Dunfrey Pires Aragão

Mr. Dunfrey Pires Aragão

Federal University of Rio Grande do Norte, Natal, Amazonas, Brazil
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 November 2021 in Environmental Research
Verified
Journal Article
Closed access
Dunfrey Pires AragãoDunfrey Pires Aragão
Dunfrey Pires Aragão
EOEmerson V. Oliveira
Emerson V. Oliveira
ABArthur A. Bezerra
Arthur A. Bezerra
DHDavi Henrique
Davi Henrique
AJAndouglas G. da Silva Junior
Andouglas G. da Silva Junior
Luiz GoncalvesLuiz Goncalves
Luiz Goncalves

Dunfrey Pires AragãoDunfrey Pires Aragão
Dunfrey Pires Aragão
DHDavi Henrique
Davi Henrique
AMAdriano Mondini
Adriano Mondini
Luiz GoncalvesLuiz Goncalves
Luiz Goncalves
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.

Dunfrey Pires AragãoDunfrey Pires Aragão
Dunfrey Pires Aragão
AJAndouglas Goncalves Silva Junior
Andouglas Goncalves Silva Junior
AMAdriano Mondini
Adriano Mondini
Cosimo DistanteCosimo Distante
Cosimo Distante
Luiz GoncalvesLuiz Goncalves
Luiz Goncalves
The epidemiology of COVID-19 presented major shifts during the pandemic period. Factors such as the most common symptoms and severity of infection, the circulation of different variants, the preparedness of health services, and control efforts based on pharmaceutical and non-pharmaceutical interventions played important roles in the disease incidence. The constant evolution and changes require the continuous mapping and assessing of epidemiological features based on time-series forecasting. Nonetheless, it is necessary to identify the events, patterns, and actions that were potential factors that affected daily COVID-19 cases. In this work, we analyzed several databases, including information on social mobility, epidemiological reports, and mass population testing, to identify patterns of reported cases and events that may indicate changes in COVID-19 behavior in the city of Araraquara, Brazil. In our analysis, we used a mathematical approach with the fast Fourier transform (FFT) to map possible events and machine learning model approaches such as Seasonal Auto-regressive Integrated Moving Average (ARIMA) and neural networks (NNs) for data interpretation and temporal prospecting. Our results showed a root-mean-square error (RMSE) of about 5 (more precisely, a 4.55 error over 71 cases for 20 March 2021 and a 5.57 error over 106 cases for 3 June 2021). These results demonstrated that FFT is a useful tool for supporting the development of the best prevention and control measures for COVID-19.

EOEmerson Vilar De Oliveira
Emerson Vilar De Oliveira
Dunfrey Pires AragãoDunfrey Pires Aragão
Dunfrey Pires Aragão
Luiz GoncalvesLuiz Goncalves
Luiz Goncalves
The SARS-CoV-2 global pandemic prompted governments, institutions, and researchers to investigate its impact, developing strategies based on general indicators to make the most precise predictions possible. Approaches based on epidemiological models were used but the outcomes demonstrated forecasting with uncertainty due to insufficient or missing data. Besides the lack of data, machine-learning models including random forest, support vector regression, LSTM, Auto-encoders, and traditional time-series models such as Prophet and ARIMA were employed in the task, achieving remarkable results with limited effectiveness. Some of these methodologies have precision constraints in dealing with multi-variable inputs, which are important for problems like pandemics that require short and long-term forecasting. Given the under-supply in this scenario, we propose a novel approach for time-series prediction based on stacking auto-encoder structures using three variations of the same model for the training step and weight adjustment to evaluate its forecasting performance. We conducted comparison experiments with previously published data on COVID-19 cases, deaths, temperature, humidity, and air quality index (AQI) in São Paulo City, Brazil. Additionally, we used the percentage of COVID-19 cases from the top ten affected countries worldwide until May 4th, 2020. The results show 80.7% and 10.3% decrease in RMSE to entire and test data over the distribution of 50 trial-trained models, respectively, compared to the first experiment comparison. Also, model type#3 achieved 4th better overall ranking performance, overcoming the NBEATS, Prophet, and Glounts time-series models in the second experiment comparison. This model shows promising forecast capacity and versatility across different input dataset lengths, making it a prominent forecasting model for time-series tasks.

24 October 2022
Verified
Conference Paper
Open access
PDF file
Dunfrey Pires AragãoDunfrey Pires Aragão
Dunfrey Pires Aragão
DHDavi Henrique
Davi Henrique
AMAdriano Mondini
Adriano Mondini
Cosimo DistanteCosimo Distante
Cosimo Distante
Luiz GoncalvesLuiz Goncalves
Luiz Goncalves
In this article, we perform the SARIMA model to regress the curve of daily COVID-19 deaths and the impact of implementing restrictive measures like lockdown. For comparison, we adopt two neighboring Brazilian cities with similar characteristics and decompose the original curve of cases to extract the seasonal curve. Using Fast Fourier Transform, we noticed that restriction of human circulation had a direct impact on COVID-19 cases and deaths in Araraquara by identifying the frequencies that compose the seasonal curves during the disease’s transmission period, which for future work allows analysis and identification of events and actions through the approach.