Shamshul Bahar Yaakob
Thumbnail Image
Preferred name
Shamshul Bahar Yaakob
Official Name
Shamshul Bahar, Yaakob
Alternative Name
Yaakob, Shamsul Bahar
Yaakob, Shamshul B.
Bahar Yaakob, Shamshul
Yaakob, Sb
Yaakob, S. B.
Yaakob, Shamshul Bahar
Main Affiliation
Scopus Author ID
24825943100
Researcher ID
EDU-6433-2022

Research Output

Filters

1
Reset filters

Settings
Now showing 1 - 7 of 7
No Thumbnail Available
Publication

Automated diagnosis of diabetic retinopathy using deep learning: on the search of segmented retinal blood vessel images for better performance

2023 , Mohammad Badhruddouza Khan , Mohiuddin Ahmad , Shamshul Bahar Yaakob , Rahat Shahrior , Mohd Abdur Rashid , Hiroki Higa

Diabetic retinopathy is one of the most significant retinal diseases that can lead to blindness. As a result, it is critical to receive a prompt diagnosis of the disease. Manual screening can result in misdiagnosis due to human error and limited human capability. In such cases, using a deep learning-based automated diagnosis of the disease could aid in early detection and treatment. In deep learning-based analysis, the original and segmented blood vessels are typically used for diagnosis. However, it is still unclear which approach is superior. In this study, a comparison of two deep learning approaches (Inception v3 and DenseNet-121) was performed on two different datasets of colored images and segmented images. The study’s findings revealed that the accuracy for original images on both Inception v3 and DenseNet-121 equaled 0.8 or higher, whereas the segmented retinal blood vessels under both approaches provided an accuracy of just greater than 0.6, demonstrating that the segmented vessels do not add much utility to the deep learning-based analysis. The study’s findings show that the original-colored images are more significant in diagnosing retinopathy than the extracted retinal blood vessels.

View
No Thumbnail Available
Publication

Finite elementary analysis of electrical performance for glass type insulator under the inclination effects

2025-07 , Ting Yan Su , Shamshul Bahar Yaakob , Amizah Mohd. Ariffen

This paper presents the modelling of a glass type of insulator with a voltage rating of 132 kV. The insulators play a critical role in transmission lines to ensure the stability and reliability of the system. Glass insulators are still widely used in overhead transmission systems because of their dielectric strength capability. Whenever faults occur in the transmission line or system, a considerable cost for maintenance and repair is required. The outdoor application of the insulator has resulted in exposure to various service conditions such as weather, pollution and lightning. Indeed, the inclination effect under the wind load is one of the significant challenges for outdoor insulators. Therefore, this paper studied the electrical performance of the 132 kV glass insulators under the inclination effects through Finite Elementary Modelling (FEM). In this simulation, the model of the glass insulator is constructed in four different inclination angles using the modelling software Ansys Maxwell 3D. From the results, the electric field distribution for the insulator became uneven when the insulator was inclined. With the reduction of clearance distance under inclination effects, the localised electric field form may increase the electrical discharge and arching likelihood. In a worst-case scenario, the flashover may cause faulty transmission equipment. In either case, the electrical performance of the insulator is reduced under the inclination effects.

View
Thumbnail Image
Publication

Power system investment planning based on double layer boltzmann machine method

2018 , Shamshul Bahar Yaakob

Quadratic programming problems arise in many scientific and engineering applications for a long time. Meta-heuristic methods have been employed so as to obtain optimal solutions for the problems such as artificial neural network, genetic algorithm, simulated annealing, ant colony optimization and others. Great progress has been made in research on artificial neural networks in recent decades. Artificial neural networks have been applied to many fields such as pattern recognition, forecasting, data mining, multiple objective decision making and combinatorial optimization problems. Recently, power-supply failures have caused major social losses. Therefore, power supply systems need to be highly reliable. The objective of this research is to present a significant and effective method of determining a productive investment to protect a power supply system from damage. Previous studies have examined the utility and social impact of investment in distributed generation. In this research, an artificial neural network has been applied to solve the portfolio selection problem efficiently. The reliability and risks of each of the units are evaluated with a variance-covariance matrix, and the effects and expenses of replacement are analysed. The mean-variance analysis is formulated as a mathematical program with the following two objectives which are to minimize the risk and to maximize the expected return. Finally, a structural learning model of a mutual connection neural network (double layered Boltzmann machine) is used to solve problems defined by mixed-integer quadratic programming, and is employed in the mean-variance analysis. This method is applied to a power system network in the Tokyo Metropolitan area. As a result, it was shown that the structural learning can provide an alternative solution for decision makers to select the best solution from their respective point of view, as a numerical example shows. The simulation also showed that computational cost is significantly decreased compared with a conventional Boltzmann machine. The obtained results show that the selection, investment expense rate to units and reduced computation time can be prolonged to increase cost savings.

