EMG Based Control of Prosthetic Hand for Trans-Humeral Amputee

This study investigates the use of electromyography (EMG) signals for the control of a prosthetic hand designed for trans humeral amputees. The solution for transradial amputees is well-established, but there is a significant need for further development and improvement in non-invasive brain-computer interfaces (BCI) for transhumeral amputees. EMG signals are obtained from the upper arm muscles and then preprocessed to enhance their quality and remove noise. Key features peak, mean, variance, root mean square, and skewness were extracted from these signals, which were subsequently classified to generate control commands for the prosthetic hand. Since for most common daily activity tasks of humans, they need three fingers, thumb, index and middle fingers and reaming two are just for support, so four most common gestures based on these three fingers are studied, including tip grip, thumbs up, victory and power grip and rest. This approach offers a promising solution for enhancing the functionality and usability of prosthetic hands for Trans humeral amputees with an average accuracy of 86.3%.