Electromyography (EMG)-based thump-tip force estimation for prosthetic thumb

• Published in: 2012 International Conference on Computer and Communication Engineering (ICCCE) pp. 783 - 786
• Main Authors: Jalaludin, Nor Anija, Shamsudin, Abu Ubaidah, Sidek, Shahrul Na'im, Aibinu, A. M.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-07-2012
• Subjects: Artificial neural networks; Electromyograpgy (EMG) signal; Electromyography; Force; force sensor (FSR); Muscles; Prosthetics; Thumb; thumb-tip force
• DOI: 10.1109/ICCCE.2012.6271324
• ISBN: 1467304786; 9781467304788

Every normal-born human have 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 can be worn to complement the function of the rest of the fingers. In this work the relationship between the electromyography (EMG) and thumb tip force is 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 relationship between the EMG signals to the thumb-tip force is established by using Artificial Neural Network (ANN). A series of experiments have been conducted and preliminary results show the efficacy of ANN to capture the relationship model.