<![CDATA[Corn plants can grow well in areas with hot or tropical temperatures as long as there is adequate rainfall and an adequate irrigation system. Corn is a strategic agricultural commodity that plays an important role in the economy, both on a national and global scale. According to data from the official website satudata.pertanian.go.id, the projection of corn production in Indonesia in the period 2020 to 2024 is estimated to experience a stable annual increase, ranging from 0.94% to 0.97%. However, during its life cycle from seed to seed, every part of the corn is susceptible to a number of diseases that can reduce the quantity and quality of the results. Therefore, the problem of disease is one of the factors that constrains the production and quality of seeds. In this study, detection of types of diseases and pests in corn plants was carried out using YOLOV8 technology as a form of innovation in corn agricultural intelligence. The dataset used in this study consists of four classes of corn leaf images, namely dry spots, blight, rust and healthy plants with a total of 1162 datasets. The dataset was taken at the same time using the POVA Pro5 smartphone. Based on the results of model training and evaluation, it was obtained that with a batch size of 32 and epoch 64, the precision value reached 0.67, recall 0.78, f1 score 0.67, Map0.5 0.701, and Map0.5:0.95 0.295. Meanwhile, with a batch size of 64 and epoch 100, the precision value increased to 0.75, recall 0.79, f1 score 0.75, Map0.5 0.792, and Map0.5:0.95 0.343. These findings indicate that the application of YOLOv8 technology has the potential to provide significant contributions to the development of smart farming systems, especially in efforts to detect early disturbances in corn plants automatically and efficiently. The availability of accurate information on the types of diseases and pests that attack corn plants allows farmers to respond quickly and appropriately, including through the selection of more targeted pesticide use or the application of organic control methods that are appropriate to field conditions.]]>
