基于网格和密度的数据流聚类算法  

Grid and density on data stream clustering algorithm

作　　者：张丽[1] 胡颖[1] 

机构地区：[1]商丘师范学院计算机科学系,河南商丘476000

出　　处：《商丘师范学院学报》2011年第3期70-73,78,共5页Journal of Shangqiu Normal University

摘　　要：针对数据流的特点,提出了一种新的网格密度结合的GCTS算法.它采用了双层架构,在线层实现了网格密度参数的自设定,离线层以网格单元的重心为中心点,建立一个最大的子网格,使候选网格中的局部密集区域转化成了密集网格.最后使用最小生成树的算法生成进行聚类结果.提高了聚类效果.According to the characteristics of the data stream,his paper presented a new clustering algorithm GTCS which combined the approach based on density and grid.By means of the model of double-layer construction,the online layer set the key of densities of the data grids automatically,the offline layer using the data gravity for the center,build a maximum of subgrid,making the dense regions of the candidate grids into dense grid.In the end,it use the minimum spanning tree chlstering Algorithm to get the clustering results,improved the clustering affect.

关 键 词：数据流 聚类 子网格 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置]