Saipunidzam Mahamad
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Saipunidzam Mahamad has a total of 66 co-authors. Here are the top co-authors by number of shared publications:
- Abdullateef Oluwagbemiga Balogun
Department of Computing, Universiti Teknologi PETRONAS, Seri Iskandar, Malaysia
10 shared publications - Shuib Basri
Department of Computing, Universiti Teknologi PETRONAS, Seri Iskandar, Malaysia
7 shared publications - Ganesh Kumar
Department of Computing, Universiti Teknologi PETRONAS, Seri Iskandar 32610, Malaysia
5 shared publications - Luiz Fernando Capretz
Department of Electrical and Computer Engineering, Western University, London, ON N6A 5B9, Canada
5 shared publications - Malek Ahmad Almomani
Department of Software Engineering, Faculty of Information Technology, The World Islamic Sciences and Education University, Amman 11947, Jordan
5 shared publications - Suziah Sulaiman
Universiti Teknologi PETRONAS
5 shared publications
Latest Publications
- 2 June 2026
- Published by Wiley in Applied Research
- Vol. 5 (3)
Noise‐Space Adaptive Multi‐Domain Filtering: A Unified Framework for Low‐Light Urban Surveillance and Medical Retinal Imaging
The increasing demand of imaging systems in urban surveillance and medical diagnostic systems is the ability to adapt to non‐homogeneous acquisition conditions without manually adjusting the system parameters. Current methods are generally tailored to specific domains, struggle to generalise to unseen noise patterns, and often depend on retraining computationally intensive deep networks that require large amounts of annotated data. We seal this divide with MDAF++, a single filtering framework that automatically classifies the input domain, and dynamically repurposes its processing strategy at inference time. Instead of parameterized models, or trained weights, MDAF++ interconnects wavelet‐based noise estimation, retinex‐based illumination normalization, multi‐scale frequency fusion, and a dedicated vessel‐preservation branch of retinal data. We test the framework on four standard benchmarks, ExDark and LOL‐v2 to test urban low‐light imagery, DRIVE and STARE to test retinal fundus imaging, and find it is consistent in preserving diagnostically and operationally critical structures. On DRIVE, MDAF++ can achieve a vessel sensitivity of 0.71, which is significantly better than the best classical baseline (0.49), and provides perceptually superior reconstructions in low‐light scenes. These findings indicate a conscious design trade‐off: structural and perceptual utility are put at the forefront over pixel‐wise fidelity, and all the differences reported are statistically significant ( p < 0.001). MDAF++ is currently capable of running on edge platforms where it is infeasible to execute the inference using a GPU. The framework thus provides a practical, cross‐domain denoising pipeline which emphasizes anatomical integrity and scene clarity over traditional fidelity measures.
- 2 June 2026
- Published by Wiley in Applied Research
- Vol. 5 (3)
Noise‐Space Adaptive Multi‐Domain Filtering: A Unified Framework for Low‐Light Urban Surveillance and Medical Retinal Imaging
The increasing demand of imaging systems in urban surveillance and medical diagnostic systems is the ability to adapt to non‐homogeneous acquisition conditions without manually adjusting the system parameters. Current methods are generally tailored to specific domains, struggle to generalise to unseen noise patterns, and often depend on retraining computationally intensive deep networks that require large amounts of annotated data. We seal this divide with MDAF++, a single filtering framework that automatically classifies the input domain, and dynamically repurposes its processing strategy at inference time. Instead of parameterized models, or trained weights, MDAF++ interconnects wavelet‐based noise estimation, retinex‐based illumination normalization, multi‐scale frequency fusion, and a dedicated vessel‐preservation branch of retinal data. We test the framework on four standard benchmarks, ExDark and LOL‐v2 to test urban low‐light imagery, DRIVE and STARE to test retinal fundus imaging, and find it is consistent in preserving diagnostically and operationally critical structures. On DRIVE, MDAF++ can achieve a vessel sensitivity of 0.71, which is significantly better than the best classical baseline (0.49), and provides perceptually superior reconstructions in low‐light scenes. These findings indicate a conscious design trade‐off: structural and perceptual utility are put at the forefront over pixel‐wise fidelity, and all the differences reported are statistically significant ( p < 0.001). MDAF++ is currently capable of running on edge platforms where it is infeasible to execute the inference using a GPU. The framework thus provides a practical, cross‐domain denoising pipeline which emphasizes anatomical integrity and scene clarity over traditional fidelity measures.
