基于裁边策略的空间离群区域检测算法  

Spatial outlier region detection algorithm based on cutting edge strategy

作　　者：陈涛[1] 万家强[1] 朱庆生[1] 

机构地区：[1]重庆大学计算机学院,重庆400044

出　　处：《计算机应用研究》2013年第3期783-786,共4页Application Research of Computers

基　　金：国家自然科学基金资助项目(61073058)

摘　　要：为了检测空间数据集中存在的离群区域,提出一种基于裁边策略的空间离群区域检测算法。首先利用Delaunay三角网格确定空间邻接关系,根据非空间属性描述邻接节点间的差异性;然后反复裁去最大权边,且并发地检测离群区域,直到发现足够多离群点。实验结果表明,该算法能有效检测离群区域,并且准确给出局部离群性,克服了普通算法中易受坏邻居干扰和区域缺乏原子性的局限。In order to detect the existed outlier regions in spatial data sets, this paper proposed a cutting-long-edges-based ap- proach. It used Delaunay triangle mesh to construct adjacency relationships. Then it according to non-spatial attributes ad- dressed the difference between nodes. Finaly it iteratively cut long edges, and concurrently detected anomalous regions, and it found till enough outlier. Experiments demonstrate that out approach can effectively discover anomalous regions and the abnor- mality measure can reflect real local difference. Especially, the approach overcomes the general drawbacks such as the dis- turbance of bad neighbors and the lack of atomicity of regions.

关 键 词：空间离群点 区域检测 DELAUNAY三角网 裁边 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论] TP391[自动化与计算机技术—计算机科学与技术]