Surface Electromyography (sEMG)-based Thumb-tip Angle and Force Estimation Using Artificial Neural Network for Prosthetic Thumb

Abstract

Normally, humans were born with five fingers connected to each of the hands. These fingers have their own specific role that contributes to different hand functions. Among the five fingers, the thumb plays the most special function as an anchor to many of hand activities such as turning a key, gripping a ball and holding a spoon for eating. As a result, the lost of thumb due to traumatic accidents could be catastrophic as proper hand function will be severely limited. In order to solve this problem, a prosthetic thumb is developed to be worn in complementing the function of the rest of the fingers. In this work the relationship between the electromyogram (EMG) signals and thumb tip forces are investigated in order to develop a more natural controlled prosthetic thumb. The signals are measured from the thumb intrinsic muscles namely the Adductor Pollicis (AP), Flexor Pollicis Brevis (FPB), Abductor Pollicis Brevis (APB) and First Dorsal Interosseous (FDI). Meanwhile the thumb tip force is recorded by using the force sensor (FSR). The classification of the EMG signals based on different force and thumb configuration is performed by using Artificial Neural Network (ANN). A series of experiments have been conducted and preliminary results show the efficacy of ANN to classify the EMG signals.