Search

In this paper, the MGIW-ARIMA model is proposed to predict the newly diagnosed cases of COVID-19. The MGIW model is used to predict the trend components, and the ARIMA model is used to predict the random components. Finally, the prediction results of trend components and random components are added together to get the estimation results. The data of COVID-19 in the United States is used to verify and evaluate the model. In the short-term prediction, the combined model of MGIW-ARIMA is better than the single MGIW model. In the long-term prediction, the prediction accuracy of the MGIW model is slightly higher than that of the MGIW-ARIMA model. The MGIW-ARIMA model proposed in this paper makes up for the shortcoming of the lack of randomness in the estimated values of the MGIW model. The combination model can effectively capture the short-term changes of the epidemic while grasping the long-term development trend. [ABSTRACT FROM AUTHOR]

In this paper, the MGIW-ARIMA model is proposed to predict the newly diagnosed cases of COVID-19. The MGIW model is used to predict the trend components, and the ARIMA model is used to predict the random components. Finally, the prediction results of trend components and random components are added together to get the estimation results. The data of COVID-19 in the United States is used to verify and evaluate the model. In the short-term prediction, the combined model of MGIW-ARIMA is better than the single MGIW model. In the long-term prediction, the prediction accuracy of the MGIW model is slightly higher than that of the MGIW-ARIMA model. The MGIW-ARIMA model proposed in this paper makes up for the shortcoming of the lack of randomness in the estimated values of the MGIW model. The combination model can effectively capture the short-term changes of the epidemic while grasping the long-term development trend. [ABSTRACT FROM AUTHOR]

• In this paper, we propose a Long Short-Term Memory (LSTM) based model trained on cumulative COVID-19 cases and deaths. • Our model can be adjusted based on the parameters in order to provide predictions as needed. • We provide results at both the country and county levels. • We compare mitigation measures in various counties in the United States based on the proposed LSTM model. • We can obtain insights based on the trends in the rate of infections and deaths. • Our proposed model can be of help for countries and counties deciding on mitigation and reopening strategies. The COrona VIrus Disease (COVID-19) pandemic caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV2) has resulted in a challenging number of infections and deaths worldwide. In order to combat the pandemic, several countries worldwide enforced mitigation measures in the forms of lockdowns, social distancing, and disinfection measures. In an effort to understand the dynamics of this disease, we propose a Long Short-Term Memory (LSTM) based model. We train our model on more than four months of cumulative COVID-19 cases and deaths. Our model can be adjusted based on the parameters in order to provide predictions as needed. We provide results at both the country and county levels. We also perform a quantitative comparison of mitigation measures in various counties in the United States based on the rate of difference of a short and long window parameter of the proposed LSTM model. The analyses provided by our model can provide valuable insights based on the trends in the rate of infections and deaths. This can also be of help for countries and counties deciding on mitigation and reopening strategies. We believe that the results obtained from the proposed method will contribute to societal benefits for a current global concern. [ABSTRACT FROM AUTHOR]