Hybridized Model for Improved Papaya Leaf Disease Classification: CNN and Random Forest Integration

The main goal of the study is to find a way to group things into categories that can be used to find diseases in papaya leaves. To reach this objective, this framework will be planned and checked in line with the requirements. Plants can be put into the following six groups so the model can properly sort them: “Healthy,” “Papaya Ringspot Virus (PRSV),” “Papaya Leaf Curl Virus (PLCV),” “Powdery Mildew,” “Papaya Mosaic Virus (PapMV),” and “Leaf Spot Diseases.” Random Forest along with Convolutional Neural Networks, or CNN for short, are both used together by the model at the same time. Several variables, including accuracy, recall, and F1-score, are used to measure how well the model can tell the difference between these groups. The model has accuracy rates that range from 94.44% to 96.22%, which shows that it can correctly identify a wide range of illnesses, as the results show. This shows that the system can give accurate positive predictions. The remembering rates run from 94.12% to 96.13%, which also shows that the model can correctly tell the difference between events that involve each illness. These things are clear because this model works well. The F1 scores, which add up to an average of 95.48%, show that tasks have been consistently completed. In this study, the results show that there is a mix of accuracy and memory. The model has also gotten a total value of 95.49%, which shows how well it can find diseases that show up on papaya leaves right now. This number includes both good and bad results. The system seems to be accurate and useful for finding diseases based on the results of these tests. This means that the technology might be able to be used in real farming situations.