从动态空间数据库中挖掘共生关系和竞争关系  

Mining the symbiotic and competitive relationships from dynamic spatial databases

作　　者：芦俊丽 王丽珍[1] 赵家松 肖清[1] Lu Junli1,2 ,Wang Lizhen1 ,Zhao Jiasong1 ,Xiao Qing1(1.Department of Computer Science and Engineering,School of Information Science and Engineering, Yunnan University, Kunming, 650091, China; 2.Department of Mathematics and Computer Science, Yunnan Minzu University,Kunming, 650031 ,Chin)

机构地区：[1]云南大学信息学院计算机科学与工程系,昆明650091 [2]云南民族大学数学与计算机科学学院,昆明650031

出　　处：《南京大学学报（自然科学版）》2018年第2期436-451,共16页Journal of Nanjing University（Natural Science）

基　　金：国家自然科学基金(61472346;61662086);云南省自然科学基金(2015FB149;2016FA026)

摘　　要：空间co-location模式挖掘是空间数据挖掘的一个重要研究方向.空间co-location模式是空间特征的一个子集,它们的实例在空间中频繁关联,模式中的各个特征之间是位置共存的关系.然而,除了位置共存之外,这些特征可能还具有进一步的关系,例如相互依存的共生关系、争夺同一个环境资源的竞争关系.从动态空间数据库中挖掘隐含在空间co-location模式中的共生关系和竞争关系,挖掘目标分别为强共生模式和竞争对.给出了强共生模式和竞争对的定义,提出了挖掘强共生模式和竞争对的新颖的算法及剪枝策略.并在"合成+真实"数据中验证了算法的效率以及挖掘结果的意义.Spatial co-location pattern mining is an important direction in spatial data mining. Spatial co-location patterns represent the subsets of spatial features which are frequently located together in a geographic space. Spatial co-location patterns also show the co-located relationship among features. However, the features have further relationships such as symbiotic relationship and competitive relationship,besides co-located relationship. This paper mines symbiotic relationship and competitive relationship from the dynamic spatial databases. The objectives are strong symbiotic patterns and competitive pairs, respectively. The data between two adjacent time slots will change, and the changed data will incur changed neighbor relationships. The changed neighbor relationships reflect the symbiotic/competitive relationships among the features. According to this idea, the definitions of strong symbiotic patterns and competitive pairs are given,and the novel methods and pruning strategies for mining strong symbiotic patterns and competitive pairs are proposed. The experiments on synthetic databases evaluate the efficiency and scalability of the algorithms. Statistical comparison and partial results show of prevalent co-location patterns,strong symbiotic patterns and competitive pairs are conducted on real databases.

关 键 词：空间数据挖掘 空间co—location模式 共生关系 竞争关系 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]