<![CDATA[This study developed a web-based oil palm disease detection system to help farmers and related parties quickly and accurately identify diseases based on symptoms observed in the field. The system was built using the CRISP-DM framework, which includes the stages of business understanding, data understanding, data preparation, modelling, evaluation, and implementation. The classification method used is Classification and Regression Tree (CART) due to its ability to handle categorical data and provide easy-to-understand interpretations. The symptom dataset was compiled based on literature references, direct observations, and official data from the North Aceh District Food Crop Agriculture Office and a number of scientific journals. The data consists of 11 main symptoms with a predetermined severity scale. The evaluation results showed excellent model performance, with an accuracy of 95.45%, precision of 97%, recall of 95%, and an F1-score of 95%. The trained model was then integrated into a Flask-based web application, enabling users to input symptoms to obtain disease predictions and management solutions. The novelty of this research lies in the use of relevant local data, the adoption of a symptom-based approach instead of image-based methods, and the integration of the classification model into an applicable web-based system. This system is expected to enhance efficiency, accessibility, and accuracy in decision-making related to disease management.]]>
Copyrights © 2025
