Kee Huong Lai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Kee Huong Lai has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Zarita Zainuddin
School of Mathematical Sciences Universiti Sains Malaysia 11800 USM Penang Malaysia
8 shared publications Pauline Ong
5 shared publications- Pauline Ong
Universiti Tun Hussein Onn Malaysia
3 shared publications Chee Kiong Sia
1 shared publication- David Andrew Bradley
Centre for Applied Physics and Radiation Technologies, School of Engineering and Technology, Sunway University, Petaling Jaya 47500, Selangor, Malaysia
1 shared publication - Jack Bee Chook
Department of Medical Sciences, School of Medical and Life Sciences Sunway University Bandar Sunway Selangor Darul Ehsan Malaysia
1 shared publication
Latest Publications
- Open Access
- 5 April 2023
- Published by Elsevier in Decision Analytics Journal
- Vol. 7
A deep convolutional neural network for vibration-based health-monitoring of rotating machinery
- 5 April 2023
- Published by Elsevier in Decision Analytics Journal
- Vol. 7
Open AccessA deep convolutional neural network for vibration-based health-monitoring of rotating machinery
- Open Access
- 20 September 2022
- Published by Wiley in Journal of Environmental and Public Health
- Vol. 2022 (1) , 4533957
Insights into Controlling the Spread of COVID‐19: A Study Inspired by Seven of the Earliest Vaccinated Countries
Background. The aim of the study is to derive deeper insights into the control of the spread of COVID‐19 during the second half of 2021, from seven countries that are among the earliest to have accelerated the deployment of COVID‐19 vaccines. Methodology. This study used data from the Global COVID‐19 Index and Google COVID‐19 Community Mobility Reports. Data was extracted on the 5th of each month from July to December 2021. Seven countries were selected—United Kingdom, United States of America, Israel, Canada, France, Italy, and Austria. The sample comprised number of new cases, hospitalisations, ICU admissions and deaths due to COVID‐19, government stringency measures, partial and full vaccination coverage, and changes in human mobility. Principal component analysis was conducted, and the results were interpreted and visualized through 2‐dimensional and 3‐dimensional plots to reveal the systematic patterns of the data. Results. The first three principal components captured around 77.3% of variance in the data. The first component was driven by the spread of COVID‐19 (31.6%), the second by mobility activities (transit, retail, and recreational) (24.3%), whereas the third by vaccination coverage, workplace‐related mobility, and government stringency measures (21.4%). Visualizations showed lower or moderate levels of severity in COVID‐19 during this period for most countries. By contrast, the surge in the USA was more severe especially in September 2021. Human mobility activities peaked in September for most countries and then receded in the following months as more stringent government measures were imposed, and countries began to grapple with a surge in COVID‐19 cases. Conclusion. This study delineated the spread of COVID‐19, human mobility patterns, widespread vaccination coverage, and government stringency measures on the overall control of COVID‐19. While at least moderate levels of stringency measures are needed, high vaccine coverage is particularly important in curbing the spread of this disease.
- 20 September 2022
- Published by Wiley in Journal of Environmental and Public Health
- Vol. 2022 (1) , 4533957
Open AccessInsights into Controlling the Spread of COVID‐19: A Study Inspired by Seven of the Earliest Vaccinated Countries
Background. The aim of the study is to derive deeper insights into the control of the spread of COVID‐19 during the second half of 2021, from seven countries that are among the earliest to have accelerated the deployment of COVID‐19 vaccines. Methodology. This study used data from the Global COVID‐19 Index and Google COVID‐19 Community Mobility Reports. Data was extracted on the 5th of each month from July to December 2021. Seven countries were selected—United Kingdom, United States of America, Israel, Canada, France, Italy, and Austria. The sample comprised number of new cases, hospitalisations, ICU admissions and deaths due to COVID‐19, government stringency measures, partial and full vaccination coverage, and changes in human mobility. Principal component analysis was conducted, and the results were interpreted and visualized through 2‐dimensional and 3‐dimensional plots to reveal the systematic patterns of the data. Results. The first three principal components captured around 77.3% of variance in the data. The first component was driven by the spread of COVID‐19 (31.6%), the second by mobility activities (transit, retail, and recreational) (24.3%), whereas the third by vaccination coverage, workplace‐related mobility, and government stringency measures (21.4%). Visualizations showed lower or moderate levels of severity in COVID‐19 during this period for most countries. By contrast, the surge in the USA was more severe especially in September 2021. Human mobility activities peaked in September for most countries and then receded in the following months as more stringent government measures were imposed, and countries began to grapple with a surge in COVID‐19 cases. Conclusion. This study delineated the spread of COVID‐19, human mobility patterns, widespread vaccination coverage, and government stringency measures on the overall control of COVID‐19. While at least moderate levels of stringency measures are needed, high vaccine coverage is particularly important in curbing the spread of this disease.
