变精度粗集模型在决策树生成过程中的应用

Pawlak粗集模型所描述的分类是完全精确的，而没有某种程度上的近似。在利用Pawlak粗集模型构造决策树的过程中，生成方法会将少数特殊实例特化出来，使生成的决策树过于庞大，从而降低了决策树对未来数据的预测和分类能力。利用变精度粗集模型，对基于Pawlak粗集模型的决策树生成方法进行改进，提出变精度明确区的概念，允许在构造决策树的过程中划入明确区的实例类别存在一定的不一致性，可简化生成的决策树，提高决策树的泛化能力。

Application of the Variable Precision Rough Set Model in Decision Tree Construction

The accurate classification of the Pawlak Rough Set Model restricts its application in the real world. In the process of inducing a decision tree with the Pawlak Rough Set Model, the inducing approach draws out some minority special instances, which makes the decision tree too large and reduces its ability of predicting and classifying future data. This paper proposes a new decision tree inducing approach based on the Variable Precision Rough Set Model to improve the one based on the Pawlak Rough Set Model. The concept of the variable precision explicit region has been proposed for selecting attributes as the current nodes of the decision tree.