Modeling and Predicting Monkeypox Spread Using Fuzzy Logic and Machine Learning Regression Techniques

Understanding the dynamics of infectious disease such as Monkeypox is critical for effective public health intervention. This study integrates fuzzy logic based mathematical modeling and machine learning techniques to capture the complexities and uncertainties inherent in real world disease dynamics. A fuzzy logic approach was employed to assign weighted values to key parameters, enabling a more flexible representation of disease spread. Simulations revealed a significant shift in the disease-free equilibrium, with the number of susceptible individuals declining from 1000 to 185 as parameter weights varied. To complement the modeling, three machine learning regression models - Linear Regression Polynomial Regression and Decision Tree Regression were evaluated for predicting univariate time series data. Results showed that polynomial Regression outperformed the others across all standard metrics (RMSE, MAE, MAPE, MSE), effectively capturing the underlying nonlinear patterns in data. These findings emphasize the importance of incorporating both uncertainty aware modeling and appropriate machine learning techniques for accurate prediction and strategic planning on disease control. Further work may explore advanced nonlinear models such as Support Vector Regression and LSTM networks for enhanced long-term forecasting.