• Dr MEENAKSHI T

Plant diseases pose a serious threat to global food security by significantly reducing crop yield and quality. Conventional disease detection techniques rely on manual inspection, which is labour-intensive, time-consuming, and prone to human error. This paper proposes a novel AI–IoT enabled Smart Agriculture Pivot system for real-time plant disease detection and automated treatment. The system integrates a ResNet50 deep learning model for image-based disease classification with an IoT-based actuation framework using an ESP32-CAM controller. A dataset of 25,940 augmented leaf images across 11 classes was used for training and evaluation. Experimental results demonstrate a testing accuracy of 99.8%, precision of 100%, recall of 99.9%, and an F1-score of 99.9%. Unlike drone- or robot-based systems, the proposed pivot-based approach offers a stable, energy-efficient, and closed-loop solution that enables immediate localized treatment, reducing pesticide usage by up to 40%. The results confirm the effectiveness of the proposed system for scalable and sustainable precision agriculture.

Smart Agriculture, Plant Disease Detection, ResNet50, Internet of Things, ESP32-CAM, Precision Farming, Edge AI

"Smart Agriculture Pivot for Real-Time Plant Disease Detection and Automated Treatment Using AI–IoT Techniques", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 1, page no.d629-d633, January-2026, Available :http://www.jetir.org/papers/JETIR2601382.pdf

"Smart Agriculture Pivot for Real-Time Plant Disease Detection and Automated Treatment Using AI–IoT Techniques", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 1, page no. ppd629-d633, January-2026, Available at : http://www.jetir.org/papers/JETIR2601382.pdf