Abstract
Although weighted total least-squares (WTLS) adjustment within the errors-in-variables (EIV) model is a rigorous method developed for parameter estimation, its exact solution is complicated since the matrix operations are extremely time-consuming in the whole repeated iteration process, especially when dealing with large data sets. This paper rewrites the EIV model to a similar Gauss–Markov model by taking the random error of the design matrix and observations into account, and reformulates it as an iterative weighted least-squares (IWLS) method without complicated theoretical derivation. IWLS approximates the “exact solution” of the general WTLS and provides a good balance between computational efficiency and estimation accuracy. Because weighted LS (WLS) method has a natural advantage in solving the EIV model, we also investigate whether WLS can directly replace IWLS and WTLS to implement the EIV model when the parameters in the EIV model are small. The results of numerical experiments confirmed that IWLS can obtain almost the same solution as the general WTLS solution of Jazaeri [21] and WLS can achieve the same accuracy as the general WTLS when the parameters are small.
References
[1] Adcock, R. (1877). “Note on the method of least squares.” Analyst, (4), 183–184.10.2307/2635777Search in Google Scholar
[2] Akyilmaz, O. (2007). “Total Least Squares Solution of Coordinate Transformation.” Survey Review, 39(303), 68–80.10.1179/003962607X165005Search in Google Scholar
[3] Amiri-Simkooei, A. R., Zangeneh-Nejad, F., Asgari, J., and Jazaeri, S. (2014). “Estimation of straight line parameters with fully correlated coordinates.” Measurement, Elsevier Ltd, 48(1), 378–386.10.1016/j.measurement.2013.11.005Search in Google Scholar
[4] Cai, J., and Grafarend, E. (2009). “Systematical analysis of the transformation between Gauss–-Krueger-coordinate/DHDN and UTMcoordinate/ETRS89 in Baden–Württemberg with different estimation methods.” Drewes, H. (ed.) Geodetic reference frames, International Association of Geodesy Symposia, Springer, Berlin, 205–211.10.1007/978-3-642-00860-3_32Search in Google Scholar
[5] Carroll, R., Ruppert, D., Stefanski, L., and Crainiceanu, C. (2006). Measurement error in nonlinear models—a modern perspective, 2nd edn. Chapman and Hall, New York.10.1201/9781420010138Search in Google Scholar
[6] Chang, G. (2015). “On least-squares solution to 3D similarity transformation problem under Gauss–Helmert model.” Journal of Geodesy, 89(6), 573–576.10.1007/s00190-015-0799-zSearch in Google Scholar
[7] Chenf, W., Zhang, J., Ma, B., and Lu, J. (2006). “Application of the Total Least Squares Method to the Determination of Preliminary Orbit.” Chinese Astronomy and Astrophysics, 47(2), 186–191.Search in Google Scholar
[8] Dastgahian, M. S., Tehrani, M. N., and Khoshbin, H. (2018). “The off-grid frequency selective millimeter wave channel estimation.” International Journal of Communication Systems, 31(15), e3770.10.1002/dac.3770Search in Google Scholar
[9] Deming, W. E. (1931). “The application of least squares.” Philosophical Magazine Series, 11, 146–158.10.1080/14786443109461671Search in Google Scholar
[10] Deming, W. E. (1934). “On the application of least squares—II.” Philosophical Magazine Series, 17, 804–829.10.1080/14786443409462437Search in Google Scholar
[11] Fang, X. (2011). “Weighted Total Least Squares Solutions for Applications in Geodesy.” Gottfried Wilhelm Leibniz Universität Hannover.Search in Google Scholar
[12] Fang, X. (2014). “A total least squares solution for geodetic datum transformations.” Acta Geodaetica et Geophysica, 49(2), 189–207.10.1007/s40328-014-0046-8Search in Google Scholar
[13] Felus, Y. A. (2004). “Application of Total Least Squares for Spatial Point Process Analysis.” Journal of Surveying Engineering, 130(3), 126–133.10.1061/(ASCE)0733-9453(2004)130:3(126)Search in Google Scholar
[14] Felus, Y. A., and Burtch, R. C. (2009). “On symmetrical three-dimensional datum conversion.” GPS Solutions, 13(1), 65–74.10.1007/s10291-008-0100-5Search in Google Scholar
[15] Fuller, W. (1987). Measurement error models. Wiley Interscience, New York.10.1002/9780470316665Search in Google Scholar
[16] Golub, G., and Loan, V. (1980). “An analysis of the Total least-squares problem.” SIAM J Numer Anal, 17(6), 883–893.10.1137/0717073Search in Google Scholar
[17] Guan, Y., Liu, S., Zhou, S., and Zhang, L. (2011). “Robust plane fitting of point clouds based on TLS.” Journal of Geodesy and Geodynamics, 31(5), 80–83.Search in Google Scholar
[18] Han, J. (2010). “Noniterative Approach for Solving the Indirect Problems of Linear Reference Frame Transformations.” Journal of Surveying Engineering, 136(4), 150–156.10.1061/(ASCE)SU.1943-5428.0000026Search in Google Scholar
