空间数据模糊聚类的有效性评价  

Validity Measure on Fuzzy Clustering for Spatial Data

作　　者：胡春春[1] 孟令奎[1] 谢文君[1] 周新忠[1] 

机构地区：[1]武汉大学遥感信息工程学院,武汉市珞喻路129号430079

出　　处：《武汉大学学报（信息科学版）》2007年第8期740-743,共4页Geomatics and Information Science of Wuhan University

基　　金：国家863计划资助项目(2005AA113150)

摘　　要：基于模糊划分中存在的分类不确定性因素和空间数据的空间位置特征,提出了一种新的空间数据模糊聚类有效性函数。实验结果表明,这种新的有效性函数能够对模糊聚类结果的有效性进行正确的评价,特别是对于空间数据模糊聚类有效性评价,其分类效果较理想,同其他有效性指标相比,能得到较优的分类数。The validity index of the result produced by fuzzy clustering based on two aspects is studied, which are the uncertainty of classification during fuzzy partition and spatial location feature of spatial data, and a new validity function of fuzzy clustering for spatial data is proposed. The experimental result indicates that the new validity index can accurately meas- ure the validity of the result of fuzzy clustering. Specially, for the result of fuzzy clustering of spatial data, it is robust and its classification result is more perfect compared with other indices.

关 键 词：模糊聚类 空间数据 有效性 

分 类 号：P208[天文地球—地图制图学与地理信息工程]