A Novel Framework to Forecast COVID-19 Incidence Based on Google Trends Search Data

The global outbreak of coronavirus disease 2019 (COVID-19) has spread to more than 200 countries worldwide, leading to severe health and socioeconomic consequences. As such, the topic of monitoring and predicting epidemics has been attracting a lot of interest. Previous work reported search volumes from Google Trends are beneficial in decoding influenza dynamics, implying its potential for COVID-19 prediction. Therefore, a predictive model using the Wiener methods was built based on epidemic-related search queries from Google Trends, along with climate variables, aiming to forecast the dynamics of the weekly COVID-19 incidence in Washington, DC, USA. The Wiener model, which shares the merits of interpretability, low computation costs, and adaptation to nonlinear fluctuations, was used in this study. Models with multiple sets of features were constructed and further optimized by the highest weight selecting strategy. Furthermore, comparisons to the other two commonly used prediction models based on the autoregressive integrated moving average (ARIMA) and long short-term memory (LSTM) were also performed. Our results showed the predicted COVID-19 trends significantly correlated with the actual (rho <inline-formula> <tex-math notation="LaTeX">$=$</tex-math> </inline-formula> 0.88, <inline-formula> <tex-math notation="LaTeX">$p $</tex-math> </inline-formula> <inline-formula> <tex-math notation="LaTeX">$<$</tex-math> </inline-formula> 0.0001), outperforming those with ARIMA and LSTM approaches, indicating Google Trends data as a useful tool in terms of COVID-19 prediction. Also, the model using 20 search queries with the highest weighting outperformed all other models, supporting the highest weight feature selection as a feasible criterion. Google Trends search query data can be used to forecast the outbreak of COVID-19, which might assist health policymakers to allocate health care resources and taking preventive strategies. IEEE

Optimizing Hammerstein-Wiener Model for Forecasting Confirmed Cases of Covid-19

Noise poses challenge to nonlinear Hammerstein-Wiener (HW) subsystem model application, because HW subsystem need large number of parameter interactions. However, flexibility, soft computing, and automatic adjustment to dynamic observation for best model fitting make it potential for forecasting nonlinear data. In this article, we adopted improved HW inference from Levenberg-Marquardt optimization algorithm to optimize HW subsystem and to select best model parameters. Therefore, the adopted model is tested on COVID-19 confirmed reported cases, to estimate transmission rate of COVID-19 virus for period from 15th March 2020 to 29th April 2020. Model validation is carried out on small dataset, which outperforms some existing models. The adopted model is further evaluated using statistical metrics and reported best accuracy of 0.127 and 0.998 for Mean Absolute percentage error (MAPE) and coefficient of determination (R2) respectively, with best model complexity of 1.86. The obtained results are promising enough in predicting spread of COVID-19 virus and may inspire as guidance to relax lockdown restriction policies. © 2022, IAENG International Journal of Applied Mathematics. All Rights Reserved.