Hand Posture and Force Estimation using Surface Electromyography and an Artificial Neural Network

Abstract

Prior epidemiological studies have shown that heavy hand exertion force and hand posture (grip versus pinch) are important risk factors for distal upper extremity disorders such as wrist tendinosis and carpal tunnel syndrome (CTS). However, quantifying the magnitude of hand exertions reliably and accurately is challenging and has relied heavily upon subjective worker or analyst observations. Prior studies have used electromyography (EMG) with machine learning models to estimate hand exertion but relatively few studies have assessed whether hand posture and exertion forces can be predicted at varying levels of force exertion, duty cycle and repetition rate. Therefore, the purpose of this study was to develop an approach to estimate hand posture (pinch versus grip) and hand exertion force using forearm surface electromyography (sEMG) and artificial neural networks.