主成分估计在多项式曲面拟合GPS高程中的应用  

PRINCIPAL COMPONENT ANALYSIS FOR GPS ELEVATION INTERPOLATION

作　　者：冯光财[1] 陈正阳[1] 

机构地区：[1]中南大学测绘与国土信息工程系,长沙市麓山南路410083

出　　处：《测绘信息与工程》2006年第4期12-13,共2页Journal of Geomatics

摘　　要：阐述了多项式曲面拟合GPS高程中参数数目对结果的影响,比较了传统最小二乘平差、主成分估计和岭估计在不同参数时的计算结果,主成分回归在不同参数时都可以取得比较满意的结果。This paper analyzed the influence of parameters of many-sided curve fit models on the calculating results, and compared the results of least squares, principal component analysis and ridge estimation with different parameters. The comparison indicates that Principal Component Analysis can obtain correct results with different parameters, and centering and standardization is very important to improve the precision.

关 键 词：主成分估计 岭估计 GPS高程 多项式曲面拟合 

分 类 号：P228.42[天文地球—大地测量学与测量工程]