考虑数据不确定性的非均匀挖掘算法  

Non-Uniform Mining Algorithm for Considering Data Uncertainty

作　　者：刘竹松[1] 陈洁[1] 

机构地区：[1]广东工业大学计算机学院,广东广州510006

出　　处：《华侨大学学报（自然科学版）》2016年第3期308-311,共4页Journal of Huaqiao University(Natural Science)

基　　金：国家自然科学基金资助项目(61572144);广东省科技计划项目(2013B090200006);广东省现代信息服务业发展专项基金资助项目(GDEID2011IS022)

摘　　要：针对高维大数据不确定性的非均匀挖掘问题,提出一种基于不确定频繁模式树的模糊逻辑非均匀数据挖掘算法.首先,在考虑数据不确定性的前提下建立高维数据的区域连接演算(RCC)模型,并基于数据集合组元定义分析不确定数据集合的模糊距离;然后,采用不确定模式树对数据的非均匀特性进行均匀泛化处理,并给出了具体的实现步骤.仿真结果表明:文中方法有效地提升不确定非均匀数据集合在不同支持度情况下的挖掘效率.In order to solve high-dimensional large data uncertainty and non-uniform mining problems,this paper proposed a new kind of non-uniform data mining algorithm based on the fuzzy logic and uncertain frequent pattern tree.Firstly,the high-dimensional region connection calculus（RCC）data model is established under the premise of considering the data uncertainty.The uncertain fuzzy distance of data sets is defined and analyzed based on the data sets elements.Secondly,the non-uniform data is generalized by the uncertain frequent pattern tree,and the specific implementation steps is given.Simulation results show that the proposed method effectively improved the mining efficiency of the uncertain heterogeneous data sets in different support conditions.

关 键 词：高维大数据 数据挖掘 模糊逻辑 不确定频繁模式树 区域连接演算 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]