摘要
为了拓展算法的应用领域,降低算法的复杂性,提高分类器的性能,提出了网格平台下的模糊积分分类数据挖掘,依据模糊积分的概念,应用隶属度矩阵来确定模糊积分密度,再对分类器集成,对网格中采集的原始数据进行处理,实验证明用该集成方法所构成的分类系统能明显提高分类器的性能.
In order to develop the application area, reduce the complexity for the algorithm and improve the capability of classifier demonstrably, we present a method of fuzzy - integral classified data mining based on grid. With the conception of the fuzzy integral and membership degree matrix, we ascertain the fuzzy integral density, and integrate the classifier. We can manage the primary data of the Grid. The experiments show that this algorithm can improve the capability of classifier considerably.
出处
《湖北民族学院学报（自然科学版）》
CAS
2006年第4期391-393,共3页
Journal of Hubei Minzu University(Natural Science Edition)
基金
湖南省教育厅重点项目资助(04A037)
关键词
网格
模糊积分
隶属度矩阵
分类
数据挖掘
grid
fuzzy integral
membership degree matrix
class
data mining
