摘要
从多个数据源进行综合知识发现已经成为当前数据挖掘领域中的一个热点研究问题。然而,由于各数据源中数据的差异,使得从各数据源上提取出来的知识,在相互融合的时候会显示出各自的局部性,有时甚至彼此间会出现矛盾,因此,有效的知识融合方法对挖掘结果的质量是至关重要的。该文探讨了基于多概念格的分类规则挖掘,提出了一种融合不同数据源中的分类规则的方法,该方法能保证规则的完整性,即获得适用于全局的所有分类规则,给出了实验结果并加以验证。
Synthesized knowledge discovery from multiple data sources has been a hot research topic in the current field of data mining. However, the differences among sources often make the knowledge extracted from various sources appear to be local, and sometimes there is even conflict when the knowledge is amalgamated. So an effective amalgamation method is crucial to the result＇s quality of mining from multiple sources. In this paper, classification rules mining from multiple concept lattices is discussed, and a method of amalgamating rules is proposed, by which all rules can be gotten. Experiment results are given to verify this method.
出处
《合肥工业大学学报（自然科学版）》
CAS
CSCD
北大核心
2006年第9期1081-1084,共4页
Journal of Hefei University of Technology：Natural Science
基金
安徽省自然科学基金资助项目(050420207)
合肥工业大学科研发展基金资助项目(050504F)
关键词
知识发现
数据挖掘
分类规则
概念格
knowledge discovery
data mining
classification rule
concept lattice
