id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-225640-l0z56qx4	Ghamizi, Salah	Data-driven Simulation and Optimization for Covid-19 Exit Strategies	2020-06-12		.txt	text/plain	4956	242	54	We have therefore built a pandemic simulation and forecasting toolkit that combines a deep learning estimation of the epidemiological parameters of the disease in order to predict the cases and deaths, and a genetic algorithm component searching for optimal trade-offs/policies between constraints and objectives set by decision-makers. As illustrated in Figure 1 , we propose to combine a genetic algorithm (to search for policy schedules), a deep learning model (to predict the evolution of the effective reproduction number induced by a given policy schedule) and an epidemiological model (to forecast, based on the computed effective reproduction numbers, the effect of the scheduled policies on public health over time, e.g. deaths and hospitalization occupancy). Epidemiological models predict the state of a population struck by a pandemic over time, based on state transition parameters and the evolution of the effective reproductive number, R t , of the disease.	./cache/cord-225640-l0z56qx4.txt	./txt/cord-225640-l0z56qx4.txt