摘要
1 引言在知识发现和数据挖掘技术的实际应用中,为了对大规模数据库进行高效处理,通常采用数据缩减的预处理方法。数据缩减(又称数据浓缩)就是将原始数据转换到某种更加紧凑形式而又不丢失有意义的语义信息的过程。有效的数据缩减方法不仅能显著削减数据量,提高知识发现效率。
Data reduction is one of the important techniques for the application of knowledge discovery and data mining. In this paper the data reduction is conceptually divided into three dimensions ,such as attribute dimension,object dimension and attribute value dimension. The conceptions,classification and approaches on three dimensions data reduction are introduced and analyzed. Finally, some problems, which should be focused on,are pointed out.
出处
《计算机科学》
CSCD
北大核心
2000年第7期53-58,28,共7页
Computer Science
关键词
数据挖掘
三维缩减
数据库
Data mining,Data reduction,Feature selection,Object selection,Discretization
