一种基于集合运算的分类规则处理方法  

A Processing Method of Classification Rule Based on Set Operation

作　　者：杨海峰[1] 冀英伟[1] 

机构地区：[1]太原科技大学计算机科学与技术学院,太原030024

出　　处：《太原科技大学学报》2011年第2期131-134,共4页Journal of Taiyuan University of Science and Technology

基　　金：太原科技大学青年科学基金(20083015)

摘　　要：通过分析分类规则与训练集之间的映射关系,采用集合的相关运算寻找特征规则及相应特征集,从而消除分类规则集中存在的冗余,并在此基础上提出了基于集合运算的分类规则处理算法(PASO)。最后,以恒星光谱数据为背景,实验验证了该方法的正确性和可行性。In this paper, a processing algorithm of classification rule based on set operation is presented by analyzing the mapping relationship between rules and training data, and set operations are used to get characteristic rule and its characteristic set, so that the redundant rules may be discovered and eliminated. In the end, experimental results validate its correctness and efficiency by using star spectra data as the decision system.

关 键 词：数据挖掘 分类规则 集合 恒星光谱数据 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]