Evaluation the efficiency of Radial Basis Function Neural Network for Prediction of water quality parameters

Ali Najah Ahmed, Ahmed Elshafie, Othman A. Karim, Othman Jaafar

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

This manuscript attempts to acquaint with the suitability of Artificial Neural Networks (ANN) especially Radial Basis Function RBF to predict water quality parameters. Search for optimal model parameters within RBF-NN is carried out in two steps, each of which can be made to be more efficient and much faster than in MLP. This study focused on electrical conductivity, total dissolved solids and turbidity as the main water quality parameters for rivers. The employed model proved its capabilities to mimic the inter-relationship between such water quality parameters. Normalization and partitioning for the row data have been carried out to accelerate the training process and to achieve pre-defined Sum Square Error SSE equal to 10-4. The results show that the proposed RBF-NN after normalization and partitioning outperformed the linear regression model and achieve Mean Absolute Prediction Error MAPE equal to 8.3%.

Original languageEnglish
Pages (from-to)221-231
Number of pages11
JournalEngineering Intelligent Systems
Volume17
Issue number4
Publication statusPublished - Dec 2009

Fingerprint

Water quality
Neural networks
Turbidity
Linear regression
Rivers
Electric Conductivity

Keywords

  • Artificial Neural Network
  • Johor river basin
  • Radial Basis Function
  • Water quality Prediction

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Computer Science Applications

Cite this

Evaluation the efficiency of Radial Basis Function Neural Network for Prediction of water quality parameters. / Ahmed, Ali Najah; Elshafie, Ahmed; A. Karim, Othman; Jaafar, Othman.

In: Engineering Intelligent Systems, Vol. 17, No. 4, 12.2009, p. 221-231.

Research output: Contribution to journalArticle

@article{a3551923eac04950bb6f1f218e064788,
title = "Evaluation the efficiency of Radial Basis Function Neural Network for Prediction of water quality parameters",
abstract = "This manuscript attempts to acquaint with the suitability of Artificial Neural Networks (ANN) especially Radial Basis Function RBF to predict water quality parameters. Search for optimal model parameters within RBF-NN is carried out in two steps, each of which can be made to be more efficient and much faster than in MLP. This study focused on electrical conductivity, total dissolved solids and turbidity as the main water quality parameters for rivers. The employed model proved its capabilities to mimic the inter-relationship between such water quality parameters. Normalization and partitioning for the row data have been carried out to accelerate the training process and to achieve pre-defined Sum Square Error SSE equal to 10-4. The results show that the proposed RBF-NN after normalization and partitioning outperformed the linear regression model and achieve Mean Absolute Prediction Error MAPE equal to 8.3{\%}.",
keywords = "Artificial Neural Network, Johor river basin, Radial Basis Function, Water quality Prediction",
author = "Ahmed, {Ali Najah} and Ahmed Elshafie and {A. Karim}, Othman and Othman Jaafar",
year = "2009",
month = "12",
language = "English",
volume = "17",
pages = "221--231",
journal = "Engineering Intelligent Systems",
issn = "1472-8915",
publisher = "CRL Publishing",
number = "4",

}

TY - JOUR

T1 - Evaluation the efficiency of Radial Basis Function Neural Network for Prediction of water quality parameters

AU - Ahmed, Ali Najah

AU - Elshafie, Ahmed

AU - A. Karim, Othman

AU - Jaafar, Othman

PY - 2009/12

Y1 - 2009/12

N2 - This manuscript attempts to acquaint with the suitability of Artificial Neural Networks (ANN) especially Radial Basis Function RBF to predict water quality parameters. Search for optimal model parameters within RBF-NN is carried out in two steps, each of which can be made to be more efficient and much faster than in MLP. This study focused on electrical conductivity, total dissolved solids and turbidity as the main water quality parameters for rivers. The employed model proved its capabilities to mimic the inter-relationship between such water quality parameters. Normalization and partitioning for the row data have been carried out to accelerate the training process and to achieve pre-defined Sum Square Error SSE equal to 10-4. The results show that the proposed RBF-NN after normalization and partitioning outperformed the linear regression model and achieve Mean Absolute Prediction Error MAPE equal to 8.3%.

AB - This manuscript attempts to acquaint with the suitability of Artificial Neural Networks (ANN) especially Radial Basis Function RBF to predict water quality parameters. Search for optimal model parameters within RBF-NN is carried out in two steps, each of which can be made to be more efficient and much faster than in MLP. This study focused on electrical conductivity, total dissolved solids and turbidity as the main water quality parameters for rivers. The employed model proved its capabilities to mimic the inter-relationship between such water quality parameters. Normalization and partitioning for the row data have been carried out to accelerate the training process and to achieve pre-defined Sum Square Error SSE equal to 10-4. The results show that the proposed RBF-NN after normalization and partitioning outperformed the linear regression model and achieve Mean Absolute Prediction Error MAPE equal to 8.3%.

KW - Artificial Neural Network

KW - Johor river basin

KW - Radial Basis Function

KW - Water quality Prediction

UR - http://www.scopus.com/inward/record.url?scp=77956684693&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956684693&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:77956684693

VL - 17

SP - 221

EP - 231

JO - Engineering Intelligent Systems

JF - Engineering Intelligent Systems

SN - 1472-8915

IS - 4

ER -