Feature Selection Approaches on Emg Design Based on Artifi-Cial Intelligence Techniques

Abstract

The process of feature extraction is crucial for electromyography (EMG) pattern recognition. Redundancy of characteristics is caused by high-dimensional EMG feature vector. In order to classify the EMG signal pattern, a classifier must perform more computations, which increases computation time and lowers classification accuracy. To reduce feature redundancy, many studies adopted the feature selection method. The focus of this work is on how two alternative feature selection techniques-SFS and PSO-affect the detection of EMG patterns. To assess the various effects of various feature selection methodologies on EMG pattern identification, we suggested three different approaches. Support vector machine (SVM) combined with none feature selection method, SVM combined with SFS (SFSSVM), and SVM combined with PSO (PSOSVM) are the three options. To classify 11 arm movements, we employed SVM, SFSSVM, and PSOSVM, respectively. We explored the various effects of various feature selection strategies on EMG pattern identification by comparing the classification accuracy and calculation times of the three methods. The outcomes demonstrated that the PSOSVM performed better than SVM and SFSSVM.