Variable Ordering in the Conditional Independence Bayesian Classifier Induction Process: An Evolutionary Approach

Author

Hruschka, Estevam R., Jr. ; dos Santos, Edimilson B. ; de O.Galvao, S.D.C.

Author_Institution

Univ. Fed. de Sao Carlos, Sao Carlos

fYear

2007

Firstpage

204

Lastpage

209

Abstract

This work proposes, implements and discusses a hybrid Bayes/genetic collaboration (VOGAC-MarkovPC) designed to induce conditional independence Bayesian classifiers from data. The main contribution is the use of MarkovPC algorithm in order to reduce the computational complexity of a genetic algorithm (GA) designed to explore the variable orderings (VOs) in order to optimize the induced classifiers. Experiments performed in a number of datasets revealed that VOGAC-MarkovPC required less than 25% of the time demanded by VOGAC-PC on average. In addition, when concerning the classification accuracy, VOGAC-MakovPC performed as well as VOGAC-PC did.

Keywords

Bayes methods; Markov processes; computational complexity; genetic algorithms; pattern classification; VOGAC-MarkovPC; computational complexity; conditional independence Bayesian classifier induction process; evolutionary approach; genetic algorithm; genetic collaboration; variable ordering; Algorithm design and analysis; Bayesian methods; Classification algorithms; Collaborative work; Computational complexity; Design optimization; Genetic algorithms; Hybrid intelligent systems; International collaboration; Random variables;

fLanguage

English

Publisher

ieee

Conference_Titel

Hybrid Intelligent Systems, 2007. HIS 2007. 7th International Conference on

Conference_Location

Kaiserlautern

Print_ISBN

978-0-7695-2946-2

Type

conf

DOI

10.1109/HIS.2007.67

Filename

4344052