【摘要】 在分析空间数据和空间数据挖掘的不确定性基础上,针对传统空间数据挖掘的局限性,将空间数据的不确定性和空间数据挖掘的不确定性有机结合,以EM算法和Apriori算法为基础,建立了不确定性空间数据挖掘算法模型,包括不确定性空间数据聚类算法(UNEM)和不确定性空间数据关联规则挖掘模型(USAR).并以中国37个有代表性的大中城市的地理空间经济数据为例,进行实验验证,结果表明:采用不确定性空间数据挖掘算法模型比传统的空间数据挖掘方法得到的知识更为真实客观.更多还原

【Abstract】 On the basis of analyzing the uncertainties of spatial data and spatial data mining(SDM),in view of the limits of traditional spatial data mining,the uncertainties of spatial data and spatial data mining were properly combined.Based on EM algorithm and Apriori algorithm,the uncertain spatial data mining algorithms,including uncertain spatial clustering algorithm(uncertain neighborhood expectation maximum,UNEM) and uncertain spatial association rules mining(USAR) model were presented.Meanwhile,the experiments concerned have been performed using the geo-spatial data from 37 typified cites in China.The results show that the knowledge acquired through the uncertain spatial data mining algorithms is more real and objective than those through traditional spatial data mining methods.更多还原