A ROBUST TOTAL LEAST-SQUARES METHOD
Chen Weixian 1) ; and Yuan Qing 2)
1)Wuhan Urban & Rural Construction Committee,Wuhan 430023;2)China Railway Siyuan Survey and Design Group Co.,Ltd,Wuhan 430063
Abstract Aiming at the situation that there is single gross error in the observation vector of the Errorsin variables(EIV) model, we propose the robust total leastsquares method. On the basis of the generalized maximum likelihood estimation, we use the observation vector residual function which grows more slowly instead of observation vector squared residuals items, and have deduced robust total leastsquares estimation calculation formula with the iteration method with variable weights. Finally, we apply the new method to the coordinate transformation parameters determination, and verify the feasibilities of the new method.
Key words ：
Errors-in-variables(EIV) model
robust estimation
total least-squares method
robust total least-squares method
coordinate transformation
Received: 01 January 1900
Corresponding Authors:
Chen Weixian
[1]
ZOU Shilin,WU Xing,WANG Fengwei. Regularized Robust Solution for Ill-Posed Weighted Total Least Squares Model
[2]
WANG Leyang,XU Ranran. Robust Weighted Total Least Squares Algorithm for Three-Dimensional Coordinate Transformation
[3]
WU Guangming，LU Tieding. New Methods of Ill-Posed Total Least-Squares with Targeting Singular Value Corrections
[4]
WANG Leyang,ZOU Chuanyi,WU Lulu. The WHP Quasi Newton Correction Method for Inequality Constrained Partial EIV Model and the SUT Method for Its Precision Estimation
[5]
JI Kunpu. A Regularized Solution and Accuracy Evaluation of Ill-PosedTotal Least Squares Problem with Equality Constraints
[6]
TAO Wuyong,HUA Xianghong,LU Tieding,CHEN Xijiang,ZHANG Wei. A Total Least Squares Algorithm for Non-Equidistant GM(1,1) Model and Its Ill-Posed Problem
[7]
PU Lun,TANG Shihua,ZHANG Ziping,HU Xinkai,XIAO Yan. Application of Multi-Quadric Function Based on Ant Colony Algorithm in GPS Elevation Fitting
[8]
XIAO Zhaobing,SONG Yingchun,XIE Xuemei. Application of a Method for Obtaining Uncertainty in Dislocation Model
[9]
CHEN Yang,WEN Hongyan,QIN Hui,WANG Qingtao,ZHOU Lü. Robust Total Least Squares Estimated in GM(1,1) for High-Speed Railway Foundation Deformation Prediction
[10]
QIU Dechao, LU Tieding, DENG Xiaoyuan. A Circular Curve Fitting Solution Based on Partial EIV Model
[11]
QIU Dechao,LU Tieding,MAO Wenfei,WU Guangming. Model and Solution of PEIV Model for Spatial Straight Line Fitting
[12]
TAO Wuyong,LU Tieding,WU Fei,LI Ding. An Improved Total Least Squares Algorithm for Solving Sphere Surface Fitting
[13]
SUN Tonghe，YAN Guoqing. A Hybrid Regularization Algorithm to Ill-Posed Total Least Squares
[14]
WANG Leyang，CHEN Hanqing，WEN Yangmao. Analysis of Crust Deformation Based on Total Least Squares Collocation
[15]
WANG Qisheng. The New Algorithm for Multivariate Weighted Total Least Squares
