Artificial Neural Network Prediction of Angle Based on Surface Electromyography

The electromyography (EMG) signal can be considered as a manifestation of the muscle activity. An artificial neural network to predict the elbow joint angle using SEMG signals was developed in this paper. SEMG was collected from biceps and triceps and analyzed in statistic characteristics. A three-layer BP neural network was constructed and then was trained by improved back propagation algorism to predict the elbow joint angle by using the RMS of the raw SEMG signal. The experimental results show that this neural network model can well represent the relationship between SEMG signals and elbow joint angles.