计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (10): 111-112.DOI: 10.3778/j.issn.1002-8331.2010.10.036

• 数据库、信号与信息处理 • 上一篇    下一篇

基于Copula的贝叶斯分类器

杜会锋,刘琼荪   

  1. 重庆大学 数理学院,重庆 400030
  • 收稿日期:2008-09-22 修回日期:2009-04-28 出版日期:2010-04-01 发布日期:2010-04-01
  • 通讯作者: 杜会锋

Bayesian classifier using Copula.Computer Engineering and Applications

DU Hui-feng,LIU Qiong-sun   

  1. College of Mathematics and Physics,Chongqing University,Chongqing 400030,China
  • Received:2008-09-22 Revised:2009-04-28 Online:2010-04-01 Published:2010-04-01
  • Contact: DU Hui-feng

摘要: 利用Copula的理论提出了基于Copula贝叶斯分类算法,克服了一般的朴素贝叶斯分类器要求属性独立性假设的不足,进一步扩展了朴素贝叶斯分类器,实验结果表明,基于Copula贝叶斯算法取得了较好的分类效果。

关键词: 朴素贝叶斯分类器, 独立性假设, Copula函数

Abstract: In this paper,a Bayesian classification algorithm based on the theory of Copula is presented,it overcomes the lack of attribute independence assumption which the general Naive Bayesian classifiers request,and further expands the Naive Bayesian classifiers.The results show that classification results have been markedly improved by using the Bayesian classification algorithm based on Copula.

Key words: Naive Bayesian classifier, independence assumption, Copula function

中图分类号: