Temporal Prediction Model of the Evolution of Confirmed Cases of the New Coronavirus (SARS-CoV-2) in Brazil

Siqueira, Elton; Portela, Carlos dos Santos; Farias, Fabricio; Braga, Camila Pereira

doi:10.1109/tla.2021.9451238

Cited by 4 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Os resultados obtidos para os três cenários de modelos de regressão, para previsão de carga considerando o horizonte de médio prazo (com 𝑆𝐷 = 1719,6) encontram-se nas Tabelas 1, 2 e 3. (Lindberg et al, 2019;Siqueira et al, 2021).…”

Section: Resultados Da Previsão De Médio Prazounclassified

Construção De Reator De Plasma Frio Para Aplicações De Filmes Finos

Cirino

Pinto

2022

Proceedings IX Simpósio Brasileiro De Sistemas Elétricos

View full text Add to dashboard Cite

The load forecasting for an electrical system is the basis for expansion projections in generation, transmission and distribution sectors, and also for planning, operation and control. The errors minimization of load forecasting is brought with the reduction of costs and improvement of the general performance of the sectors involved, in such a way as to guarantee the quality of the services provided by the system, and to keep the operation safe and reliable. In this sense, the proposed study consists on carrying out the load forecasting of the Brazil's southern subsystem using three regression models (neutral, optimistic and pessimistic), evaluating the performance of each model considering their trend curve and deviations (maximum and minimum) compared with load data samples. In addition, the load forecasting will be performed from a Multi-Layer Perceptron (MLP) artificial neural network considering the same load data, in order to evaluate the accuracy of the model. Afterwards, the regression model which presents the best performance will be combined with the MLP, extending the forecasting the future load with a long-term horizon, based on the current conjuncture of the Brazilian electricity sector.Resumo: A previsão de carga para um sistema elétrico é a base para as projeções de expansão do setor de geração, transmissão e distribuição, assim como para as questões de planejamento, operação e controle. A minimização dos erros da previsão de carga traz consigo a redução de custos e melhoria de desempenho geral dos setores envolvidos, de tal forma a garantir a qualidade dos serviços prestados pelo sistema, e mantenimento da operação segura e confiável. Neste sentido, o estudo proposto consiste em realizar a previsão de carga do subsistema sul brasileiro, fazendo o uso de três modelos de regressão (neutro, otimista e pessimista), avaliando o desempenho dos modelos considerando a sua curva de tendência e seus desvios (máximo e mínimo) em comparação com amostras de dados de carga. Adicionalmente, será realizada a previsão de carga a partir de uma rede neural Multi-Layer Perceptron (MLP) considerando os mesmos dados de carga, avaliando a precisão do modelo. Após, será realizada a junção do modelo de regressão, que apresentar melhor desempenho, com a MLP, fazendo a previsão de carga futura com um horizonte de longo prazo, com base na conjuntura atual do setor elétrico brasileiro.

show abstract

Section: Resultados Da Previsão De Médio Prazounclassified

Construção De Reator De Plasma Frio Para Aplicações De Filmes Finos

Cirino

Pinto

2022

Proceedings IX Simpósio Brasileiro De Sistemas Elétricos

View full text Add to dashboard Cite

show abstract

“…Approaches to forecast the temporal curves of SARS-CoV-2 contagion, in general use only temporal information, without considering existing spatial characteristics [18], [19], [24]. Hence, the mutual influence of neighboring regions is neglected.…”

Section: Related Literaturementioning

confidence: 99%

“…Within the scope of Brazil, some similar-purpose models can be found in the literature [18], [19], [22], [23], as compared in Table 1. Their performance to forecast the number of contagions for one day ahead were grouped according to the target location of the analysis and scope.…”

