浓缩数据立方中约束立方梯度的挖掘(英文)  

Mining Constrained Cube Gradient for the Condensed Data Cube

作　　者：冯玉才[1] 刘玉葆[1] 冯剑琳[1] 

机构地区：[1]华中科技大学计算机科学技术学院,湖北武汉430074

出　　处：《软件学报》2003年第10期1706-1716,共11页Journal of Software

基　　金：国家科技部电子政务项目~~

摘　　要：约束立方梯度挖掘是一项重要的挖掘任务,其主要目的是从数据立方中挖掘出满足梯度约束的梯度-探测元组对.然而,现有的研究都是基于一般数据立方的.研究了浓缩数据立方中约束数据立方梯度的挖掘问题.通过扩展LiveSet驱动算法,提出了一个eLiveSet算法.测试表明,该算法在立方梯度挖掘效率上比现有算法要高.Constrained cube gradient mining is an important mining task and its goal is to extract the pairs of gradient-probe cell that satisfy the gradient constraint from a data cube. However, previous work are explored for a general data cube. In this paper, the problem of the mining constrained cube gradient for a condensed cube is studied. An algorithm named as eLiveSet for the problem is developed through the extension of the existing efficient mining algorithm LiveSet-driven. The experimental results show that the algorithm is more effective than the existing algorithm on the performance of mining constrained cube gradient.

关 键 词：数据立方 立方梯度 浓缩数据立方 数据立方计算 关联规则 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]