ELBOW FLEXION AND EXTENSION IDENTIFICATION USING SURFACE ELECTROMYOGRAPHY SIGNALS

In this paper, a new approach is presented for the analysis and the identification of the surface electromyography (EMG) signals of biceps and triceps muscles. The objective of this study is the accurate classification of elbow flexion and ex-tension movements. We propose a cropping method based on the agreement of the movement changes and the EMG signal using the upper limb kinematic. Then, we perform the extrac-tion and selection of several well known features in time and frequency domain. The selected features are used as inputs for our support vector machine classifier which is designed using an optimal weight vector criterion. Afterward, the train-ing and test steps are performed in the proposed scheme. Fi-nally, numerical simulation assess the accuracy of the classi-fication, as well as the robustness of the proposed approach considering noisy measurements. Index Terms — Electromyography, feature extraction, upper limb kinematic, support vector machine, quaternions. 1