Monkeypox Transmission Dynamics Using Fractional Disease Informed Neural Network: A Global and Continental Analysis

The prediction of disease dynamics is crucial for understanding and managing the spread of diseases. This research focuses on developing a hybrid deep learning-based system to predict disease dynamics using skin image data. The dataset, which includes images related to monkeypox and other diseases, is analyzed through three hybrid models: MobileNet+Spatial, CNN, and Inception+GRU. The system is implemented using a Flask-based backend and a web interface built with HTML, CSS, and JavaScript, allowing users to upload images for disease classification. By combining the strengths of each model, the system aims to offer high accuracy in predicting disease progression across global and continental regions. The research aims to contribute to better healthcare decision-making by providing a tool that can aid in early detection and classification of diseases, thus mitigating potential health risks. The evaluation metrics include accuracy, precision, recall, and F1 score, with comparative analysis against traditional models. The hybrid approach offers improved performance and scalability, ensuring robust disease prediction.

Keywords: Disease Prediction, Hybrid Deep Learning, MobileNet, CNN, GRU, Inception, Flask, Image Classification, Disease Dynamics, Global Study.