A real-valued genetic algorithm to optimize the parameters of support vector machine for classification of multiple faults in NPP

Fathy Z. Amer, Ahmed M. El-Garhy, Medhat H. Awadalla, Samia M. Rashad, Asmaa K. Abdien

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Two parameters, regularization parameter c, which determines the trade off cost between minimizing the training error and minimizing the complexity of the model and parameter sigma (σ) of the kernel function which defines the non-linear mapping from the input space to some high-dimensional feature space, which constructs a non-linear decision hyper surface in an input space, must be carefully predetermined in establishing an efficient support vector machine (SVM) model. Therefore, the purpose of this study is to develop a genetic-based SVM (GASVM) model that can automatically determine the optimal parameters, c and σ, of SVM with the highest predictive accuracy and generalization ability simultaneously. The GASVM scheme is applied on observed monitored data of a pressurized water reactor nuclear power plant (PWRNPP) to classify its associated faults. Compared to the standard SVM model, simulation of GASVM indicates its superiority when applied on the dataset with unbalanced classes. GASVM scheme can gain higher classification with accurate and faster learning speed.

Original languageEnglish
Pages (from-to)323-332
Number of pages10
JournalNukleonika
Volume56
Issue number4
Publication statusPublished - 2011

Fingerprint

genetic algorithms
genetic algorithm
Support vector machines
Genetic algorithms
pressurized water reactors
kernel functions
nuclear power plants
Pressurized water reactors
nuclear power plant
high gain
learning
Nuclear power plants
trade-off
education
costs
parameter
support vector machine
cost
simulation
Costs

Keywords

  • Fault classification
  • Genetic algorithm (GA)
  • Machine learning
  • Multi fault classification
  • Support vector machine (SVM)

ASJC Scopus subject areas

  • Nuclear Energy and Engineering
  • Safety, Risk, Reliability and Quality
  • Waste Management and Disposal
  • Condensed Matter Physics
  • Instrumentation
  • Nuclear and High Energy Physics

Cite this

A real-valued genetic algorithm to optimize the parameters of support vector machine for classification of multiple faults in NPP. / Amer, Fathy Z.; El-Garhy, Ahmed M.; Awadalla, Medhat H.; Rashad, Samia M.; Abdien, Asmaa K.

In: Nukleonika, Vol. 56, No. 4, 2011, p. 323-332.

Research output: Contribution to journalArticle

Amer, Fathy Z. ; El-Garhy, Ahmed M. ; Awadalla, Medhat H. ; Rashad, Samia M. ; Abdien, Asmaa K. / A real-valued genetic algorithm to optimize the parameters of support vector machine for classification of multiple faults in NPP. In: Nukleonika. 2011 ; Vol. 56, No. 4. pp. 323-332.
@article{c3c2cc75d55244c5b1cb30d5131dda8a,
title = "A real-valued genetic algorithm to optimize the parameters of support vector machine for classification of multiple faults in NPP",
abstract = "Two parameters, regularization parameter c, which determines the trade off cost between minimizing the training error and minimizing the complexity of the model and parameter sigma (σ) of the kernel function which defines the non-linear mapping from the input space to some high-dimensional feature space, which constructs a non-linear decision hyper surface in an input space, must be carefully predetermined in establishing an efficient support vector machine (SVM) model. Therefore, the purpose of this study is to develop a genetic-based SVM (GASVM) model that can automatically determine the optimal parameters, c and σ, of SVM with the highest predictive accuracy and generalization ability simultaneously. The GASVM scheme is applied on observed monitored data of a pressurized water reactor nuclear power plant (PWRNPP) to classify its associated faults. Compared to the standard SVM model, simulation of GASVM indicates its superiority when applied on the dataset with unbalanced classes. GASVM scheme can gain higher classification with accurate and faster learning speed.",
keywords = "Fault classification, Genetic algorithm (GA), Machine learning, Multi fault classification, Support vector machine (SVM)",
author = "Amer, {Fathy Z.} and El-Garhy, {Ahmed M.} and Awadalla, {Medhat H.} and Rashad, {Samia M.} and Abdien, {Asmaa K.}",
year = "2011",
language = "English",
volume = "56",
pages = "323--332",
journal = "Nukleonika",
issn = "0029-5922",
publisher = "Institute of Nuclear Chemistry and Technology",
number = "4",

}

TY - JOUR

T1 - A real-valued genetic algorithm to optimize the parameters of support vector machine for classification of multiple faults in NPP

AU - Amer, Fathy Z.

AU - El-Garhy, Ahmed M.

AU - Awadalla, Medhat H.

AU - Rashad, Samia M.

AU - Abdien, Asmaa K.

PY - 2011

Y1 - 2011

N2 - Two parameters, regularization parameter c, which determines the trade off cost between minimizing the training error and minimizing the complexity of the model and parameter sigma (σ) of the kernel function which defines the non-linear mapping from the input space to some high-dimensional feature space, which constructs a non-linear decision hyper surface in an input space, must be carefully predetermined in establishing an efficient support vector machine (SVM) model. Therefore, the purpose of this study is to develop a genetic-based SVM (GASVM) model that can automatically determine the optimal parameters, c and σ, of SVM with the highest predictive accuracy and generalization ability simultaneously. The GASVM scheme is applied on observed monitored data of a pressurized water reactor nuclear power plant (PWRNPP) to classify its associated faults. Compared to the standard SVM model, simulation of GASVM indicates its superiority when applied on the dataset with unbalanced classes. GASVM scheme can gain higher classification with accurate and faster learning speed.

AB - Two parameters, regularization parameter c, which determines the trade off cost between minimizing the training error and minimizing the complexity of the model and parameter sigma (σ) of the kernel function which defines the non-linear mapping from the input space to some high-dimensional feature space, which constructs a non-linear decision hyper surface in an input space, must be carefully predetermined in establishing an efficient support vector machine (SVM) model. Therefore, the purpose of this study is to develop a genetic-based SVM (GASVM) model that can automatically determine the optimal parameters, c and σ, of SVM with the highest predictive accuracy and generalization ability simultaneously. The GASVM scheme is applied on observed monitored data of a pressurized water reactor nuclear power plant (PWRNPP) to classify its associated faults. Compared to the standard SVM model, simulation of GASVM indicates its superiority when applied on the dataset with unbalanced classes. GASVM scheme can gain higher classification with accurate and faster learning speed.

KW - Fault classification

KW - Genetic algorithm (GA)

KW - Machine learning

KW - Multi fault classification

KW - Support vector machine (SVM)

UR - http://www.scopus.com/inward/record.url?scp=84859317684&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84859317684&partnerID=8YFLogxK

M3 - Article

VL - 56

SP - 323

EP - 332

JO - Nukleonika

JF - Nukleonika

SN - 0029-5922

IS - 4

ER -