- Open Access
- 12 January 2026
- Published by IIUM Press in IIUM Engineering Journal
- Vol. 27 (1) , 321-347
ToxoSegFusion: Attention-enhanced Dual-backbone Neural Architecture for Retinal Lesion Segmentation
Ocular toxoplasmosis (OT) often presents a diagnostic dilemma in clinics, with retinal lesions that are not only varied in appearance but also frequently subtle and underrepresented in fundus images. Current automated segmentation tools, though promising, are often hampered by class imbalance and a lack of robust testing across real-world scenarios. To address these gaps, we developed ToxoSegFusion, a dual-backbone deep learning framework that capitalizes on the complementary strengths of DenseNet121 and ResNet101, enhanced with attention modules. Unlike typical single-backbone models, this hybrid approach was specifically tuned for the intricate challenges of OT lesion segmentation, using a combined Dice and binary cross-entropy loss to better balance rare lesion pixels. We trained and validated on 149 image-mask pairs from the OTFID-Version 3 dataset, achieving an intersection over union of 0.858 and a Dice coefficient of 0.795, both exceeding the current MobileNetV2/U-Net baseline. The model also demonstrated reliable performance on the DRIVE dataset for vessel segmentation, indicating practical flexibility. By facilitating accurate lesion localization, ToxoSegFusion enables more timely interventions in ophthalmology. Future directions include larger multi-center trials and streamlined models for routine deployment. ABSTRAK: Toksoplasmosis okular (OT) sering menimbulkan cabaran diagnostik di klinik, dengan lesi retina halus pelbagai rupa dan kurang terwakili pada imej fundus. Alat segmentasi automatik semasa, walaupun memberi harapan, sering terhad pada ketidakseimbangan kelas dan kekurangan ujian di peringkat perubatan. Bagi mengatasi kekurangan ini, kajian ini membangunkan ToxoSegFusion, sebuah rangka kerja pembelajaran mendalam berkomponen dua yang memanfaatkan kekuatan saling melengkapi DenseNet121 dan ResNet101, diperkaya dengan mekanisme perhatian. Tidak seperti model komponen tunggal biasa, pendekatan hibrid ini dirancang khusus bagi cabaran kompleks segmentasi lesi OT, menggunakan kehilangan Dice dan entropi silang binari gabungan bagi keseimbangan terbaik antara piksel lesi yang jarang. Kajian ini melatih dan mengesahkan 149 pasangan imej-topeng dari set data OTFID-Versi 3, mencapai persilangan atas kesatuan 0.858 dan pekali Dice 0.795, keduanya melebihi garis dasar MobileNetV2/U-Net semasa. Model juga menunjukkan prestasi terbaik pada DRIVE bagi segmentasi salur darah, mencadangkan fleksibiliti praktis. Melalui pengesanan lokasi lesi yang tepat, ToxoSegFusion membuka jalan bagi intervensi lebih tepat pada masa oftalmologi. Pada masa hadapan, cadangan bagi penyebaran rutin adalah melalui ujian berbilang pusat yang lebih besar dan perkemasan model.
