Wan Khairunizam Wan Ahmad
Thumbnail Image
Preferred name
Wan Khairunizam Wan Ahmad
Official Name
Wan Khairunizam, Wan Ahmad
Alternative Name
Wan, Khairunizam
Ahmad, Wan Khairunizam Wan
Khairunizam, W. A. N.
Main Affiliation
Scopus Author ID
57200576499
Researcher ID
E-6072-2011

Research Output

Filters

74
Reset filters

Settings
Now showing 1 - 10 of 74
Thumbnail Image
Publication

Virtual Markers based Facial Emotion Recognition using ELM and PNN Classifiers

2020-02-01 , Murugappan M. , Maruthapillai V. , Wan Khairunizam Wan Ahmad , Mutawa A.M. , Sruthi S. , Yean C.W.

Detecting different types of emotional expressions from the subject's face is important for developing intelligent systems for a variety of applications. This present work proposed virtual markers based on Facial emotion expression recognition using the Extreme Learning Machine (ELM) and Probabilistic Neural Network (PNN). A facial emotional expression database is developed with 55 undergraduate university students (male: 35, female: 20) of age range between 20-25 years with a mean age of 23.9 years. A HD webcam is used to capture the facial image and Haar Like features and Ada Boost classifier is used to detect the face and eyes through Open CV. A mathematical model based is used to place ten virtual markers called Action Units (AUs) on subjects face at a defined location. Later, Lucas-kanade optical flow algorithm is used to track the marker movement while the subject expressing different emotions and the distance between the center of the face to each marker is used as a feature for classifying emotions. One way Analysis of Variance (ANOVA) is used to test the statistical significance of the features and five fold cross-validation method is used to input the feature for classifiers. In this work, two non-linear classifiers namely, ELM and PNN are used for emotional expression classification. The experimental results give a maximum mean emotion classification rate of 88% and 92% in ELM and PNN classifiers, respectively. Maximum individual class accuracy of happiness-96%, surprise-94%, anger-92%, sadness-88%, disgust-90% and fear 89% is achieved using PNN. The experimental results confirm that the proposed system is able to distinguish six different emotional expressions and could be used as a potential tool for a variety of applications which include, e-learning, pain assessment, psychological counseling, human-machine interaction-based applications, etc.

View
Thumbnail Image
Publication

Study of eddy current density distribution in a contactless breast cancer detection mechanism using magnetic induction spectroscopy

2017-01-01 , Gowry Balasena , Shahriman Abu Bakar , Zulkarnay Zakaria , Ryojun Ikeura , Zuradzman Mohamad Razlan , Hazry Desa , Wan Khairunizam Wan Ahmad , Cheng Ee Meng , Mohd Afendi Rojan

Breast cancer is a throbbing disease that no longer needs an introduction. This is especially true among women due to their unique breast structure that naturally has more breast tissues compared to that of man’s. It is been forecasted that in 2015, a minimum of 60290 new cases of breast cancer will be reported. The goal of this study is to analytically evaluate the changes in the induced Eddy current densities as a function of di-electrical properties of the breast tissue with respect to tumor positioning as well as its size. This is achieved by running numerical simulations on the proposed mechanism of magnetic induction to detect tumors among healthy breast tissue via a 2D breast model configuration. The analytical results presented in this article, proved that the multi frequency magnetic induction principle is viable in detecting the breast lesions as small as 0.2 cm non-invasively through the distributions of the induced Eddy current density. While important pattern of the induced current were reflected when the tumors are located at the far ends of the breast diameter. The minimum results computational time with the proposed system is 10 s.

View
Thumbnail Image
Publication

Approach to enhance the heat transfer of valve seats through thermal analysis

2022-02-05 , Hassan M.A.S.M. , Zuradzman Mohamad Razlan , Shahriman Abu Bakar , Mohd Afendi Rojan , Wan Khairunizam Wan Ahmad , Ibrahim Z. , Ishak A.A. , Rahman A.A. , Mohd Ridzuan Mohd Jamir

The valve seat insert is a component of the engine cylinder head, whose primary function is to seal the combustion chamber and absorb the valve's heat, releasing it to the engine cylinder head. The valves experience high temperatures owing to high thermal loading and low heat absorption in the valve seat, which can potentially damage the engine. Therefore, the thermal characteristics of the valve seat must be optimised to increase the heat transmission between the valve and its seat. Here, three copper alloy valve seats, brass, beryllium copper, and bronze copper, were tested against the existing sintered iron valve seat, and their temperature maps were determined using actual engine operation conditions. The instantaneous heat transfer coefficients of the valves, seats, and engine cylinder head during the four-stroke cycle were evaluated using a one-dimensional thermal simulation analysis. The values obtained were used to assess the finite-element model using a three-dimensional thermal simulation in the Ansys software. The results show that the brass, beryllium-, and bronze-copper valve seats increased the overall heat flux by 4.46%, 4.16%, and 2.06%, respectively, compared to those for sintered iron. Thus, the results are essential to improve the thermal characteristics of the copper alloy valve seat imposed on the cylinder head. For validation, an experimental engine thermal survey and uncertainty magnification factors were used to validate the model. The results indicate that the maximum difference between the simulation and experimental values is 8.42%. Therefore, this approach offers a direct and comprehensible application for evaluating the temperature distribution, heat gradient, and heat flux of the cylinder head of air-cooled spark-ignition moped motorcycle engines using copper alloy valve seat materials at intermediate engine speeds. Furthermore, this method is applicable as a platform for the automotive industry to improve the heat transfer of the structural parts of internal combustion engines.

