Plant Leaf Disease Detection and Recommendation System using Alex Net-Honey Badger Fusion Algorithm

Introduction: Plant diseases pose a significant challenge to the agriculture sector, affecting crop yield and quality, and thereby impacting the global economy. This paper discusses the urgent requirement for effective and precise detection and management of plant diseases. Objective: Utilizing the latest developments in machine learning and deep learning, specifically Convolutional Neural Networks (CNNs), we present a streamlined algorithm for identifying plant leaf diseases and providing treatment recommendations. To increase feature selection and classification accuracy, this method combines the strengths of the Honey Badger method (HBA) and antlion optimisation (ALO). Methods: This research thoroughly validates the suggested algorithm on a dataset of 87,000 RGB images that are categorised into 38 distinct plant diseases in order to compare it with state-of-the-art methods already in use. Result: The outcomes demonstrate outstanding performance with respect to accuracy, precision, recall, and F1-score, outperforming traditional models like Random Forest (RF), Support Vector Machine (SVM), and other deep learning models. By adding a recommendation mechanism to the algorithm, this work significantly advances the field by providing useful guidance on the management and prevention of diseases. Conclusion: The study has important ramifications for plant pathology and agricultural technologies. It offers farmers practical ways to successfully fight plant diseases, hence lowering food insecurity and improving crop productivity.