- 12 January 2026
- Published by IIUM Press in IIUM Engineering Journal
- Vol. 27 (1) , 321-347
Open AccessToxoSegFusion: Attention-enhanced Dual-backbone Neural Architecture for Retinal Lesion Segmentation
Ocular toxoplasmosis (OT) often presents a diagnostic dilemma in clinics, with retinal lesions that are not only varied in appearance but also frequently subtle and underrepresented in fundus images. Current automated segmentation tools, though promising, are often hampered by class imbalance and a lack of robust testing across real-world scenarios. To address these gaps, we developed ToxoSegFusion, a dual-backbone deep learning framework that capitalizes on the complementary strengths of DenseNet121 and ResNet101, enhanced with attention modules. Unlike typical single-backbone models, this hybrid approach was specifically tuned for the intricate challenges of OT lesion segmentation, using a combined Dice and binary cross-entropy loss to better balance rare lesion pixels. We trained and validated on 149 image-mask pairs from the OTFID-Version 3 dataset, achieving an intersection over union of 0.858 and a Dice coefficient of 0.795, both exceeding the current MobileNetV2/U-Net baseline. The model also demonstrated reliable performance on the DRIVE dataset for vessel segmentation, indicating practical flexibility. By facilitating accurate lesion localization, ToxoSegFusion enables more timely interventions in ophthalmology. Future directions include larger multi-center trials and streamlined models for routine deployment. ABSTRAK: Toksoplasmosis okular (OT) sering menimbulkan cabaran diagnostik di klinik, dengan lesi retina halus pelbagai rupa dan kurang terwakili pada imej fundus. Alat segmentasi automatik semasa, walaupun memberi harapan, sering terhad pada ketidakseimbangan kelas dan kekurangan ujian di peringkat perubatan. Bagi mengatasi kekurangan ini, kajian ini membangunkan ToxoSegFusion, sebuah rangka kerja pembelajaran mendalam berkomponen dua yang memanfaatkan kekuatan saling melengkapi DenseNet121 dan ResNet101, diperkaya dengan mekanisme perhatian. Tidak seperti model komponen tunggal biasa, pendekatan hibrid ini dirancang khusus bagi cabaran kompleks segmentasi lesi OT, menggunakan kehilangan Dice dan entropi silang binari gabungan bagi keseimbangan terbaik antara piksel lesi yang jarang. Kajian ini melatih dan mengesahkan 149 pasangan imej-topeng dari set data OTFID-Versi 3, mencapai persilangan atas kesatuan 0.858 dan pekali Dice 0.795, keduanya melebihi garis dasar MobileNetV2/U-Net semasa. Model juga menunjukkan prestasi terbaik pada DRIVE bagi segmentasi salur darah, mencadangkan fleksibiliti praktis. Melalui pengesanan lokasi lesi yang tepat, ToxoSegFusion membuka jalan bagi intervensi lebih tepat pada masa oftalmologi. Pada masa hadapan, cadangan bagi penyebaran rutin adalah melalui ujian berbilang pusat yang lebih besar dan perkemasan model.
- Top Cited PapersOpen Access
- 26 August 2025
- Published by MDPI AG in Future Internet
- Vol. 17 (9) , 383
Technical Review: Architecting an AI-Driven Decision Support System for Enhanced Online Learning and Assessment
The rapid expansion of online learning platforms has necessitated advanced systems to address scalability, personalization, and assessment challenges. This paper presents a comprehensive review of artificial intelligence (AI)-based decision support systems (DSSs) designed for online learning and assessment, synthesizing advancements from 2020 to 2025. By integrating machine learning, natural language processing, knowledge-based systems, and deep learning, AI-DSSs enhance educational outcomes through predictive analytics, automated grading, and personalized learning paths. This study examines system architecture, data requirements, model selection, and user-centric design, emphasizing their roles in achieving scalability and inclusivity. Through case studies of a MOOC platform using NLP and an adaptive learning system employing reinforcement learning, this paper highlights significant improvements in grading efficiency (up to 70%) and student performance (12–20% grade increases). Performance metrics, including accuracy, response time, and user satisfaction, are analyzed alongside evaluation frameworks combining quantitative and qualitative approaches. Technical challenges, such as model interpretability and bias, ethical concerns like data privacy, and implementation barriers, including cost and adoption resistance, are critically assessed, with proposed mitigation strategies. Future directions explore generative AI, multimodal integration, and cross-cultural studies to enhance global accessibility. This review offers a robust framework for researchers and practitioners, providing actionable insights for designing equitable, efficient, and scalable AI-DSSs to transform online education.
