A Prosthetic Hand Control Based on Nonstationary EMG at the Start of Movement

We propose using a multiple neural network to determine the movement intended by an amputee from electromyogram (EMG) signals. Most previous approaches to the discrimination of movement using EMG signals have required EMG data with a relative long period exceeding 200 ms. Our approach enables the amputee's intended movement to be determined from among six limb functions based on EMG signals using an initial rise zone 70 ms long. Experiments with four subjects and four electrode locations demonstrated that our proposal determines six forearm movements at a discrimination rate exceeding than 90%.