Tay Kim Gaik | Universiti Tun Hussein Onn Malaysia (original) (raw)

Papers by Tay Kim Gaik

Lecture notes in electrical engineering, 2023

Healthcare Informatics Research

Objectives: Various techniques for dorsal hand vein (DHV) pattern extraction have been introduced... more Objectives: Various techniques for dorsal hand vein (DHV) pattern extraction have been introduced using small datasets with poor and inconsistent segmentation. This work compared manual segmentation with our proposed hybrid automatic segmentation method (HHM) for this classification problem.Methods: Manual segmentation involved selecting a region-of-interest (ROI) in images from the Bosphorus dataset to generate ground truth data. The HHM combined histogram equalization and morphological and thresholding-based algorithms to localize veins from hand images. The data were divided into training, validation, and testing sets with an 8:1:1 ratio before training AlexNet. We considered three image augmentation strategies to enlarge our training sets. The best training hyperparameters were found using the manually segmented dataset.Results: We obtained a good test accuracy (91.5%) using the model trained with manually segmented images. The HHM method showed slightly inferior performance (76...

TELKOMNIKA (Telecommunication Computing Electronics and Control)

Optimization of light source wavelength for ammonia detection in surface water is presented in th... more Optimization of light source wavelength for ammonia detection in surface water is presented in this work. For the ammonia detection, the surface water sample is mixed with sodium chloride and nessler reagent, whereas the sensor head consists of unclad plastic optical fiber. The unclad region has a length of 1 cm and the cladding is removed by immersing it in acetone solution. Experimental results indicate that the output light intensity of the sensor has linear relationship with the ammonia concentration. At the wavelength of 510 nm, the output light increases linearly as the ammonia concentration varies from 0.07 mg/L to 8.97 mg/L. At the same wavelength, the proposed sensor achieves the sensitivity of 0.0139 (mg/L)-1 , accuracy of 99.59% and resolution of 0.72 µg/L. The analysis of light source wavelength reveals that a wavelength range from 450 nm to 580 nm produces the optimized performances. Within this wavelength range, the proposed sensor achieves sensitivity of higher than 0.01 (mg/L)-1 , accuracy of higher than 99% and resolution of less than 1 µg/L.

International Journal of Emerging Technology and Advanced Engineering

This study proposes using a dorsal hand vein authentication system using transfer learning from c... more This study proposes using a dorsal hand vein authentication system using transfer learning from convolutional neural network models of VGG16 and VGG19. The required images were obtained from Bosphorus Hand Vein Database. Among the 100 users, the first 80 users were treated as registered users, while the remaining users as unregistered users. 960 left-hand images of the registered users were trained during the training phase. Meanwhile, 100 images, consisting of 80 registered and 20 unregistered users, were randomly selected for the authentication application testing. Our results showed that VGG19 produced a superior validation accuracy as compared to that of VGG16 given by 96.9% and 94.3%, respectively. The testing accuracy of VGG16 and VGG19 is 99% and 100%, respectively. Since VGG19 is shown to outperform its shallower counterpart, we implemented a User Interface (UI) based on VGG19 model for dorsal hand vein identification. These findings indicate that our system may be deployed ...

2018 IEEE 7th International Conference on Photonics (ICP), 2018

The impact of random dispersion fluctuations on the saturation behavior of fiber optical parametr... more The impact of random dispersion fluctuations on the saturation behavior of fiber optical parametric amplifier was investigated. The coupled amplitude equations which represents the parametric amplification process were solved numerically. The saturation behavior was analyzed with variation of dispersion fluctuations amplitudes. It is found that the parametric gain with low fluctuations amplitude saturates quicker than that with high amplitude. This analysis is beneficial in understanding the evolution of the pump and signal power in the small and saturated regimes of parametric amplifiers.

