Structure learning of bayesian networks using a semantic genetic algorithm-based approach

Sachin Shetty, Min Song

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

12 Scopus citations

Abstract

A Bayesian network model is a popular technique for data mining due to its intuitive interpretation. This paper presents a semantic genetic algorithm (SGA) to learn a complete qualitative structure of a Bayesian network from a database. SGA builds on recent advances in the field and focuses on the generation of initial population, crossover, and mutation operators. Particularly, we introduce two semantic crossover and mutation operators that aid in faster convergence of the SGA. The crossover and mutation operators in SGA incorporate the semantic of the Bayesian network structures to learn the structure with very minimal errors. SGA has been proved to perform better than existing classical genetic algorithms for learning Bayesian networks. We present empirical results to prove the fast convergence of SGA and the predictive power of the obtained Bayesian network structures.

Original languageEnglish
Title of host publicationITRE 2005 - 3rd International Conference on Information Technology
Subtitle of host publicationResearch and Education - Proceedings
Pages454-458
Number of pages5
DOIs
StatePublished - 2005
EventITRE 2005 - 3rd International Conference on Information Technology: Research and Education - Hsinchu, Taiwan, Province of China
Duration: 27 Jun 200530 Jun 2005

Publication series

NameITRE 2005 - 3rd International Conference on Information Technology: Research and Education - Proceedings
Volume2005

Conference

ConferenceITRE 2005 - 3rd International Conference on Information Technology: Research and Education
Country/TerritoryTaiwan, Province of China
CityHsinchu
Period27/06/0530/06/05

Keywords

  • Bayesian networks
  • Data mining
  • Genetic algorithms
  • Structure learning

Fingerprint

Dive into the research topics of 'Structure learning of bayesian networks using a semantic genetic algorithm-based approach'. Together they form a unique fingerprint.

Cite this