基于聚类分析的关联规则挖掘方法.pdfVIP

( ) 计算机工程与设计 Computer Engineering and Design 52 14 2009,30 22 计算机工程与设计 Computer Engineering and Design 人工智能 基于聚类分析的关联规则挖掘方法 1 1 2 邬长安 ， 尤 磊 ， 苏晓珂 (1. 信阳师范学院计算机与信息技术学院，河南信阳464000 ；2. 东华大学信息科学与技术学院，上海201620) 摘 要：从数据集中挖掘数据间的相互关系及其关联规则是数据挖掘研究领域的核心内容之一，为了挖掘实体表现出的数 据特征与实体具备因素间的关系，提出了一种挖掘方法。先采用聚类分析的方法对实体的数据进行了聚类，再通过关联分 析的方法分析聚类簇中实体的因素，继而得出实体具备的因素与实体数据间的相互影响及其关联规则。通过该方法分析了 学生具有的因素对学生学习成绩的影响，分析结果表明了方法的可行性。 关键词：聚类分析; 关联分析; K-Means 算法; FP-Growth 算法; 频繁项集 中图法分类号：TP301 文献标识码：A 文章编号：1000-7024 (2009) 22-52 14-04 Method of mining association rules based on clustering analysis 1 1 2 WU Chang-an , YOU Lei , SU Xiao-ke (1. College of Computer and Information Technology, Xinyang Normal University, Xinyang 464000, China; 2. College of Information Science and Technology, Donghua University, Shanghai 201620, China) Abstract ：It is one of the core content of data mining research field which mining the correlation and association rules between data stored in database. To mining the relation between entity ’s behaved data and entity ’s possessed factor, a mining method is presented. Firstly, clustering analysis is used to classify entity by entity ’s behaved data, then association rules is used to analysis entity ’s possessed factor which belongs to the same cluster, and then the interrelationship between factor and behaved data is gotten. By use this method to analysis the affect of student ’s factors on student ’s study score, the validity of the presented method is demonstrated, the method and the conclusion can promote in other related fields. Key words ：cluster analysis; association analysi