IOP Conference Series: Materials Science and Engineering, 2020

There is a great development of Universiti Tun Hussein Onn Malaysia (UTHM) infrastructure since i... more There is a great development of Universiti Tun Hussein Onn Malaysia (UTHM) infrastructure since its formation in 1993. The development will be accompanied by the increasing demand for electricity. Hence, there is a need to forecast UTHM electricity consumption accurately so that UTHM can plan for future energy demand and utility saving decisions. Previous studies on UTHM electricity consumption prediction have been carried out using time series models, multiple linear regression and first-order fuzzy time series (FTS). The first-order FTS yield the best accuracy among these three methods. Previous forecasting problem showed higher order FTS can yield better accuracy. Therefore, in this study, the second-order FTS with trapezoidal membership function was implemented on the UTHM monthly electricity consumption from January 2009 to December 2018 to forecast January to December 2019 monthly electricity consumption. The procedure of the FTS and trapezoidal membership function was describ...

Communications in Computational and Applied Mathematics, Oct 22, 2020

International Journal of Pure and Apllied Mathematics, 2017

In this paper, we solved the forced perturbed Korteweg-de vries (FpKdV) with variable coefficient... more In this paper, we solved the forced perturbed Korteweg-de vries (FpKdV) with variable coefficient arises in nonlinear wave propagation in an elastic tube filled with a symmetrical stenosis filled with a viscous fluid by two numerical methods, namely method of lines and pseudospectral method. We then compared both numerical solution with its progressive wave solution. Both methods solve FpKdV equation with maximum absolute errors of 10 −2 .

International Journal of Integrated Engineering, 2021

Urbanization is a transition to improving our current world civilization. With the aid of educati... more Urbanization is a transition to improving our current world civilization. With the aid of education and technology, human gains the ability to communicate with others from far. Technology shortens the distance between people from other nations. Hence, energy has been the key to excel urbanization and improves human living standards. The relationship between economic and energy consumption has been a wide research topic since the past few decades. Poverty alleviation project has been part of the topic to discuss in World Summit on Sustainable Development in 2002 [1]. Access to sustainable energy had been acknowledged as an important element in poverty alleviation. The concept is to ensure people can obtain affordable energy services in daily life. Hence, energy poverty is considered part of the main section of the poverty issue. Developing countries are mostly cases that are trapped in the energy poverty problem. According to the International Energy Agency (IEA) 2017, the Asia region has around 439 million people who lack access to electricity with India is the rate countries [2]. Indonesia is the largest coal exporter and 8th in natural gas export among the ASEAN. Fossil fuel is an important income for national economic activities. Approximately 130 million Indonesians use raw biomass and kerosene as daily cooking or lighting purpose according to the report. The access to electricity in Indonesia is 97.01% but the access to clean fuel and technology for cooking is 56.64% in 2014 [3]. The energy poverty issue has long existed in Indonesia and facing a lot of challenges. Indonesia territories are a Abstract: Energy poverty is a global threat to human development path. This study is about the cointegration relationship between energy poverty and the economy of Indonesia for the period of 1995 to 2014. Autoregressive Distributed Lag (ARDL) model and vector error correction model (VECM) were used in this study to study the cointegration and causality analysis. Unit root test and stability test were adopted to increase the reliability and accuracy of the model. The analysis shows that parity purchase power (PPP) has a positive relationship with inflation (INF) in both long-run and short-run. Result shows in long-run, the increment of 1% for both energy consumption (EC) and PPP will result-1.12% and 0.032% effect respectively towards inflation in Indonesia. While for 1% increase in energy consumption is expected to give 1.5297% increment on inflation in short-run cases. Granger causality test shows only unidirectional causality between parity purchase power and inflation in both the long-run and short-run. Energy consumption only shows unidirectional causality toward inflation in the long-run. Overall mean increase of PPP or EC has a single direction influence on the inflation rate. The study can aid policy planning in eradication energy poverty.

In this paper, the application of the method of lines (MOL) to the FKdV equation is presented. Th... more In this paper, the application of the method of lines (MOL) to the FKdV equation is presented. The MOL is a general technique for solving partial differential equations by typically using finite-difference relationships for the spatial derivatives and ordinary differential equations (ODEs) for the time derivative. The MOL approach of the FKdV equation led to a system of ODEs. Solution of the system of ODEs was obtained by applying fourth order Runge Kutta (RK4) method. In order to show the accuracy of the presented method, the numerical solutions obtained were compared with progressive wave solution.

