Genetic algorithm based optimization for EMG pattern recognition system

The paper presents the concept of genetic algorithm based optimization for the EMG pattern recognition system controlling the hand prosthesis. The recognition of EMG signals for determining the hand movements is made by a linear neural network discriminating between five predefined grasps. The input feature vector for the classification was established using AR model, and its coefficients became the features. The genetic algorithms are used to optimize the number of elements in the input feature vector and simultaneously maintain the recognition efficiency at the same level. Experimental results show a good efficiency in the optimization method maintaining the performance of the recognition system for the studied grasp movements’ repertoire.