id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-332412-lrn0wpvj	Ibrahim, Mohamed R.	Variational-LSTM Autoencoder to forecast the spread of coronavirus across the globe	2020-04-24		.txt	text/plain	6819	309	56	Overall, the trained models show high validation for forecasting the spread for each country for short and long-term forecasts, which makes the introduce method a useful tool to assist decision and policymaking for the different corners of the globe. Relying on deep learning, we introduce a novel variational Long-Short Term Memory (LSTM) autoencoder model to forecast the spread of coronavirus per country across the globe. The main advantages of the proposed method are: 1) It can structure and learns from different data sources, either that belongs to spatial adjacency, urban and population factors, or various historical related data, 2) the model is flexible to apply to different scales, in which currently, it can provide prediction at global and country scales, however, it can be also applied to city level.	./cache/cord-332412-lrn0wpvj.txt	./txt/cord-332412-lrn0wpvj.txt