Amputee Electromyography Signal Classification Using Convolutional Neural Network

The classification of EMG signals for the amputees is important to develop a powered-prosthetic that is capable of replacing with lost limbs. The EMG signals collected from residual limbs reduce the classification accuracy due to muscle movements that cannot be realized properly. In this study, classification performance is aimed to be increased by combining CNN with root mean square (RMS) and waveform length (WL) that are used in analysis of EMG signals successfully. The features such as RMS and WL extracted from EMG signals for the classification of six hand movements at the low, medium, and high force levels were applied to CNN input, and classification results were compared with nearest neighbour and linear discriminant analysis.