Nurshazlyn Mohd Aszemi
Nurshazlyn Mohd Aszemi has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Noreen Izza Arshad
Universiti Teknologi PETRONAS
5 shared publications - Ahmad Kamil Mahmood
Department of Computer and Information Sciences, Universiti Teknologi PETRONAS, Perak, Malaysia
3 shared publications - Hui Min Low
School of Educational Studies, Universiti Sains Malaysia, Malaysia
3 shared publications - Izuddin Zainal-Abidin
Department of Computer and Information Sciences, Universiti Teknologi PETRONAS, Perak, Malaysia
3 shared publications - Mazeyanti Mohd Ariffin
Universiti Teknologi PETRONAS
3 shared publications - Ahmad Sobri Hashim
Department of Computing, Universiti Teknologi PETRONAS, Seri Iskandar, Perak, Malaysia
2 shared publications
Latest Publications
- 14 July 2024
- Published by Springer Nature
- p. 787-793
Teaching Ergonomics Using Virtual Reality (VR) to Higher Education Learners
- 14 July 2024
- Published by Springer Nature
- p. 787-793
Teaching Ergonomics Using Virtual Reality (VR) to Higher Education Learners
- 18 March 2022
- Published by Society of Petroleum Engineers (SPE)
A Literature Review on Site Suitability and Structural Hydrodynamic Viability for Artificial Reefs Purposes
In Malaysia, over 400 oil and gas platforms are in operation. In every life cycle of a platform, it undergoes decommissioning. The most used method is by relocating the asset to an onshore fabrication facility. The alternative to onshore decommissioning is by reefing structures in-situ or ex-situ basis. to achieve the environmental assurance of a successful decommissioning by reefing, two domains of parameters were overviewed. the study involved hydrodynamic simulation of platforms. The first domain is in relations to the site to determine its suitability against hosting marine life and thriving coral formulation (Site Suitability). the other domain is in relations to the structure's physical and hydrodynamic properties (structural viability). Site suitability is governed by water depth and current velocity. Structural viability is governed by two sub-domains, one is where dimensions and complexity of the structure are assessed using dimensionality analysis. And the other is its hydrodynamic properties (Vortex Shedding Frequency, Pressure, Wake Region indices).
- 18 March 2022
- Published by Society of Petroleum Engineers (SPE)
A Literature Review on Site Suitability and Structural Hydrodynamic Viability for Artificial Reefs Purposes
In Malaysia, over 400 oil and gas platforms are in operation. In every life cycle of a platform, it undergoes decommissioning. The most used method is by relocating the asset to an onshore fabrication facility. The alternative to onshore decommissioning is by reefing structures in-situ or ex-situ basis. to achieve the environmental assurance of a successful decommissioning by reefing, two domains of parameters were overviewed. the study involved hydrodynamic simulation of platforms. The first domain is in relations to the site to determine its suitability against hosting marine life and thriving coral formulation (Site Suitability). the other domain is in relations to the structure's physical and hydrodynamic properties (structural viability). Site suitability is governed by water depth and current velocity. Structural viability is governed by two sub-domains, one is where dimensions and complexity of the structure are assessed using dimensionality analysis. And the other is its hydrodynamic properties (Vortex Shedding Frequency, Pressure, Wake Region indices).
- 21 December 2021
- Published by Taylor & Francis in Knowledge Management Research & Practice
- Vol. 20 (1) , 123-140
A sustainable enterprise content management technologies use framework supporting agile business processes
Organisations invest in a considerable number of resources towards implementing Enterprise Content Management Systems (ECMS), expecting productive outcomes from the ECMS utilisation. A well-designed ECMS is impressive and deserves admiration, but to the organisations the ECMS limited value is often a major highlight. This motivates this study to understand how sustainable investment in Enterprise Content Management (ECM) technologies could support organisational Agile Business Processes (ABP). In studying how different organisation types utilise ECMS, the research employs a cross-sectional multiple-case studies approach with participation of seven large-scaled organisations. An investigation and an exploration into how these organisations interacted with ECMS are pivotal to the research. Based on the qualitative data analysis, this study proposes a sustainable ECMS-use framework that explains how ABP could benefit from it. Essentially, the framework enlightens researchers and practitioners to leverage ECM technologies for different work practices supporting ABP and organisational structures.
