摘要： 商业智能系统应用联机分析处理技术将数据组织为多维数据立方体。该文建立了数据立方体中非空单元与决策表中等价类的一一映射关系。通过复用数据立方体中的聚合结果，提出一种基于数据立方体计算相容决策表属性核的方法，并证明了该方法的正确性。利用UCI数据集进行实验，结果表明在大数据量下该方法具有较好的时间效率。
关键词:
数据立方体,
联机分析处理,
粗集,
属性核
Abstract: In BI system, data are formed as a multidimensional OLAP cube. This paper focuses on computing the feature core of the decision table by reusing the aggregation in cube. After the relation is established between nonempty cells in a data cube and equal classes from a decision table, a new cube-based approach of computing the feature core of a consistent decision table is put forward in this paper. And the correctness of the new approach is proved. The experiments with UCI data set show that the new approach has high time performance.
Key words:
data cube,
online analysis processing,
rough set,
feature core
中图分类号:
刘亚波;刘大有;高 滢;齐 红;. 基于数据立方体的属性核计算方法[J]. 计算机工程, 2008, 34(20): 46-48.
LIU Ya-bo; ; LIU Da-you; GAO Ying; QI Hong;. Data Cube-based Feature Core Computing Approach[J]. Computer Engineering, 2008, 34(20): 46-48.