SPREADING OF COVID-19 IN INDIA, ITALY, JAPAN, SPAIN, UK, US

The spread of COVID-19 around the entire world has placed humankind in an unprecedented situation. Because of the rise of the number of cases and its subsequent load on the organizations and wellbeing experts, some immediate strategies are required to envision the number of cases in the future. In this article, the authors have presented two data-driven estimation techniques, namely, Auto-Regressive Integrated Moving Average (ARIMA) and Long Short-Term Memory (LSTM) for prediction of the cumulative number of COVID-19 cases and the cumulative number of deaths due to COVID-19. Various measures of goodness of fit such as Akaike Information Criteria (AIC), Mean Absolute Percentage Error (MAPE), and Root Mean Square Error (RMSE) are computed for the ARIMA model. For LSTM, two parameters such as Mean Absolute Percentage Error (MAPE) and Root Mean Squared Error (RMSE) are computed. 80% of the available data are used to create the model and the remaining 20% are used for testing. The predicted and actual figures are compared to test the prediction accuracy. This article aims to aid India, Italy, Japan, Spain, the UK, and the US administration by providing a statistical tool to predict the future figures of upcoming suspected and death cases because of COVID-19.

[1]  W. Gao,et al.  Epidemiological features and time-series analysis of influenza incidence in urban and rural areas of Shenyang, China, 2010–2018 , 2020, Epidemiology and Infection.

[2]  L. Cao,et al.  Relationship of meteorological factors and human brucellosis in Hebei province, China. , 2019, The Science of the total environment.

[3]  David J. Hill,et al.  Short-Term Residential Load Forecasting Based on Resident Behaviour Learning , 2018, IEEE Transactions on Power Systems.

[4]  Guoqiang Peter Zhang,et al.  Time series forecasting using a hybrid ARIMA and neural network model , 2003, Neurocomputing.

[5]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[6]  J. Lenzer.  Covid-19: US gives emergency approval to hydroxychloroquine despite lack of evidence , 2020, BMJ.

[7]  Yugang Niu,et al.  Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM , 2018 .

[8]  Forecasting incidence of infectious diarrhea using random forest in Jiangsu Province, China , 2020, BMC Infectious Diseases.

[9]  Md. Shahidul Hoque,et al.  Selection of Best ARIMA Model for Forecasting Average Daily Share Price Index of Pharmaceutical Companies in Bangladesh: A Case Study on Square Pharmaceutical Ltd. , 2013 .

[10]  G. Remuzzi,et al.  COVID-19 and Italy: what next? , 2020, The Lancet.

[11]  J. Guarner.  Three Emerging Coronaviruses in Two Decades , 2020, American journal of clinical pathology.

[12]  Peter C. Y. Chen,et al.  LSTM network: a deep learning approach for short-term traffic forecast , 2017 .