Pattern Recognition Of EMG Signal During Load Lifting Using Artificial Neural Network (ANN)

• Main Authors: Mohd Hafiz, Jali, Ahmad Izzuddin, Tarmizi, Zul Hasrizal, Bohari, Hazriq Izzuan, Jaafar, Mohamad Na'im, Mohd Nasir
• Format: Article
• Language: English
• Published: Institute Of Electrical And Electronics Engineers Inc. (IEEE) 2016
• Subjects: T Technology (General)
• Online Access: http://eprints.utem.edu.my/id/eprint/17260/1/Pattern%20Recognition%20Of%20EMG%20Signal%20During%20Load%20Lifting%20Using%20Artificial%20Neural%20Network%20%28ANN%29.pdf; http://eprints.utem.edu.my/id/eprint/17260/; http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7482179
• Institution: Universiti Teknikal Malaysia Melaka

This paper describes pattern recognition of electromyography (EMG) signal during load lifting using Artificial Neural Network (ANN). EMG is a method to measure and record the muscle activity when individuals perform certain operation and actions. This research will classify the EMG signal based on force apply to the arm due to the gravity act on it during load lifting. Recognizing pattern based on EMG signal is not an easy task because of the nonlinearities behavior of the signal. It required a good classifier to distinguish each pattern. The motivation of this project is to help the person suffer with hemiparesis to perform daily activities as well as to improve the lifestyle. It is important for patients to realize the hopes of hemiparesis after experiencing their inability to do activity as a normal human. Recognizing EMG pattern is crucially important for rehabilitation control that enables the patients to lift the heavy load despite of their muscle weaknesses. Therefore, a proper analysis of muscle behavior is necessary. The objectives of this research are to extract the important features of EMG signal using time domain analysis and to classify EMG signal based on load lifting using ANN. The experiment was performed to five subjects that were selected mainly based on criteria specified. The EMG signals are acquired at long head biceps brachii. Then, the subjects were asked to lift the loads of 2kg, 5kg, and 7kg. It is expected an accurate classifier which can recognize the pattern precisely and could be further used for arm rehabilitation control.