Cultivating Precision: A Multi-Layer Perceptron Approach for Accurate Classification of Maize Rust Disease Intensity in Precision Agriculture

Corn rust disease, which is induced by diverse fungal infections, presents a substantial peril to global food security since it impacts a fundamental crop that serves as a mainstay for many populations worldwide. This study aims to tackle the difficulties associated with conventional manual assessment techniques for measuring the intensity of maize rust disease. It proposes a systematic methodology that harnesses the power of deep learning. The research utilizes a multi-layer perceptron (MLP) model, employing a well-selected dataset to attain a noteworthy overall accuracy of 94.87%. The architecture of the MLP demonstrates proficiency in catching intricate patterns that are linked to varying levels of illness severity. The findings, as demonstrated by a detailed performance parameter table and confusion matrix, showcase the model's accuracy in detecting differences in disease severity. The suggested MLP has both superior accuracy and computational efficiency when compared to state-of-the-art approaches, as highlighted by the comparative study. In addition to its direct relevance to the management of maize rust disease, this study makes a valuable contribution to the wider field of precision agriculture. It presents scalable and efficient approaches that can be applied to tackle significant issues in global food security.