iLu Vsion: A CNN-Based Classification of Coconut Tree Diseases for Smart Farming

Utilizing advanced machine learning methods in agriculture has great potential for enhancing crop management and increasing productivity. This research introduces iLuVsion, a novel CNN methodology for precisely classifying and identifying diseases in coconut trees. The main goal of this innovation is to encourage the implementation of smart farming practices. The study area is within a certain municipality on Sibuyan Island in the Philippines. The proposed method utilizes images of coconut tree leaves and trunks to identify and classify widespread diseases such as leaf spots, white flies, leaf miners, beetles, and termites. iLuVsion performs well in disease detection because of the utilization of a deep CNN model using VGG16 architectures, which is trained on an extensive dataset comprising images of diseased leaves and trunks. This enables early intervention and effective disease management. This research enhances smart agriculture techniques in coconut farming by integrating new technologies and machine learning models. The model's effectiveness is assessed using established measures, showcasing its performance in real-world situations. The model's improves accuracy of 98.21% and minimizes the necessity for human inspections, resulting in time and resource savings for farmers.