- 21 December 2021
- Published by Taylor & Francis in Knowledge Management Research & Practice
- Vol. 20 (1) , 123-140
A sustainable enterprise content management technologies use framework supporting agile business processes
Organisations invest in a considerable number of resources towards implementing Enterprise Content Management Systems (ECMS), expecting productive outcomes from the ECMS utilisation. A well-designed ECMS is impressive and deserves admiration, but to the organisations the ECMS limited value is often a major highlight. This motivates this study to understand how sustainable investment in Enterprise Content Management (ECM) technologies could support organisational Agile Business Processes (ABP). In studying how different organisation types utilise ECMS, the research employs a cross-sectional multiple-case studies approach with participation of seven large-scaled organisations. An investigation and an exploration into how these organisations interacted with ECMS are pivotal to the research. Based on the qualitative data analysis, this study proposes a sustainable ECMS-use framework that explains how ABP could benefit from it. Essentially, the framework enlightens researchers and practitioners to leverage ECM technologies for different work practices supporting ABP and organisational structures.
- 1 January 2021
- Published by Smt Vimla Devi Education Society
- p. 463-473
Comparative Study of Surrogate Techniques for CNN Hyperparameter Optimization
Optimizing hyper parameters in Convolutional Neural networks is a tedious process for many researchers and practitioners. It requires a high degree of expertise or experience to optimize the hyper parameters, and manual optimization is likely to be biased. To date, methods or approaches to automate hyper parameter optimization include grid search, random search, and Genetic Algorithms (GAs). However, evaluating large number of sample points in the hyperparameter configuration space, as is typically required by these methods, is a computationally expensive process. Hence, the objective of this paper is to explore regression as a surrogate technique in CNN hyperparameter optimization. Performance in terms of accuracy, error rate, training time and coefficient of determination (R2) are evaluated and recorded. Although there is no significant performance difference between the resulting optimized Deep Learning and state-of-the-art on CIFAR-10 datasets, using regression as a surrogate technique for CNN hyperparameter optimization contributes to minimizing the time taken for the optimization process, a benefit which has not been fully explored in the literature to the best of the author's knowledge.
- 1 January 2021
- Published by Smt Vimla Devi Education Society
- p. 463-473
Comparative Study of Surrogate Techniques for CNN Hyperparameter Optimization
Optimizing hyper parameters in Convolutional Neural networks is a tedious process for many researchers and practitioners. It requires a high degree of expertise or experience to optimize the hyper parameters, and manual optimization is likely to be biased. To date, methods or approaches to automate hyper parameter optimization include grid search, random search, and Genetic Algorithms (GAs). However, evaluating large number of sample points in the hyperparameter configuration space, as is typically required by these methods, is a computationally expensive process. Hence, the objective of this paper is to explore regression as a surrogate technique in CNN hyperparameter optimization. Performance in terms of accuracy, error rate, training time and coefficient of determination (R2) are evaluated and recorded. Although there is no significant performance difference between the resulting optimized Deep Learning and state-of-the-art on CIFAR-10 datasets, using regression as a surrogate technique for CNN hyperparameter optimization contributes to minimizing the time taken for the optimization process, a benefit which has not been fully explored in the literature to the best of the author's knowledge.
- Open Access
- 20 November 2020
- Published by JMIR Publications Inc. in JMIR mHealth and uHealth
Stuttering mHealth Applications: Development of A Qualitative Rubric Assessment (Preprint)
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Mobile applications (apps) that offer a variety of techniques to improve stuttering have been flourishing in the digital marketplace. In evidence-based clinical practice, speech therapists will recommend audio-enriched mobile apps to individuals with stuttering problems based on empirical research evidence. Unfortunately, many stuttering mobile apps available in the market are developed without a substantial research base. Hence, speech therapists necessitate a guideline which they could use to assess the quality of a stuttering mobile app before recommending the app to stutterers. Objective: The objective of this study is to develop a rubric for assessing the quality of the stuttering mobile app in assisting speech therapists to make informed recommendations Methods: The rubric was initially developed based on a set of criteria reviewed from the literature. Online surveys and focused group discussion were then conducted for results verification. Results: The outcome of this study is a rubric designed with four categories and 18-evaluative dimensions tailored to analyze the quality of stuttering mobile apps. The stuttering mobile app assessment rubric presented in the serve multiple purposes, including an evaluation instrument, providing guidelines for developing stuttering mobile apps and for creating a standard form that can be shared with professionals to facilitate a collective effort. Conclusions: This rubric also offers a guidance to steer drive the future development of stuttering mobile apps that are evidence-based, and theoretically grounded
