Saiful Zaimy Yahaya

Dynamic modeling and control of wheel-chaired elliptical stepping exercise

This paper presents the model development of Functional Electrical Stimulation (FES)-assisted wheel-chaired elliptical stepping exercise. This exercise specially designed for persons with hemiplegic or spinal cord injury (SCI). The design involves the development of humanoid, wheelchair and elliptical stepping machine models. A feedback control system is used to implement the control and coordinate the exercise movement. Knee extension of the subject is initiate to lead the elliptical stepping movement. The torque production and cadence speed of the exercise is observed at different setting of the control gain. The result obtained shows that the implementation of the exercise required an adequate amount of torque applied to produce the well coordinate knee movement for left and right knee. Integration with muscle model and implementation of more advance control system is required for further improvement to the exercise model.

Electrically Stimulated Quadriceps Muscle Model for Wheel-chaired Elliptical Stepping Exercise

This paper presents the development of physiologically based mathematical model of quadriceps muscle and the implementation on Functional Electrical Stimulation (FES) assisted wheel-chaired elliptical stepping exercise. Two muscles that make up quadriceps muscle namely rectus femoris and vasti were developed. The muscle models were integrated with humanoid, elliptical stepping ergometer and wheelchair model to simulate the wheel-chaired elliptical stepping exercise. During contraction, both rectus femoris and vasti muscles produce active and passive joint moments at knee and hip joint and hence drive the movement of the elliptical stepping exercise. At appropriate position and timing, a constant 220 μs of stimulation pulse width and 30 Hz of stimulation frequency is delivered to both left and right quadriceps muscles. The produced active, passive and total joint moments during the stimulation were recorded and analyzed. From the analysis, it was confirmed that the produced joint moments were able to drive the movement of the elliptical stepping exercise. The exercise may be performed smoothly with appropriate pattern of FES delivered to quadriceps muscle through the implementation of more advanced control strategy.

Gel Electrophoresis Image Segmentation with Kapur Method Based on Particle Swarm Optimization

Gel electrophoresis (GE) is an important tool in genomic analysis. It is a process of DNA, RNA and protein molecules separation using electric field applied to a gel matrix. This paper describes the image processing techniques applied on GE image to segment the bands from their background. Numerous pre-processing steps are applied on the image prior to the segmentation technique for the purpose of removing noise in the image. Then multilevel thresholding using Otsu method based on Particle Swarm Optimization is applied. The experimental results show that the PSO-Otsu successfully segmented all the bands.

Dynamic modeling and simulation of free swinging shank for hemiplegics

The lower extremities of a humanoid model having the parameters of stroke patient is designed to promote an understanding of its paralysis behaviour. The assemblies of the model are designed using SolidWork, a three dimensional computer-aided design (CAD) software and converted into SimMechanics models for further simulations. The humanoid-lower extremities model is designed based on anthropometric data of a healthy human and modified accordingly to changes of body composition and weight of stroke patients. Difference of 0.56 kg between paretic and non-paretic leg might gives significant results in control simulations. The developed model can offer prediction and much insight into the nature of movement generation and behaviour of the real stroke system.

Design and simulation of wheel-chaired elliptical stepping exercise for stroke rehabilitation

Stroke disease is one of the major killer diseases worldwide and most of the survivors will end with certain level of impairment. They commonly are wheelchair bounded and require scheduled rehabilitation exercise to regain their walking capability or mobility. This paper presents the design of elliptical stepping exercise ergometer for functional electrical stimulation (FES) assisted exercise. The concept of wheel-chaired cycling and elliptical stepping had been adapted in producing the ergometer design. The dynamic simulation has been performed on Visual Nastran 4D and Matlab Simulink to evaluate the performance of the exercise that includes the exercise ergometer, humanoid model and quadriceps muscle model. In the simulation work, the paretic leg (left side) is driven via FES-assisted while the non-paretic leg (right side) is driven via controlled knee joint torque. The result shows that the FES-assisted elliptical stepping exercises with voluntary non-paretic movement contribute better cadence speed control. Further improvement on the controller design is required to make sure suitable FES pattern can be delivered and better cadence speed control can be achieved in simulation environment as well as real implementation.

