National Holidays and Social Mobility Behaviors: Alternatives for Forecasting COVID-19 Deaths in Brazil

Abstract

In this paper, we investigate the influence of holidays and community mobility on the transmission rate and death count of COVID-19 in Brazil. We identify national holidays and hallmark holidays to assess their effect on disease reports of confirmed cases and deaths. First, we use a one-variate model with the number of infected people as input data to forecast the number of deaths. This simple model is compared with a more robust deep learning multi-variate model that uses mobility and transmission rates (R0, Re) from a SEIRD model as input data. A principal components model of community mobility, generated by the principal component analysis (PCA) method, is added to improve the input features for the multi-variate model. The deep learning model architecture is an LSTM stacked layer combined with a dense layer to regress daily deaths caused by COVID-19. The multi-variate model incremented with engineered input features can enhance the forecast performance by up to 18.99% compared to the standard one-variate data-driven model.

A Data Lake and Analytics Platform with Application to COVID-19 Dynamic Analysis

“…Our main contribution is the platform itself, which integrates a new concept of development, with data acquisition and code deployment done at the same time, in the same tool. An immediate application is in the project that is undergoing, where our data scientists are using our tool in their works on data-driven and mathematical modeling of Covid-19 dynamics [6].…”

“…It starts with visualization of data from Brazil as a whole and allows the user to see data from the states, just by selecting the map to get data from a specific state. Currently, it is showing predictions using LSTM approach [6]. However, other source codes can be easily deployed following the same process using our proposal.…”

“…Several data-driven approaches can be This work is sponsored by CAPES under grant 88887.506889/2020-00. found in the literature [4]- [6] with development of models based on ARIMA, SEIRD, auto-encoders, among others.…”

Unravelling the effect of winter holiday celebrations on SARS-CoV-2 transmission

“…Surges in COVID-19 case numbers have been observed following public holidays and celebrations, although causal evidence remains limited [1][2][3][4][5][6][7] . Modelling studies and empirical data have implicated superspreading events (SSE) as major contributors to the spread of SARS-CoV-2 and other pathogens [8][9][10][11][12] .…”

Analysis with SARIMA and FFT Between Two Neighboring Cities Regarding the Implementation of Restrictive Lockdown Measures

“…Studies have demonstrated the importance of implementing NPIs. Such studies have expanded knowledge of how to fight and prevent COVID-19 spread [8], [9]. This work is sponsored by CAPES under grant 88887.506889/2020-00.…”