- 20 November 2020
- Published by JMIR Publications Inc. in JMIR mHealth and uHealth
Open AccessStuttering mHealth Applications: Development of A Qualitative Rubric Assessment (Preprint)
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Mobile applications (apps) that offer a variety of techniques to improve stuttering have been flourishing in the digital marketplace. In evidence-based clinical practice, speech therapists will recommend audio-enriched mobile apps to individuals with stuttering problems based on empirical research evidence. Unfortunately, many stuttering mobile apps available in the market are developed without a substantial research base. Hence, speech therapists necessitate a guideline which they could use to assess the quality of a stuttering mobile app before recommending the app to stutterers. Objective: The objective of this study is to develop a rubric for assessing the quality of the stuttering mobile app in assisting speech therapists to make informed recommendations Methods: The rubric was initially developed based on a set of criteria reviewed from the literature. Online surveys and focused group discussion were then conducted for results verification. Results: The outcome of this study is a rubric designed with four categories and 18-evaluative dimensions tailored to analyze the quality of stuttering mobile apps. The stuttering mobile app assessment rubric presented in the serve multiple purposes, including an evaluation instrument, providing guidelines for developing stuttering mobile apps and for creating a standard form that can be shared with professionals to facilitate a collective effort. Conclusions: This rubric also offers a guidance to steer drive the future development of stuttering mobile apps that are evidence-based, and theoretically grounded
- Open Access
- 20 November 2020
- Published by JMIR Publications Inc. in JMIR Preprints
Stuttering mHealth Applications: Development of A Qualitative Rubric Assessment (Preprint)
BACKGROUND Mobile applications (apps) that offer various techniques to improve stuttering have flourished the digital marketplace. In evidence-based clinical practice, speech therapists will recommend audio-enriched mobile apps to individuals with stuttering problems based on empirical research evidence. Unfortunately, many developers of stuttering mobile apps have overlooked a substantial research base before the apps become available in the market. Hence, speech therapists necessitate a guideline to assess the quality of a stuttering mobile app before recommending the app to stutterers. OBJECTIVE The study aims to develop a rubric intended to be an instrument to assess the quality of stuttering mobile apps in helping speech therapists to make appropriate recommendations on stuttering mobile apps as an assistive technology to support stuttering treatments and therapies. METHODS In the study, three rubric development phases are involved: a review of the literature, an online expert survey, and a focus group discussion. In Phase 1, a thorough review of the literature is carried out in search of the criteria of a quality m-health. Strong theoretical grounds and empirical works are the basis of the criteria identification, resulting in a total of 45 criteria are extracted. In Phase 2, an online survey questionnaire designed to establish content validity for each criterion is distributed with seven speech therapists and a researcher in speech disfluency participate in the rating process of each criterion critical for a stuttering mobile app. In Phase 3, a focus group discussion aims to jointly develop a rubric serving as a tool to assess stuttering m-health apps quality. RESULTS Each criterion of the 45 evaluative dimensions is rated based on the experts’ experience and knowledge in using assistive mobile apps in conducting a therapy with stutterers under their care. These ratings are collected and analyzed. The validity of each criterion based on the ratings collected is identified through the Content Validity Ratio (CVR). The outcome of this study is a rubric designed with four categories and 18-evaluative dimensions tailored to analyze the quality of stuttering mobile apps. The stuttering mobile app assessment rubric serves multiple purposes, chiefly as an evaluation instrument, providing guidelines for developing stuttering mobile apps and creating a standard form that the professionals working with speech disfluency individuals can utilize to facilitate a collective effort. CONCLUSIONS The study has included evidence-based research determined based on health practitioners’ feedbacks for the development of rubric in assessing the stuttering mobile apps quality. This final rubric offers guidance for future development of evidence-based and theoretically grounded stuttering mobile apps. CLINICALTRIAL
- 20 November 2020
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessStuttering mHealth Applications: Development of A Qualitative Rubric Assessment (Preprint)
