Ahmad Kadri Junoh
Thumbnail Image
Preferred name
Ahmad Kadri Junoh
Official Name
Ahmad Kadri, Junoh
Alternative Name
Junoh, Ahmad Kadri
Junoh, A. K.
Ahmad Kadri, Junoh
Junoh, A. K.
Kadri, J. Ahmad
Main Affiliation
Scopus Author ID
38561331300
Researcher ID
FZU-4175-2022

Research Output

Filters

33
Reset filters

Settings
Now showing 1 - 10 of 33
Thumbnail Image
Publication

Tropical algebra based adaptive filter for noise removal in digital image

2020-07-01 , Abdurrazzaq A. , Mohd I. , Ahmad Kadri Junoh , Zainab Yahya

The concept of the tropical algebra was first introduced to solve problems in mathematical economy such as optimization and approximation problems. In this paper, the concept of tropical algebra is used to build an image filtering algorithm. By using this concept, the lowest and highest pixel values are considered in determining the new pixel value. In addition, adaptive window will also be implemented to help the filtering process become more effective at high density noise. Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) are used to evaluate the output image quality produced by the filtering method. In this experiment, the performance of proposed method and existing methods such as switching median filter (SMF), adaptive fuzzy noise switching median filter (NAFSM), modified decision based on unsymmetric trimmed median filter (MDBUTMF), adaptive type-2 fuzzy filter (AT2FF)), based on pixel density filters (BPDF), different applied median filters (DAMF), and tropical SVD filters (TSVD) will be compared. PSNR and SSIM results show that the proposed method outperforms most existing methods: SMF (27.13/0.7954), NAFSM (29.11/0.8459), MDBTUMF (29.18/0.8462), AT2FF (28.10/0.8159), BPDF (25.65/0.7545), DAMF (31.20/0.8833), TSVD (28.39/0.7906), and proposed (31.26/0.8827).

View
Thumbnail Image
Publication

New Problem Transformation Method Based on the Local Positive Pairwise Dependencies among Labels

2020-03-01 , Alluwaici M. , Ahmad Kadri Junoh , Alazaidah R.

Multi-label classification (MLC) generalises the conventional binary and multi-class classification by allowing instances to be linked with one or more of the class labels. Therefore, class labels in MLC are not mutual exclusive as in single label classification (SLC). Consequently, the search space of the MLC problem is large compared with that of SLC and grows in an exponential way. One main approach to solve MLC problem is through forcing instances to be associated with only one class label. This approach of handling the problem of MLC has been widely known as problem transformation method (PTM). Existing PTMs depend on the frequency of class labels as a transformation criterion, which causes several problems such as imbalance class distribution, complicating the training phase and most importantly decreasing the accuracy of the classification task. Therefore, in this paper, a new PTM is proposed based on the positive local dependencies among labels. The proposed PTM aims to facilitate capturing the most accurate positive dependencies among labels and hence improve the predictive performance of the classification task. Experiments on several datasets revealed the superiority of the proposed PTM compared with the existing PTMs, especially with high cardinality datasets.

View
Thumbnail Image
Publication

An Experimental Framework for Assessing Emotions of Stroke Patients using Electroencephalogram (EEG)

2020-06-17 , Wan Khairunizam Wan Ahmad , Yean C.W. , Murugappan M. , Ahmad Kadri Junoh , Zuradzman Mohamad Razlan , Wan Azani Wan Mustafa , Shahriman Abu Bakar , Ibrahim Z. , Nurhafizah S.

This research aims to assess the emotional experiences of stroke patients using Electroencephalogram (EEG) signals. Since emotion and health are interrelated, thus it is important to analyse the emotional states of stroke patients for neurofeedback treatment. Moreover, the conventional methods for emotional assessment in stroke patients are based on observational approaches where the results can be fraud easily. The observational-based approaches are conducted by filling up the international standard questionnaires or face to face interview for symptom recognition from psychological reactions of patients and do not involve experimental study. This paper introduces an experimental framework for assessing emotions of the stroke patient. The experimental protocol is designed to induce six emotional states of the stroke patient in the form of video-audio clips. In the experiments, EEG data are collected from 3 groups of subjects, namely the stroke patients with left brain damage (LBD), the stroke patients with right brain damage (RBD), and the normal control (NC). The EEG signals exhibit nonlinear properties, hence the non-linear methods such as the Higher Order Spectra (HOS) could give more information on EEG in the signal's analysis. Furthermore, the EEG classification works with a large amount of complex data, a simple mathematical concept is almost impossible to classify the EEG signal. From the investigation, the proposed experimental framework able to induce the emotions of stroke patient and could be acquired through EEG.