- 26 August 2025
- Published by MDPI AG in Future Internet
- Vol. 17 (9) , 383
Top Cited PapersOpen AccessTechnical Review: Architecting an AI-Driven Decision Support System for Enhanced Online Learning and Assessment
The rapid expansion of online learning platforms has necessitated advanced systems to address scalability, personalization, and assessment challenges. This paper presents a comprehensive review of artificial intelligence (AI)-based decision support systems (DSSs) designed for online learning and assessment, synthesizing advancements from 2020 to 2025. By integrating machine learning, natural language processing, knowledge-based systems, and deep learning, AI-DSSs enhance educational outcomes through predictive analytics, automated grading, and personalized learning paths. This study examines system architecture, data requirements, model selection, and user-centric design, emphasizing their roles in achieving scalability and inclusivity. Through case studies of a MOOC platform using NLP and an adaptive learning system employing reinforcement learning, this paper highlights significant improvements in grading efficiency (up to 70%) and student performance (12–20% grade increases). Performance metrics, including accuracy, response time, and user satisfaction, are analyzed alongside evaluation frameworks combining quantitative and qualitative approaches. Technical challenges, such as model interpretability and bias, ethical concerns like data privacy, and implementation barriers, including cost and adoption resistance, are critically assessed, with proposed mitigation strategies. Future directions explore generative AI, multimodal integration, and cross-cultural studies to enhance global accessibility. This review offers a robust framework for researchers and practitioners, providing actionable insights for designing equitable, efficient, and scalable AI-DSSs to transform online education.
- 14 July 2024
- Published by Springer Nature
- p. 378-387
Alluring Learning on Computer Component Module Using Augmented Reality
- 14 July 2024
- Published by Springer Nature
- p. 378-387
Alluring Learning on Computer Component Module Using Augmented Reality
- 12 October 2023
- Published by Elsevier in Sustainable Energy Technologies and Assessments
- Vol. 60
ECCANS: Enhanced CRITIC-based Context-Aware Network Selection algorithm for 5G HetNet
- 12 October 2023
- Published by Elsevier in Sustainable Energy Technologies and Assessments
- Vol. 60
ECCANS: Enhanced CRITIC-based Context-Aware Network Selection algorithm for 5G HetNet
- Open Access
- 29 May 2023
- Published by MDPI AG in Future Internet
- Vol. 15 (6) , 196
Task Automation Intelligent Agents: A Review
As technological advancements increase exponentially, mobile phones become smarter with machine learning and artificial intelligence algorithms. These advancements have allowed mobile phone users to perform most of their daily routine tasks on mobile phones; tasks performed in daily routines are called repetitive tasks and are performed manually by the users themselves. However, machine learning and artificial intelligence have enabled those tasks to be performed automatically, known as task automation. The users can perform task automation, e.g., through creating automation rules or an intelligent agent, e.g., conversational agents, virtual personal assistants, etc. Several techniques to achieve task automation have been proposed, but this review shows that task automation by programming by demonstration has had massive developmental growth because of its user-centered approach. Apple Siri, Google Assistant, MS Cortana, and Amazon Alexa are the most known task automation agents. However, these agents are not widely adopted because of their usability issues. In this study, two research questions are evaluated through the available literature to expand the research on intelligent task automation agents: (1) What is the state-of-the-art in task automation agents? (2) What are the existing methods and techniques for developing usability heuristics, specifically for intelligent agents? Research shows groundbreaking developments have been made in mobile phone task automation recently. However, it must still be conducted per usability principles to achieve maximum usability and user satisfaction. The second research question further justifies developing a set of domain-specific usability heuristics for mobile task automation intelligent agents.
