@Article{JNMA-3-4,
author = {Lei, Ceyu and Xiaoling, Han},
title = {Regional Prediction of COVID-19 in the United States Based on the Difference Equation Model},
journal = {Journal of Nonlinear Modeling and Analysis},
year = {2021},
volume = {3},
number = {4},
pages = {547--559},
abstract = {<p style="text-align: justify;">The novel coronavirus pneumonia 2019 (COVID-19) has swept the
globe in just a few months with negative social and psychological consequences
for public health. So far, the United States has been one of the countries most
affected by the epidemic. In this study, 51 states in the United States are
divided into 10 state clusters according to relevant factors, and a difference
equation model with spatio-temporal dynamic characteristics is established to
predict the transmission dynamics of COVID-19 in the 10 state clusters and
obtain data on regional aggregation levels (the United States). The study
showed that the Pearson Correlation Coefficient between the actual data and
the predicted data in the 10 state clusters is between 0.6 and 0.96 (mean $R^2$=0.8448), and the mean absolute error (MAE) of the newly confirmed cases
in each cluster is between 300 and 1650 (mean MAE=878) and the average
forecasting error rate (AFER) of the total confirmed cases in each cluster is
between 0.9% and 3% (mean AFER=1.57%). These results show that the
difference equation model can well predict the changes in the recent confirmed
cases of infectious diseases such as COVID-19.</p>},
issn = {2562-2862},
doi = {https://doi.org/10.12150/jnma.2021.547},
url = {https://global-sci.com/article/87989/regional-prediction-of-covid-19-in-the-united-states-based-on-the-difference-equation-model}
}