基于粗糙集理论的决策树分类方法

决策树是数据挖掘中常用的分类方法。本文提出了基于粗糙集的决策树方法,利用粗糙集近似精确度来选择决策树的根节点,分支由分类产生。该方法计算简单,易于理解。本文还提出用悲观剪枝法简化决策树,提高决策树的预测与分类能力。实例说明了本文方法均简单有效。

A Classification Method Using Decision Trees Based on Rough Sets

Decision tree is a usual method of classification in data mining.The decision tree method on the basis of RS is proposed in this paper,which chooses the root node on the basis of approximation quality,and produces branches via classification.The method is simple in calculation and easy-to-understand.In order to improve the efficiency of decision tree classification and forecast,the paper also proposes a pessimistic pruning algorithm for decision tree simplification.The example shows that the methods are simple and effective.