犹豫模糊核C-均值聚类用于数据库系统选择  

Hesitant Fuzzy Kernel C-Means Clustering for Database System Selection

作　　者：邓小燕[1] DENG Xiao-yan(Center of Modem Education Technology,Jiangsu Food and Pharmaceutical Science College,Jiangsu Huai'an 223005,China)

机构地区：[1]江苏食品药品职业技术学院现代教育技术中心

出　　处：《控制工程》2020年第1期182-187,共6页Control Engineering of China

基　　金：江苏食品药品职业技术学院基金(JSSPXN2016014);江苏省教育科学研究院现代教育技术研究所项目(2018-R-61423)

摘　　要：在处理属性值为犹豫模糊信息的聚类分析问题过程中,一般性的犹豫模糊聚类算法在样本空间层面处理过程中存在消耗时间长、距离结果不精确等不足。为了解决这一问题,建立了一种新颖的犹豫模糊聚类算法,即犹豫模糊核C-均值聚类算法,该算法运用核函数将样本空间中的数据映射到一个高维特征空间。结果显示,通过提出的犹豫模糊核C-均值聚类算法能够扩大不同样本之间的差异,并且使得聚类结果更加准确。最后,通过数据库系统选择的仿真实验,验证了所提出的犹豫模糊核C-均值聚类算法的可行性和有效性。In order to deal with clustering problems for hesitant fuzzy information, this paper normally solves them on sample space by using a certain hesitant fuzzy clustering algorithm, which is usually time-consuming or generates inaccurate clustering results. To overcome the issue, we propose a novel hesitant fuzzy clustering algorithm called hesitant fuzzy kernel C-means clustering(HFKCM) algorithm by means of kernel functions, which maps the data from the sample space to a high-dimensional feature space. As a result, the proposed HFKCM algorithm expands the differences between different samples, and makes the clustering results much more accurate. Finally, by conducting simulation experiments on the selection of database systems, and the results reveal the feasibility and availability of the proposed hesitant fuzzy kernel C-means clustering algorithm.

关 键 词：聚类算法 犹豫模糊集 核函数 样本空间 数据库系统 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]