Mohd Hafiz Jali

JOINT TORQUE ESTIMATION MODEL OF SEMG SIGNAL FOR ARM REHABILITATION DEVICE USING ARTIFICIAL NEURAL NETWORK TECHNIQUES

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.

Predicting EMG Based Elbow Joint Torque Model Using Multiple Input ANN Neurons for Arm Rehabilitation

This paper illustrates the Artificial Neural Network (ANN) technique to predict the joint torque estimation model for arm rehabilitation device in a clear manner. This device acts as an exoskeleton for people who had failure of their limb. 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 prevent the muscles from paralysis becomes spasticity the force of movements should minimize the mental efforts. The objective of this work is to model the muscle EMG signal to torque using 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). The experimental results show that ANN can well represent EMG-torque relationship for arm rehabilitation device control.

Analysis of the Biceps Brachii Muscle by Varying the Arm Movement Level and Load Resistance Band

Biceps brachii muscle illness is one of the common physical disabilities that requires rehabilitation exercises in order to build up the strength of the muscle after surgery. It is also important to monitor the condition of the muscle during the rehabilitation exercise through electromyography (EMG) signals. The purpose of this study was to analyse and investigate the selection of the best mother wavelet (MWT) function and depth of the decomposition level in the wavelet denoising EMG signals through the discrete wavelet transform (DWT) method at each decomposition level. In this experimental work, six healthy subjects comprised of males and females (26 ± 3.0 years and BMI of 22 ± 2.0) were selected as a reference for persons with the illness. The experiment was conducted for three sets of resistance band loads, namely, 5 kg, 9 kg, and 16 kg, as a force during the biceps brachii muscle contraction. Each subject was required to perform three levels of the arm angle positions (30°, 90°, and 150°) for each set of resistance band load. The experimental results showed that the Daubechies5 (db5) was the most appropriate DWT method together with a 6-level decomposition with a soft heursure threshold for the biceps brachii EMG signal analysis.

Pattern recognition of EMG signal during load lifting using Artificial Neural Network (ANN)

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.

Movement intention detection using neural network for quadriplegic assistive machine

Biomedical signal lately have been a hot topic for researchers, as many journals and books related to it have been publish. In this paper, the control strategy to help quadriplegic patient using Brain Computer Interface (BCI) on basis of Electroencephalography (EEG) signal was used. BCI is a technology that obtain users thought to control a machine or device. This technology has enabled people with quadriplegia or in other words a person who had lost the capability of his four limbs to move by himself again. Within the past years, many researchers have come out with a new method and investigation to develop a machine that can fulfill the objective for quadriplegic patient to move again. Besides that, due to the development of bio-medical and healthcare application, there are several ways that can be used to extract signal from the brain. One of them is by using EEG signal. This research is carried out in order to detect the brain signal to controlling the movement of the wheelchair by using a single channel EEG headset. A group of 5 healthy people was chosen in order to determine performance of the machine during dynamic focusing activity such as the intention to move a wheelchair and stopping it. A neural network classifier was then used to classify the signal based on major EEG signal ranges. As a conclusion, a good neural network configuration and a decent method of extracting EEG signal will lead to give a command to control robotic wheelchair.

Features extraction of EMG signal using time domain analysis for arm rehabilitation device

Rehabilitation device is used as an exoskeleton for people who had failure of their limb. Arm rehabilitation device may help the rehab program whom suffers from arm disability. The device that is 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 prevent the muscles from paralysis becomes spasticity, the force of movements should minimize the mental efforts. Therefore, the rehabilitation device should analyze the surface EMG signal of normal people that can be implemented to the device. The signal is collected according to procedure of surface electromyography for non-invasive assessment of muscles (SENIAM). The EMG signal is implemented to set the movements’ pattern of the arm rehabilitation device. The filtered EMG signal was extracted for features of Standard Deviation (STD), Mean Absolute Value (MAV) and Root Mean Square (RMS) in time-domain. The extraction of EMG data is important to have the reduced vector in the signal features with less of error. In order to determine the best features for any movements, several trials of extraction methods are used by determining the features with less of errors. The accurate features can be use for future works of rehabilitation control in real-time.Rehabilitation device is used as an exoskeleton for people who had failure of their limb. Arm rehabilitation device may help the rehab program whom suffers from arm disability. The device that is 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 prevent the muscles from paralysis becomes spasticity, the force of movements should minimize the mental efforts. Therefore, the rehabilitation device should analyze the surface EMG signal of normal people that can be implemented to the device. The signal is collected according to procedure of surface electromyography for non-invasive assessment of muscles (SENIAM). The EMG signal is implemented to set the movements’ pattern of the arm rehabilita...

