The control of the 5-finger myoelectric hand prosthesis using an armband emg module

A 5-finger myoelectric hand prosthesis of 7 different hand postures was successfully controlled using ANN with an armband-type multi-channel EMG module. The classification accuracy was evaluated for 10 normal volunteers, considering the independence of the EMG feature groups, donning and doffing training data size, and whether or not majority voting was applied. The results revealed an optimized accuracy of 97.49 3.87% when majority voting was applied for the high independence feature group (HIFG) to perform classification training for 7 or more sessions. Confusion matrices and separability indexes of ANN classifiers showed that the major misclassifications, in spite of a good accuracy, were found to be lateral pinch vs. palmar pinch, and index vs. thumb-up However, with the classification training for seven or more sessions, the probability of misclassification significantly decreased.