Evolutionary Optimization of Epidemic Control Strategies for Livestock Disease Prevention

This paper concerns optimizing counter-epidemic strategies selecting actions which differ with respect to the cost, damage to the animal population and the potential of stopping the disease. Important factors that have to be taken into account are the time it takes for the vaccine to become effective and the dynamic of the epidemic. This paper focuses on optimizing control strategies rather than individual decisions in the case of a particular epidemic. An evolutionary optimizer using simulations for solution evaluation is run in order to gather training data. Based on the training data a regression model is built which can subsequently be used to improve the results obtained when solving new instances of the proposed problem. Experimental results show, that the model can be used to transfer knowledge from previously solved instances to new ones.