Journal of Multidisciplinary Sustainability Asean https://journal.ypidathu.or.id/index.php/multidisciplinary <p style="text-align: justify;"><strong>Journal of Multidisciplinary Sustainability Asean </strong>is an international peer-reviewed journal dedicated to facilitating the exchange of results of high-quality research in all aspects of all areas of knowledge. The scope of the Journal of Multidisciplinary Sustainability Asean is not only in the form of study, research, or development but also book review. This journal publishes articles from all areas, including agricultural sciences, health sciences, biological sciences, engineering, and other exact sciences, as well as social and human sciences, which should contribute to scientific knowledge. Types of papers accepted: Review Articles, Mini-Reviews, and Research Articles with Questionnaires Application. As our commitment to advancing science and technology, the Journal of Multidisciplinary Sustainability Asean follows an open-access policy that allows published articles to be freely available online without any subscription. Submitted papers must be written in English for the initial review stage by editors and further review by at least two international reviewers.</p> Yayasan Pendidikan Islam Daarut Thufulah en-US Journal of Multidisciplinary Sustainability Asean 3048-2461 Design of Shrimp Skin-Based Nano-Biodegradable Material for Eco-Friendly Food Packaging https://journal.ypidathu.or.id/index.php/multidisciplinary/article/view/2250 <p><strong>Background. </strong>The problem of plastic waste from food packaging continues to increase and poses a serious threat to the environment. The development of biodegradable-based eco-friendly packaging materials is one of the solutions that is getting more and more attention, especially those that come from organic waste such as shrimp skins that are rich in chitin.</p> <p><strong>Purpose.</strong> This research aims to design a nano-biodegradable material based on shrimp skin that can be used as environmentally friendly food packaging, by evaluating its mechanical strength, water resistance, biodegradability ability, and application effectiveness in real conditions.</p> <p><strong>Method.</strong> The research uses laboratory experiment methods with a quantitative approach. The shrimp skin is extracted into chitosan, then modified into a nanoform using the ionic gelation technique. Performance tests include tensile strength analysis, water contact tests, biodegradation tests, as well as application case studies on fresh fruit packaging.</p> <p><strong>Results. </strong>The developed material shows high mechanical strength, good water resistance, and decomposes perfectly in a humid soil environment in less than 30 days. Direct application to the fruit shows effectiveness in maintaining freshness and preventing microbial contamination.</p> <p><strong>Conclusion</strong>. The design of nano-biodegradable material from shrimp skin has the potential to be an alternative solution to plastic in food packaging, with ecological benefits and added value from the use of marine organic waste. </p> Juwairiah Juwairiah Ming Pong Copyright (c) 2025 Juwairiah Juwairiah, Ming Pong https://creativecommons.org/licenses/by-sa/4.0 2025-07-18 2025-07-18 2 3 120–130 120–130 10.70177/ijmsa.v2i3.2250 AI-Assisted Early Detection of Crop Disease Using Hyperspectral Imaging and Deep Learning in Smallholder Farms https://journal.ypidathu.or.id/index.php/multidisciplinary/article/view/2305 <p><strong>Background. </strong>Crop disease is a major threat to smallholder farmers who lack access to timely diagnostic tools. Traditional detection methods rely on visual inspection and often occur too late to prevent significant yield losses. Early detection using hyperspectral imaging and artificial intelligence presents a transformative solution for precision agriculture in resource-limited settings.</p> <p><strong>Purpose.</strong> This study aims to develop and evaluate an AI-assisted early detection system for crop diseases using hyperspectral imaging and deep learning, tailored for application in smallholder farms.</p> <p><strong>Method.</strong> A convolutional neural network (CNN) model was trained on hyperspectral data collected from five farm sites, with ground-truth annotations by agricultural experts. The model’s performance was evaluated using standard classification metrics, including accuracy, precision, recall, and F1-score. A case study was also conducted to assess real-world applicability.</p> <p><strong>Results. </strong>The model achieved an average detection accuracy of 94.2% across all locations, with F1-score reaching 0.92 when using hyperspectral features. Confusion matrix analysis indicated high true positive and true negative rates, confirming reliability. In a field case, early diagnosis enabled targeted intervention and improved yield by 22% compared to prior seasons.</p> <p><strong>Conclusion</strong>. The integration of hyperspectral imaging and deep learning offers a practical and scalable solution for early disease detection in smallholder farms. The system demonstrates high accuracy, adaptability, and operational feasibility in real-world conditions. Future work should focus on expanding crop and disease types, user interface development, and integration with mobile and IoT-based platforms. </p> Ardi Azhar Nampira Siti Mariam Copyright (c) 2025 Ardi Azhar Nampira, Siti Mariam https://creativecommons.org/licenses/by-sa/4.0 2025-07-18 2025-07-18 2 3 109–119 109–119 10.70177/ijmsa.v2i3.2305