Treffer: Design and Implementation of Alex Net-Honey Badger Fusion Algorithm for Feature Selection and Classification Using Multiclass Support Vector Machine Classifier to Recognize Plant Leaf Disease

In agricultural practices, spotting disease on a crop's leaf is an important yet time-consuming task. Specialized labour and a sizable quantity of time are both required. This paper proposes a computer vision and machine learning-based methodology for the early detection of agricultural leaf disease. An Alex net-Honey badger fusion algorithm for feature selection and classification using multiclass support vector machine classifier to recognize plant leaf disease has been applied in this work. Using Alex Net, features will be extracted and optimized using the HBA fitness function. This performs well in terms of F1 score, recall, precision, and accuracy when compared to previous methods. Using the Honey Badger optimization methodology, the recommended algorithm was further optimized. The exploration and exploitation phases of the HBA model describe the honey badger's dynamic search activity, which includes digging and honey-seeking strategies. In addition, HBA keeps the population diversity sufficient even when the search process comes as a result of carefully chosen randomization procedures. The newly suggested approach is found to have a satisfactory convergence rate using the Alex net-HBA fusion algorithm.