Comparative study of EMG based Joint torque estimation ANN models for arm rehabilitation device

• Main Authors: Jali, Mohd Hafiz, Sulaima, Mohamad Fani, Ahmad Izzuddin, Tarmizi, Wan Daud, Wan Mohd Bukhari, Baharom, Mohamad Faizal
• Format: Article
• Language: English
• Published: Research India Publications 2014
• Subjects: TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://eprints.utem.edu.my/id/eprint/12245/1/HAPIZ-2014-IJAER__pp_1289-1301.pdf; http://eprints.utem.edu.my/id/eprint/12245/; https://www.ripublication.com/ijaerv6/ijaerv9n10_06.pdf

Rehabilitation device is used as an exoskeleton for people who had failure of their limb. Arm rehabilitation device may help the rehab program whom suffered with arm disability. The device used to facilitate the tasks of the program should improve the electrical activity in the motor unit and minimize the mental effort of the user. Electromyography (EMG) is the techniques to analyze the presence of electrical activity in musculoskeletal systems. The electrical activity in muscles of disable person is failed to contract the muscle for movements. In order to minimize the used of mental forced for disable patients, the rehabilitation device can be utilize by analyzing the surface EMG signal of normal people that can be implemented to the device. The objective of this work is to compare the performance of the joint torque estimation model from the muscle EMG signal to torque for a motor control of the arm rehabilitation device using Artificial Neural Network (ANN) technique. The EMG signal is collected from Biceps Brachii muscles to estimate the elbow joint torque. A two layer feed-forward network is trained using Back Propagation Neural Network (BPNN) to model the EMG signal to torque value. The comparison between two ANN models is made to observe the performance difference between these models. The experimental results show that ANN model with double input nodes has a better performance result in term of Mean Squared Error (MSE) and Regression (R) which is crucially important to represent EMG-torque relationship for arm rehabilitation device control.