- Open Access
- 10 September 2021
- Published by Prague University of Economics and Business in Acta Informatica Pragensia
- Vol. 10 (2) , 138-154
A Neural Network-Based Approach in Predicting Consumers' Intentions of Purchasing Insurance Policies
Insurance is a crucial mechanism used to lighten the financial burden as it provides protection against financial losses resulting from unexpected events. Insurers adopt various approaches, such as machine learning, to attract the uninsured. B... Insurance is a crucial mechanism used to lighten the financial burden as it provides protection against financial losses resulting from unexpected events. Insurers adopt various approaches, such as machine learning, to attract the uninsured. B...
- 10 September 2021
- Published by Prague University of Economics and Business in Acta Informatica Pragensia
- Vol. 10 (2) , 138-154
Open AccessA Neural Network-Based Approach in Predicting Consumers' Intentions of Purchasing Insurance Policies
Insurance is a crucial mechanism used to lighten the financial burden as it provides protection against financial losses resulting from unexpected events. Insurers adopt various approaches, such as machine learning, to attract the uninsured. B... Insurance is a crucial mechanism used to lighten the financial burden as it provides protection against financial losses resulting from unexpected events. Insurers adopt various approaches, such as machine learning, to attract the uninsured. B...
- 7 August 2017
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 21 (2) , 515-527
A novel selection of optimal statistical features in the DWPT domain for discrimination of ictal and seizure-free electroencephalography signals
- 7 August 2017
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 21 (2) , 515-527
A novel selection of optimal statistical features in the DWPT domain for discrimination of ictal and seizure-free electroencephalography signals
- 1 January 2017
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 1870, 040039
A study on the performance comparison of metaheuristic algorithms on the learning of neural networks
- 1 January 2017
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 1870, 040039
A study on the performance comparison of metaheuristic algorithms on the learning of neural networks
- 1 July 2016
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 53, 143-162
An enhanced harmony search based algorithm for feature selection: Applications in epileptic seizure detection and prediction
- 1 July 2016
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 53, 143-162
An enhanced harmony search based algorithm for feature selection: Applications in epileptic seizure detection and prediction
- 1 January 2015
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 1682, 020026
On the use of harmony search algorithm in the training of wavelet neural networks
Wavelet neural networks (WNNs) are a class of feedforward neural networks that have been used in a wide range of industrial and engineering applications to model the complex relationships between the given inputs and outputs. The training of WNNs involves the configuration of the weight values between neurons. The backpropagation training algorithm, which is a gradient-descent method, can be used for this training purpose. Nonetheless, the solutions found by this algorithm often get trapped at local minima. In this paper, a harmony search-based algorithm is proposed for the training of WNNs. The training of WNNs, thus can be formulated as a continuous optimization problem, where the objective is to maximize the overall classification accuracy. Each candidate solution proposed by the harmony search algorithm represents a specific WNN architecture. In order to speed up the training process, the solution space is divided into disjoint partitions during the random initialization step of harmony search algorithm. The proposed training algorithm is tested onthree benchmark problems from the UCI machine learning repository, as well as one real life application, namely, the classification of electroencephalography signals in the task of epileptic seizure detection. The results obtained show that the proposed algorithm outperforms the traditional harmony search algorithm in terms of overall classification accuracy.
- 1 January 2015
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 1682, 020026
On the use of harmony search algorithm in the training of wavelet neural networks
Wavelet neural networks (WNNs) are a class of feedforward neural networks that have been used in a wide range of industrial and engineering applications to model the complex relationships between the given inputs and outputs. The training of WNNs involves the configuration of the weight values between neurons. The backpropagation training algorithm, which is a gradient-descent method, can be used for this training purpose. Nonetheless, the solutions found by this algorithm often get trapped at local minima. In this paper, a harmony search-based algorithm is proposed for the training of WNNs. The training of WNNs, thus can be formulated as a continuous optimization problem, where the objective is to maximize the overall classification accuracy. Each candidate solution proposed by the harmony search algorithm represents a specific WNN architecture. In order to speed up the training process, the solution space is divided into disjoint partitions during the random initialization step of harmony search algorithm. The proposed training algorithm is tested onthree benchmark problems from the UCI machine learning repository, as well as one real life application, namely, the classification of electroencephalography signals in the task of epileptic seizure detection. The results obtained show that the proposed algorithm outperforms the traditional harmony search algorithm in terms of overall classification accuracy.
- 1 January 2014
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 1605 (1) , 209-214
Efficient feature selection using a hybrid algorithm for the task of epileptic seizure detection
Feature selection is a very important aspect in the field of machine learning. It entails the search of an optimal subset from a very large data set with high dimensional feature space. Apart from eliminating redundant features and reducing computational cost, a good selection of feature also leads to higher prediction and classification accuracy. In this paper, an efficient feature selection technique is introduced in the task of epileptic seizure detection. The raw data are electroencephalography (EEG) signals. Using discrete wavelet transform, the biomedical signals were decomposed into several sets of wavelet coefficients. To reduce the dimension of these wavelet coefficients, a feature selection method that combines the strength of both filter and wrapper methods is proposed. Principal component analysis (PCA) is used as part of the filter method. As for wrapper method, the evolutionary harmony search (HS) algorithm is employed. This metaheuristic method aims at finding the best discriminating set of features from the original data. The obtained features were then used as input for an automated classifier, namely wavelet neural networks (WNNs). The WNNs model was trained to perform a binary classification task, that is, to determine whether a given EEG signal was normal or epileptic. For comparison purposes, different sets of features were also used as input. Simulation results showed that the WNNs that used the features chosen by the hybrid algorithm achieved the highest overall classification accuracy.