View
Thumbnail Image
Publication

New white blood cell detection technique by using singular value decomposition concept: White blood cell detection technique

2021-01-01 , Abdurrazzaq A. , Ahmad Kadri Junoh , Zainab Yahya , Mohd I.

Segmentation technique is a commonly used method to detect white blood cells. The segmentation technique aims to separate the blood image into several parts based on the similarity of features in the image. Therefore, the detection results do not completely contain white blood cells but also contain other parts with similar features to white blood cells. This study proposes a new detection technique that directly considers the features of white blood cells using singular value decomposition approach. The experimental results show that the proposed method works better in detecting white blood cell nuclei than the existing methods. The existing methods only work well for white blood cells with dense color intensities such as basophil and monocyte. Meanwhile, the proposed method works well overall as it directly compares the level of similarity in white blood cells.

View
Thumbnail Image
Publication

Distance weighted K-means algorithm for center selection in training radial basis function networks

2019-03-01 , Aik L.E. , Hong T.W. , Ahmad Kadri Junoh

The accuracies rates of the neural networks mainly depend on the selection of the correct data centers. The K-means algorithm is a widely used clustering algorithm in various disciplines for centers selection. However, the method is known for its sensitivity to initial centers selection. It suffers not only from a high dependency on the algorithm's initial centers selection but, also from data points. The performance of K-means has been enhanced from different perspectives, including centroid initialization problem over the years. Unfortunately, the solution does not provide a good trade-off between quality and efficiency of the centers produces by the algorithm. To solve this problem, a new method to find the initial centers and improve the sensitivity to the initial centers of K-means algorithm is proposed. This paper presented a training algorithm for the radial basis function network (RBFN) using improved K-means (KM) algorithm, which is the modified version of KM algorithm based on distance-weighted adjustment for each centers, known as distance-weighted K-means (DWKM) algorithm. The proposed training algorithm, which uses DWKM algorithm select centers for training RBFN obtained better accuracy in predictions and reduced network architecture compared to the standard RBFN. The proposed training algorithm was implemented in MATLAB environment; hence, the new network was undergoing a hybrid learning process. The network called DWKM-RBFN was tested against the standard RBFN in predictions. The experimental models were tested on four literatures nonlinear function and four real-world application problems, particularly in Air pollutant problem, Biochemical Oxygen Demand (BOD) problem, Phytoplankton problem, and forex pair EURUSD. The results are compared to proposed method for root mean square error (RMSE) in radial basis function network (RBFN). The proposed method yielded a promising result with an average improvement percentage more than 50 percent in RMSE.

View
Thumbnail Image
Publication

A comparative study on interior acoustic comfort level of compact cars using data mining approach

2020-01-01 , Azuddin K.A. , Ahmad Kadri Junoh , Mohamed Z. , Md. Tasyrif bin Abdul Rahman

Vehicle acoustic comfort is one of the ergonomic measurement criteria that are essential for car occupants. Furthermore, interior cabin noise of a car may affect the driver's concentration when driving. This study is to investigate the noise comfort level of car interior on several compact cars. The objective is to measure interior cabin noise for all three cars and then to compare their acoustic comfort level using subfield data mining approach. A deduction was made to rate the best car among the three in term of acoustic comfort. The interior cabin noise was obtained for the cases where engine speed is varied while the cars are in stationary and moving condition. The noise was assessed according to pre-determined subjective and objective criteria. The sound quality parameters was assessed by regression analysis. In subjective assessment, the recorded noise was evaluated based on jury assessment. Then, the data mining approach was implemented to illustrate the noise level. The collected noise data were divided into five clusters through hierarchical clustering method. To assess the accuracy of noise data clusters, the method of k-nearest neighbours was performed and the results show a high accuracy rate (> 95%). Finally, the interior noise of the three cars was compared by using the analysis of variation. The vehicle acoustic comfort index was produced for the three cars tested in this study. In addition, the acoustic quality among the three cars is presented using anova. Annoyance index of the three cars was generated using data mining method. From the results, Axia car model has the best acoustic comfort compared to the other two cars by objective evaluation. By subjective evaluation, Axia car model recorded the lowest level of annoyance.

