<![CDATA[The durian plant (Durio zibethinus Murr.) is one of the leading tropical fruit agricultural products in Indonesia with high economic value. However, durian productivity is often disrupted by leaf disease attacks such as Algal Leaf Spot, Leaf Blight, and Leaf Spot, which results in a decrease in the quality of the crop and its quantity. As a step to address this problem, the goal of this study is to automatically detect durian leaf disease using the YOLOv8 algorithm, a new deep learning model developed to detect objects directly in real time. This study used a data set that included 420 images of durian leaf disease in four categories, Algal Leaf Spot, Leaf Blight, Leaf Spot, and No Disease. This study uses three dataset distribution scenarios (70:20:10, 75:15:10, and 80:10:10), with various epoch and batch size configurations. The results show that the 70:20:10 scenario with 100 epochs and batch size 16 produces the best performance, with a precision value of 0.994, recall of 0.989, mAP50 of 0.990, and mAP50-95 of 0.927. The model developed is able to detect durian leaf disease with high accuracy and fast inference time. The implementation of this model through the Roboflow platform allows efficient use and is ready to be implemented to support the sustainable increase in durian productivity. This research also makes a significant contribution to the development of deep learning-based agricultural technology in Indonesia.]]>
Copyrights © 2024
