Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) Journal of Sustainable Software Engineering and Information Systems
Wan Hussain Wan Ishak
Universiti Utara Malaysia
Computer Science & IT Engineering

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Evaluation of scratch and pre-trained convolutional neural networks for the classification of Tomato plant diseases Mohammad Amimul Ihsan Aquil; Wan Hussain Wan Ishak
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 10, No 2: June 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v10.i2.pp467-475

Abstract

Plant diseases are a major cause of destruction and death of most plants and especially trees. However, with the help of early detection, this issue can be solved and treated appropriately. A timely and accurate diagnosis is critical in maintaining the quality of crops. Recent innovations in the field of deep learning (DL), especially in convolutional neural networks (CNNs) have achieved great breakthroughs across different applications such as the classification of plant diseases. This study aims to evaluate scratch and pre-trained CNNs in the classification of tomato plant diseases by comparing some of the state-of-the-art architectures including densely connected convolutional network (Densenet) 120, residual network (ResNet) 101, ResNet 50, ReseNet 30, ResNet 18, squeezenet and Vgg.net. The comparison was then evaluated using a multiclass statistical analysis based on the F-Score, specificity, sensitivity, precision, and accuracy. The dataset used for the experiments was drawn from 9 classes of tomato diseases and a healthy class from PlantVillage. The findings show that the pretrained Densenet-120 performed excellently with 99.68% precision, 99.84% F-1 score, and 99.81% accuracy, which is higher compared to its non-trained based model showing the effectiveness of using a combination of a CNN model with fine-tuning adjustment in classifying crop diseases.
Personalized E-Portfolio: A Dynamic Web-based Tool for Students’ Professional Growth Muhammad Syamil bin Manaf; Wan Hussain Wan Ishak; Fadhilah Mat Yamin
Journal of Sustainable Software Engineering and Information Systems Vol. 1 No. 1 (2025): Journal of Sustainable Software Engineering and Information Systems
Publisher : CV Media Inti Teknologi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58723/jsseis.v1i1.64

Abstract

Background of study: Electronic portfolios (e-portfolios) have become vital tools for students to document learning and build professional identity. Yet, many existing platforms are hindered by technical complexity, limited personalization, and low engagement. Aims and scope of paper: This paper introduces a personalized e-portfolio system designed to overcome these issues by applying agile and user-centered approaches, focusing on usability and adaptability in higher education. Methods: The system was developed using HTML, CSS, JavaScript, PHP, and phpMyAdmin through six agile phases: planning, design, development, testing, deployment, and review. User needs were gathered from students and lecturers, while 30 students evaluated the system using the Website Analysis and Measurement Inventory (WAMMI) across five usability factors. Result: Usability testing showed high satisfaction. Learnability (4.47), controllability (4.22), and efficiency (4.17) scored the highest, indicating that the system is intuitive and effective. Participants valued its role in reflection and personal branding, while suggesting improvements in visual design, customization, and integration with platforms like LinkedIn. Conclusion: The study confirms that agile and user-centered design can produce an adaptable e-portfolio system that enhances students’ professional growth and provides a scalable model for higher education institutions.
Development of a Web-Based Industrial Training Student Activity Management System Wan Hussain Wan Ishak; Siti Nur Aisyah binti Abdullah
Journal of Sustainable Software Engineering and Information Systems Vol. 1 No. 1 (2025): Journal of Sustainable Software Engineering and Information Systems
Publisher : CV Media Inti Teknologi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58723/jsseis.v1i1.65

Abstract

Background of study: Industrial training is essential for bridging academic knowledge and workplace practice, equipping students with technical and soft skills required for future employment. However, traditional documentation methods such as manual logbooks are often inefficient, error-prone, and limit effective supervision and timely feedback. Aims and scope of paper: This paper presents the development of the Web-Based Industrial Training Student Activity Management System (WIT), designed to streamline industrial training management at the School of Computing, Universiti Utara Malaysia. The system aims to enhance communication, ensure accurate reporting, and support sustainable digital supervision. Methods: The WIT system was developed using the Waterfall Model, with stakeholder input incorporated at each stage of requirements, design, development, testing, and maintenance. Usability testing was conducted with 30 participants (students and staff) using the WAMMI framework, which evaluates five key usability dimensions. Result: The evaluation results demonstrated high levels of user satisfaction across all metrics: Attractiveness (91.67%), Controllability (97.5%), Helpfulness (94.17%), Efficiency (92.5%), and Learnability (96.67%). These findings confirm that WIT provides an effective, user-friendly platform for activity logging, reporting, and supervision. Conclusion: WIT successfully addresses challenges in traditional training management by promoting transparency, accountability, and efficient supervision. The system contributes to ICT-driven educational innovation and has strong potential for future scalability, including mobile integration and advanced analytics.
Co-Authors Fadhilah Mat Yamin Mohammad Amimul Ihsan Aquil Muhammad Syamil bin Manaf Siti Nur Aisyah binti Abdullah