View
Thumbnail Image
Publication

Determination of flexibility of workers working time through Taguchi method approach

2020-10-01 , Saidat S. , Ahmad Kadri Junoh , Wan Zuki Azman Wan Muhamad , Zainab Yahya

Human factor is one of the important elements in manufacturing world, despite their important role in improvement the production flow, they have been neglected while scheduling for many decades. In this paper the researchers taken the human factor throughout their job performance weightage into consideration while using job shop scheduling (JSS) for a factory of glass industry, in order to improving the workers' flexibility. In other hand, the researchers suggested a new sequence of workers' weightage by using Taguchi method, which present the best flexibility that workers can have, while decreasing the total time that the factory need to complete the whole production flow.

View
No Thumbnail Available
Publication

Hybrid deep learning for estimation of state-of-health in lithium-ion batteries

2025-02 , Denis Eka Cahyani , Langlang Gumilar , Arif Nur Afandi , Aji Prasetya Wibawa , Ahmad Kadri Junoh

Lithium-ion (li-ion) batteries have a high energy density and a long cycle life. Lithium-ion batteries have a finite lifespan, and their energy storage capacity diminishes with use. In order to properly plan battery maintenance, the state of health (SoH) of lithium-ion batteries is crucial. This study aims to combine two deep learning techniques (hybrid deep learning), namely convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM), for SoH estimation in li-ion batteries. This study contrasts hybrid deep learning methods to single deep learning models so that the most suitable model for accurately measuring the SoH in lithium-ion batteries can be determined. In comparison to other methodologies, CNN-BiLSTM yields the best results. The CNN-BiLSTM algorithm yields RMSE, mean square error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) in the following order: 0.00916, 0.000084, 0.0048, and 0.00603. This indicates that CNN-BiLSTM, as a hybrid deep learning model, is able to calculate the approximate capacity of the lithium-ion battery more accurately than other methods.

View
Thumbnail Image
Publication

Extended median filter for salt and pepper noise

2017-01-01 , Bilal Charmouti , Ahmad Kadri Junoh , Wan Zuki Azman Wan Muhamad , Muhammad Naufal Mansor , Mohd Zamri Hasan , Mohd Yusoff Mashor

Image have a significant importance in many fields in human life such as, in medicine, photography, biology, astronomy, industry and defence. Thus, it attracts the attention of large number of researchers, among them those interested in preserving the image features from any factors that may reduce the image quality. One of these factors is the noise which affects the visual aspect of the image and makes others image processing more difficult. Thus far, solving this noise problem remains a challenge point for the researchers in this field, a huge number of image denoising techniques have been introduced in order to remove the noise with taking care of the image featurs, in other words, get the best similarity to the original image from the noisy one. However, beside the enormous amount of researches and studies which adopt several mathematical concepts (statistics, probabilities, modeling, PDEs, wavelet, fuzzy logic, etc.), the findings proved to be inconclusive yet. From this point, the current study aims to introduce a new denoising method for removing salt & pepper noise from the digital image through developed Median filter, so as to overcome this problem of noise and achieve a good image restoration.

View
Thumbnail Image
Publication

Estimation of Remaining Useful Life in Lithium-Ion Batteries using Bidirectional Long-Short Term Memory

2023-01-01 , Cahyani D.E. , Setyawan F.F. , Hariadi A.D. , Gumilar L. , Ahmad Kadri Junoh

Lithium-ion batteries are a type of rechargeable battery known for their high energy capacity and extended lifespan. Although lithium-ion battery technology is advancing rapidly, these batteries have a limited operational lifespan and their energy storage capability decreases with time and usage. This is where Remaining Useful Life (RUL) calculations become essential for battery maintenance planning. This study aims to employ the Bidirectional Long-Short Term Memory (BiLSTM) technique to predict the RUL of Li-ion batteries and compare it with the Long-Short Term Memory (LSTM) method to determine the most effective approach. The training data included batteries B0005, B0006, B0007, B0018, B0025, B0026, B0027, B0028, and B0055 for experiments. The BiLSTM approach consistently outperformed the LSTM method for each battery. The best results were achieved with battery B0005 using BiLSTM, with RMSE, MSE, MAE, and MAPE values of 0.01612, 0.00026, 0.00971, and 0.00684, respectively, indicating that the BiLSTM method is capable of accurately estimating the RUL of lithium-ion batteries.

View