• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

J4 ›› 2007, Vol. 29 ›› Issue (1): 123-125.

• 论文 • 上一篇    下一篇

基于粗集理论的决策树剪枝

由军平 卫金茂 王名扬   

  • 出版日期:2007-01-01 发布日期:2010-05-30

  • Online:2007-01-01 Published:2010-05-30

摘要:

本文在理论上分析比较了基于粗糙集理论的剪枝方法和C4.5中的EBP剪枝方法,并通过在多个数据集上进行实验比较,证实了基于粗糙集理论剪枝方法的优越性。

关键词: 过匹配 剪枝 深度拟合率 错误率 决策树

Abstract:

In this paper, the decision tree pruning method based on RST is compared with the Error Based Pruning method used in C4.5 in theory, and they are comp  ared by tests on some databases. The result proves the validity of the pruning method based on RST.

Key words: over-fitting;pruning;depth-fitting ratio;error ratio;decision tree