Research on Grid based Spatial Outliers Mining and Its Implementation
Integrated and deep-seated applications call forthe intelligentization of spatial data processing.Spatial data mining is becoming more and moreimportant to satisfy practical application andbusiness intelligence.With the rapid development ofdistributed sharing infrastructures such as grid andweb services,providing knowledge services on gridenvironment is becoming the trend of knowledgediscovery and application technologies.This paperintroduces an architecture of geographicalknowledge grid platform based on globus(GeoKS-Grid),then puts forward a spatial data integrationscheme by the combination of GML and WFSspecification,finally,taking spatial outliers miningbased on MST clustering as an example to illustratesthe design and realization of knowledge service.Experimentation finds that it is feasible andpracticable to extend the grid environment by addingmore and more distributed high performanceknowledge discovery services implemented based ondata grid mechanisms and globus toolkit,to meet therequirements of application.For the application inreal system,a task-oriented architecture based onKSDM is proposed and an implementation ofknowledge service is introduced.
Lin Jiaxiang Chen hongcheng Ye Dongyi Wang Weibin
Spatial Information Research Center of Fufian,Fuzhou University College of Mathematics and Computer Science,Fuzhou University
国际会议
厦门
英文
324-328
2008-11-17（万方平台首次上网日期，不代表论文的发表时间）