Abstract
We describe a method for recognizing hand motions using multichannel EMG (surface Electromyogram), in which the channels are selected by using the Monte Carlo method. In our system, to select 16 channels that are suitable for recognition from the available 96 channels of the multichannel electrode is a key of our system. We generate 1000 sets of randomly selected 16 channels, and those sets are evaluated for the recognition rate of hand movement. One set of 16 channels that records the highest recognition rate is used for real-time recognition. The recognition rates of 18 hand motions, including 10 finger movements, were assessed for every subject. By using the proposed method, we were able to distinguish all the motions, and the average recognition rate in the real-time recognition experiment was measured to be greater than 97%.
