BDBComp
Parceria:
SBC
SIG como apoio ao Processo de Estudos Hidrológicos para determinar pontos de vazão para outorga

Método Neuro-Estatístico para Predição de Séries Temporais Ruidosas

Clóvis Lemos TavaresTaciana de Lemos DiasDaniel RigoMaria Helena AlvesKarina Luna

Eliseu Celestino SchopfPaulo Martins Engel

This paper presents an application of a knowledge process used by the Hydrological Studies IEMA 2008 to generate a geographic information system for estimating runoff in the state of Espírito Santo. A new interface was developed, based on spatial analysis, flow study, isohyetal interpolation of precipitation, and identification of layers of regionalization in all 12 major river basins of Espírito Santo State. The result of the estimates can be used for planning application for the grant, identify areas for definition of points of water abstraction and effluent discharge. The paper presents results from a case study, based on the experience of the Water Company of Espírito Santo State (CESAN) developed by NIPSA and Nip do Brazil with funds from World Bank (BIRD) in the clean water program. This paper describes a new forecast technique over highly nonlinear noisy time series. The neural statistical method uses a multi-layer perceptron and the Extended Kalman Filter. The method combines the modeling of the noise of the Kalman Filter with the nonparametric modeling and treatment of high nonlinearities of the neural network. The filter is adjusted with internal data of the net, filtering the data so that the net can have better results. The method reaches satisfactory performance in experiments with complex time series with noise addition. The method presents a satisfactory filtering of series values. The feedback with filtering values increments the method's performance.

http://www.lbd.dcc.ufmg.br/colecoes/wcama/2011/004.pdf

Caso o link acima esteja inválido, faça uma busca pelo texto completo na Web: Buscar na Web

Biblioteca Digital Brasileira de Computação - Contato: bdbcomp@lbd.dcc.ufmg.br
     Mantida por:
LBD