- 29 May 2023
- Published by MDPI AG in Future Internet
- Vol. 15 (6) , 196
Open AccessTask Automation Intelligent Agents: A Review
As technological advancements increase exponentially, mobile phones become smarter with machine learning and artificial intelligence algorithms. These advancements have allowed mobile phone users to perform most of their daily routine tasks on mobile phones; tasks performed in daily routines are called repetitive tasks and are performed manually by the users themselves. However, machine learning and artificial intelligence have enabled those tasks to be performed automatically, known as task automation. The users can perform task automation, e.g., through creating automation rules or an intelligent agent, e.g., conversational agents, virtual personal assistants, etc. Several techniques to achieve task automation have been proposed, but this review shows that task automation by programming by demonstration has had massive developmental growth because of its user-centered approach. Apple Siri, Google Assistant, MS Cortana, and Amazon Alexa are the most known task automation agents. However, these agents are not widely adopted because of their usability issues. In this study, two research questions are evaluated through the available literature to expand the research on intelligent task automation agents: (1) What is the state-of-the-art in task automation agents? (2) What are the existing methods and techniques for developing usability heuristics, specifically for intelligent agents? Research shows groundbreaking developments have been made in mobile phone task automation recently. However, it must still be conducted per usability principles to achieve maximum usability and user satisfaction. The second research question further justifies developing a set of domain-specific usability heuristics for mobile task automation intelligent agents.
- Open Access
- 4 November 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (21) , 11191
Visual Signifier for Large Multi-Touch Display to Support Interaction in a Virtual Museum Interface
The signifier is regarded as a crucial part of interface design since it ensures that the user can manage the device appropriately and understand the interaction that is taking place. Useful signifiers keep users’ attention on learning, but poorly designed signifiers can disrupt learning by slowing progress and making it harder to use the interface. The problem is that prior research identified the qualities of signifiers, but their attributes in terms of being visually apparent in broad interaction areas were not well recognized. Implementing the signifier without sufficient visual features such as a picture, figure or gesture may interfere with the user’s ability to navigate the surface, particularly when dealing with domains that demand “leisure exploration,” such as those in culture and heritage, and notably the museum application. As technology has evolved and expanded, adopting a multi-touch tabletop as a medium of viewing should be advantageous in conserving cultural heritage. As technology advances and improves, employing a multi-touch tabletop as a public viewing medium should be advantageous in maintaining cultural heritage. Some visual elements should be incorporated into the signifier to produce a conspicuous presentation and make it easier for users to identify. In this study, a preliminary study, a card sorting survey, and a high-fidelity experiment were used to investigate users’ experience, perspective, and interpretation of the visual signifier of the museum interface for large displays. This work offered a set of integrated visual signifiers on a big multi-touch display that makes a substantial contribution to supporting navigation and interaction on a large display, therefore aiding comprehension of the exhibited information visualization.
- 4 November 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (21) , 11191
Open AccessVisual Signifier for Large Multi-Touch Display to Support Interaction in a Virtual Museum Interface
The signifier is regarded as a crucial part of interface design since it ensures that the user can manage the device appropriately and understand the interaction that is taking place. Useful signifiers keep users’ attention on learning, but poorly designed signifiers can disrupt learning by slowing progress and making it harder to use the interface. The problem is that prior research identified the qualities of signifiers, but their attributes in terms of being visually apparent in broad interaction areas were not well recognized. Implementing the signifier without sufficient visual features such as a picture, figure or gesture may interfere with the user’s ability to navigate the surface, particularly when dealing with domains that demand “leisure exploration,” such as those in culture and heritage, and notably the museum application. As technology has evolved and expanded, adopting a multi-touch tabletop as a medium of viewing should be advantageous in conserving cultural heritage. As technology advances and improves, employing a multi-touch tabletop as a public viewing medium should be advantageous in maintaining cultural heritage. Some visual elements should be incorporated into the signifier to produce a conspicuous presentation and make it easier for users to identify. In this study, a preliminary study, a card sorting survey, and a high-fidelity experiment were used to investigate users’ experience, perspective, and interpretation of the visual signifier of the museum interface for large displays. This work offered a set of integrated visual signifiers on a big multi-touch display that makes a substantial contribution to supporting navigation and interaction on a large display, therefore aiding comprehension of the exhibited information visualization.