View
No Thumbnail Available
Publication

Modelling and analysis of electrical performance outdoor glass insulator under various services and lightning impulse

2023 , TY Su , Shamshul Bahar Yaakob , Amizah Md. Ariffen

This paper is focus on modelling of glass type insulator with voltage rating of 275 kV. The glass insulators are still widely served in overhead transmission line because of its high dielectric strength capability. However, their outdoor application has resulted in the exposure to the various service conditions such as weather, pollution and lightning conditions. Further, the inclination effect of the insulator under the nominal voltage and lightning impulse is modelling through Finite Elementary Method (FEM). Then, the model of glass insulator is constructed in three different inclination angles by using the Ansys Maxwell 3D for simulation purpose. The results show the inclined insulator due to the wind load effect has the lowest breakdown voltage at most 53.33% compared with the vertical insulator. Under the outdoor environment factors such as humid, wet and contamination, the localized electric field and current density had increased significantly. Consequently, this situation may cause the power losses, localized heating effect also reduces the electrical performance of the insulators.

View
Thumbnail Image
Publication

Corneal arcus classification for hyperlipidemia detection using gray level co-occurrence matrix features

2020-01-07 , Ramlee R.A. , Subramaniam S.K. , Shamshul Bahar Yaakob , Ahmad Shukri Fazil Rahman , Saad N.M.

The arcus cornea is an eye problem that is often encountered among older people, but the situation is risky to teenagers and young people, in which it gave a sign the presence of lipid abnormalities in their blood and the risk of disease problems such as diabetes and heart disease. This paper presents the classification of the arcus cornea, using the extraction of texture features of the gray level co-occurrence matrix, along with several models of the classifiers, namely as scale conjugate gradient, Bayesian regulation, and Levenberg-Marquardt. Percentage fractions for training, testing and validation for classifier are 70%, 15%, and 15% respectively. The comparison of the classifiers used by the past researchers for classification the eye abnormalities, also were analyzed and studied in this work. In this experiment, a total of 125 image eyes were used, consisting of two classes of the eye image, which is normal and abnormal. The best result demonstrated in this proposed framework using Bayesian regulation classifier is, a sensitivity of 96%, and a specificity of 100%. However, this classifier did not achieve perfectly classification or an accuracy of 100%. Nevertheless, it is able and evident that the system is effective by the output of 98.4% accuracy.

View
No Thumbnail Available
Publication

Supercapacitor’s parameter calculation based on three branch equivalent circuit model under different constant charging current

2023 , Makhdoom Abdul Jabbar , Muhammad Izuan Fahmi Romli , Shamshul Bahar Yaakob , Liew Hui Fang , Md Shahrukh Adnan Khan

Supercapacitor is a type of energy storage with higher capacitance value compared to the normal capacitor. But it has lower voltage level compared to normal capacitor. However, it can be charged with high current and provide higher current to the load when needed when compared to the same size energy storage such as battery. The Three Branch Equivalent Circuit is one of the simple yet accurate model that has been proposed. The parameter of the Three Branch model included the capacitance, resistance and a unit of voltage dependent capacitance. The Parameter needed to be calculated accurately as it depends heavily on the terminal voltage of the supercapacitor at respective time which obtained through a charging and self-discharging experiment under constant current charging. The different constant charging current give effect toward the parameter calculation as it manipulates the rate of charging and self-discharging. This paper will calculate the parameter of supercapacitor based on the Three Branch model under different constant charging current and compared the result using the simulation to show the accuracy of the model. The parameter obtained throughout the study shows a high accuracy especially the parameters obtained using higher charging current.

View
Thumbnail Image
Publication

Investment planning problem in power system using Artificial Neural Network

2018-12 , Shamshul Bahar Yaakob , Siti Hajar Mohd Tahar , Amran Ahmed

This paper presents a model to solve Distribution Expansion Planning (DEP) problem. An effective method is proposed to determine an optimal solution for strategic investment planning in distribution system. The proposed method will be formulated by using meanvariance analysis (MVA) approach in the form of mixed-integer quadratic programming problem. Its target is to minimize the risk and maximize the expected return. The proposed method consists of two layers neural networks combining Hopfield network at the upper layer and Boltzmann machine in the lower layer resulting the fast computational time. The originality of the proposed model is it will delete the unit of the lower layer, which is not selected in upper layer in its execution. Then, the lower layer is restructured using the selected units. Due to this feature, the proposed model will improve times and the accuracy of obtained solution. The significance of output from this project is the improvement of computational time and the accurate solution will be obtained. This model might help the decision makers to choose the optimal solution with variety options provided from this proposed method. Therefore, the performance of strategic investment planning in solving DEP problem certainly enhance

View