2021 2nd International Conference on Artificial Intelligence and Data Sciences (AiDAS), 2021

Voiceprint identification is a popular and highly develop potential technology that is used to id... more Voiceprint identification is a popular and highly develop potential technology that is used to identify characteristic of a person or subject. However, selection of classification algorithms behind the voiceprint identification system have to be optimized in order to maximize the performance and capability of the model. In this study, five classification algorithms were presented which are Logistic Regression (LR), K-Nearest Neighbour (KNN), Support Vector Machine (SVM), Naïve Bayes (NB) and Random Forest (RF). The performances of these algorithms were evaluated before and after the application of feature extraction technique. The result showed that SVM have the best performance in term of accuracy and AUC either with or without PCA. However, NB was identified as the fastest algorithm in term of computational time. The results also showed that feature extraction techniques have insignificant improvement over the classification of gender voiceprint dataset.

Dynamics of Continuous Discrete and Impulsive Systems-series B-applications & Algorithms, 2017

Propagation of undular bores with damping is considered in the framework of perturbed extended Ko... more Propagation of undular bores with damping is considered in the framework of perturbed extended Korteweg-de Vries (peKdV) equation. Two types of damping terms for the peKdV equation, namely linear and Chezy frictional terms, which describe the turbulent boundary layers in the fluid flow are considered. Solving the peKdV equation numerically using the method of lines shows that under the influence of damping, the lead- ing solitary wave of the undular bores will split from the nonlinear wavetrain, propagates and behaves like an isolated solitary wave. The amplitude of the leading wave will remain the same for some times before it starts to decay again at a larger time. In general the amplitude of the leading wave and the mean level across the undular bore decreases due to the effect of damping.

International Journal of Electrical and Computer Engineering (IJECE), 2021

Breast cancer is the second most common cancer occurring in women. Early detection through mammog... more Breast cancer is the second most common cancer occurring in women. Early detection through mammogram screening can save more women’s lives. However, even senior radiologists may over-diagnose the clinical condition. Machine learning (ML) is the most used technique in the diagnosis of cancer to help reduce human errors. This study is aimed to develop a computer-aided detection (CAD) system using ML for classification purposes. In this work, 80 digital mammograms of normal breasts, 40 of benign and 40 of malignant cases were chosen from the mini MIAS dataset. These images were denoised using median filter after they were segmented to obtain a region of interest (ROI) and enhanced using histogram equalization. This work compared the performance of artificial neural network (ANN), support vector machine (SVM), reduced features of SVM and the hybrid SVM-ANN for classification process using the statistical and gray level co-occurrence matrix (GLCM) features extracted from the enhanced ima...

International Journal of Trend in Scientific Research and Development, 2018

Indonesian Journal of Electrical Engineering and Computer Science, 2021

Biometric feature authentication technology had been developed and implemented for the security a... more Biometric feature authentication technology had been developed and implemented for the security access system. However, the known biometric features such as fingerprint, face and iris pattern failed to provide ideal security. Dorsal hand vein is the features beneath the skin which makes it not easily be duplicated and forged. It was expected to be used in biometric authentication technology to achieve an ideal accuracy with the uniqueness of its characteristics. In this study, 240 images of 80 users were obtained from Bosphorus Hand Vein Database. The images were then pre-processed by cropping ROI, mean filtering, CLAHE enhancing and histogram equalizing. The ROI was then segmented by implementing binarization. The local binary pattern (LBP) features were then extracted from the binarized image. The extracted features were sent to an artificial neural network (ANN) for the classification of the images. The training result shows that the LBP features and ANN can recognize the dorsal hand vein pattern quite well with 90% recognition rate. The NN net was then utilized in the MATLAB GUI program for testing 100 images (80 trained images of 80 users and 20 untrained images of 20 users) from the Bosphorus Hand Vein Database. The results revealed 100% accuracy in their matching result.

