Emerson Vilar De Oliveira

Mrs. Emerson Vilar De Oliveira


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
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
EOEmerson Vilar De Oliveira
Emerson Vilar De Oliveira
DHDavi Henrique
Davi Henrique
Luiz GoncalvesLuiz Goncalves
Luiz Goncalves
Due to the global pandemic disclaimer caused by the SARS-COV-2 virus propagation, also called COVID-19, governments, institutions, and researchers have mobilized intending to try to mitigate the effects caused by the virus on society. Some approaches were proposed and applied to try to make predictions of the behavior of possible pandemics indicators. Among those methodologies, some models are data orientated, also known as data-driven, which had considerable prominence over the others. Artificial Neural Networks are a widely used model among datadriven models. In this work, we propose a novel Auto-Encoder RNA architecture. This architecture aims to forecast time series related to the COVID-19 pandemic, particularly the number of deaths. The model uses as inputs possible associated time series with the desired forecasting. In the experiments, we used the representation in time series from the number of COVID-19 cases, deaths, temperature, humidity, and the Air Quality Index (AQI) of São Paulo city in Brazil. The results show that the model has a prominent forecasting accuracy for the COVID-19 deaths time series.