BACKGROUND Mobile applications (apps) that offer various techniques to improve stuttering have flourished the digital marketplace. In evidence-based clinical practice, speech therapists will recommend audio-enriched mobile apps to individuals with stuttering problems based on empirical research evidence. Unfortunately, many developers of stuttering mobile apps have overlooked a substantial research base before the apps become available in the market. Hence, speech therapists necessitate a guideline to assess the quality of a stuttering mobile app before recommending the app to stutterers. OBJECTIVE The study aims to develop a rubric intended to be an instrument to assess the quality of stuttering mobile apps in helping speech therapists to make appropriate recommendations on stuttering mobile apps as an assistive technology to support stuttering treatments and therapies. METHODS In the study, three rubric development phases are involved: a review of the literature, an online expert survey, and a focus group discussion. In Phase 1, a thorough review of the literature is carried out in search of the criteria of a quality m-health. Strong theoretical grounds and empirical works are the basis of the criteria identification, resulting in a total of 45 criteria are extracted. In Phase 2, an online survey questionnaire designed to establish content validity for each criterion is distributed with seven speech therapists and a researcher in speech disfluency participate in the rating process of each criterion critical for a stuttering mobile app. In Phase 3, a focus group discussion aims to jointly develop a rubric serving as a tool to assess stuttering m-health apps quality. RESULTS Each criterion of the 45 evaluative dimensions is rated based on the experts’ experience and knowledge in using assistive mobile apps in conducting a therapy with stutterers under their care. These ratings are collected and analyzed. The validity of each criterion based on the ratings collected is identified through the Content Validity Ratio (CVR). The outcome of this study is a rubric designed with four categories and 18-evaluative dimensions tailored to analyze the quality of stuttering mobile apps. The stuttering mobile app assessment rubric serves multiple purposes, chiefly as an evaluation instrument, providing guidelines for developing stuttering mobile apps and creating a standard form that the professionals working with speech disfluency individuals can utilize to facilitate a collective effort. CONCLUSIONS The study has included evidence-based research determined based on health practitioners’ feedbacks for the development of rubric in assessing the stuttering mobile apps quality. This final rubric offers guidance for future development of evidence-based and theoretically grounded stuttering mobile apps. CLINICALTRIAL
- 25 June 2020
- Published by The World Academy of Research in Science and Engineering in International Journal of Advanced Trends in Computer Science and Engineering
- Vol. 9 (1.3) , 164-167
CHECKDYSC©: Mobile Game for Early Detection of Dyscalculia Signs in Children
- 25 June 2020
- Published by The World Academy of Research in Science and Engineering in International Journal of Advanced Trends in Computer Science and Engineering
- Vol. 9 (1.3) , 164-167
CHECKDYSC©: Mobile Game for Early Detection of Dyscalculia Signs in Children
- Open Access
- 11 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 116279-116291
Robots as Assistive Technology Tools to Enhance Cognitive Abilities and Foster Valuable Learning Experiences among Young Children With Autism Spectrum Disorder
This study examines the efficacy of robots as assistive technology (AT) learning tools for children with autism spectrum disorder (ASD). The study attempts to find answers to whether robots as assistive tools can (i) profoundly improve achievement in learning and (ii) provide valuable learning experiences among this group of children. Using LEGO Mindstorms EV3, a robot was built and programmed to teach the basic concept of place value in mathematics. Eight children with ASD, specifically, four females and four males, participated in the single case study, and six special education teachers took part in the interviews. The children participated in both traditional and robotic intervention lessons and were assessed at the end of each session. The results indicate a positive increase in content knowledge and an improved disposition toward learning, thus demonstrating the potential utilization of robots as AT tools for harnessing classroom learning. Data from the interviews with teachers highlighted four valuable learning experiences that occurred in the classrooms as a result of the robotic interventions; namely, with respect to young children with ASD, the AT (1) promoted interest and engagement, (2) increased attention and focus, (3) triggered interactions and communication, and (4) created a happy and fun learning environment.
- 11 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 116279-116291
Open AccessRobots as Assistive Technology Tools to Enhance Cognitive Abilities and Foster Valuable Learning Experiences among Young Children With Autism Spectrum Disorder
This study examines the efficacy of robots as assistive technology (AT) learning tools for children with autism spectrum disorder (ASD). The study attempts to find answers to whether robots as assistive tools can (i) profoundly improve achievement in learning and (ii) provide valuable learning experiences among this group of children. Using LEGO Mindstorms EV3, a robot was built and programmed to teach the basic concept of place value in mathematics. Eight children with ASD, specifically, four females and four males, participated in the single case study, and six special education teachers took part in the interviews. The children participated in both traditional and robotic intervention lessons and were assessed at the end of each session. The results indicate a positive increase in content knowledge and an improved disposition toward learning, thus demonstrating the potential utilization of robots as AT tools for harnessing classroom learning. Data from the interviews with teachers highlighted four valuable learning experiences that occurred in the classrooms as a result of the robotic interventions; namely, with respect to young children with ASD, the AT (1) promoted interest and engagement, (2) increased attention and focus, (3) triggered interactions and communication, and (4) created a happy and fun learning environment.
