Published Paper Details:

Covid-19 has been responsible for the deaths of people in lakhs and millions of people have been affected worldwide. To avoid future deaths, it is of utmost importance to identify the future cases and virus spread rate in advance. It is an analytical and challenging real-world task to forecast accurately the spread of this virus. Therefore, we use day level information of COVID-19 spread for cumulative cases from whole world. The dataset used in this research is from Jhon Hopkin University which contains the spread of the virus from January 22, 2020 to till date. It is a daily updating dataset. We model the evolution of the COVID-19 outbreak, and perform prediction using Machine learning and Deep learning-based time series forecasting models for next 20 days. Effectiveness of the models are evaluated based on the prediction curves, mean absolute error, and mean square error. Our analysis can help in understanding the trends of the disease outbreak, and provide epidemiological stage information of adopted countries. Our investigations show that Deep learning approach is best for time series-based problems and more effective for forecasting COVID-19 prevalence. The forecasting results have potential to assist governments to plan policies to contain the spread of the virus.