International Journal of Information Technology and Applications, Vol. 1, No. 2, pp. 74-80, June 2024.
Abstract: In recent years, plant disease detection has grown in importance for biotechnology, and its uses include growth guidance for plants. This paper presents a novel deep neural method based on the sensor network Swin Transformer-YOLO (ST-YOLO) that performs plant disease detection and segmentation to prevent the plants and fruits from spreading disease and to guide biological growth. Several experiments were performed to validate the proposed method. The results showed that obtaining information on the disease detection and biological state based on the RoCoLe dataset using ST-YOLO was more accurate and efficient than other typical methods. In particular, the mAP50 of the proposed approach is 0.987, 0.7% higher than state-of-the-art approaches. Therefore, the proposed approach is practical.