Ruzzakiah Jenal
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ruzzakiah Jenal has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Nur Fazidah Elias
Center for Software Technology and Management, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia (UKM), Bangi 43600, Malaysia
4 shared publications - Hazura Mohamed
Faculty of Information Science & Technology, National University of Malaysia, Selangor, Malaysia
3 shared publications - Yazrina Yahya
Center for Software Technology and Management, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia (UKM), Bangi 43600, Malaysia
2 shared publications - Yu Chao
Center for Software Technology and Management, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia (UKM), Bangi 43600, Malaysia
2 shared publications - Eliza Annis Thangaiah
Universiti Kebangsaan Malaysia,Faculty of Information Science Technology,Selangor,Malaysia
1 shared publication - Emy Salfarina Alias
Center for Software Technology and Management Faculty of Information Science and Technology Universiti Kebangsaan Malaysia 43600 Bangi Selangor Malaysia
1 shared publication
Latest Publications
- Open Access
- 7 August 2026
- Published by MDPI AG in Forecasting
- Vol. 8 (4) , 68
Distinguishing Contemporaneous Rule Recovery from Financial Risk Forecasting in Higher Education Institutions: A Controlled Synthetic-Panel Experiment
High classification performance in financial-risk early-warning research may reflect recovery of a constructed contemporaneous rating rule rather than prediction of an independent future outcome. This study distinguishes these two forms of evidence through a controlled synthetic-panel experiment situated in the context of higher education institutions (HEIs). Task 1 is a contemporaneous positive-control audit in which the four components defining a deterministic three-class rating are supplied to the classifiers. Task 2 uses predictors measured at year to classify the rating at year t through strict rolling-origin evaluation under prespecified Weak, Moderate, and Strong temporal-persistence conditions. In Task 1, the four fitted classifiers achieved held-out Macro-F1 values of 0.9968–1.0000, demonstrating near-complete recovery of the disclosed rating rule but providing no prospective forecasting evidence. In Task 2, the best mean annual Macro-F1/Macro-AUC increased from 0.480/0.696 under Weak persistence to 0.549/0.747 under Moderate persistence and 0.633/0.824 under Strong persistence. The Weak–Moderate–Strong ordering was observed for both primary metrics across all four fitted classifiers, while higher model complexity provided no consistent advantage within the disclosed synthetic mechanism. These findings confirm contemporaneous rule recoverability and sensitivity to deliberately embedded temporal persistence only within the controlled experiment. They do not establish predictive validity, transportability, or decision benefit in real HEIs. The study contributes a reproducible task-to-claim approach that aligns target construction, predictor–target overlap, information timing, rolling-origin evaluation, probability quality, and model performance with the inferences that the resulting evidence can legitimately support. Real-world validation would require source-indexed longitudinal HEI data, independently adjudicated post-origin outcomes, verified information-availability dates, external testing, and prospective decision evaluation.- 7 August 2026
- Published by MDPI AG in Forecasting
- Vol. 8 (4) , 68
Open AccessDistinguishing Contemporaneous Rule Recovery from Financial Risk Forecasting in Higher Education Institutions: A Controlled Synthetic-Panel Experiment
High classification performance in financial-risk early-warning research may reflect recovery of a constructed contemporaneous rating rule rather than prediction of an independent future outcome. This study distinguishes these two forms of evidence through a controlled synthetic-panel experiment situated in the context of higher education institutions (HEIs). Task 1 is a contemporaneous positive-control audit in which the four components defining a deterministic three-class rating are supplied to the classifiers. Task 2 uses predictors measured at year to classify the rating at year t through strict rolling-origin evaluation under prespecified Weak, Moderate, and Strong temporal-persistence conditions. In Task 1, the four fitted classifiers achieved held-out Macro-F1 values of 0.9968–1.0000, demonstrating near-complete