Navegando por Assunto "Forecast"

Agora exibindo 1 - 2 de 2

Acesso aberto (Open Access)
Metodologia de monitoramento de epidemias: uma abordagem baseada em redes neurais artificiais
(Universidade Federal do Pará, 2018-01-26) SILVA, Wilson Rogério Soares e; FRANCÊS, Carlos Renato Lisboa; http://lattes.cnpq.br/7458287841862567
Dengue fever is a viral infectious disease that is present in more than 100 countries worldwide. In underdeveloped countries such as Brazil, this pathology presents dramatic contours when prevailing socioeconomic factors are added, such as the precarious basic sanitation conditions characteristic of large cities. When we associate this scenario with the Amazon we perceive that the geographic location and climatic conditions of this space contribute to the occurrence of this disease is dimensioned. The Ministry of Health provided data from a survey that found that of the 409,073 reported cases in the North, 106,433 occurred in the state of Pará, where the municipalities with the highest reports of dengue cases are: Belém, Parauapebas, Altamira and Santarém. This work proposes a methodology to monitor epidemics based on the use of Artificial Neural Networks, based on a case study of prediction of dengue cases in the state of Pará. To this end, a system was developed that uses a public database of cases of the disease, of weekly occurrence of the municipalities already mentioned. In addition, it performs the statistical analysis of the series of municipalities showing complexity, and justifying the use of neural networks for this type of problem. It performs the layer adjustments, time window of the trained neural model which in this case is a variation known as recurrent neural network. It implements a module for issuing alerts to detect a sudden increase in new cases of the disease, contributing to the decision-making of public health agencies and their respective actions to control epidemics in the municipalities under study. From our analysis we can conclude that the methodology described in the research is valid for predicting dengue cases using neural networks, anticipating combat actions and contributing to decision making, which can be used by public health managers . And that the use of recurrent neural networks can adjust to the complexity of the series studied. The results demonstrated that the RNA model, for the current scenario, performed well in the epidemiological prediction, reaching satisfactory accuracy
Acesso aberto (Open Access)
Previsão de séries temporais no sistema elétrico brasileiro utilizando preditores baseados em aprendizado de máquina: uma análise empírica
(Universidade Federal do Pará, 2024-04-05) CONTE, Thiago Nicolau Magalhães de Souza; OLIVEIRA, Roberto Célio Limão de; http://lattes.cnpq.br/4497607460894318; https://orcid.org/0000-0002-6640-3182
The overview of electric energy in Brazil is influenced by a variety of complex factors and nonlinear relationships, making forecasting challenging. With the increasing demand for energy and growing environmental concerns, it is crucial to seek solutions based on clean and renewable energy practices, aiming to make the energy market more sustainable. These practices aim to reduce waste and optimize the efficiency of processes involved in the operation of electricity distribution and generation technologies. A promising approach to enable sustainable energy is the application of forecasting techniques for various variables in the energy market. This thesis proposes an empirical analysis of the use of regressors to make predictions in the databases of the Price of Settlement Differences (PLD) in the Brazilian market and wind speed in wind turbines in Northeast Brazil, through principal component analysis. We aim to provide significant information about machine learning techniques that can be employed as effective tools for time series prediction in the electric sector. The results obtained may encourage the implementation of these techniques to extract knowledge about the behavior of the Brazilian energy system. This is particularly relevant, given that energy prices often exhibit seasonality, high volatility, and peaks, and wind power generation is widely influenced by weather conditions. To model the prediction of these two time series, we use the database on the Price of Settlement Differences (PLD), focusing especially on the average energy price of the Brazilian National System. The most relevant variables are related to hydrological conditions, electrical load, and fuel prices for thermal units. For collecting variables related to wind energy, two distinct locations in the Northeast region of Brazil were considered: Macau and Petrolina. For the prediction study, we use a Multilayer Perceptron Neural Network (MLP), a Long Short Term Memory (LSTM), Auto-Regressive Integrated Moving Average (ARIMA), and Support Vector Machine (SVM) to determine baseline results in prediction. To enhance the results of these regressors, we employ two different prediction approaches. One approach involves combining deep artificial neural network techniques based on the Canonical Genetic Algorithm (AG) meta-heuristic to adjust the hyperparameters of MLP and LSTM regressors. The second strategy focuses on machine committees, which include MLP, decision tree, linear regression, and SVM in one committee, and MLP, LSTM, SVM, and ARIMA in another. These approaches consider two types of voting, voting average (VO) and voting weighted average (VOWA), to assess the impact on the performance of the machine committee.