Advanced Classification of Rice Diseases through Hybrid CNN and SVM Models: A Comprehensive Approach

In an effort to advance personalized farming, this study presents a novel hybrid model that combines Support Vector Machine (SVM) and Convolutional Neural Network (CNN) techniques for the accurate classification of rice illnesses. The results of this analysis as revealed by precision scores varying from 91.94% to 95.47% confirm the validity of the model’s ability to eliminate errors of prediction and raise true positives. Despite this, high recall rates ranging from 90.82% to 94.64% also indicate that the model effectively identifies a substantial proportion of true positives. Finally, the harmony of F1 values ranges between 0.9137 and 0.9467, thus confirming the correctness of disease grouping in the given model. Future research directions could be incorporating of new features, investigating data augmentation techniques, or using transfer learning methods for more enhancement of the model’s utility in agricultural set-ups.