recovery of the disclosed rating rule but providing no prospective forecasting evidence. In Task 2, the best mean annual Macro-F1/Macro-AUC increased from 0.480/0.696 under Weak persistence to 0.549/0.747 under Moderate persistence and 0.633/0.824 under Strong persistence. The Weak–Moderate–Strong ordering was observed for both primary metrics across all four fitted classifiers, while higher model complexity provided no consistent advantage within the disclosed synthetic mechanism. These findings confirm contemporaneous rule recoverability and sensitivity to deliberately embedded temporal persistence only within the controlled experiment. They do not establish predictive validity, transportability, or decision benefit in real HEIs. The study contributes a reproducible task-to-claim approach that aligns target construction, predictor–target overlap, information timing, rolling-origin evaluation, probability quality, and model performance with the inferences that the resulting evidence can legitimately support. Real-world validation would require source-indexed longitudinal HEI data, independently adjudicated post-origin outcomes, verified information-availability dates, external testing, and prospective decision evaluation. - Open Access
- 22 October 2025
- Published by MDPI AG in Forecasting
- Vol. 7 (4) , 61
Research on Dynamic Hyperparameter Optimization Algorithm for University Financial Risk Early Warning Based on Multi-Objective Bayesian Optimization
Financial sustainability in higher education is increasingly fragile due to policy shifts, rising costs, and funding volatility. Legacy early-warning systems based on static thresholds or rules struggle to adapt to these dynamics and often overlook fairness and interpretability—two essentials in public-sector governance. We propose a university financial risk early-warning framework that couples a causal-attention Transformer with Multi-Objective Bayesian Optimization (MBO). The optimizer searches a constrained Pareto frontier to jointly improve predictive accuracy (AUC↑), fairness (demographic parity gap, DP_Gap↓), and computational efficiency (time↓). A sparse kernel surrogate (SKO) accelerates convergence in high-dimensional tuning; a dual-head output (risk probability and health score) and SHAP-based attribution enhance transparency and regulatory alignment. On multi-year, multi-institution data, the approach surpasses mainstream baselines in AUC, reduces DP_Gap, and yields expert-consistent explanations. Methodologically, the design aligns with LLM-style time-series forecasting by exploiting causal masking and long-range dependencies while providing governance-oriented explainability. The framework delivers earlier, data-driven signals of financial stress, supporting proactive resource allocation, funding restructuring, and long-term planning in higher education finance.
- 22 October 2025
- Published by MDPI AG in Forecasting
- Vol. 7 (4) , 61
Open AccessResearch on Dynamic Hyperparameter Optimization Algorithm for University Financial Risk Early Warning Based on Multi-Objective Bayesian Optimization
Financial sustainability in higher education is increasingly fragile due to policy shifts, rising costs, and funding volatility. Legacy early-warning systems based on static thresholds or rules struggle to adapt to these dynamics and often overlook fairness and interpretability—two essentials in public-sector governance. We propose a university financial risk early-warning framework that couples a causal-attention Transformer with Multi-Objective Bayesian Optimization (MBO). The optimizer searches a constrained Pareto frontier to jointly improve predictive accuracy (AUC↑), fairness (demographic parity gap, DP_Gap↓), and computational efficiency (time↓). A sparse kernel surrogate (SKO) accelerates convergence in high-dimensional tuning; a dual-head output (risk probability and health score) and SHAP-based attribution enhance transparency and regulatory alignment. On multi-year, multi-institution data, the approach surpasses mainstream baselines in AUC, reduces DP_Gap, and yields expert-consistent explanations. Methodologically, the design aligns with LLM-style time-series forecasting by exploiting causal masking and long-range dependencies while providing governance-oriented explainability. The framework delivers earlier, data-driven signals of financial stress, supporting proactive resource allocation, funding restructuring, and long-term planning in higher education finance.
