Enhanced Citrus Fruit Disease Detection: Combining CNN and Random Forest Models

In this study, through an emphasis on the precision, recollection, F1-Score, encouragement, support proportion, etc. accuracy metrics across different criticality stages, indicating varied degrees of disease severity, the abstract gives a general summary of the classification of the model's performance evaluation. This evaluation is shown in the table. The accurate values for each of the criticality stages, which range between 92.57% to 93.75%, show how accurately the model can categorize occurrences within each stage. This demonstrates its accuracy in reducing false positives and ensuring that situations are found that are relevant. The model's accuracy in properly detecting pertinent cases is further demonstrated by the recall values, which range from 92.49% to 93.68%, demonstrating its capacity to reduce false negatives. This supports the model's accuracy in classifying diseases The model's ability to simultaneously optimize recall and accuracy across several criticality stages is shown by the balanced F1-scores, which range from 92.75% to 93.51%. This balance highlights its reliable functioning. With counts that vary from 865 to 965, the support values show how the dataset is distributed throughout the criticality stages. The model's capacity to adapt to diverse illness severity levels is demonstrated by the model's ability to efficiently handle a variety of cases in each stage. The model's ability to function dependably across various proportions of the importance stages is highlighted by the support proportion values, further demonstrating the consistency of the model. The model regularly makes correct predictions throughout all criticality phases, with a remarkable overall accuracy of 98%. This high level of accuracy highlights how well it classifies the severity of diseases. The abstract concludes with a succinct review of the performance of the classification model, highlighting its precision, remember, F1-scores, assistance, support proportion, etc. accuracy metrics. A helpful tool for healthcare or disease management applications, the model routinely exhibits accuracy and dependability in identifying illness severity across several criticality stages.