ABSTRACT

This study developed a Pinilisa Rice Disease Detection and Classification Support System to address the challenges rice growers face, such as limited knowledge of diseases, misdiagnosis, and restricted access to agricultural experts. Using a descriptive and developmental research design, the system employed YOLOv8 and Convolutional Neural Networks (CNNs) for accurate disease detection. Implemented as a desktop application, the system demonstrated high compliance with ISO 25010 Software Quality Standards and delivered significant benefits, including timely interventions and improved crop yields. User feedback suggested enhancements such as severity detection, real-time imaging, and multilingual support. This research demonstrates the potential of machine learning to revolutionize agricultural practices, benefiting farmers and policymakers while contributing to sustainable rice cultivation.

Keywords: Agile eXtreme programming, Decision Support System (DSS), Pinilisa Rice Disease Detection, Supervised Convolutional Neural Network (CNN)
https://doi.org/ 10.57180/dofs9114