Browse > Article

A Virtual Robot Arm Control by EMG Pattern Recognition of Fuzzy-SOFM Method  

이정훈 (동국대학교 전자공학과)
정경권 (동국대학교 전자공학과)
이현관 (호남대학교 인터넷프로그램학과)
엄기환 (동국대학교 전자공학과)
Publication Information
Abstract
We proposed a method of a virtual robot arm controlled by the EMG pattern recognition using an improved SOFM method. The proposed method is simple in that the EMG signals are used as SOFM's input directly without preprocessing but nevertheless input patterns are reliably classified and then used for fuzzy logic systems to automatically tune the neighborhood and the learning rate. In order to verify the effectiveness of the proposed method, we experimented on EMG pattern recognition of 6 movements from the shoulder, wrist, and elbow. Experimental results show that the proposed SOFM method has 21.7% higher recognition rate than the general SOFM method, the average number of learning iterations has been decreased, and then the virtual robot arm is controlled by EMG pattern recognition.
Keywords
fuzzy; SOFM; pattern recognition; EMG signal; virtual robot arm;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Carlo J. De Wiener, Surface EMG Detection and Recording. Neuro Muscular Research Center. 1997
2 Karst G M, Hasan Z, 'Timing and magnitude of electromyo graphic activity for two joint arm movements in different directions' J Neurophysiol 66: 1594-1604. 1991   DOI
3 Yasuharu Koike, Mitsuo Kawato, Estimation of dynamic joint torque and trajectory formation from surface electromyo graphy signals using a neural network model, Biological Cybernetics, Springer Verlag. 1995   DOI
4 Christodoulou C. I. and C. S. Pattichis, 'Unsupervised pattern recognition for the classification of EMG Signals', IEEE Trans. On Biomedical Eng. VOL. 46, NO. 2, pp.169-178, FEB. 1999   DOI   ScienceOn
5 Li Xin Wang, A Course in Fuzzy Systems and Control, Prentice Hall, Inc., 1997
6 T. Kohonen, 'The self organizing map' Proc. IEEE, Vol. 78, pp. 1464 1480, 1990   DOI   ScienceOn
7 Sukhan Lee, and George N. Saridis, 'The control of a prosthetic arm by EMG pattern recognition,' IEEE trans, 1997   DOI