Diagnostic Framework for Mumps Based on Deep Learning with Enhanced Mayfly Optimization Algorithm

The mumps virus causes a very infectious sickness. The enlargement of the parotid salivary glands can be quite uncomfortable. Mumps treatment centers on symptom management. The illness must take its natural course. While most people experience very moderate symptoms, some develop severe consequences. The mumps virus can be avoided with the use of the MMR vaccination. In this research, we employ a convolutional neural network (CNN) technique to better automate mumps detection. In order to automate mumps detection, the authors of this research suggest a convolutional neural network (CNN) trained using XGBoost Classifier data. Incorporating machine learning (ML) technique comparisons. A mumps dataset consisting of 50×50 RGB picture patches served as the basis for all the models. Quantitative findings from each approach were put through validation testing based on their respective effectiveness metrics. To improve the efficiency of the model, the Mayfly Optimization Algorithm is implemented. Results show that the suggested method is effective, with 97% accuracy, suggesting that it might help decrease diagnostic errors caused by human error. And the suggested system we've developed is so precise that it outperforms the CNN model, which only gets around 92% of the time. Consequently, the suggested method is 5% more accurate than the CNN Model.