Artificial Rabbit Optimization with Improved Deep Learning Model for Plant Disease Classification

Agriculture has played a key role in the Indian economy. Earlier diagnosis of plant disease is highly necessary to avoid spread further of diseases and crop loss. Most plants like apples, cherries, grapes, and tomatoes demonstration visible symptoms of diseases on the leaf. This observable pattern is recognized to correctly forecast the disease and take earlier measures to prevent it. The traditional technique is that plant pathologist or farmers manually detect the plant leaf and recognize the category of diseases. This study introduces an Artificial Rabbit optimization with Improved Deep Learning Model for Plant Disease Classification (AROIDL-PDC) technique. The goal of the AROIDL-PDC technique lies in the recognition and categorization of different plant diseases. At the pre-processing stage, the AROIDL-PDC technique uses median filtering (MF) approach. Besides, improved MobileNeXt technique was executed as a feature extraction approach. Then, the ARO technique is applied for hyperparameter adjustment process. At last, logistic regression (LR) classifier is used for plant disease classification. A series of simulations have been conducted to demonstrate the greater performance of the AROIDL-PDC approach. The experimental results stated that the AROIDL-PDC technique has gained improved results over other models.