Publication

Abstract :

Improving infectious disease prediction is vital for understanding epidemic dynamics and guiding public health interventions. Accurate predictive models are crucial for comprehending the complexities of epidemics. This research introduces a predictive framework using Dynamic Mode Decomposition (DMD) to model and forecast infectious disease spread. DMD, a data-driven technique, extracts insights from time-series data, identifying inherent dynamics and predicting future trends. The methodology is applied to COVID-19 data, demonstrating its practicality. Dynamic modes are computed through low-rank truncation and singular value decomposition in the proposed approach. These modes are then processed to forecast the disease spread's future trend. This research presents a robust infectious disease prediction approach, integrating DMD with comprehensive data analysis. Ensuring accurate predictions is essential for timely identification of potential disease outbreaks.