Non-Naive Bayesian Classifiers for Classification Problems With Continuous Attributes

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

90 Scopus Citations
View graph of relations

Author(s)

  • Zhao-Xi Wang
  • Yu-Lin He
  • Debby D. Wang

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)21-39
Number of pages19
Journal / PublicationIEEE Transactions on Cybernetics
Volume44
Issue number1
Online published26 Feb 2013
Publication statusPublished - Jan 2014

Abstract

An important way to improve the performance of naive Bayesian classifiers (NBCs) is to remove or relax the fundamental assumption of independence among the attributes, which usually results in an estimation of joint probability density function (p.d.f.) instead of the estimation of marginal p.d.f. in the NBC design. This paper proposes a non-naive Bayesian classifier (NNBC) in which the independence assumption is removed and the marginal p.d.f. estimation is replaced by the joint p.d.f. estimation. A new technique of estimating the class-conditional p.d.f. based on the optimal bandwidth selection, which is the crucial part of the joint p.d.f. estimation, is applied in our NNBC. Three well-known indexes for measuring the performance of Bayesian classifiers, which are classification accuracy, area under receiver operating characteristic curve, and probability mean square error, are adopted to conduct a comparison among the four Bayesian models, i.e., normal naive Bayesian, flexible naive Bayesian (FNB), the homologous model of FNB (FNBROT), and our proposed NNBC. The comparative results show that NNBC is statistically superior to the other three models regarding the three indexes. And, in the comparison with support vector machine and four boosting-based classification methods, NNBC achieves a relatively favorable classification accuracy while significantly reducing the training time.

Research Area(s)

  • Joint probability density estimation, kernel function, naive Bayesian classifier (NBC), optimal bandwidth, probability mean square error, KERNEL DENSITY-ESTIMATION, BANDWIDTH SELECTION, ACCURACY, CHOICE, CURVE, PCA, ROC

Citation Format(s)

Non-Naive Bayesian Classifiers for Classification Problems With Continuous Attributes. / Wang, Zhao-Xi; He, Yu-Lin; Wang, Debby D.
In: IEEE Transactions on Cybernetics, Vol. 44, No. 1, 01.2014, p. 21-39.

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review