考虑数据不确定性的非均匀挖掘算法

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.

Non-Uniform Mining Algorithm forConsidering Data Uncertainty

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.