Practical Surface EMG Pattern Classification by Using a Selective Desensitization Neural Network
Real-time pattern classification of electromyogram (EMG) signals is significant and useful for developing prosthetic limbs. However, the existing approaches are not practical enough because of several limitations in their usage, such as the large amount of data required to train the classifier. Here, we introduce a method employing a selective desensitization neural network (SDNN) to solve this problem. The proposed approach can train the EMG classifier to perform various hand movements by using a few data samples, which provides a highly practical method for real-time EMG pattern classification.
KeywordsEMG Pattern Classification Selective Desensitization Neural Network Prosthetic Limb Hand Movement Classification
Unable to display preview. Download preview PDF.
- 1.Tsuji, T., Fukuda, O., Bu, N.: New Developments in Biological Signal Analysis (in Japanese). Journal of the Japan Society of Applied Electromagnetics 13(3), 201–207 (2005)Google Scholar
- 2.Yokoi, H., Chiba, R.: Now and Future of Cyborg Technology (in Japanese). Journal of the Society of Instrument and Control Engineers 47(4), 351–358 (2008)Google Scholar
- 3.Morita, M., Murata, K., Morokami, S., Suemitsu, A.: Information Integration Ability of Layered Neural Networks with the Selective Desensitization Method (in Japanese). The IEICE Transactions on Information and Systems J87-D-II(12), 2242–2252 (2004)Google Scholar
- 4.Oisaka Electronic Device Ltd., http://www.oisaka.co.jp/P-EMG.html
- 5.Fujita, T.: Guide Anthropotomy (in Japanese), pp. 88–92. Nankodo (2003)Google Scholar
- 6.Yoshikawa, M., Mikawa, M., Tanaka, K.: Real-Time Hand Motion Classification and Joint Angle Estimation Using EMG Signals (in Japanese). The IEICE Transactions on Information and Systems J92-D(1), 93–103 (2009)Google Scholar
- 7.Real-Time Classification of Multiple Hand Movements, http://volga.esys.tsukuba.ac.jp/~kawata/demovideo/demovideo.wmv