Abstract
This paper develops a novel approach to characterise muscle force from electromyography (EMG) signals, which are the electric activities generated by muscles. Based on the nonlinear Hammerstein–Wiener model, the first part of this study outlines the estimation of different sub-models to mimic diverse force profiles. The second part fixes the appropriate sub-models of a multimodel library and computes the contribution of sub-models to estimate the desired force. Based on a pre-existing dataset, the obtained results show the effectiveness of the proposed approach to estimate muscle force from EMG signals with reasonable accuracy. The coefficient of determination ranges from 0.6568 to 0.9754 using the proposed method compared with a range of 0.5060 to 0.9329 using an artificial neural network (ANN), generating significantly different accuracy (p < 0.03). Results imply that the use of multimodel approach can improve the accuracy in proportional control of prostheses.
Highlights
Since 1952, the relationship between electromyography (EMG) and muscle force has been the focus of research for many applications ranging from prostheses control to active user-driven exoskeletons
This figure illustrates the simulation results of the proposed scenarios to show the interest of the proposed approach compared with the artificial neural network in the prediction of forces
This paper aims to characterise muscle forces from electromyography signals of the upper limb
Summary
Since 1952, the relationship between electromyography (EMG) and muscle force has been the focus of research for many applications ranging from prostheses control to active user-driven exoskeletons. Mechanical models are developed from physical laws (mechanics, biologics, electric, etc.). They are to be helpful in applications where individual muscle kinetics and kinematics are of interest. Hill’s muscle model is considered the most used physical model in musculoskeletal application to study phenomena in which only mechanical behaviour is considered [1,2,3,4]. This model has not shown its complete suitability in the control of upper limb myoelectric prosthesis
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have