Computer Engineering and Applications ›› 2009, Vol. 45 ›› Issue (13): 163-165.DOI: 10.3778/j.issn.1002-8331.2009.13.047

• 数据库、信号与信息处理 • Previous Articles     Next Articles

Improved method of decision tree based on variable precision rough set theory

HONG Xue-fei,XU Wei-xiang   

  1. Beijing Jiaotong University,Beijing 100044,China
  • Received:2008-03-10 Revised:2008-05-15 Online:2009-05-01 Published:2009-05-01
  • Contact: HONG Xue-fei

基于变精度粗糙集的决策树改进方法

洪雪飞,徐维祥   

  1. 北京交通大学 交通运输学院,北京 100044
  • 通讯作者: 洪雪飞

Abstract: In this paper,a new method of constructing decision tree with rules that have definite confidence is proposed based on variable precision rough sets theory.This method chooses the boundary region of rough sets as the criterion of selecting partitional attributes and redefines the conception of confidence of leaf nodes.The experiment shows that,decision tree built in this way is more effective and comprehensible.

Key words: variable precision rough set, decision tree, confidence, data mining

摘要: 基于变精度粗糙集理论提出了具有置信度规则决策树的新的构造方法,该方法采用β-边界域的大小作为选择分类属性的标准,并对叶节点的置信度进行了重新的定义。经实验证明,该方法能有效提高分类效率且更加容易理解。

关键词: 可变精度粗糙集, 决策树, 置信度, 数据挖掘