- Open Access
- 28 April 2025
- Published by Universiti Pendidikan Sultan Idris in Jurnal Pendidikan Sains dan Matematik Malaysia
- Vol. 15 (15) , 1-18
Inovasi Smart RoMat dalam meningkatkan penguasaan operasi tambah bagi pembelajaran matematik sekolah rendah
Matematik menjadi subjek yang digeruni oleh pelbagai peringkat umur seawal usia menjejaki kaki di sekolah rendah. Murid sekolah rendah diberi latih tubi dari masa ke semasa dengan memperkenalkan konsep operasi dalam matematik iaitu tambah, tolak, darab dan bahagi. Pelbagai kaedah dan alat bantu mengajar disediakan untuk menarik minat murid dalam mempelajari matematik. Namun, murid masih tidak dapat menguasai matematik. Latih tubi yang diberi di buku tulis mendapati murid memperlihatkan hasil kerja yang kurang kemas dan jawapan yang kurang tepat. Dalam menyelesaikan masalah operasi tambah, murid menunjukkan kesilapan menyelesaikannya pada ruang nilai tempat yang betul. Ini menunjukkan bahawa murid tidak memahami konsep tambah yang betul dan menyebabkan mereka mendapat markah yang rendah. Oleh itu, kajian dilakukan untuk membangunkan sebuah inovasi yang dinamakan Smart RoMat yang diintegrasi dengan elemen STEM (Sains, Teknologi, Kejuruteraan, Matematik) bagi membantu murid menguasai dan menyelesaikan masalah berkaitan operasi tambah. Smart RoMat membolehkan murid menukarkan ayat matematik tambah kepada bentuk lazim. Smart RoMat mengandungi koleksi soalan-soalan matematik bagi operasi tambah yang mengandungi nilai digit ‘sa’, ‘puluh’ dan ‘ratus’ serta pelbagai aktiviti-aktiviti PAK-21 (Pembelajaran Abad ke-21) yang interaktif. Smart RoMat duji ke atas murid-murid yang tidak menguasai kemahiran menyelesaikan masalah menggunakan bentuk lazim untuk operasi tambah. Hasil ujian mendapati bahawa murid dapat menyelesaikan operasi tambah bagi nombor dalam lingkungan 0 hingga1000. Murid juga dapat menyelesaikan masalah tambah mengikut nilai tempat dengan betul melalui aktiviti yang disediakan. Maka, penghasilan Smart RoMat berjaya mengatasi masalah pembelajaran operasi tambah bagi murid dan menjadi alat bantu mengajar bagi guru supaya proses pengajaran dan pembelajaran berlaku dengan lancar.
- 28 April 2025
- Published by Universiti Pendidikan Sultan Idris in Jurnal Pendidikan Sains dan Matematik Malaysia
- Vol. 15 (15) , 1-18
Open AccessInovasi Smart RoMat dalam meningkatkan penguasaan operasi tambah bagi pembelajaran matematik sekolah rendah
Matematik menjadi subjek yang digeruni oleh pelbagai peringkat umur seawal usia menjejaki kaki di sekolah rendah. Murid sekolah rendah diberi latih tubi dari masa ke semasa dengan memperkenalkan konsep operasi dalam matematik iaitu tambah, tolak, darab dan bahagi. Pelbagai kaedah dan alat bantu mengajar disediakan untuk menarik minat murid dalam mempelajari matematik. Namun, murid masih tidak dapat menguasai matematik. Latih tubi yang diberi di buku tulis mendapati murid memperlihatkan hasil kerja yang kurang kemas dan jawapan yang kurang tepat. Dalam menyelesaikan masalah operasi tambah, murid menunjukkan kesilapan menyelesaikannya pada ruang nilai tempat yang betul. Ini menunjukkan bahawa murid tidak memahami konsep tambah yang betul dan menyebabkan mereka mendapat markah yang rendah. Oleh itu, kajian dilakukan untuk membangunkan sebuah inovasi yang dinamakan Smart RoMat yang diintegrasi dengan elemen STEM (Sains, Teknologi, Kejuruteraan, Matematik) bagi membantu murid menguasai dan menyelesaikan masalah berkaitan operasi tambah. Smart RoMat membolehkan murid menukarkan ayat matematik tambah kepada bentuk lazim. Smart RoMat mengandungi koleksi soalan-soalan matematik bagi operasi tambah yang mengandungi nilai digit ‘sa’, ‘puluh’ dan ‘ratus’ serta pelbagai aktiviti-aktiviti PAK-21 (Pembelajaran Abad ke-21) yang interaktif. Smart RoMat duji ke atas murid-murid yang tidak menguasai kemahiran menyelesaikan masalah menggunakan bentuk lazim untuk operasi tambah. Hasil ujian mendapati bahawa murid dapat menyelesaikan operasi tambah bagi nombor dalam lingkungan 0 hingga1000. Murid juga dapat menyelesaikan masalah tambah mengikut nilai tempat dengan betul melalui aktiviti yang disediakan. Maka, penghasilan Smart RoMat berjaya mengatasi masalah pembelajaran operasi tambah bagi murid dan menjadi alat bantu mengajar bagi guru supaya proses pengajaran dan pembelajaran berlaku dengan lancar.
