Presentation 1993/12/14
Identification of Water Demand Prediction Model using a Neural Network and a GMDH
Susumu Saitoh,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Neural networks with backpropagaton algorithm have been used to predict daily water demand.To train the network the time series data of weathers and temperatures are used.The network trained with 10 weeks sets of data showed oveffdtng characteristi to the training data.On the other hand the one trained with 20 weeks sets of data showed reasonable accuracy through both the training data and the testing data.A GMDH model trained with the same data is compared wath the neural network model.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) water demand prediction / modeling / non-linear system / GMDH / neural network
Paper # NC93-63
Date of Issue

Conference Information
Committee NC
Conference Date 1993/12/14(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Identification of Water Demand Prediction Model using a Neural Network and a GMDH
Sub Title (in English)
Keyword(1) water demand prediction
Keyword(2) modeling
Keyword(3) non-linear system
Keyword(4) GMDH
Keyword(5) neural network
1st Author's Name Susumu Saitoh
1st Author's Affiliation Faculty of Administration and Informatics,Tokoha-gakuen Hamamatsu University()
Date 1993/12/14
Paper # NC93-63
Volume (vol) vol.93
Number (no) 376
Page pp.pp.-
#Pages 8
Date of Issue