ORCID Profile
0000-0002-7724-114X
Current Organisation
Monash University Malaysia
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: Hindawi Limited
Date: 23-12-2019
DOI: 10.1002/ER.4912
Publisher: IOP Publishing
Date: 03-2018
Publisher: Public Library of Science (PLoS)
Date: 03-10-2014
Publisher: SAGE Publications
Date: 24-05-2022
DOI: 10.1177/14759217221089571
Abstract: Automated pavement crack segmentation is challenging due to the random shape of cracks, complex background textures and the presence of miscellaneous objects. In this paper, we implemented a Self-Guided Attention Refinement module and incorporated it on top of a Feature Pyramid Network (FPN) to model long-range contextual information. The module uses multi-scale features integrated from different layers in the FPN to refine the features at each layer of the FPN using a self-attention mechanism. The module enables the earlier layers and deeper layers of FPN to suppress noise and increase the crack details, respectively. The proposed network obtains an F1 score of 79.43% and 96.19% on the Crack500 and CFD datasets, respectively. Furthermore, the network also generalizes better than other state-of-the-art methods when tested on uncropped Crack500 and field images using the weights trained on CFD. In addition, ablation tests using the Crack500 dataset are conducted. The Self-Guided Attention Refinement module increases the average F1 score and recall by 0.6% and 0.8% while roughly maintaining the average precision. From the ablation test, the inclusion of the Self-Guided Attention Refinement module allows the network to segment finer and more continuous cracks. Then, the module is incorporated on PANet, DeepLab v3+ and U-Net to verify the improvements made to FPN. The results show that the module improves the F1 score, precision and recall compared to the absence of it. Moreover, the Self-Guided Attention Refinement Module is compared with the Self-Adaptive Sparse Transform Module (SASTM). The results show that the Self-Guided Attention Refinement Module provides a more consistent improvement.
Publisher: EDP Sciences
Date: 2018
DOI: 10.1051/MATECCONF/201822506021
Abstract: With the continuous improvement in Computer Modelling and Simulation Environment (CMSE) applications being made, computer modelling and simulation (CMS) is proven a better alternative as opposed to conventional physical modelling. The advancement of computing hardware allows accurate results to be obtained faster, safer and at a fraction of its original cost. Despite the proven advantages, CMSE adoption among companies may be fairly new in Malaysia. This study is aimed at quantifying the demand of CMSE specialists in Malaysia as well as gaining insights in the companies’ requirements of specialists’ knowledge, competencies and skills. Thus, a survey, consisted of 3 main parts, was conducted among industries in Malaysia as a tool of measurement of the demand. The survey included questions related to the general information of the organization, specialists’ competencies relation to the job scope, and finally the professional and educational standards among specialists. In general, it was found that practically-competent specialists in CMSE are in high demand among engineering companies. Furthermore, professional courses through distance learning would be of high interest among companies to send their employees to gain practical competency in CMSE.
Publisher: Springer Science and Business Media LLC
Date: 26-07-2016
Publisher: AIP Publishing
Date: 03-2011
DOI: 10.1063/1.3560386
Abstract: The vortex breakdown inside a cylinder with a rotating top lid is controlled experimentally by injecting at the bottom a fluid with a small density difference. The density difference is obtained by mixing a heavy dye or alcohol with water in order to create a jet denser or lighter than water. The injection of a heavy fluid creates a buoyancy force downward, which counteracts the meridional recirculation in the cylinder and thus enhances the formation of a vortex breakdown bubble. The stability diagram shows that even a very small density difference of 0.02% is able to decrease by a factor of 2 the critical Reynolds number of appearance of the breakdown. On the other hand, the injection of a lighter fluid does not destroy the vortex breakdown. However, for large enough density differences (larger than 0.03%), the lighter fluid is able to pierce through the bubble and leads to a new structure of the vortex breakdown. Finally, a parallel is drawn between a light jet and a vortex ring generated at the bottom of the cylinder: strong vortex rings are able to pierce through the bubble, whereas weak vortex rings are simply advected around the bubble.
Publisher: Elsevier BV
Date: 10-2021
Publisher: SAGE Publications
Date: 06-02-2017
Abstract: The use of defense hole system allows the flow of the stresses to be redistributed by introducing auxiliary holes in the low stress area near the main hole. However, the question remains on the optimal configuration of the defense hole system for effective stress mitigation at the bolt-hole region and, hence, increasing the bearing capacity of particular composite bolted joints. This study presents the influence of defense hole system geometrical design on the stress reduction in a single-bolt, double-lap composite bolted joint. The nonlinear material behavior of the joint was simulated using ANSYS through a progressive failure model, considering the circumferential and radial stresses at bearing, shear-out, and net tension regions of the bolt-hole. It was found that the stress has been reduced between 2.3% and 6.1% for the narrow laminates over a range of E/ D ratios (1–5) with the benefits of the defense hole was clearly marked at DS = 2 D and DHD = 0.75 D. In contrast, for those of wider laminates, the stress reduction ranged from 1.9% to remarkably 18.6%.
Publisher: Public Library of Science (PLoS)
Date: 11-06-2013
Publisher: MDPI AG
Date: 17-10-2014
DOI: 10.3390/PR2040753
Publisher: Elsevier BV
Date: 02-2020
DOI: 10.1016/J.WATRES.2019.115187
Abstract: There is a pressing need for efficient biological treatment systems for the removal of organic compounds in greywater given the rapid increase in household wastewater produced as a consequence of rapid urbanisation. Moreover, proper treatment of greywater allows its reuse that can significantly reduce the demand for freshwater supplies. Herein, we demonstrate the possibility of enhancing the removal efficiency of solid contaminants from greywater using MHz-order surface acoustic waves (SAWs). A key distinction of the use of these high frequency surface acoustic waves, compared to previous work on its lower frequency (kHz order) bulk ultrasound counterpart for wastewater treatment, is the absence of cavitation, which can inflict considerable damage on bacteria, thus limiting the intensity and duration, and hence the efficiency enhancement, associated with the acoustic exposure. In particular, we show that up to fivefold improvement in the removal efficiency can be obtained, primarily due to the ability of the acoustic pressure field in homogenizing and reducing the size of bacterial clusters in the s le, therefore providing a larger surface area that promotes greater bacteria digestion. Alternatively, the SAW exposure allows the reduction in the treatment duration to achieve a given level of removal efficiency, thus facilitating higher treatment rates and hence processing throughput. Given the low-cost of the miniature chipscale platform, these promising results highlight its possibility for portable greywater treatment for domestic use or for large-scale industrial wastewater processing through massive parallelization.
No related grants have been discovered for Mohd-Zulhilmi Ismadi.