View
Thumbnail Image
Publication

Development of Computer Aided System for Classification of Gastrointestinal Lesions

2022-01-01 , Azian Azamimi Abdullah , Kamardin N.A.A. , Wan Khairunizam Wan Ahmad

Colorectal cancer is a major global health problem and is one of the major contributors to deaths worldwide. Because malignant transformations are rare, endoscopic resection of hyperplastic polyps exacerbates medical costs, including those for resection and unnecessary pathological assessment. The proposed work is based on assessment of exploratory data analysis and visualization, initial pre-processing step followed by selection of attributes and performance assessment of proposed supervised machine learning algorithms. For features selection, two method were implemented (Boruta and SelectFromModel (SFM) Random Forest) to compare the performances of the models. The comparative analysis of machine learning included Random Forest (RF), Support Vector Machines (SVM), Deep Neural Network (DNN). For Boruta algorithm, it is shown that RF has the highest accuracy of 90.32%, sensitivity of 93.05% and specificity of 95.95%. Therefore, the adenoma detection rate (ADR) is desirable for improvement. A computer-aided system is developed which offers the opportunity to evaluate the presence of colorectal polyps objectively during colonoscopy.

View
Thumbnail Image
Publication

Breast Cancer Detection and Classification on Mammogram Images Using Morphological Approach

2022-01-01 , Wan Azani Wan Mustafa , Azmi A.A. , Mohd Aminudin Jamlos , Alquran H. , Wan Khairunizam Wan Ahmad , Ismail S. , Alkhayyat A. , Haron J.

Breast cancer is one of the most common cancers affecting women worldwide. Mammography is the most well-known and effective method to detect early signs of breast cancer. The purpose of this paper is to detect breast cancer on the mammogram image to classify the disease through morphological techniques. Using conventional methods makes radiology difficult to detect cancer found in the patient's breast. This proposal can be divided into several elements, which are input database, image preprocessing, image segmentation, morphological analysis, and object recognition. First, image preprocessing will be done using the Weiner and Median filters. Second, the thresholding method for image segmentation will be performed, and lastly, morphology will remove imperfections introduced during the image segmentation process. Finally, the image is classified into two classes: normal and cancerous images. A median filter and 0.95 thresholding achieve an accuracy of 93.71%, a sensitivity of 94.36%, and a specificity of 82.53% for the cancerous images.

View
Thumbnail Image
Publication

Diagnosis of Heart Disease Using Machine Learning Methods

2021-01-01 , Azian Azamimi Abdullah , Alhadi N.A. , Wan Khairunizam Wan Ahmad

The World Health Organization (WHO) estimated 12 million deaths around the world appear each year from heart disease. Heart disease includes coronary artery disease, heart rhythm problem and heart defects. Each disease has similar symptoms but cause different effects and severity on patient. The common factors of heart disease include high blood pressure, diabetes, cholesterol and age. These factors are independent of each other; thus, the use of artificial intelligence and machine learning will be a suitable choice to model them. Correct diagnosis of heart disease is difficult due to the complicated processes and different system and it is vital because heart disease can lead to a heart attack, chest pain, stroke and sudden death. Hence, an accurate and early detection of heart disease with proper and adequate treatment is needed. The main aim of this research is to identify suitable feature selection method and machine learning algorithms for the diagnosis of heart disease. Chi Square Feature Selection (CSFS), Random Forest Feature Selection (RFFS), Forward Feature Selection (FFS), Backward Feature Selection (BFS) and Exhaustive Feature Selection (EFS) are the feature selection methods applied in this research. These feature selection methods are then implemented in the machine learning algorithms including Random Forest (RF), Support Vector Machine (SVM), Logistic Regression (LR) and k-Nearest Neighbour (KNN). The performance of these machine learning algorithms is evaluated through accuracy, sensitivity and specificity based on Confusion Matrix, ROC Curve and area under ROC (AUC). Based on the results, combination of RF with RFFS produced the highest accuracy value with 85.25% accuracy.

View
Thumbnail Image
Publication

Hurst exponent based brain behavior analysis of stroke patients using eeg signals

2021-01-01 , Choong W.Y. , Wan Khairunizam Wan Ahmad , Murugappan M. , Omar M.I. , Bong S.Z. , Ahmad Kadri Junoh , Zuradzman Mohamad Razlan , Shahriman Abu Bakar , Wan Azani Wan Mustafa

The stroke patients perceive emotions differently with normal people due to emotional disturbances, the emotional impairment of the stroke patients can be effectively analyzed using the EEG signal. The EEG signal has been known as non-linear and the neuronal oscillation under different mental states can be observed by non-linear method. The non-linear analysis of different emotional states in the EEG signal was performed by using hurst exponent (HURST). In this study, the long-range temporal correlation (LRTC) was examined in the emotional EEG signal of stroke patients and normal control subjects. The estimation of the HURST was more statistically significant in normal group than the stroke groups. In this study, the statistical test on the HURST has shown a more significant different among the emotional states of normal subject compared to the stroke patients. Particularly, it was also found that the gamma frequency band in the emotional EEG has shown more statistically significant among the different emotional states.

