顾及数据空间分布特性的模糊C-均值聚类算法研究
A New Method of FCM Considering the Distribution of Spatial Data
-
摘要: 利用描述空间数据分布的Voronoi图的有关理论分析了样本空间数据分布特性,从理论上论述了样本集中各类样本数差异较大产生的根源,并在此基础上提出了一种顾及数据空间分布特性的模糊C-均值聚类算法。Abstract: A new method of FCM considering the distribution of spatial data is put forward.In the new method,the weight factor related to the characteristics of the distribution of spatial data is taken into account.Thus,the result of classification by the new method is improved.Last,two tests are given to show the advantages and effectiveness of the new method.