Self adaptive neuro-fuzzy control of FES-assisted paraplegics indoor rowing exercise

This paper describes the development of a self adaptive neuro-fuzzy control mechanism for FES-assisted indoor rowing exercise (FES-rowing). The FES-rowing is introduced as a total body exercise for rehabilitation of function of lower body through the application of functional electrical stimulation (FES). The neuro-fuzzy control technique is a control technique that combines fuzzy logic controller and a neural network, which makes the controller self tuning and adaptive. An adaptive control strategy is purposed to control the FES-rowing with the adaptation of the muscle fitness of the physiological based muscle model in the FLC. The adaptive control is able to modify the control law used by the FLC to cope with the muscle fatigue in adjusting the rowing ergometer inclination and generating the stimulation pulse width required by the system. This study indicates that the self adaptive neuro-fuzzy control developed provides an effective mechanism for automatically adjusting the ergometer inclination and regulating the stimulation pulse width for FES-rowing to overcome muscle fatigue.

Implementation of quadcopter as a teaching tool to enhance engineering courses

This paper proposed a new teaching technique for engineering courses based on the implementation of drone technology. In some engineering related courses, teaching and learning are difficult due to very complex theoretical and technical explanation need to be digested by the non experienced students. In Malaysia, quadcopter is one of the technologies that become popular among young generation due to its capabilities and interesting features in various application such as aerial photography, aerial monitoring as well as aerial racing tournament. The use of quadcopter thought to be one of the best ways to introduce some engineering concept through a practical exposure followed by project based learning. The concept is able to enhance the understanding as students are exposed to a practical and visual approach used during the learning process. The outcomes shows that once the student gain confidence in building the drone unit, they are ready to explore more on the engineering disciplines through the process. Open source flight software, Mission Planner, is used to configure every components used in the development.

Optimization of FLC parameters for optimal control of FES-assisted elliptical stepping exercise using GA and PSO

This paper presents the parameter optimization of the fuzzy logic controller (FLC) for the Functional Electrical Stimulation (FES)-assisted elliptical stepping exercise. The FLC is used to control the cadence of the elliptical stepping exercise for smooth exercise movement. Genetic algorithm (GA) and particle swarm optimization (PSO) are used to optimize the parameters of the FLC. Both algorithms are implemented in Matlab and simulated with the dynamic model of the elliptical stepping exercise. In the performance analysis, the GA has faster convergence compared to the PSO where both converged at 40th and 51st iterations, respectively. The root mean square error (RMSE) for the GA and PSO are 7.873 rpm and 7.087 rpm respectively showing that the PSO has better performance in terms of the RMSE. Both techniques also have shown good performance in stepping cycle completion. The use of the GA and PSO had led towards more efficient FLC control for the FES-assisted elliptical stepping exercise.

Implementation of HMLP network with different activation function for cervical cells classification

In this paper, the implementation of Hybrid Multilayered Perceptron (HMLP) network with two different activation functions has been studied. The study was conducted for PC based system and hardware based system and was evaluated in classifying the cervical cells data into it classes. For the hardware based system, this system was implemented in the 8051 microcontroller system. The structure of the HMLP network was arranged in two stages of hierarchy for acquiring four (4) types of input data and producing two outputs for each stage of hierarchy. The number of data used for training and testing of the HMLP network was 200 and 120 respectively. The HMLP network was trained using a Modified Recursive Prediction Error (MRPE) algorithm to obtain the appropriate parameters for the network. The result was evaluated in term of the percentage of accuracy, sensitivity, specificity, false negative and false positive. The result showed good performance of HMLP network for both types of activation function for the implementation on PC based system and hardware based system. For single number of hidden node, the performance of HMLP implemented with sigmoid and Elliot activation function was proven to be equals.

Assessing intensity of white matter hyperintensity and normal appearing white matter in healthy adults

There have been interest on white matter hyperintensity (WMH) and normal white matter (WM) changes reported but have not yet been fully characterized. Different image sequences of magnetic resonance imaging (MRI) scans may shows different gray scale intensity. However, it is difficult to differentiate the intensity of normal WM and WMH as their intensities are visually not much different. In this study, normal WM and WMH changes were investigated based on their intensity to determine the correlation of WMH types and severity in brain of healthy subjects. The assessment was performed by using fully automatic WMH detection and computing algorithms. The main brain regions were segregated into gray matter (GM), normal WM, cerebrospinal fluid (CSF) and non-brain tissue. From the results, it shows that there was significant difference seen between normal appearing WM and hyperintense WM in terms of their intensity levels. The study shows that the development of WMH is prevalent to the occasion of normal WM changes. This is shows that WMH intensity reflects the level of WMH classes and severity; however, further investigations are needed to improve their efficiency.