View
Thumbnail Image
Publication

Temperature Distribution Analysis of Lithium-Ion Polymer Battery Surface

2022-01-01 , Murali Rishan , Zuradzman Mohamad Razlan , Shahriman Abu Bakar , Suffer K.H. , Ibrahim Z. , Wan Khairunizam Wan Ahmad , Mohd Rudzuan Mohd Nor , Muhammad Faisal Hamidi @ Abdul Rani

The main objective of this study is to investigate the heat load generated by the Lithium-ion (Li-ion) battery during the completion of the cycle. Besides that, the objective is also to identify the most affected surface of the Li-ion battery towards the temperature during the charging and discharging process. An experiment is carried out for five different conditions of battery to obtain the data for heat load calculation purposes. The five conditions are differences in discharge ampere. From the result obtained there are differences in heat load generated by the battery during the charging and discharging process for every condition. Furthermore, the greater the discharge ampere, the lower the time taken for the battery to discharge and the higher the heat load generated by the battery. Besides that, an experiment to investigate the temperature distribution along the experiment is also carried out. Four surfaces of battery (front, right, left, back in vertical position of battery) are put into concern in obtaining the temperature distribution. Every surface gives a different temperature distribution during the experiment. Surface 4 recorded the highest average temperature distribution. Thus, the cooling system will consider the cooling capacity at this surface.

View
Thumbnail Image
Publication

Heat transfer improvement in simulated small battery compartment using metal oxide (CuO)/deionized water nanofluid

2020-02-01 , Bin-Abdun N.A. , Zuradzman Mohamad Razlan , Shahriman Abu Bakar , Voon Chun Hong , Ibrahim Z. , Wan Khairunizam Wan Ahmad , Mohd Ridzuan Mohd Jamir

Improving the heat transfer coefficient of working fluids is essential for achieving the best performance of manufacturing systems. As a replacement of conventional working fluids, nanofluids have a high potential for improving this heat transfer coefficient. However, nanofluids are seldom implemented in actual systems, and several factors should be considered before actual application. Accordingly, this study investigated the thermophysical properties and heat transfer rate of CuO/deionized water nanofluid with and without sodium dodecyl sulfate (SDS) surfactants. Three different volumetric concentrations of the nanofluid were prepared using a two-step preparation method. The experimental steps were divided into two phases: static and dynamic. In these experiments, the thermophysical properties of the prepared nanofluids and the heat transfer coefficient were measured using an apparatus designed based on an actual heat exchanger for a lithium ion polymer battery compartment. The effects of flow rate and surfactants on the heat transfer rate of the nanofluids with varying volumetric concentrations of 0.08%, 0.16%, and 0.40% were analyzed. The results indicate that the heat transfer rate increases considerably as the flow rate increases from 0.5 L/min to 1.2 L/min and with the presence of surfactants. The highest heat transfer rate was obtained at a 0.40% volumetric concentration of CuO/deionized water nanofluid with SDS surfactant.

View
Thumbnail Image
Publication

Performance Comparison of Machine Learning Algorithms for Classification of Chronic Kidney Disease (CKD)

2020-06-17 , Azian Azamimi Abdullah , Hafidz S.A. , Wan Khairunizam Wan Ahmad

Kidney is one of the vital organs in a human body while ironically, chronic kidney disease (CKD) is one of the main causes of death in the world. Due to the low rate of loss of kidney function, the disease is often overlooked until it is in a really bad condition. Dysfunctional kidney may lead to accumulation of wastes in blood which would affect several other systems and functions of the body such as blood pressure, red blood cell production, vitamin D and bone health. Machine learning algorithms can help in classifying the patients who have CKD or not. Even though several studies have been made to classify CKD on patients using machine-learning tool, not many researchers perform pre-processing and feature selection technique to obtain quality and dependable result. Machine learning used with feature selection techniques are shown to have better and more dependable result. In this study, feature selection methods such as Random Forest feature selection, forward selection, forward exhaustive selection, backward selection and backward exhaustive selection were identified and evaluated. Then, machine learning classifiers such as Random Forest, Linear and Radial SVM, Naïve Bayes and Logistic Regression were implemented. Lastly, the performance of each machine-learning model was evaluated in terms of accuracy, sensitivity, specificity and AUC score. The results showed that Random Forest classifier with Random Forest feature selection is the most suitable machine learning model for classification of CKD as it has the highest accuracy, sensitivity, specificity and AUC with 98.825%, 98.04%, 100% and 98.9% respectively which outperformed other classifiers.

View