Environmental Monitoring Of Mango Leaf Diseases And Sustainable Treatment Using Hybrid Pso Optimization

Abstract

The categorization of the mango leaf enhances the classification process's performance by selecting the best attributes. The process becomes less complex in terms of time and algorithms when the best features are chosen. To identify the diseases in the photos of the mango leaf infection zone, KAGGLE images were utilized. Mango leaf illnesses, including bacterial black spot, twig blight, gummosis, anthracnose, and bark splitting, have been tested. From LBP features, features were retrieved. Five distinct classifiers were then used to classify the chosen features in order to evaluate their effectiveness.The performance measures were used to gauge the process's overall effectiveness. The process's primary goal is to choose the best characteristics from among the several feature types that were retrieved using various techniques. to evaluate how well various classifiers perform using the chosen features. to extract various aspects from the photos, such as texture-based and intensity-based features. Using hybrid PSO optimization techniques, this work uses the best analysis of mango leaf disease detection, classification, and therapy. The accuracy of this work in the testing datasets is 97%. Performance indicators such as accuracy, sensitivity, and specificity were used to gauge the process's effectiveness. This job was carried out with exceptional efficiency using MATLAB.