罚处共享最近邻密度峰聚类算法  

Penalty shared nearest neighbor density peak clustering algorithm

作　　者：高润峰 苏一丹[1] 覃华[1] GAO Run-feng;SU Yi-dan;QIN Hua(School of Computer,Electronics and Information,Guangxi University,Nanning 530004,China)

机构地区：[1]广西大学计算机与电子信息学院,广西南宁530004

出　　处：《计算机工程与设计》2021年第12期3407-3414,共8页Computer Engineering and Design

基　　金：国家自然科学基金项目(51667004、61762009)。

摘　　要：为解决传统密度峰聚类算法容易忽略低密度簇中心以及难以自动选择聚类中心的问题,提出罚处共享最近邻密度峰聚类算法。设计罚处系数,减少高密度簇中非中心点的共享最近邻局部密度值,降低低密度簇中心点被忽视的机率;采用迭代阈值法实现簇中心点的自动选择。在人工数据集、UCI真实数据集以及图像数据集上进行仿真实验,其结果表明,该算法能找到数据集的簇中心和簇数目,聚类精度优于相比较的其它算法,该算法是可行的、有效的。To solve the problem that the traditional density peak clustering algorithm easily ignores the low density cluster center and is difficult to automatically select the cluster center,a penalty shared nearest neighbor density peak clustering algorithm was proposed.The penalty coefficient was designed to reduce the local density value of the shared nearest neighbor of the non-center points in the high-density cluster,and reduce the probability of the center point being ignored in the low-density cluster.The iterative threshold method was used to realize the automatic selection of the cluster center point.The simulation results on artificial datasets,UCI real datasets and image data sets show that the proposed algorithm can find the cluster centers and the number of datasets,and its clustering accuracy is better than that of other algorithms.The algorithm is feasible and effective.

关 键 词：密度峰聚类算法 共享最近邻局部密度 簇中心点 罚处系数 迭代阈值法 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]