           !"##"! $ %%"#$ &"#&#’ ( ’" #’#&) *"’)"! #+,- ./  "!)+’ #’#0#$ www.arpnjournals.com 1170                 M. H. Jali 1 , T. A. Izzuddin 1 , Z. H. Bohari 1 , H. Sarkawi 2 , M. F. Sulaima 1 , M. F. Baharom 1 and W. M. Bukhari 1 1 Faculty of Electrical Engineering, Universiti Teknikal Malaysia Melaka, Malacca, Malaysia 2 Faculty of Electronics and Computer Engineering, Universiti Teknikal Malaysia Melaka, Malacca, Malaysia E-Mail: mohd.hafiz@utem.edu.my ABSTRACT Rehabilitation device is used as an exoskeleton for peoples who had failure of their limb. Arm rehabilitation device may help the rehab program to who suffered with arm disability. The device is used to facilitate the tasks of the program 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. 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 model 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 performance result of the network is measured based on the Mean Squared Error (MSE) of the training data and Regression (R) between the target outputs and the network outputs. The experimental results show that ANN can well represent EMG-torque relationship for arm rehabilitation device control. Keywords: electromyography, torque, artificial neural network. INTRODUCTION Human support system is endoskeleton. Endoskeleton plays a role as a framework of the body which is bone. Our daily movements are fully depends on the functionality of our complex systems in the body. The disability one or more of the systems in our body will reduce our physical movements. The assistive device is a need for rehab as an exoskeleton. The functionality of the rehabilitation device has to smooth as the physical movement of normal human. The rehabilitation programs provide the suitable program for conducting the nerve and stimulate the muscles. People who have temporary physical disability have the chances to recover. Nowadays, rehabilitation program are using exoskeleton device in their tasks. The functionality of exoskeleton depends on muscle contraction. Electromyogram studies help to facilitate the effectiveness of the rehabilitation device by analysing the signal transmitted from the muscle. The rehabilitation device is a tool that used to help the movements for daily life activities of the patients who suffer from the failure of muscle contractions, due to the failure of the muscles contractions the movements is limited. The ability of the patients to do the tasks in the rehabilitation programs need to be measured. The rehabilitation programs have to assure whether the tasks will cause effective or bring harm to the patients [1]. Historically, the rehabilitation tasks have been avoided due to a belief that it would increase spasticity [2]. In this research, the analysis of the data will be focusing on upper limb muscles contraction consisting of biceps muscles only. The experiment is limited to the certain of upper limb movements that use in training. EMG is a division of bio signal; the bio signal analysis is the most complex analysis. Thus, the signal analysis is a complicated process that has to be through many phases of analysis [3]. EMG signal function as a control signal for the arm rehabilitation device. A system needs a model to estimate relationship between EMG and torque [4]. EMG signal based control could increase the social acceptance of the disabled and aged people by improving their quality of life. The joint torque is estimated from EMG signals using Artificial Neural Network [5, 6]. The Back Propagation Neural Network (BPNN) is used to find a solution for EMG-joint torque mapping. The EMG signal of the biceps brachii muscle act as the input of the ANN model whiles the desired torque act as the ideal output of the model. Hence the EMG signals considered the ‘intent’ of the system while the joint torque is the ‘controlled’ variable for the arm rehabilitation device [7]. The network is evaluated based on the best linear regression between the actual joint torque and the estimated joint torque [4]. The experiment results shows that the model can well represent the relationship between EMG signals and elbow joint torque by producing MSE of 0.13807 and average regression of 0.999. This paper is organized as follows. Section 1 explains brief introduction about this research work. Section 2 describes all the related works of this study. Section 3 demonstrates the method implemented for this work that covered the experimental setup, EMG data processing, desired torque determination and ANN technique. Section 4 presents the experimental results as