A NOVEL APPROACH TO CONSTRUCT THE BINARY DECISION TREE BASED ON CONSISTENT SET

摘要：

In this paper, consistent set and non-consistent set are derived based on the Pawlak rough sets theory and the operation of projection in the database. The definition about important attribute based on consistent set is used to choose the testing attributes. The comparison between novel binary decision tree and traditional decision tree such as single or multivariate binary tree is done through example. The results show that the former is simpler than the latter. The suitable rules also can be explained by the embranchment of this novel tree.

关键词： Consistent set rough sets theory binary decision tree stop criterion

作者: YU-SHENG CHENG YOU-SHENG ZHANG XUE-GANG HU

作者单位: School of Computer Science, Hefei University of Technology, Hefei 230009,China;School of Computer Sc School of Computer Science, Hefei University of Technology, Hefei 230009,China

会议类型: 国际会议

会议名称: 2006 International Conference on Machine Learning and Cybernetics(IEEE第五届机器学习与控制论坛)

会议地点: 大连

会议语种:英文

页码: 1347-1351

在线出版日期: 2006-08-13（万方平台首次上网日期，不代表论文的发表时间）