id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-311054-dwns5l64	Rafiq, Danish	Evaluation and prediction of COVID-19 in India: a case study of worst hit states	2020-06-19		.txt	text/plain	2165	119	57	For example, in [12] , a data-driven estimation method like long short-term memory (LSTM) is used for the prediction of total number of COVID-19 cases in India for a 30-days ahead prediction window. The model is then used for the prediction of the total number of cases and deaths in most affected states of India for the next 30 days. To estimate the spread of COVID-19 in India, we used a Predictive Error Minimization (PEM) based system identification technique to identify a discrete-time, single-input, single-output (SISO) model [19] [20] [21] . The models were then verified on the testing data and upon validation, the models were used to predict the total number of cases and deaths for the next 30-days in the 10 worst hit states in India. As per our prediction based on data up to 17 th May 2020, Delhi along with other states would continue to see marginal surge in the number of COVID-19 cases owing to the relaxations in lock-down measures.	./cache/cord-311054-dwns5l64.txt	./txt/cord-311054-dwns5l64.txt