计算机科学与探索 ›› 2013, Vol. 7 ›› Issue (11): 1018-1025.DOI: 10.3778/j.issn.1673-9418.1305014

• 学术研究 • 上一篇    下一篇

有序决策树的比较研究

王  鑫+,王熙照,陈建凯,翟俊海   

  1. 河北大学 数学与计算机学院 河北省机器学习与计算智能重点实验室,河北 保定 071002
  • 出版日期:2013-11-01 发布日期:2013-11-04

Comparative Study on Ordinal Decision Trees

WANG Xin+, WANG Xizhao, CHEN Jiankai, ZHAI Junhai   

  1. Key Laboratory of Machine Learning and Computational Intelligence, College of Mathematics and Computer Science, Hebei University, Baoding, Hebei 071002, China
  • Online:2013-11-01 Published:2013-11-04

摘要: 有序分类是现实生活中广泛存在的一种分类问题。基于排序熵的有序决策树算法是处理有序分类问题的重要方法之一,这种方法是以排序互信息作为启发式来构建有序决策树。基于这项工作,通过引入模糊有序熵,并以模糊有序互信息作为启发式构建模糊有序决策树,对有序决策树进行了扩展。这两种算法在实际应用中各有自己的优劣之处,从四个方面对这两种算法进行了详细的比较,并指出了这两种算法的异同及优缺点。

关键词: 有序分类, 模糊有序互信息, 有序决策树

Abstract: Ordinal classification tasks widely exist in real life. Rank entropy based ordinal decision tree is one of the most important ways of dealing with ordinal classification problems. This decision tree algorithm selects rank mutual information as a heuristic. This paper introduces fuzzy rank entropy to construct an algorithm for building a fuzzy ordinal decision tree, which is an extension of ordinal decision tree. Both of them have been applied to dispose the ordinal classification tasks in a wide range. This paper compares the two algorithms based on four aspects, and shows their comparative advantages and disadvantages.

Key words: ordinal classification, fuzzy rank mutual information, ordinal decision tree