移动型数据与静态型数据的混合聚类算法  

Hybrid Clustering Algorithm for Mobile Data and Static Data

作　　者：何云斌[1] 董恒 万静[1] HE Yun-bin;DONG Heng;WAN Jing(School of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080,China)

机构地区：[1]哈尔滨理工大学计算机科学与技术学院,哈尔滨150080

出　　处：《哈尔滨理工大学学报》2021年第2期26-34,共9页Journal of Harbin University of Science and Technology

基　　金：国家自然科学基金(61872105);黑龙江省自然科学基金(F201302);黑龙江省教育厅科学技术研究项目(1253lz004).

摘　　要：针对移动型数据与静态型数据同时存在的混合数据聚类问题,提出了混合数据聚类MMPSP算法。首先分析了包含静态型数据集与只有一个移动型数据的混合数据聚类问题,再扩展到包含静态型数据集与移动型数据集的混合数据聚类问题。混合数据聚类研究中对两种类型的数据分别进行聚类处理,即对静态型数据聚类处理得到静态簇,对移动型数据聚类处理得到移动簇,在获得两种数据类型的簇后,再以簇为单位对两种数据类型的数据进行聚类处理。最后通过实验证明,MMPSP算法针对混合数据的聚类处理相比实验对比算法,取得了更好的聚类效果和聚类准确率。A hybrid data clustering algorithm MMPSP is proposed to solve the clustering problem involving both mobile data and static data.Firstly,the clustering problem of mixed data containing static data sets and only one mobile data is analyzed,and then the clustering problem of mixed data containing static data sets and mobile data sets is discussed.In the study of mixed data clustering problem,the data of the two data types are separately clustered.The static data is clustered to get the static cluster,and the mobile cluster is obtained by the mobile data clustering.After obtaining the clusters of the two data types,the data of the two data types are clustered in units of clusters.Finally,the experimental results show that compared with experimental comparison algorithm,the algorithm MMPSP has better effect and accuracy for the clustering processing of this kind of mixed data.

关 键 词：移动数据 静态数据 混合聚类 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]