Memetic multiobjective particle swarm optimization-based radial basis function network for classification problems

Sultan Noman Qasem, Siti Mariyam Shamsuddin, Siti Zaiton Mohd Hashim, Maslina Darus, Eiman Al-Shammari

Research output: Contribution to journalArticle

39 Citations (Scopus)

Abstract

This paper presents a new multiobjective evolutionary algorithm applied to a radial basis function (RBF) network design based on multiobjective particle swarm optimization augmented with local search features. The algorithm is named the memetic multiobjective particle swarm optimization RBF network (MPSON) because it integrates the accuracy and structure of an RBF network. The proposed algorithm is implemented on two-class and multiclass pattern classification problems with one complex real problem. The experimental results indicate that the proposed algorithm is viable, and provides an effective means to design multiobjective RBF networks with good generalization capability and compact network structure. The accuracy and complexity of the network obtained by the proposed algorithm are compared with the memetic non-dominated sorting genetic algorithm based RBF network (MGAN) through statistical tests. This study shows that MPSON generates RBF networks coming with an appropriate balance between accuracy and simplicity, outperforming the other algorithms considered.

Original languageEnglish
Pages (from-to)165-190
Number of pages26
JournalInformation Sciences
Volume239
DOIs
Publication statusPublished - 1 Aug 2013

Fingerprint

Radial basis function networks
Radial Basis Function Network
Multiobjective optimization
Multi-objective Optimization
Classification Problems
Particle swarm optimization (PSO)
Particle Swarm Optimization
RBF Network
Multi-class Classification
Sorting algorithm
Pattern Classification
Multi-objective Evolutionary Algorithm
Network Design
Statistical test
Statistical tests
Network Structure
Local Search
Radial basis function
Particle swarm optimization
Sorting

Keywords

  • Hybrid learning
  • Pareto optimization
  • Particle swarm optimization
  • Radial basis function network

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Theoretical Computer Science
  • Computer Science Applications
  • Information Systems and Management

Cite this

Memetic multiobjective particle swarm optimization-based radial basis function network for classification problems. / Qasem, Sultan Noman; Shamsuddin, Siti Mariyam; Hashim, Siti Zaiton Mohd; Darus, Maslina; Al-Shammari, Eiman.

In: Information Sciences, Vol. 239, 01.08.2013, p. 165-190.

Research output: Contribution to journalArticle

Qasem, Sultan Noman ; Shamsuddin, Siti Mariyam ; Hashim, Siti Zaiton Mohd ; Darus, Maslina ; Al-Shammari, Eiman. / Memetic multiobjective particle swarm optimization-based radial basis function network for classification problems. In: Information Sciences. 2013 ; Vol. 239. pp. 165-190.
@article{c0ae9eaae2394de6a000256641258f33,
title = "Memetic multiobjective particle swarm optimization-based radial basis function network for classification problems",
abstract = "This paper presents a new multiobjective evolutionary algorithm applied to a radial basis function (RBF) network design based on multiobjective particle swarm optimization augmented with local search features. The algorithm is named the memetic multiobjective particle swarm optimization RBF network (MPSON) because it integrates the accuracy and structure of an RBF network. The proposed algorithm is implemented on two-class and multiclass pattern classification problems with one complex real problem. The experimental results indicate that the proposed algorithm is viable, and provides an effective means to design multiobjective RBF networks with good generalization capability and compact network structure. The accuracy and complexity of the network obtained by the proposed algorithm are compared with the memetic non-dominated sorting genetic algorithm based RBF network (MGAN) through statistical tests. This study shows that MPSON generates RBF networks coming with an appropriate balance between accuracy and simplicity, outperforming the other algorithms considered.",
keywords = "Hybrid learning, Pareto optimization, Particle swarm optimization, Radial basis function network",
author = "Qasem, {Sultan Noman} and Shamsuddin, {Siti Mariyam} and Hashim, {Siti Zaiton Mohd} and Maslina Darus and Eiman Al-Shammari",
year = "2013",
month = "8",
day = "1",
doi = "10.1016/j.ins.2013.03.021",
language = "English",
volume = "239",
pages = "165--190",
journal = "Information Sciences",
issn = "0020-0255",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Memetic multiobjective particle swarm optimization-based radial basis function network for classification problems

AU - Qasem, Sultan Noman

AU - Shamsuddin, Siti Mariyam

AU - Hashim, Siti Zaiton Mohd

AU - Darus, Maslina

AU - Al-Shammari, Eiman

PY - 2013/8/1

Y1 - 2013/8/1

N2 - This paper presents a new multiobjective evolutionary algorithm applied to a radial basis function (RBF) network design based on multiobjective particle swarm optimization augmented with local search features. The algorithm is named the memetic multiobjective particle swarm optimization RBF network (MPSON) because it integrates the accuracy and structure of an RBF network. The proposed algorithm is implemented on two-class and multiclass pattern classification problems with one complex real problem. The experimental results indicate that the proposed algorithm is viable, and provides an effective means to design multiobjective RBF networks with good generalization capability and compact network structure. The accuracy and complexity of the network obtained by the proposed algorithm are compared with the memetic non-dominated sorting genetic algorithm based RBF network (MGAN) through statistical tests. This study shows that MPSON generates RBF networks coming with an appropriate balance between accuracy and simplicity, outperforming the other algorithms considered.

AB - This paper presents a new multiobjective evolutionary algorithm applied to a radial basis function (RBF) network design based on multiobjective particle swarm optimization augmented with local search features. The algorithm is named the memetic multiobjective particle swarm optimization RBF network (MPSON) because it integrates the accuracy and structure of an RBF network. The proposed algorithm is implemented on two-class and multiclass pattern classification problems with one complex real problem. The experimental results indicate that the proposed algorithm is viable, and provides an effective means to design multiobjective RBF networks with good generalization capability and compact network structure. The accuracy and complexity of the network obtained by the proposed algorithm are compared with the memetic non-dominated sorting genetic algorithm based RBF network (MGAN) through statistical tests. This study shows that MPSON generates RBF networks coming with an appropriate balance between accuracy and simplicity, outperforming the other algorithms considered.

KW - Hybrid learning

KW - Pareto optimization

KW - Particle swarm optimization

KW - Radial basis function network

UR - http://www.scopus.com/inward/record.url?scp=84876937656&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84876937656&partnerID=8YFLogxK

U2 - 10.1016/j.ins.2013.03.021

DO - 10.1016/j.ins.2013.03.021

M3 - Article

VL - 239

SP - 165

EP - 190

JO - Information Sciences

JF - Information Sciences

SN - 0020-0255

ER -