Particle swarm optimisation for learning Bayesian networks

J. Cowie, L. Oteniya, R. Coles

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper discusses the potential of Particle Swarm Optimisation (PSO) for inducing Bayesian Networks (BNs). Specifically, we detail two methods which adopt the search and score approach to BN learning. The two algorithms are similar in that they both use PSO as the search algorithm, and the K2 metric to score the resulting network. The difference lies in the way networks are constructed. The CONstruct And Repair (CONAR) algorithm generates structures, validates, and repairs if required, and the REstricted STructure (REST) algorithm, only permits valid structures to be developed. Initial experiments indicate that these approaches produce promising results when compared to other BN learning strategies.
Original languageEnglish
Title of host publicationProceedings of the World Congress on Engineering 2007
EditorsS.I. Ao, Len Gelman, David WL Hukins, Andrew Hunter, A. M. Korsunsky
PublisherNewswood
Pages71-76
Number of pages6
Volume1
ISBN (Electronic)9789889867157, 9789889867126
Publication statusPublished - 30 Jun 2007

Fingerprint

Bayesian networks
Particle swarm optimization (PSO)
Repair
Experiments

Keywords

  • Particle Swarm Optimisation
  • Bayesian Network Construction

Cite this

Cowie, J., Oteniya, L., & Coles, R. (2007). Particle swarm optimisation for learning Bayesian networks. In S. I. Ao, L. Gelman, D. WL. Hukins, A. Hunter, & A. M. Korsunsky (Eds.), Proceedings of the World Congress on Engineering 2007 (Vol. 1, pp. 71-76). Newswood .
Cowie, J. ; Oteniya, L. ; Coles, R. / Particle swarm optimisation for learning Bayesian networks. Proceedings of the World Congress on Engineering 2007. editor / S.I. Ao ; Len Gelman ; David WL Hukins ; Andrew Hunter ; A. M. Korsunsky. Vol. 1 Newswood , 2007. pp. 71-76
@inproceedings{0beb5050306040cf9e3fb78a7235e68f,
title = "Particle swarm optimisation for learning Bayesian networks",
abstract = "This paper discusses the potential of Particle Swarm Optimisation (PSO) for inducing Bayesian Networks (BNs). Specifically, we detail two methods which adopt the search and score approach to BN learning. The two algorithms are similar in that they both use PSO as the search algorithm, and the K2 metric to score the resulting network. The difference lies in the way networks are constructed. The CONstruct And Repair (CONAR) algorithm generates structures, validates, and repairs if required, and the REstricted STructure (REST) algorithm, only permits valid structures to be developed. Initial experiments indicate that these approaches produce promising results when compared to other BN learning strategies.",
keywords = "Particle Swarm Optimisation, Bayesian Network Construction",
author = "J. Cowie and L. Oteniya and R. Coles",
year = "2007",
month = "6",
day = "30",
language = "English",
volume = "1",
pages = "71--76",
editor = "S.I. Ao and Len Gelman and Hukins, {David WL} and Andrew Hunter and Korsunsky, {A. M.}",
booktitle = "Proceedings of the World Congress on Engineering 2007",
publisher = "Newswood",

}

Cowie, J, Oteniya, L & Coles, R 2007, Particle swarm optimisation for learning Bayesian networks. in SI Ao, L Gelman, DWL Hukins, A Hunter & AM Korsunsky (eds), Proceedings of the World Congress on Engineering 2007. vol. 1, Newswood , pp. 71-76.

Particle swarm optimisation for learning Bayesian networks. / Cowie, J.; Oteniya, L.; Coles, R.

Proceedings of the World Congress on Engineering 2007. ed. / S.I. Ao; Len Gelman; David WL Hukins; Andrew Hunter; A. M. Korsunsky. Vol. 1 Newswood , 2007. p. 71-76.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Particle swarm optimisation for learning Bayesian networks

AU - Cowie, J.

AU - Oteniya, L.

AU - Coles, R.

PY - 2007/6/30

Y1 - 2007/6/30

N2 - This paper discusses the potential of Particle Swarm Optimisation (PSO) for inducing Bayesian Networks (BNs). Specifically, we detail two methods which adopt the search and score approach to BN learning. The two algorithms are similar in that they both use PSO as the search algorithm, and the K2 metric to score the resulting network. The difference lies in the way networks are constructed. The CONstruct And Repair (CONAR) algorithm generates structures, validates, and repairs if required, and the REstricted STructure (REST) algorithm, only permits valid structures to be developed. Initial experiments indicate that these approaches produce promising results when compared to other BN learning strategies.

AB - This paper discusses the potential of Particle Swarm Optimisation (PSO) for inducing Bayesian Networks (BNs). Specifically, we detail two methods which adopt the search and score approach to BN learning. The two algorithms are similar in that they both use PSO as the search algorithm, and the K2 metric to score the resulting network. The difference lies in the way networks are constructed. The CONstruct And Repair (CONAR) algorithm generates structures, validates, and repairs if required, and the REstricted STructure (REST) algorithm, only permits valid structures to be developed. Initial experiments indicate that these approaches produce promising results when compared to other BN learning strategies.

KW - Particle Swarm Optimisation

KW - Bayesian Network Construction

UR - http://www.iaeng.org/publication/WCE2007/

M3 - Conference contribution

VL - 1

SP - 71

EP - 76

BT - Proceedings of the World Congress on Engineering 2007

A2 - Ao, S.I.

A2 - Gelman, Len

A2 - Hukins, David WL

A2 - Hunter, Andrew

A2 - Korsunsky, A. M.

PB - Newswood

ER -

Cowie J, Oteniya L, Coles R. Particle swarm optimisation for learning Bayesian networks. In Ao SI, Gelman L, Hukins DWL, Hunter A, Korsunsky AM, editors, Proceedings of the World Congress on Engineering 2007. Vol. 1. Newswood . 2007. p. 71-76