Cover Image

Improving robustness of artificial neural networks model using genetic algorithm

Artificial Neural Networks (ANN) has been widely accepted as process estimators due its ability to capture complex relationships. However, experiences in implementing ANN estimators in research and industry have exposed some weakness that can be detrimental to the overall performance of plant operat...

Full description

Saved in:
Bibliographic Details
Main Authors: Ahmad, Arshad, Chen, Wah Sit
Format: Article
Language:English
Published: Universiti Malaysia Sabah 2003
Subjects:
T Technology (General)
Online Access:http://eprints.utm.my/id/eprint/8025/1/ArshadAhmad2003_ImprovingRobustnessOfArtificialNeuralNetworks.pdf
http://eprints.utm.my/id/eprint/8025/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.8025
record_format eprints
spelling my.utm.80252010-06-02T01:50:47Z http://eprints.utm.my/id/eprint/8025/ Improving robustness of artificial neural networks model using genetic algorithm Ahmad, Arshad Chen, Wah Sit T Technology (General) Artificial Neural Networks (ANN) has been widely accepted as process estimators due its ability to capture complex relationships. However, experiences in implementing ANN estimators in research and industry have exposed some weakness that can be detrimental to the overall performance of plant operations. Among these, the issue of robustness is of particular importance. This paper proposes adaptation of networks weight as means to improve robustness. Comparisons between GA approach and conventional backpropagation in adaptation of weights are in on-line estimation and control of fatty acid composition in a distillation column. Significant improvements were obtained by the adaptive model especially model generalization perspective. Universiti Malaysia Sabah 2003 Article PeerReviewed application/pdf en http://eprints.utm.my/id/eprint/8025/1/ArshadAhmad2003_ImprovingRobustnessOfArtificialNeuralNetworks.pdf Ahmad, Arshad and Chen, Wah Sit (2003) Improving robustness of artificial neural networks model using genetic algorithm. Proceedings of International Conference On Chemical and Bioprocess Engineering, 2 . pp. 793-800.
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
language English
topic T Technology (General)
spellingShingle T Technology (General)
Ahmad, Arshad
Chen, Wah Sit
Improving robustness of artificial neural networks model using genetic algorithm
description Artificial Neural Networks (ANN) has been widely accepted as process estimators due its ability to capture complex relationships. However, experiences in implementing ANN estimators in research and industry have exposed some weakness that can be detrimental to the overall performance of plant operations. Among these, the issue of robustness is of particular importance. This paper proposes adaptation of networks weight as means to improve robustness. Comparisons between GA approach and conventional backpropagation in adaptation of weights are in on-line estimation and control of fatty acid composition in a distillation column. Significant improvements were obtained by the adaptive model especially model generalization perspective.
format Article
author Ahmad, Arshad
Chen, Wah Sit
author_facet Ahmad, Arshad
Chen, Wah Sit
author_sort Ahmad, Arshad
title Improving robustness of artificial neural networks model using genetic algorithm
title_short Improving robustness of artificial neural networks model using genetic algorithm
title_full Improving robustness of artificial neural networks model using genetic algorithm
title_fullStr Improving robustness of artificial neural networks model using genetic algorithm
title_full_unstemmed Improving robustness of artificial neural networks model using genetic algorithm
title_sort improving robustness of artificial neural networks model using genetic algorithm
publisher Universiti Malaysia Sabah
publishDate 2003
url http://eprints.utm.my/id/eprint/8025/1/ArshadAhmad2003_ImprovingRobustnessOfArtificialNeuralNetworks.pdf
http://eprints.utm.my/id/eprint/8025/
_version_ 1643644906110976000
score 13.211869

Similar Items