基于可变精度的ID3改进算法  

Improved ID3 algorithm based on variable precision

作　　者：王艳兵[1] 赵锐[1] 姚青[1] 

机构地区：[1]山东大学计算机科学与技术学院,山东济南250061

出　　处：《计算机工程与设计》2006年第14期2683-2685,共3页Computer Engineering and Design

摘　　要：ID3算法是数据挖掘中经典的决策树分类算法,该算法具有抗噪声能力差的缺点。通过对ID3算法的研究,依据可变精度粗糙集理论的思想,采用在计算属性信息熵时设定阈值的方法,以放宽属性选择的要求,从而对经典的ID3算法做了相应的改进。改进后的ID3算法(VPID3)可在一定程度上降低噪声对系统分类的干扰,使分类结果更加符合实际要求。最后通过举例,说明了改进算法的可行性。ID3 algorithm is a classical algorithm in data mining, this algorithm has the worse ability to resist noise. Via the research on ID3 algorithm, according to the thought of variable precision rough set, the algorithm is improved by setting threshold value while cal- culating attributes＇ entropy, in order to relax the restrictions while selecting attributes. After the improved ID3 algorithm （VPID3）, the interference of noise to classification could be reduced to a certain extent, this made result correspond to reality even more, is used finally, the feasibility of the improved algorithm is illustrated with an example.

关 键 词：数据挖掘 决策树 粗糙集 ID3 熵 

分 类 号：TP311.131[自动化与计算机技术—计算机软件与理论]