- Open Access
- 5 April 2020
- Published by Lembaga Publikasi Ilmiah dan Penerbitan Universitas Muhammadiyah Purwokerto in Dinamika Jurnal Ilmiah Pendidikan Dasar
- Vol. 12 (1) , 25
A Study on Student Attitudes in Learning Programming using Physical Computing
Learning to program can be difficult for the students. Students must master language syntax, programming theory, and problem-solving techniques. Efforts have been made to assist students in understanding how to program. This study is intended to examine whether Arduino, as a teaching and learning tool, helps in generating students’ interests towards programming. Arduino is one of the physical computing tools which has an open-source electronics platform based on user-friendly hardware and software for creating different projects and applications. Arduino is easy to be used by beginners, yet flexible enough for advanced users to learn physical computing and programming. This study adopted a quantitative research method to measure the student’s attitude in learning programming using physical computing. The sample of this study is 56 students from the foundation program and undergraduate program. To gauge students’ perception, students’ attitude survey was adapted. The collected data were analyzed using descriptive analysis. Based on the analysis, the study found that the overall mean score was 4.253. The result indicated that student has a positive attitude in learning programming using physical computing.
- 5 April 2020
- Published by Lembaga Publikasi Ilmiah dan Penerbitan Universitas Muhammadiyah Purwokerto in Dinamika Jurnal Ilmiah Pendidikan Dasar
- Vol. 12 (1) , 25
Open AccessA Study on Student Attitudes in Learning Programming using Physical Computing
Learning to program can be difficult for the students. Students must master language syntax, programming theory, and problem-solving techniques. Efforts have been made to assist students in understanding how to program. This study is intended to examine whether Arduino, as a teaching and learning tool, helps in generating students’ interests towards programming. Arduino is one of the physical computing tools which has an open-source electronics platform based on user-friendly hardware and software for creating different projects and applications. Arduino is easy to be used by beginners, yet flexible enough for advanced users to learn physical computing and programming. This study adopted a quantitative research method to measure the student’s attitude in learning programming using physical computing. The sample of this study is 56 students from the foundation program and undergraduate program. To gauge students’ perception, students’ attitude survey was adapted. The collected data were analyzed using descriptive analysis. Based on the analysis, the study found that the overall mean score was 4.253. The result indicated that student has a positive attitude in learning programming using physical computing.
- Open Access
- 1 January 2019
- Published by The Science and Information Organization in International Journal of Advanced Computer Science and Applications
- Vol. 10 (6)
Hyperparameter Optimization in Convolutional Neural Network using Genetic Algorithms
Optimizing hyperparameters in Convolutional Neural Network (CNN) is a tedious problem for many researchers and practitioners. To get hyperparameters with better performance, experts are required to configure a set of hyperparameter choices manually. The best results of this manual configuration are thereafter modeled and implemented in CNN. However, different datasets require different model or combination of hyperparameters, which can be cumbersome and tedious. To address this, several works have been proposed such as grid search which is limited to low dimensional space, and tails which use random selection. Also, optimization methods such as evolutionary algorithms and Bayesian have been tested on MNIST datasets, which is less costly and require fewer hyperparameters than CIFAR-10 datasets. In this paper, the authors investigate the hyperparameter search methods on CIFAR-10 datasets. During the investigation with various optimization methods, performances in terms of accuracy are tested and recorded. Although there is no significant difference between propose approach and the state-of-the-art on CIFAR-10 datasets, however, the actual potency lies in the hybridization of genetic algorithms with local search method in optimizing both network structures and network training which is yet to be reported to the best of author knowledge.
- 1 January 2019
- Published by The Science and Information Organization in International Journal of Advanced Computer Science and Applications
- Vol. 10 (6)
Open AccessHyperparameter Optimization in Convolutional Neural Network using Genetic Algorithms
Optimizing hyperparameters in Convolutional Neural Network (CNN) is a tedious problem for many researchers and practitioners. To get hyperparameters with better performance, experts are required to configure a set of hyperparameter choices manually. The best results of this manual configuration are thereafter modeled and implemented in CNN. However, different datasets require different model or combination of hyperparameters, which can be cumbersome and tedious. To address this, several works have been proposed such as grid search which is limited to low dimensional space, and tails which use random selection. Also, optimization methods such as evolutionary algorithms and Bayesian have been tested on MNIST datasets, which is less costly and require fewer hyperparameters than CIFAR-10 datasets. In this paper, the authors investigate the hyperparameter search methods on CIFAR-10 datasets. During the investigation with various optimization methods, performances in terms of accuracy are tested and recorded. Although there is no significant difference between propose approach and the state-of-the-art on CIFAR-10 datasets, however, the actual potency lies in the hybridization of genetic algorithms with local search method in optimizing both network structures and network training which is yet to be reported to the best of author knowledge.