Real-time Learning Method for Adaptable Motion-Discrimination using Surface EMG Signal

This paper describes a new real-time learning method for the development of a robust motion discriminating method from an EMG signal, to adjust to the change in user's characteristics. This method is done under the assumptions that the input motions are continuous, and the teaching motions are ambiguous in nature, therefore, automatic addition, elimination and selection of learning data are possible. Applying our proposed method, we conducted experiments to discriminate eight forearm motions, with the results, a stable and highly effective discrimination rate was achieved and maintained even when changes occurred in user's characteristics