Nonlinear Prediction of River Water-Stages by Feedback Artificial Neural Network

Kazuaki Hiramatsu, Shiomi Shikasho, Ken Mori

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

The feedback artificial neural network model (FBANNM) was applied to the prediction of the water-stages in a tidal river. The difference between a feed forward artificial neural network model and a FBANNM was investigated. A simple genetic algorithm (SGA) was then incorporated into a FBANNM to help search for the optimal network structure, especially the unit numbers of an input layer and a hidden layer. It was concluded that the FBANNM was a useful tool in the short-term prediction of the water-stages that had a strong autocorrelation due to tidal motion. The optimal network structure of the FBANNM was effectively determined by the SGA incorporating the fitness defined by Akaike's Information Criterion.

Original languageEnglish
Pages (from-to)137-147
Number of pages11
JournalJournal of the Faculty of Agriculture, Kyushu University
Volume44
Issue number1-2
Publication statusPublished - Nov 1 1999

Fingerprint

Neural Networks (Computer)
river water
Rivers
neural networks
prediction
Water
autocorrelation
water
rivers

All Science Journal Classification (ASJC) codes

  • Biotechnology
  • Agronomy and Crop Science

Cite this

Nonlinear Prediction of River Water-Stages by Feedback Artificial Neural Network. / Hiramatsu, Kazuaki; Shikasho, Shiomi; Mori, Ken.

In: Journal of the Faculty of Agriculture, Kyushu University, Vol. 44, No. 1-2, 01.11.1999, p. 137-147.

Research output: Contribution to journalArticle

@article{3dfbe37930434c5d94c8b0083860cd03,
title = "Nonlinear Prediction of River Water-Stages by Feedback Artificial Neural Network",
abstract = "The feedback artificial neural network model (FBANNM) was applied to the prediction of the water-stages in a tidal river. The difference between a feed forward artificial neural network model and a FBANNM was investigated. A simple genetic algorithm (SGA) was then incorporated into a FBANNM to help search for the optimal network structure, especially the unit numbers of an input layer and a hidden layer. It was concluded that the FBANNM was a useful tool in the short-term prediction of the water-stages that had a strong autocorrelation due to tidal motion. The optimal network structure of the FBANNM was effectively determined by the SGA incorporating the fitness defined by Akaike's Information Criterion.",
author = "Kazuaki Hiramatsu and Shiomi Shikasho and Ken Mori",
year = "1999",
month = "11",
day = "1",
language = "English",
volume = "44",
pages = "137--147",
journal = "Journal of the Faculty of Agriculture, Kyushu University",
issn = "0023-6152",
publisher = "Faculty of Agriculture, Kyushu University",
number = "1-2",

}

TY - JOUR

T1 - Nonlinear Prediction of River Water-Stages by Feedback Artificial Neural Network

AU - Hiramatsu, Kazuaki

AU - Shikasho, Shiomi

AU - Mori, Ken

PY - 1999/11/1

Y1 - 1999/11/1

N2 - The feedback artificial neural network model (FBANNM) was applied to the prediction of the water-stages in a tidal river. The difference between a feed forward artificial neural network model and a FBANNM was investigated. A simple genetic algorithm (SGA) was then incorporated into a FBANNM to help search for the optimal network structure, especially the unit numbers of an input layer and a hidden layer. It was concluded that the FBANNM was a useful tool in the short-term prediction of the water-stages that had a strong autocorrelation due to tidal motion. The optimal network structure of the FBANNM was effectively determined by the SGA incorporating the fitness defined by Akaike's Information Criterion.

AB - The feedback artificial neural network model (FBANNM) was applied to the prediction of the water-stages in a tidal river. The difference between a feed forward artificial neural network model and a FBANNM was investigated. A simple genetic algorithm (SGA) was then incorporated into a FBANNM to help search for the optimal network structure, especially the unit numbers of an input layer and a hidden layer. It was concluded that the FBANNM was a useful tool in the short-term prediction of the water-stages that had a strong autocorrelation due to tidal motion. The optimal network structure of the FBANNM was effectively determined by the SGA incorporating the fitness defined by Akaike's Information Criterion.

UR - http://www.scopus.com/inward/record.url?scp=0033275675&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033275675&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0033275675

VL - 44

SP - 137

EP - 147

JO - Journal of the Faculty of Agriculture, Kyushu University

JF - Journal of the Faculty of Agriculture, Kyushu University

SN - 0023-6152

IS - 1-2

ER -