@Article{, title={HD-sEMG Gestures Recognition by SVM Classifier for Controlling Prosthesis}, author={Mofeed Turky Rashid2 and Hanadi Abbas Jaber1}, journal={IRAQI JOURNAL OF COMPUTERS, COMMUNICATIONS, CONTROL AND SYSTEMS ENGINEERING المجلة العراقية لهندسة الحاسبات والاتصالات والسيطرة والنظم}, volume={19}, number={1}, pages={10-19}, year={2019}, abstract={Electromyography signals (EMG) are an important source to infermotion intention. It has been broadly applied in human-machine interfacing tocontrol the neurorehabilitation devices such as prosthesis and rehabilitationrobot. HD-sEMG is a muscle's activity recorded at the delimited area of theskin using 2D array electrode. This strategy permits the analysis of sEMGsignals in both temporal and spatial domain. Recent studies display that thespatial distribution of HD-EMG maps improves the recognition of tasks. Thiswork investigates the use of HD-EMG recording to control upper limbprosthesis. The classification of eight hand gestures of able-bodied subjects wasdeveloped. Three feature sets were presented in this work. HOG features, timedomain features(TD) and the combination of HOG and average intensityfeatures (AIH). Combination of features possibly improved the performance ofthe classifier. Results show that the combined of intensity features and HOGfeatures achieved higher performance of classifier than other features(Acc=99.37%, P=98.375%, S=97.5%).

} }