River Suspended Sediment Prediction Using Various Multilayer Perceptron Neural Network Training Algorithms—A Case Study in Malaysia
Estimation of suspended sediment discharge in rivers has a vital role in dealing with water resources problems and hydraulic structures. In this study, a Multilayer Perceptron (MLP) feed forward neural network with four different training algorithms was used to predict the suspended sediment discha...
Saved in:
Main Authors: | , , , |
---|---|
Format: | Citation Index Journal |
Published: |
2012
|
Subjects: | |
Online Access: | http://eprints.utp.edu.my/10771/1/River%20suspended%20sediment%20prediction%20using%20various%20multilayer%20perceptron%20neural%20network%20training%20algorithms%20-%20A%20case%20study%20in%20Malaysia.pdf http://eprints.utp.edu.my/10771/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.utp.eprints.10771 |
---|---|
record_format |
eprints |
spelling |
my.utp.eprints.107712013-12-16T23:48:30Z River Suspended Sediment Prediction Using Various Multilayer Perceptron Neural Network Training Algorithms—A Case Study in Malaysia Mustafa, M.R. Rezaur, R.B. Saiedi, Saied Isa, M.H. TC Hydraulic engineering. Ocean engineering Estimation of suspended sediment discharge in rivers has a vital role in dealing with water resources problems and hydraulic structures. In this study, a Multilayer Perceptron (MLP) feed forward neural network with four different training algorithms was used to predict the suspended sediment discharge of a river (Pari River at Silibin) in Peninsular Malaysia. The training algorithms are Gradient Descent (GD), Gradient Descent with Momentum (GDM), Scaled ConjugateGradient (SCG), and Levenberg Marquardt (LM). Different statistical measures, time of convergence and number of epochs to reach the required accuracy were used to evaluate the performance of training algorithms. The analysis showed that SCG and LM performed better than GD and GDM. While the performance of the superior algorithms (i.e., SCG and LM) is similar, LM required considerably shorter time of convergence. It was concluded that both training algorithms SCG and LM could be recommended for suspended sediment prediction using MLP networks. However, LM was the faster (1/7 of SCG convergence time) of the two algorithms. 2012-05 Citation Index Journal PeerReviewed application/pdf http://eprints.utp.edu.my/10771/1/River%20suspended%20sediment%20prediction%20using%20various%20multilayer%20perceptron%20neural%20network%20training%20algorithms%20-%20A%20case%20study%20in%20Malaysia.pdf Mustafa, M.R. and Rezaur, R.B. and Saiedi, Saied and Isa, M.H. (2012) River Suspended Sediment Prediction Using Various Multilayer Perceptron Neural Network Training Algorithms—A Case Study in Malaysia. [Citation Index Journal] http://eprints.utp.edu.my/10771/ |
institution |
Universiti Teknologi Petronas |
building |
UTP Resource Centre |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknologi Petronas |
content_source |
UTP Institutional Repository |
url_provider |
http://eprints.utp.edu.my/ |
topic |
TC Hydraulic engineering. Ocean engineering |
spellingShingle |
TC Hydraulic engineering. Ocean engineering Mustafa, M.R. Rezaur, R.B. Saiedi, Saied Isa, M.H. River Suspended Sediment Prediction Using Various Multilayer Perceptron Neural Network Training Algorithms—A Case Study in Malaysia |
description |
Estimation of suspended sediment discharge in rivers has a vital role in dealing with water resources problems and hydraulic structures. In this study, a Multilayer Perceptron (MLP) feed forward neural network with four different training algorithms was used to predict the
suspended sediment discharge of a river (Pari River at Silibin) in Peninsular Malaysia. The training algorithms are Gradient Descent (GD), Gradient Descent with Momentum (GDM), Scaled ConjugateGradient (SCG), and Levenberg Marquardt (LM). Different statistical measures, time of convergence and number of epochs to reach the required accuracy were used to evaluate the performance of training algorithms. The analysis showed that SCG and LM performed better than GD and GDM. While the performance of the superior algorithms (i.e., SCG and LM) is similar, LM required considerably shorter time of convergence. It was concluded that both training algorithms SCG and LM could be recommended for suspended sediment prediction using MLP
networks. However, LM was the faster (1/7 of SCG convergence time) of the two algorithms. |
format |
Citation Index Journal |
author |
Mustafa, M.R. Rezaur, R.B. Saiedi, Saied Isa, M.H. |
author_facet |
Mustafa, M.R. Rezaur, R.B. Saiedi, Saied Isa, M.H. |
author_sort |
Mustafa, M.R. |
title |
River Suspended Sediment Prediction Using Various Multilayer Perceptron Neural Network Training Algorithms—A Case Study in Malaysia |
title_short |
River Suspended Sediment Prediction Using Various Multilayer Perceptron Neural Network Training Algorithms—A Case Study in Malaysia |
title_full |
River Suspended Sediment Prediction Using Various Multilayer Perceptron Neural Network Training Algorithms—A Case Study in Malaysia |
title_fullStr |
River Suspended Sediment Prediction Using Various Multilayer Perceptron Neural Network Training Algorithms—A Case Study in Malaysia |
title_full_unstemmed |
River Suspended Sediment Prediction Using Various Multilayer Perceptron Neural Network Training Algorithms—A Case Study in Malaysia |
title_sort |
river suspended sediment prediction using various multilayer perceptron neural network training algorithms—a case study in malaysia |
publishDate |
2012 |
url |
http://eprints.utp.edu.my/10771/1/River%20suspended%20sediment%20prediction%20using%20various%20multilayer%20perceptron%20neural%20network%20training%20algorithms%20-%20A%20case%20study%20in%20Malaysia.pdf http://eprints.utp.edu.my/10771/ |
_version_ |
1738655895056809984 |
score |
13.18916 |