基于距离和密度的d-K-means算法  

d-K-means algorithm based on distance and density

作　　者：唐泽坤 朱泽宇 杨裔[1] 李彩虹[1] 李廉[1] Tang Zekun;Zhu Zeyu;Yang Yi;Li Caihong;Li Lian(College of Information Science&Engineering,Lanzhou University,Lanzhou 730000,China)

机构地区：[1]兰州大学信息科学与工程学院,兰州730000

出　　处：《计算机应用研究》2020年第6期1719-1723,共5页Application Research of Computers

基　　金：国家重点研发计划资助项目(2018YFB1003205);国家自然科学基金资助项目(61300230,61370219);甘肃省自然科学基金资助项目(1107RJZA188);甘肃省科技支撑计划资助项目(1104GKCA037);甘肃省科技重大专项项目(1102FKDA010)。

摘　　要：针对K-means算法对初始聚类中心和噪声敏感的缺点,提出了d-K-means算法(distance&density),在K-means算法的基础上权衡了密度和距离对聚类的影响,对数据进行加权处理,在权值基础上引入最小最大原则选择初始聚类中心,自动确定类中心个数。实验结果表明,d-K-means算法在低维与高维数据上都可以取得较好的聚类效果,并且可以更好地应对低密度区域数据,更好地进行类中心选择。To deal with the disadvantages of the K-means algorithm that is sensitive to initial clustering center and noise,this paper proposed the d-K-means algorithm. On the basis of the K-means algorithm,it weighed the data considering the impact of density and distance on clustering. It selected the initial clustering center by introducing the min-max principle on the basis of weight,and automatically determined the number of class centers. Experimental results show that d-K-means algorithm can achieve better clustering results on low-dimensional data sets and high-dimensional data sets,and better deal with low-density regional data,and better select class centers.

关 键 词：聚类 K-MEANS算法 最小最大原则 类中心个数 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]