APPLICATION OF TOTAL LEAST SQUARES TO A LINEAR SURVEYING NETWORK

Despite the classical least squares being the de-facto technique for adjusting Surveying networks, this research explores the application of total least squares to solving a linear surveying network problem. The linear surveying network used for the experiment is a three-loop levelling network. The augmented matrix of the design matrix and observation vector is first computed. Thereafter the singular value decomposition of the augmented matrix of the design matrix and the vector of unknown parameters are obtained. The residuals from the total least squares when compared with those from the classical least squares, are relatively better.