EMG based prediction of elbow motion

We have evaluated the ability of a feed-forward neural network to predict elbow motion using electromyographic signal. EMG signals are recorded using surface EMG electrodes placed on the user´s skin from above elbow and below elbow positions at various angles. It has been found that various elbow joint angles can be predicted by feedforward neural network with 85% accuracy. The results indicate that the EMG signals from elbow muscles contain a significant amount of information about arm movement kinematics that could be exploited to develop robots for human motion support for physically weak people and also helps to control prostheses.