- 1 January 2014
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 1605 (1) , 209-214
Efficient feature selection using a hybrid algorithm for the task of epileptic seizure detection
Feature selection is a very important aspect in the field of machine learning. It entails the search of an optimal subset from a very large data set with high dimensional feature space. Apart from eliminating redundant features and reducing computational cost, a good selection of feature also leads to higher prediction and classification accuracy. In this paper, an efficient feature selection technique is introduced in the task of epileptic seizure detection. The raw data are electroencephalography (EEG) signals. Using discrete wavelet transform, the biomedical signals were decomposed into several sets of wavelet coefficients. To reduce the dimension of these wavelet coefficients, a feature selection method that combines the strength of both filter and wrapper methods is proposed. Principal component analysis (PCA) is used as part of the filter method. As for wrapper method, the evolutionary harmony search (HS) algorithm is employed. This metaheuristic method aims at finding the best discriminating set of features from the original data. The obtained features were then used as input for an automated classifier, namely wavelet neural networks (WNNs). The WNNs model was trained to perform a binary classification task, that is, to determine whether a given EEG signal was normal or epileptic. For comparison purposes, different sets of features were also used as input. Simulation results showed that the WNNs that used the features chosen by the hybrid algorithm achieved the highest overall classification accuracy.
- 1 January 2013
- Published by AIP Publishing in AIP Conference Proceedings
- p. 251-260
Wavelet neural networks initialization using hybridized clustering and harmony search algorithm: Application in epileptic seizure detection
Artificial neural networks (ANNs) are powerful mathematical models that are used to solve complex real world problems. Wavelet neural networks (WNNs), which were developed based on the wavelet theory, are a variant of ANNs. During the training phase of WNNs, several parameters need to be initialized; including the type of wavelet activation functions, translation vectors, and dilation parameter. The conventional k-means and fuzzy c-means clustering algorithms have been used to select the translation vectors. However, the solution vectors might get trapped at local minima. In this regard, the evolutionary harmony search algorithm, which is capable of searching for near-optimum solution vectors, both locally and globally, is introduced to circumvent this problem. In this paper, the conventional k-means and fuzzy c-means clustering algorithms were hybridized with the metaheuristic harmony search algorithm. In addition to obtaining the estimation of the global minima accurately, these hybridized algorithms also offer more than one solution to a particular problem, since many possible solution vectors can be generated and stored in the harmony memory. To validate the robustness of the proposed WNNs, the real world problem of epileptic seizure detection was presented. The overall classification accuracy from the simulation showed that the hybridized metaheuristic algorithms outperformed the standard k-means and fuzzy c-means clustering algorithms.
- 1 January 2013
- Published by AIP Publishing in AIP Conference Proceedings
- p. 251-260
Wavelet neural networks initialization using hybridized clustering and harmony search algorithm: Application in epileptic seizure detection
Artificial neural networks (ANNs) are powerful mathematical models that are used to solve complex real world problems. Wavelet neural networks (WNNs), which were developed based on the wavelet theory, are a variant of ANNs. During the training phase of WNNs, several parameters need to be initialized; including the type of wavelet activation functions, translation vectors, and dilation parameter. The conventional k-means and fuzzy c-means clustering algorithms have been used to select the translation vectors. However, the solution vectors might get trapped at local minima. In this regard, the evolutionary harmony search algorithm, which is capable of searching for near-optimum solution vectors, both locally and globally, is introduced to circumvent this problem. In this paper, the conventional k-means and fuzzy c-means clustering algorithms were hybridized with the metaheuristic harmony search algorithm. In addition to obtaining the estimation of the global minima accurately, these hybridized algorithms also offer more than one solution to a particular problem, since many possible solution vectors can be generated and stored in the harmony memory. To validate the robustness of the proposed WNNs, the real world problem of epileptic seizure detection was presented. The overall classification accuracy from the simulation showed that the hybridized metaheuristic algorithms outperformed the standard k-means and fuzzy c-means clustering algorithms.
- Open Access
- 1 January 2013
- Published by Scitechnol Biosoft Pvt. Ltd. in Australasian Medical Journal
- Vol. 06 (05)
RELIABLE EPILEPTIC SEIZURE DETECTION USING AN IMPROVED WAVELET NEURAL NETWORK
- 1 January 2013
- Published by Scitechnol Biosoft Pvt. Ltd. in Australasian Medical Journal
- Vol. 06 (05)
Open AccessRELIABLE EPILEPTIC SEIZURE DETECTION USING AN IMPROVED WAVELET NEURAL NETWORK