Development of a Decision Support System for Predicting the Evolution of Epidemics Using Open-Source Software Tools
Year: 2025
Type: book-chapter
Abstract: This study presents a Decision Support System to predict epidemic trends in Greece using Open-Source software and machine learning algorithms. The system uses data from OurWorldData.org on COVID-19 from early 2020 to December 2022. We assess the accuracy of five forecasting algorithms: Linear Regression, Back Propagation (BP), Long Short-Term Memory (LSTM), ARIMA, and Prophet. By evaluating correlation, Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE), we identify the ARIMA model as the most effective for this context. Comparative analysis highlights the system's predictive reliability in Greek COVID-19 trends and suggests implications for broader epidemic forecasting applications.
DOI: 10.3233/shti250126
Authors: Myrto Papakonstantinou, Emmanouil Zoulias, Parisis Gallos, John Mantas
Institution: National and Kapodistrian University of Athens
Language: English
Subfield: Modeling and Simulation
Field: Mathematics
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4409265860