Optimizing the impact of virus transmission on society: decreasing infection rates and enhancing public awareness.

This paper studies the interaction between viral spread and opinions during a viral pandemic, and the optimization problem of how to control infection rates and opinions. In our model, we incorporate two control inputs to minimize both the inter-community infection proportions and variations in individuals' perceptions of the disease. The optimization problem is transformed into solving an Hamilton–Jacobi–Bellman (HJB) equation. Using single-critic neural network and approximate estimation neural network, we determine the optimal control law of the optimization model. We perform parameter fitting of a virus-opinion coupled network model using SARS-CoV-2 pandemic data from Johns Hopkins University. Compare the fitted data with the actual data through the Pearson correlation coefficient to evaluate the reasonableness of the initial fitted values. Finally, the model is optimized using the obtained strategy, resulting in refined and improved results. [ABSTRACT FROM AUTHOR]