Prediction of COVID-19 Confirmed Cases after Vaccination: Based on Statistical and Deep Learning Models

Meejoung Kim

doi:10.28991/scimedj-2021-0302-7

Abstract

In this paper, we analyze and predict the number of daily confirmed cases of coronavirus (COVID-19) based on two statistical models and a deep learning (DL) model; the autoregressive integrated moving average (ARIMA), the generalized autoregressive conditional heteroscedasticity (GARCH), and the stacked long short-term memory deep neural network (LSTM DNN). We find the orders of the statistical models by the autocorrelation function and the partial autocorrelation function, and the hyperparameters of the DL model, such as the numbers of LSTM cells and blocks of a cell, by the exhaustive search. Ten datasets are used in the experiment; nine countries and the world datasets, from Dec. 31, 2019, to Feb. 22, 2021, provided by the WHO. We investigate the effects of data size and vaccination on performance. Numerical results show that performance depends on the used data's dates and vaccination. It also shows that the prediction by the LSTM DNN is better than those of the two statistical models. Based on the experimental results, the percentage improvements of LSTM DNN are up to 88.54% (86.63%) and 90.15% (87.74%) compared to ARIMA and GARCH, respectively, in mean absolute error (root mean squared error). While the performances of ARIMA and GARCH are varying according to the datasets. The obtained results may provide a criterion for the performance ranges and prediction accuracy of the COVID-19 daily confirmed cases.Doi: 10.28991/SciMedJ-2021-0302-7 Full Text: PDF

Highlights

The coronavirus outbreak in Wuhan, China, in December 2019, and named COVID-19 by the World Health Organization (WHO), made 2020 the year of global disaster [1]
Since the first death from the disease was reported in January 2020, the numbers of confirmed cases and death cases have continuously increased until the vaccination began on Dec. 8th in the United Kingdom (UK)
The data used is the daily confirmed cases of COVID-19 for 420 days from Dec. 31, 2019, to Feb. 22, 2021, extracted from the dataset obtained through GitHub [32], provided by the WHO [2]

Summary

Introduction

The coronavirus outbreak in Wuhan, China, in December 2019, and named COVID-19 by the World Health Organization (WHO), made 2020 the year of global disaster [1]. Since the first death from the disease was reported in January 2020, the numbers of confirmed cases and death cases have continuously increased until the vaccination began on Dec. 8th in the United Kingdom (UK). The numbers of confirmed cases are declining in countries where vaccinations have begun, such as the USA and the UK, while the numbers are still increasing or fluctuating in other countries where vaccinations have started late or have not yet begun. Symptomatic treatment and supportive therapy are used to cure the COVID-19 patients. It includes basic disease treatment, symptom relief, effective protective and supportive treatment of internal organs, active prevention and treatment of complications, and respiratory support if necessary. Researchers are working on the development of treatments for the disease, and countries are supporting it. The drugs that can cure the disease have not yet developed

Methods

Results

Conclusion