Achieving Thermal Power System Stability Using Load Frequency Controller

This paper focuses on load frequency control (LFC) of a single area thermal power system. The purpose of LFC is to minimize the transient varieties due to frequency deviation by ensuring zero steady state error. The frequency deviation normally caused by load perturbation. Hence, the primary goal of this paper is to design LFC for power system stability. Single area thermal power system comprises of governor framework, non-reheat turbine model and generator with load. The closed loop system performances in term of transient and steady state are observed and analyzed by injecting multifarious load perturbation. The simulation results are obtained via simulation works using MATLAB with SIMULINK toolbox.

Novel Rehab Devices’ Feature Extraction Analysis Using EMG Signal via Self-Organizing Maps (SOM)

Rehabilitation device is designed to be an exoskeleton for people who had limb failure that proven beneficial toward rehab program. The device used to facilitate the tasks of the program is able to improve the electrical activity in the motor unit and minimize the mental effort of the user. Electromyography (EMG) is the technique to analyze the presence of electrical activity in musculoskeletal systems related to muscle movement. To prevent from the muscle paralyzed, it is becoming spasticity that the force of movements should minimize the mental efforts needed. To achieve this, the rehab device should analyze the surface EMG signal of normal people to be implemented to the rehab device. The EMG signal collected using noninvasive method is implemented to set the movements’ pattern of the arm rehab device. The signal is filtered and extracted for three time-domain features of standard deviation (STD), mean absolute value (MAV), and root mean square (RMS). The features’ combinations are important to produce the best classification result with less error. To determine the best combination features for any movements, several trials of movements are used by determining the right combination using self-organizing maps (SOM) for the classification process.

Transformer mechanical integrity evaluation via unsupervised neural network (UNN) in smart grid network

This paper describes the classification of mechanical integrity of transformers using unsupervised neural networks (UNN). Transformers are the integral part of electrical system or smart grid networks since the last century. Self-Organizing Maps (SOM) is one type of UNN the widely used to do assessment on any system such as biomedical engineering, load contingency analysis and etc. The application of CIGRE standard and SOM in the research are enhancing the ability to do mechanical integrity assessment on the transformers for condition monitoring. Motivation for this research is to fill in the gap of excess FRA raw data for better assessment. This research proved that the new proposed method using SOM integrated with CIGRE standard able to do mechanical examination especially on core, winding and magnetic part of the transformer compared to current OMICRON SFRAnalyzer tool that employed Chinese Standard.

Development of Novel Fire Alarm Warning System Using Automated Remote Messaging Method

This paper discussed on design and development of fire warning system using automated remote messaging method. This device enables to alert the owner whenever fire occur that need rapid attention towards the building. This is maybe due to carelessness of user or gas leakage. Fire warning system is an existing project but it will be enhanced. This project discussed the design and implementation of a fire alarm system using the microcontroller which controlled the entire system. This system comprised of smoke detector that linked to PIC and GSM Modem. When smoke detected, the fire alarm will triggered and send a signal to the PIC. The PIC will process the data and transmit the signal to the GSM modem. The GSM modem will send message to alert the building owner. The owner can make further action by informing the nearest fire department. This module is applied for transferring of GSM SMS message to the owner mobile number. The devices can be the early and fast prevention system for building owner.