EMG-based posture classification using a convolutional neural network for a myoelectric hand

Our purpose is a development of a myoelectric hand that does not require relearning even after being reseated. Because an electromyogram is a fragile biological signal, learning is necessary every time the hand is reseated, which is a burden to the operator. A classification method is proposed that uses a convolutional neural network, and test results confirmed that the decrease in classification rate is suppressed when large-scale data are used...