- 15 September 2023
- Published by Global Academic Excellence (M) Sdn Bhd in Journal of Information System and Technology Management
- Vol. 8 (32) , 69-81
DETERMINATION OF MALAYSIAN GOVERNMENT WEBSITE EVALUATION METRICS BASED ON THE ANALYTICAL HIERARCHY PROCESS
- 15 September 2023
- Published by Global Academic Excellence (M) Sdn Bhd in Journal of Information System and Technology Management
- Vol. 8 (32) , 69-81
DETERMINATION OF MALAYSIAN GOVERNMENT WEBSITE EVALUATION METRICS BASED ON THE ANALYTICAL HIERARCHY PROCESS
- 12 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Determining the values and attributes in e-learning from vocational teacher's perspectives
Building an e-learning platform based on the user's point of view is getting the user to use the system. In this study, value co-creation is adopted from service science theory that involves users in service processes. The purpose of this paper is to use the means-end-chain (MEC) methodology by identifying the favourable attributes, consequences, and values from a teacher's point of view. The relationship among these items would build a ladder and lead to the purpose of the study. This study adopted the hard laddering - Association pattern technique (APT) method to develop the implication matrix, frequency table, and hierarchical value map (HVM). The study is aimed at vocational teachers as they are one of the primary users of the e-learning platform. The significance of this study is to help identify the co-creation value based on critical features on an e-learning platform. The results discovered that teachers develop eight important values led by self-fulfilment, sense of accomplishment, and responsible with the attributes in e-learning, which motivate them to continue using the platform for teaching and learning.
- 12 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Determining the values and attributes in e-learning from vocational teacher's perspectives
Building an e-learning platform based on the user's point of view is getting the user to use the system. In this study, value co-creation is adopted from service science theory that involves users in service processes. The purpose of this paper is to use the means-end-chain (MEC) methodology by identifying the favourable attributes, consequences, and values from a teacher's point of view. The relationship among these items would build a ladder and lead to the purpose of the study. This study adopted the hard laddering - Association pattern technique (APT) method to develop the implication matrix, frequency table, and hierarchical value map (HVM). The study is aimed at vocational teachers as they are one of the primary users of the e-learning platform. The significance of this study is to help identify the co-creation value based on critical features on an e-learning platform. The results discovered that teachers develop eight important values led by self-fulfilment, sense of accomplishment, and responsible with the attributes in e-learning, which motivate them to continue using the platform for teaching and learning.
- 12 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Conceptual Framework of Value in Use and E-learning Success
E-learning systems are increasingly becoming essentials tools for delivering education. Hence, understanding factors determining their use and continuous satisfaction is important for both practitioners and institutions of higher learning in formulating strategies for their development and instructional guidance. The narrative review method was used to review and synthesize relevant articles for this study. The review indicates that many authors have investigated e-learning adoption, implementation, and e-learning success from diverse angles. However, none of them has studied the influence of value in use on e-learning success. As a result, this study proposes a new framework that combines value-in-use construct to DeLone and McLean Information System Success constructs for examining e-learning success. This study's contribution is (1) the provision of a new framework for examining e-learning success. (2) Empirical evidence that could be achieved from this framework could guide practitioners on creating online artifacts and assist educational authorities in exploring the users' value in use of e-learning technologies and formulating e-learning strategies that meet these values. (3) An investigation of value in use of e-learning can provide new opportunities for research in learning technologies and bring new understanding in the field of instructional technology.