Section: Related Literaturementioning

confidence: 99%

“…Public actions, from more usual (e.g., social distancing and use of masks) to more extreme actions (e.g., border closures and lockdown) [11], [15], [16], depend on the correct crisis analysis. Planning when, where, and for how long to apply each action is only possible upon monitoring and understanding how the pandemic spreads and evolves [12], [17], which have shown to be very hard when it comes to Covid- 19.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Forecasting the COVID-19 Space-Time Dynamics in Brazil With Convolutional Graph Neural Networks and Transport Modals

et al. 2022

View full text Add to dashboard Cite

One of the major challenges imposed by the SARS-CoV-2 pandemic is the lack of pattern in which the virus spreads, making it difficult to create effective policies to prevent and tackle the pandemic. Several approaches have been proposed to understand the virus behavior and anticipate its infection and death curves at country ans state levels, thus supporting containment measures. Those initiatives generalize well for general extents and decisions, but they do not predict so well the trajectory of the virus through specific regions, such as municipalities, considering their distinct interconnection profiles. Specially in countries with continental dimensions, like Brazil, too general decisions imply that containment measures are applied either too soon or too late. This study presents a novel scalable alternative to forecast the numbers of case and death by SARS-CoV-2, according to the influence that certain regions exert on others. By exploiting a single-model architecture of graph convolutional networks with recurrent networks, our approach maps the main access routes to municipalities in Brazil using the modals of transport, and processes this information via neural network algorithms to forecast at the municipal level ans for the whole country. We compared the performance in forecasting the pandemic daily numbers with three baseline models using Mean Absolute Error (MAE), Symmetric Mean Absolute Percentage Error (sMAPE) and Normalized Root Mean Square Error (NRMSE) metrics, with the forecasting horizon varying from 1 to 25 days. Results show that the proposed model overcomes the baselines when considering the MAE and NRMSE (p < 0.01), being specially suitable for forecasts from 14 to 24 days ahead.INDEX TERMS Covid-19, graph convolutional networks, time series forecasting, transport modals.

show abstract

“…Li et al [5] estimated the distribution of key epidemiological delay time, the doubling time of infectious diseases, and the basic reproduction number based on the data of the earliest 425 confirmed cases. Siqueira et al [6] established a dynamic propagation model, including infectivity in the latent period, and estimated the basic regeneration number by using a simulation. Sora et al [7] considered the influence of COVID-19 latency based on the SEIR model and predicted the inflection point by using simulation experiments.…”

Section: Introductionmentioning

confidence: 99%

Construction and Simulation Analysis of Epidemic Propagation Model Based on COVID-19 Characteristics

Sheng

2022

IJERPH

View full text Add to dashboard Cite

This paper proposes the epidemic propagation model SEAIHR to elucidate the propagation mechanism of the Corona Virus Disease of 2019 (COVID-19). Based on the analysis of the propagation characteristics of COVID-19, the hospitalization isolation state and recessive healing state are introduced. The home morbidity state is introduced to consider the self-healing of asymptomatic infected populations, the early isolation of close contractors, and the impact of epidemic prevention and control measures. In this paper, by using the real epidemic data combined with the changes in parameters in different epidemic stages, multiple model simulation comparative tests were conducted. The experimental results showed that the fitting and prediction accuracy of the SEAIHR model was significantly better than the classical epidemic propagation model, and the fitting error was 34.4–72.8% lower than that of the classical model in the early and middle stages of the epidemic.

show abstract

Temporal Prediction Model of the Evolution of Confirmed Cases of the New Coronavirus (SARS-CoV-2) in Brazil

Cited by 4 publications

References 23 publications

Construção De Reator De Plasma Frio Para Aplicações De Filmes Finos

Construção De Reator De Plasma Frio Para Aplicações De Filmes Finos

Forecasting the COVID-19 Space-Time Dynamics in Brazil With Convolutional Graph Neural Networks and Transport Modals

Construction and Simulation Analysis of Epidemic Propagation Model Based on COVID-19 Characteristics

Contact Info

Product

Resources

About