. 864-870, 2014. https://doi.org/10.1016/j.robot.2014.01.008
  10. Ahsan, Md Rezwanul and Muhammad I. Ibrahimy, "EMG signal classification for human computer interaction: a review." European Journal of Scientific Research, vol. 33, no. 3, pp. 480-501, 2009.
  11. Ariyanto and Mochammad, "Finger movement pattern recognition method using artificial neural network based on electromyography (EMG) sensor." Automation, Cognitive Science, Optics, Micro Electro-Mechanical System, and Information Technology (ICACOMIT), Bandung, Indonesia, pp. 29-30, 2015.
  12. Y. R. Song, S. J. Kim, E. C. Jeong, S. M. Lee., "A Gaussian Mixture Model Based Pattern Classification Glgorithm of Rorearm Electromyogram", Rehabilitation Engineering & Assistive Technology Society of Korea, vol. 5, no. 1, pp. 95-101, 2011.
  13. Sapsanis, Christos, George Georgoulas, and Anthony Tzes., "EMG based classification of basic hand movements based on time-frequency features." Control & Automation (MED), 21st Mediterranean Conference on. IEEE, 2013.
  14. Federolf, P. A., K. A. Boyer and T. P. Andriacchi. "Application of principal component analysis in clinical gait research: identification of systematic differences between healthy and medial knee-osteoarthritic gait." Journal of biomechanics, vol. 46, no. 13, pp. 2173-2178, 2013. https://doi.org/10.1016/j.jbiomech.2013.06.032
  15. Bosco and Gianfranco. "Principal component analysis of electromyographic signals: an overview." The Open Rehabilitation Journal, vol. 3, no. 1, pp. 127-131, 2010. https://doi.org/10.2174/1874943701003010127
  16. Al-Faiz, Mohammed Z, A. Ali and Abbas H. Miry, ""A k-nearest neighbor based algorithm for human arm movements recognition using EMG signals." Energy, Power and Control (EPC-IQ), Basrah, Iraq, November, 2010.