高值空间聚类的精确检测  

Exact detection of high-value spatial clusters

作　　者：于尚洋[1] 宋向东[1] 卫军雷[1] 

机构地区：[1]燕山大学理学院,河北秦皇岛066004

出　　处：《长春大学学报》2008年第4期6-9,共4页Journal of Changchun University

摘　　要：提出了一个数据调整的方法来弥补通常空间聚类检测的不足,从而能够对高值聚类进行精确检测。利用Matlab软件将该方法在模拟的空间类型中应用于Moran'I检测。结果表明,当有高值聚类趋势时,经该方法调整数据后利用Moran'I可以显著地检测出高值聚类的存在。This paper provides an adjustment procedure that can supplement common spatial clustering tests so that one-sided conclusion can be reached. The procedure is applied to Moran＇ I in simulated spatial patterns with the use of Matlab. The results show that when there is a high-value clustering tendency,the procedure can unambiguously distinguish the existence of high-value clusters.

关 键 词：空间聚类 数据调整 精确检测 

分 类 号：O212.1[理学—概率论与数理统计]