Classification of arm movement based on upper limb muscle signal for rehabilitation device

• Main Authors: Jali, Mohd Hafiz, Ibrahim, 'Iffah Masturah, Bohari, Zul Hasrizal, Sulaima, Mohamad Fani, Mohd Nasir, Mohamad Na'im
• Format: Article
• Language: English
• Published: Little Lion Scientific Islamabad Pakistan 2014
• Subjects: TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://eprints.utem.edu.my/id/eprint/13762/1/PUBLISH-CLASSIFICATION_OF_ARM_MOVEMENT_BASED_ON_UPPER_LIMB_MUSCLE_FOR_REHABILITATION_DEVICE.pdf; http://eprints.utem.edu.my/id/eprint/13762/; http://www.jatit.org/volumes/Vol68No1/15Vol68No1.pdf
• Institution: Universiti Teknikal Malaysia Melaka

Rehabilitation device is used as an exoskeleton for people who experience limb failure. Arm rehabilitation device may ease the rehabilitation programme for those who suffer arm dysfunctional. The device used to facilitate the tasks of the program should improve the electrical activity in the motor unit by minimising the mental effort of the user. Electromyography (EMG) is the techniques to analyse the presence of electrical activity in musculoskeletal systems. The electrical activity in muscles of disable person are failed to contract the muscle for movements. To prevent the muscles from paralysis becomes spasticity or flaccid the force of movements has to minimise the mental efforts. To minimise the used of cerebral strength, analysis on EMG signals from normal people are conducted before it can be implement in the device. The signals are collect according to procedure of surface electromyography for non-invasive assessment of muscles (SENIAM). The implementation of EMG signals is to set the movements’ pattern of the arm rehabilitation device. The filtered signal further the process by extracting the features as follows; Standard Deviation(STD), Mean Absolute Value(MAV), Root Mean Square(RMS), Zero Crossing(ZCS) and Variance(VAR). The extraction of EMG data is to have the reduced vector in the signal features for minimising the signals error than can be implement in classifier. The classification of features is by SOMToolbox using MATLAB. The features extraction of EMG signals is classified into several degree of arm movement visualize in U- Matrix form.