文献类型：期刊文献

中文题名：基于Apriori算法的兴趣集加权关联规则挖掘

英文题名：Mining Interest Set_- Weighted Association Rules Based on Algorithm Apriori

作者：安颖[1,2]

第一作者：安颖

机构：[1]北京工业大学计算机学院;[2]北京联合大学旅游学院

第一机构：北京工业大学计算机学院,北京100022

年份：2008

卷号：22

期号：4

起止页码：44-47

中文期刊名：北京联合大学学报

语种：中文

中文关键词：数据发掘;关联规则;Apriori算法;算法改进;加权

外文关键词：data mining; association rule ; apriori algorithm; algorithm improvement ; weight

摘要：关联规则挖掘可以发现大量数据中项集之间有趣的关联或相关联系,并已在许多领域得到了广泛的应用。目前业界已经提出了许多发现关联规则的算法,这些算法都认为每个数据对规则的重要性相同。但在实际应用中,用户会比较倾向于自己最感兴趣或认为最重要的那部分项目,因此本文提出一种基于兴趣集和权的算法,由用户提出他们感兴趣的项目并在数据库中找出与之相关的项目,通过给每个项目赋以不同权值来标识项目不同的重要性,从而可以挖掘出Apriori算法挖不出但却极具价值的规则。
Mining association rules, some interesting associations or correlations between items among large quantity of data can be found out and they have many wide applications in some fields. Now, lots of algorithms have been proposed for finding the association rules. Most of these algorithms treat each item as uniformity. However, in real applications, users are more inclined to items they are most interested in or feel most important about. So, in this paper we proposed a new algorithm based on the Interest - set and the weight of item. The Interested item is proposed by user who concerns himself with it and then the relative item is to be found from database. We offer each item a different weight value so that it can represent the importance of each individual item from database. In this way, we can get very valuable rules that algorithm Apriori can＇t.