Control of prosthetic hand by using mechanomyography signals based on support-vector machine classifier

<div>Prosthetic devices are necessary to help amputees achieve their daily activity in the natural way possible. The prosthetic hand has controlled by type of signals such as electromyography (EMG) and mechanomyography (MMG). MMG have represented mechanical that generate during muscle contraction. These can be detected accelerometers or microphones any kind sensors detect vibrations. contribution current paper is classifying gestures control hands depends on pattern recognition through accelerometer microphone signals. In addition cost less than other designs. Six subjects involved. this present work devices. study, two them amputee subjects. Each subject performs seven classes movements. Pattern (PR) used classify gestures. wavelet packet transform (WPT) root mean square (RMS) features extracted from support vector machine (SVM) a classifier. average accuracy 88.94% for offline tests 84.45% online tests. 3D printing technology study build hands.</div>