Authors - Md. Abdul Malek Sobuj, Md. Faruk Abdullah Al Sohan, Afroza Nahar, Saeeda Sharmeen Rahman Abstract - Tomato leaf diseases lead to significant losses in yield and quality, especially in developing areas where timely diagnosis and expert help are scarce. Early and accurate disease detection is vital for sus tainable crop protection and better agricultural productivity. This pa per proposed a hybrid AI-IoT imaging framework for early-stage multi label tomato leaf disease detection in real-field agricultural settings. The proposed hybrid framework combines camera-based IoT sensing, edge and cloud computing, and a lightweight hybrid CNN, the Transformer model, to allow continuous monitoring, timely diagnosis, and decision support. The proposed hybrid framework merges local feature extrac tion with global context modeling to enable accurate multi-label clas sification while being suitable for deployment on devices with limited resources. A conceptual performance comparison and case study show the practical feasibility and benefits of this approach regarding diagnos tic reliability, scalability, and cost-effective deployment. The framework aims to improve early disease identification, reduce crop losses, and sup port precision agriculture practices. This study offers a practical and scalable solution for intelligent tomato disease management and aids the development of sustainable AI-IoT-based smart agriculture systems.
Open Zoom