Precision in Plant Pathology: A Hybrid Model Approach for BYDV Syndrome Degrees

Barley Yellow Dwarf Disorder (BYDV) is a big danger to grains, so we need better ways for early finding and the right grouping. This study answers this important question by introducing a new mixed model. It helps combine the best parts of convolutional neural networks (CNN) and naive Bayes algorithms to make smart decisions. The main goal is to classify how bad BYDV sickness is in three categories. This step will help put control measures and reduce the loss of crops into effect. The start of the model's plan comes from a very carefully chosen set of 8600 high-quality pictures showing barley plants with BYDV disease. These came together to make up its data until they were ready for use. In this data set, our mix of models does very well with an overall correct rate that could be as high as 97.30%. It is useful for seeing how different diseases show up. Going beyond simple correctness, exact performance measures like accuracy, precision, and recall give a detailed assessment of how well the model can make decisions between things. This big look shows how good the model is at reducing both wrongly saying something matters and not recognizing it enough in all levels of BYDV sickness. This three-way check helps us to know more about the model's skills in dealing with the hard job of separating BYDV into different groups. Additionally, by comparing our mixed method model with what already exists in books and research articles we gain insight into its unique benefits.