<![CDATA[Plant diseases are a serious challenge in the agricultural sector, especially bacterial leaf blight (BLB) in rice, which can reduce productivity and cause economic losses. This study aims to develop a BLB classification model based on the lightweight Gaussian Naive Bayes algorithm that can be applied in areas with limited technology. Rice leaf image data was collected from the field, processed through preprocessing and visual feature extraction stages, then classified using Gaussian Naive Bayes with evaluation based on accuracy, precision, recall, F1-score, and AUC. The results show an accuracy of 63.07%, precision of 56.16%, recall of 90.64%, F1-score of 69.35%, and AUC of 0.7728. The high recall value confirms the model's ability to detect most infected leaves, while the AUC indicates fairly good classification performance. This model has also been integrated into a web application prototype with a simple user interface, where users can upload leaf images for automatic analysis. The results of this study are expected to be used to support early warning systems for plant diseases and assist farmers in making quick and efficient disease control decisions. This research contributes to the development of machine learning-based early detection systems to improve sustainable agricultural productivity.]]>
Copyrights © 2025
