变精度粗糙集模型在决策树构造中的应用

针对ID3算法构造决策树复杂、分类效率不高等问题,本文基于变精度粗糙集模型提出了一种新的决策树构造算法。该算法采用加权分类粗糙度作为节点选择属性的启发函数,与信息增益相比,该标准更能够全面地刻画属性分类的综合贡献能力,计算简单,并且可以消除噪声数据对选择属性和生成叶节点的影响。实验结果证明,本算法构造的决策树在规模与分类效率上均优于ID3算法。

Application of the Variable Precision Rough Set Model in Building Decision Trees

Aiming at the problems of complex and low accuracy decision tree constructed by ID3, a new decision tree classification algorithm based on the Variable Precision Rough Set Model is proposed in this article, which takes the weighted classification rough degree as the heuristic function of choosing attributes at a node, this heuristic function can more synthetically measure the contribution of an attribute for classification,and is simpler in calculation than information gain too, which can eliminate the effect of noise data on choosing attributes and generating leaf nodes.Experiments prove that the size of trees generated by the new algorithm is superior to the ID3 algorithm.