基于K-means聚类的多面函数及其在DEM内插中的应用  

Multi-Quadric function based on the K-means clustering algorithm and its application in DEM spatial data interpolation

作　　者：冯杨民[1] 张菊清[1] 

机构地区：[1]长安大学地质工程与测绘学院,陕西西安710054

出　　处：《测绘工程》2009年第2期16-18,23,共4页Engineering of Surveying and Mapping

摘　　要：中心节点的位置是影响多面函数拟合精度的关键因素之一。基于聚类算法的思想,提出采用基于K-means聚类的方法选取中心点,使得构造的中心节点对数据范围内的数据得到更好的响应,从而提高拟合的精度。最后通过实例验证本方法的有效性。The location of the centre nodes is one of the key factors to affect the multi-quadric＇s accuracy approximation. Based on the clustering algorithms, this paper adopts the K-means clustering to choose the centre nodes, which will give a better response to the space data around them, and improve the fitting accuracy. Finally, an example is given to demonstrate the validity of the method.

关 键 词：多面函数 中心节点 K-MEANS聚类 

分 类 号：P228[天文地球—大地测量学与测量工程]