- 12 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Conceptual Framework of Value in Use and E-learning Success
E-learning systems are increasingly becoming essentials tools for delivering education. Hence, understanding factors determining their use and continuous satisfaction is important for both practitioners and institutions of higher learning in formulating strategies for their development and instructional guidance. The narrative review method was used to review and synthesize relevant articles for this study. The review indicates that many authors have investigated e-learning adoption, implementation, and e-learning success from diverse angles. However, none of them has studied the influence of value in use on e-learning success. As a result, this study proposes a new framework that combines value-in-use construct to DeLone and McLean Information System Success constructs for examining e-learning success. This study's contribution is (1) the provision of a new framework for examining e-learning success. (2) Empirical evidence that could be achieved from this framework could guide practitioners on creating online artifacts and assist educational authorities in exploring the users' value in use of e-learning technologies and formulating e-learning strategies that meet these values. (3) An investigation of value in use of e-learning can provide new opportunities for research in learning technologies and bring new understanding in the field of instructional technology.
- 23 July 2021
- Published by Springer Nature
- p. 1-12
Service Science Sustainability from the View of Asia Pacific
- 23 July 2021
- Published by Springer Nature
- p. 1-12
Service Science Sustainability from the View of Asia Pacific
- 1 June 2020
- Published by Penerbit Universiti Kebangsaan Malaysia (UKM Press) in Islamiyyat
- Vol. 43 (1) , 27-36
Faktor Penentu Kejayaan Sistem Penguatkuasaan dan Pendakwaan Syariah di Malaysia
Faktor Penentu Kejayaan Sistem Penguatkuasaan dan Pendakwaan Syariah di Malaysia
- 1 June 2020
- Published by Penerbit Universiti Kebangsaan Malaysia (UKM Press) in Islamiyyat
- Vol. 43 (1) , 27-36
Faktor Penentu Kejayaan Sistem Penguatkuasaan dan Pendakwaan Syariah di Malaysia
Faktor Penentu Kejayaan Sistem Penguatkuasaan dan Pendakwaan Syariah di Malaysia
- Open Access
- 7 October 2018
- Published by Insight Society in International Journal on Advanced Science, Engineering and Information Technology
- Vol. 8 (5) , 1882-1889
Adoption of Unified Communications and Collaboration from the Perspective of Diffusion of Innovation and Service Dominant Logic: A Preliminary View
Adoption of Unified Communications and Collaboration from the Perspective of Diffusion of Innovation and Service Dominant Logic: A Preliminary View
- 7 October 2018
- Published by Insight Society in International Journal on Advanced Science, Engineering and Information Technology
- Vol. 8 (5) , 1882-1889
Open AccessAdoption of Unified Communications and Collaboration from the Perspective of Diffusion of Innovation and Service Dominant Logic: A Preliminary View
Adoption of Unified Communications and Collaboration from the Perspective of Diffusion of Innovation and Service Dominant Logic: A Preliminary View
- 27 September 2018
- Published by AIP Publishing
- Vol. 2016 (1) , 020062
Implementation of digital campus in fostering campus sustainability
Digital Campus is commonly referred to as the use of advanced computer technology and networking in creating integrated services and a personalized environment to enable communication among university communities. In education sector, digital campus has to be built as an important basis for the modernization of education and to facilitate a better campus life. This paper presents the concept and framework of Digital Campus as part of the university’s challenges in fostering an economical and socially sustainable campus. The use of mobile applications is very appropriate for achieving campus sustainability because of its increasing significant and ability. UKM Mobile Application as part of Digital Campus strategy is seen to be able to contribute to the sustainability of the campus. We also present the implementation of Digital Campus based on smart card usage in the applications such as attendance system, canteen payment and academic services. Mobile application development embedding value co-creation can improve the quality of service in terms of good communication with customers and the best services to the university.
- 27 September 2018
- Published by AIP Publishing
- Vol. 2016 (1) , 020062
Implementation of digital campus in fostering campus sustainability
Digital Campus is commonly referred to as the use of advanced computer technology and networking in creating integrated services and a personalized environment to enable communication among university communities. In education sector, digital campus has to be built as an important basis for the modernization of education and to facilitate a better campus life. This paper presents the concept and framework of Digital Campus as part of the university’s challenges in fostering an economical and socially sustainable campus. The use of mobile applications is very appropriate for achieving campus sustainability because of its increasing significant and ability. UKM Mobile Application as part of Digital Campus strategy is seen to be able to contribute to the sustainability of the campus. We also present the implementation of Digital Campus based on smart card usage in the applications such as attendance system, canteen payment and academic services. Mobile application development embedding value co-creation can improve the quality of service in terms of good communication with customers and the best services to the university.