- 1 November 2022
- Published by IATED Academy in ICERI Proceedings
- Vol. 1, 4315
THE USE OF INTERACTIVE TABLETOP SURFACE IN SUPPORTING STUDENTS’ COLLABORATIVE WORK: INTERACTION AND INTERFACE DESIGN
Information about the paper titled "THE USE OF INTERACTIVE TABLETOP SURFACE IN SUPPORTING STUDENTS’ COLLABORATIVE WORK: INTERACTION AND INTERFACE DESIGN" at IATED Digital Library
- 1 November 2022
- Published by IATED Academy in ICERI Proceedings
- Vol. 1, 4315
THE USE OF INTERACTIVE TABLETOP SURFACE IN SUPPORTING STUDENTS’ COLLABORATIVE WORK: INTERACTION AND INTERFACE DESIGN
Information about the paper titled "THE USE OF INTERACTIVE TABLETOP SURFACE IN SUPPORTING STUDENTS’ COLLABORATIVE WORK: INTERACTION AND INTERFACE DESIGN" at IATED Digital Library
- Top Cited PapersOpen Access
- 3 October 2022
- Published by MDPI AG in Healthcare
- Vol. 10 (10) , 1940
Recent Advancements in Emerging Technologies for Healthcare Management Systems: A Survey
In recent times, the growth of the Internet of Things (IoT), artificial intelligence (AI), and Blockchain technologies have quickly gained pace as a new study niche in numerous collegiate and industrial sectors, notably in the healthcare sector. Recent advancements in healthcare delivery have given many patients access to advanced personalized healthcare, which has improved their well-being. The subsequent phase in healthcare is to seamlessly consolidate these emerging technologies such as IoT-assisted wearable sensor devices, AI, and Blockchain collectively. Surprisingly, owing to the rapid use of smart wearable sensors, IoT and AI-enabled technology are shifting healthcare from a conventional hub-based system to a more personalized healthcare management system (HMS). However, implementing smart sensors, advanced IoT, AI, and Blockchain technologies synchronously in HMS remains a significant challenge. Prominent and reoccurring issues such as scarcity of cost-effective and accurate smart medical sensors, unstandardized IoT system architectures, heterogeneity of connected wearable devices, the multidimensionality of data generated, and high demand for interoperability are vivid problems affecting the advancement of HMS. Hence, this survey paper presents a detailed evaluation of the application of these emerging technologies (Smart Sensor, IoT, AI, Blockchain) in HMS to better understand the progress thus far. Specifically, current studies and findings on the deployment of these emerging technologies in healthcare are investigated, as well as key enabling factors, noteworthy use cases, and successful deployments. This survey also examined essential issues that are frequently encountered by IoT-assisted wearable sensor systems, AI, and Blockchain, as well as the critical concerns that must be addressed to enhance the application of these emerging technologies in the HMS.
- 3 October 2022
- Published by MDPI AG in Healthcare
- Vol. 10 (10) , 1940
Top Cited PapersOpen AccessRecent Advancements in Emerging Technologies for Healthcare Management Systems: A Survey
In recent times, the growth of the Internet of Things (IoT), artificial intelligence (AI), and Blockchain technologies have quickly gained pace as a new study niche in numerous collegiate and industrial sectors, notably in the healthcare sector. Recent advancements in healthcare delivery have given many patients access to advanced personalized healthcare, which has improved their well-being. The subsequent phase in healthcare is to seamlessly consolidate these emerging technologies such as IoT-assisted wearable sensor devices, AI, and Blockchain collectively. Surprisingly, owing to the rapid use of smart wearable sensors, IoT and AI-enabled technology are shifting healthcare from a conventional hub-based system to a more personalized healthcare management system (HMS). However, implementing smart sensors, advanced IoT, AI, and Blockchain technologies synchronously in HMS remains a significant challenge. Prominent and reoccurring issues such as scarcity of cost-effective and accurate smart medical sensors, unstandardized IoT system architectures, heterogeneity of connected wearable devices, the multidimensionality of data generated, and high demand for interoperability are vivid problems affecting the advancement of HMS. Hence, this survey paper presents a detailed evaluation of the application of these emerging technologies (Smart Sensor, IoT, AI, Blockchain) in HMS to better understand the progress thus far. Specifically, current studies and findings on the deployment of these emerging technologies in healthcare are investigated, as well as key enabling factors, noteworthy use cases, and successful deployments. This survey also examined essential issues that are frequently encountered by IoT-assisted wearable sensor systems, AI, and Blockchain, as well as the critical concerns that must be addressed to enhance the application of these emerging technologies in the HMS.