In this study, the derivation of mathematical model for the wave modulation through an incompress... more In this study, the derivation of mathematical model for the wave modulation through an incompressible viscous fluid contained in a prestressed thin stenosed elastic tube is presented. The artery is assumed to be incompressible, prestressed thin walled elastic tube with a symmetrical stenosis, whereas the blood is considered to be incompressible and Newtonian fluid. By utilizing the nonlinear equations of tube and fluid, the weakly nonlinear wave modulation in such a medium is examined. Employing the reductive perturbation method and considering the long-wave approximation, we showed that the third-order term in the perturbation expansion is governed by the dissipative nonlinear Schrodinger equation with variable coefficient. Our results shown that this type of equation admits a downward bell-shape wave propagates to the right as time increases with decreasing wave amplitude.

A fourth-order Runge-Kutta (RK4) Spreadsheet Calculator For Solving A System of Two First-Order O... more A fourth-order Runge-Kutta (RK4) Spreadsheet Calculator For Solving A System of Two First-Order Ordinary Differential Equations Using Visual Basic (VBA) Programming Motivated by the work of a spreadsheet solution of a system of ordinary differential equations (ODEs) using the fourth-order Runge-Kutta (RK4) method, a RK4 spreadsheet calculator for solving a system of two first-order ODEs was developed using VBA programming. The main feature of this spreadsheet calculator is to provide a user-friendly interface input form for users to insert the required information instead of the standard cells in Excel. Users are prompted step by step to give relevant information beginning from providing independent and dependent variables used in the system of ODEs. Secondly, they are required to give the interval for the independent variable, initial values for the dependent variables, a step size h and desired accuracy for computation. Thirdly, they have to enter the system of two first-order ODE...

Solving systems of ordinary differential equations (ODEs) by using the fourth-order Runge-Kutta (... more Solving systems of ordinary differential equations (ODEs) by using the fourth-order Runge-Kutta (RK4) method in classroom or in examinations is quite tedious, tiring and boring since it involves many iterative calculations. Hence, there is a need to design a suitable tool in teaching and learning the numerical methods involved, especially those for solving systems of ODEs. Here, we present a new approach to solving systems of ODEs by the RK4 method through the use of an EXCEL spreadsheet to tackle these drawbacks. In doing so, we employ the concept of relative row, relative column and fixed column in the spreadsheet to obtain the solution of systems of ODEs by the RK4 method. With the appropriate differential function given by the user, it is found that the way suggested here is faster than applying a scientific calculator and the solution obtained is significantly more accurate. Besides, the concept presented here can be extended to solve systems of ODEs up to n equations using the...

Even though approximating the definite differentiation by Richardson’s extrapolation method is st... more Even though approximating the definite differentiation by Richardson’s extrapolation method is straight forward, but its repetitive calculations are quite boring. Hence, there is a need to develop a suitable tool in teaching and learning for this method. Here, we developed a Richardson’s extrapolation Excel spreadsheet calculator to approximate the numerical differentiation that can be used by students and educators who need its full solution. With an appropriate function entered by users using 3-point central formula and a starting step size h, the full solution of Richardson’s extrapolation table up to level 4 can be obtained quickly and easily.

Article history: Received 27 August 2018 Received in revised form 14 December 2018 Accepted 2 May... more Article history: Received 27 August 2018 Received in revised form 14 December 2018 Accepted 2 May 2019 Available online 16 June 2019 Internal solitary waves have been observed in oceans all over the world. This paper looks at the effect of rapidly varying topography on the propagation of internal solitary waves in the framework of the variable-coefficient extended Korteweg-de Vries equation. We consider internal solitary wave is propagating in a two-layer fluid system. Here we let the depth of the upper layer to be smaller than the depth of lower layer such that initially an internal solitary wave of negative polarity is generated. The governing equation is solved numerically using the method of lines. Numerical results show that under the influence of variable topography, internal solitary waves would fission into few smaller solitary waves, an undular bore is generated for some time before transforms into a radiation wave or the internal solitary wave loses its amplitude when prop...