엔트로피 및 최대우도추정법을 이용한 표면 근전도 기반 손가락 동작 인식

Classifying Finger Flexing Motions with Surface EMG Using Entropy and The Maximum Likelihood Method

  • 유경진 (숭실대학교 정보통신전자공학부) ;
  • 신현출 (숭실대학교 정보통신전자공학부)
  • You, Kyung-Jin (Dept. of Information & Telecommunication, School of IT, Soongsil University) ;
  • Shin, Hyun-Chool (Dept. of Information & Telecommunication, School of IT, Soongsil University)
  • 발행 : 2009.11.25

초록

표면 근전도 신호를 이용하여 손가락의 굽힘 동작을 추론하는 방법을 제안한다. 표면 근전도 신호는 인체 근육의 표면에서 무해하고 손쉽게 취득되나, 전극이 근육 내부에 침투하는 침습식 근전도와는 달리 특정 근육의 활동만을 반영하지 않는다. 따라서 소수의 전극을 사용하는 표면 근전도 신호로 다양한 신체 동작을 구분하기는 쉽지 않다. 본 연구에서는 전완 둘레에 부착된 4채널 근전도 센서를 사용하여 신호를 취득하였고, 구분을 위하여 사용한 동작은 엄지, 검지, 중지, 약지, 소지의 개별 손가락의 굽힘 동작이다. 피검자 한 명은 숙련자였으며, 다른 한 명은 비숙련자였다. 근전도 신호의 특성으로 정보 엔트로피를 추출하였으며 최대우도추정법을 사용하여 실제 동작을 추정하였다. 실험 결과 평균 95% 이상의 성능을 보였으며, 제안하는 방법이 손가락 동작의 구분에 유용함을 확인하였다.

We provide a method to infer finger flexing motions using a 4-channel surface electromyogram (sEMG). Surface EMGs are harmless to the human body and easily acquired. However, they do not reflect the activity of specific nerves or muscles, unlike invasive EMGs. On the other hand, the non-invasive type is difficult to use for discriminating various motions while using only a small number of electrodes. Surface EMG data in this study were obtained from four electrodes placed around the forearm. The motions were the flexion of the thumb, index, middle, ring, and little linger. One subject was trained with these motions and another left was untrained. The maximum likelihood estimation was used to infer the finger motion. Experimental results have showed that this method could be useful for recognizing finger motions. The average accuracy was as high as 95%.

키워드

참고문헌

  1. Leif Sornmo, and Pablo Laguna, Bioelectrical signal processing in cardiac and neurological applications. Elsevier academic press, pp 347, 2005
  2. Kevin Englehart, Bernard Hudgins, and Philip A. Parker, 'A Wavelet-Based Continuous Classification for Multifucntion Myoelectric Control', IEEE Trans. on Biomedical Engineering, vol. 48, no. 3, March 2001
  3. Kevin Englehart, and Bernard Hudgins, 'A robust, real-time control scheme for multifunction myoelectric control', IEEE Trans. on Biomedical engineering, vol. 50, no. 7, July 2003
  4. B. Hudgins, P. Parker, and R. Scott, 'A new strategy for multifunction myoelectric control', IEEE Trans. on Biomedical Engineering, vol. 40, no. 1, pp. 82-94, Jan. 1993 https://doi.org/10.1109/10.204774
  5. Kaveh Momen, Sridhar Krishnan, and Tom Chau, Real-Time Classification of Forearm Electromyographic signals Corresponding to User-Selected Intentional Movements for Multifunction Prosthesis Control , IEEE Trans. on Neural Systems and Rehabilitation Engineering, vol. 15, no. 4, Dec. 2007
  6. Daisuke Nishikawa, Wenwei Yu, Hiroshi yokoi, and Yukinori Kakazu, 'EMG Prosthetic Hand Controller Discriminating Ten Motions using Real-time Learning Method', in Proc. vol.3, IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems, Kyongju, South Korea, Oct. 1999, pp. 1592-1597
  7. Kentaro Nagata, Keiichi Ando, Kazushige Magatani, and Masafumi Yamada, 'Development of the hand motion recognition system based on surface EMG using suitable measurement channels for pattern recognition', in Proc., the 29th Annual Intl. Conf. of the IEEE EMBS, Cit$\'{e}$ Internationale, Lyon, France, August 23-26, 2007
  8. Joong-kyu Lim, Ki-hwan Eom, 'Simple SOM Method for Pattern Classification of the EMG Signals', Journal of the Institute of Electronics Engineers of Korea, vol. 38-SC, no. 4, pp 201-206, 2001