A Dragonfly Optimization based Machine Learning Framework for Plant Disease Detection and Classification to Boost Agriculture Productivity

Timely and accurate identification of plant diseases plays a crucial role in maintaining crop health and improving agricultural productivity. Traditional machine learning and deep learning methods have shown promise in plant disease classification, but challenges remain in feature selection and hyperparameter tuning. This paper proposes a methodology utilizing the Dragonfly Optimization Algorithm (DOA) to enhance both feature selection and the hyperparameter tuning of a Convolutional Neural Network (CNN) model. The optimized framework was evaluated using the several plant disease dataset. Experimental results demonstrate that the proposed DOA- based approach significantly improves classification accuracy, reaching up to 97.85%, and accelerates convergence, outperforming traditional methods such as Genetic Algorithms, Particle Swarm Optimization, and baseline CNNs. The model’s efficiency and high accuracy make it suitable for real-time deployment in agricultural decision-support systems.