一种基于面包含关系的GML空间离群面检测算法  

An Algorithm for Detecting Outlier Region in GML Data Based on Region Spatial Inclusion Relationship

作　　者：李尼格[1,2,3] 鲍培明[1,2,3] 沙露[1,2,3] 

机构地区：[1]南京师范大学计算机科学与技术学院,江苏南京210097 [2]南京师范大学虚拟地理环境教育部重点实验室,江苏南京210097 [3]江苏省信息安全保密技术工程研究中心,江苏南京210097

出　　处：《广西师范大学学报（自然科学版）》2009年第3期118-121,共4页Journal of Guangxi Normal University:Natural Science Edition

基　　金：国家自然科学基金资助项目(40771163;40871176)

摘　　要：为了研究基于空间拓扑关系的离群检测,提出了一种基于面包含关系的离群面检测算法DOR-IR。它采用算法PL I判断面包含关系,并把面包含的对象看作面对象的属性,建立面对象的密度连通集合,相应于"噪音"的面就是离群面。运用算法DOR-IR分别在人工数据集和真实数据集上进行了测试,实验结果表明,算法DOR-IR能有效挖掘基于拓扑包含关系的离群面。In order to study the outlier detection based on spatial topological relationship, an algorithm DOR _ IR to detect the outlier region is proposed based on region spatial inclusion relationship. The algorithm uses PLI algorithm in the data sets with GML document format to determine the region spatial in- clusion relationship and regards the objects contained in a region as attributes of the region. DOR _ IR sets up density-connected set o{ region and expands density-connected set. The regions which don＇t be- long to any density-connected set are outlier regions. Algorithm DOR _ IR is implemented and tested in artificial and real data sets. The results of the experiments show that the algorithm DOR _ IR is able to mine the outlier region based on region spatial inclusion relationship.

关 键 词：空间离群面检测 空间包含 拓扑关系 GML 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]