[19] Henderson, H., and Searle, S. (1981). “On deriving the inverse of a sum of matrices.” SIAM Review, (23), 53–60.10.1137/1023004Search in Google Scholar
[20] Van Huffel, S., and Vandewalle, J. (1991). The total least squares problem: computational aspects and analysis. SIAM, Philadelphia.10.1137/1.9781611971002Search in Google Scholar
[21] Jazaeri, S., Amiri-Simkooei, A. R., and Sharifi, M. A. (2014). “Iterative algorithm for weighted total least squares adjustment.” Survey Review, 46(334), 19–27.10.1179/1752270613Y.0000000052Search in Google Scholar
[22] Kummell, C. H. (1879). “Reduction of Observation Equations Which Contain More Than One Observed Quantity.” The Analyst, 6(4), 97–105.10.2307/2635646Search in Google Scholar
[23] Li, J., Gao, W., Qian, J., Guo, Q., Xi, J., and Ritz, C. H. (2019). “Robust entangled-photon ghost imaging with compressive sensing.” Sensors (Switzerland), 19(1), 1–11.10.3390/s19010192Search in Google Scholar PubMed PubMed Central
[24] Mahboub, V. (2012). “On weighted total least-squares for geodetic transformations.” Journal of Geodesy, 86(5), 59–67.10.1007/s00190-011-0524-5Search in Google Scholar
[25] Mahboub, V., Ardalan, A. A., and Ebrahimzadeh, S. (2015). “Adjustment of non-typical errors-in-variables models.” Acta Geodaetica et Geophysica, 50(2), 207–218.10.1007/s40328-015-0109-5Search in Google Scholar
[26] Mahboub, V., and Sharifi, M. A. (2013). “On weighted total least-squares with linear and quadratic constraints.” Journal of Geodesy, 87(3), 279–286.10.1007/s00190-012-0598-8Search in Google Scholar
[27] Markovsky, I., and Van Huffel, S. (2007). “Overview of total least-squares methods.” Signal Processing, 87(10), 2283–2302.10.1016/j.sigpro.2007.04.004Search in Google Scholar
[28] Neitzel, F. (2010). “Generalization of total least-squares on example of unweighted and weighted 2D similarity transformation.” Journal of Geodesy, 84(12), 751–762.10.1007/s00190-010-0408-0Search in Google Scholar
[29] Rajkumar, D. G. (2017). “Linear Cryptanalysis of Substitution Ciphers Using Particle Swarm Optimization.” Oriental journal of computer science and technology, 10(3), 580–584.10.13005/ojcst/10.03.04Search in Google Scholar
[30] Ran, L., Xie, R., Liu, Z., Zhang, L., Li, T., and Wang, J. J. (2018). “Simultaneous range and cross-range variant phase error estimation and compensation for highly squinted SAR imaging.” IEEE Transactions on Geoscience and Remote Sensing, 56(8), 4448–4463.10.1109/TGRS.2018.2820102Search in Google Scholar
[31] Schaffrin, B., and Wieser, A. (2008). “On weighted total least-squares adjustment for linear regression.” Journal of Geodesy, 82(7), 415–421.10.1007/s00190-007-0190-9Search in Google Scholar
[32] Schaffrin, B., and Wieser, A. (2011). “Total least-squares adjustment of condition equations.” Studia Geophysica et Geodaetica, 55(3), 529–536.10.1007/s11200-011-0032-3Search in Google Scholar
[33] Shen, Y., Li, B., and Chen, Y. (2011). “An iterative solution of weighted total least-squares adjustment.” Journal of Geodesy, 85(4), 229–238.10.1007/s00190-010-0431-1Search in Google Scholar
[34] Shi, Y., Xu, P., Liu, J., and Shi, C. (2015). “Alternative formulae for parameter estimation in partial errors-in-variables models.” Journal of Geodesy, 89(1), 13–16.10.1007/s00190-014-0756-2Search in Google Scholar
[35] Tong, X., Jin, Y., and Li, L. (2011). “An Improved Weighted Total Least Squares Method with Applications in Linear Fitting and Coordinate Transformation.” Journal of Surveying Engineering, 137(4), 120–128.10.1061/(ASCE)SU.1943-5428.0000055Search in Google Scholar
[36] Wang, J. (2015). “Locating and estimating multiple gross errors during coordinate transformation.” Survey Review, 47(345), 458–464.10.1179/1752270615Y.0000000019Search in Google Scholar
[37] Wang, J., Yan, W., Zhang, Q., and Chen, L. (2021a). “Enhancement of Computational Efficiency for Weighted Total Least Squares.” Journal of Surveying Engineering, 147(4), 04021019.10.1061/(ASCE)SU.1943-5428.0000373Search in Google Scholar
[38] Wang, J., Zhao, J., Liu, Z., and Kang, Z. (2021b). “Location and estimation of multiple outliers in weighted total least squares.” Measurement, 181, 109591.10.1016/j.measurement.2021.109591Search in Google Scholar
[39] Wang, L. (2012). “Properties of the total least squares estimation.” Geodesy and Geodynamics, 3(4), 39–46.10.3724/SP.J.1246.2012.00039.1Search in Google Scholar
[40] Wang, L., Yu, H., and Cheng, X. (2016). “An Algorithm for Partial EIV Model.” Acta Geodaetica et Cartographica Sinica, 45(1), 22–29.Search in Google Scholar
[41] Wang, Q., Fang, Y., Wang, W., Wu, M., Wang, R., and Fang, Y. (2014). “Research on automatic reading recognition of index instruments based on computer vision.” Proceedings of 2013 3rd International Conference on Computer Science and Network Technology, ICCSNT 2013, IEEE, Dalian, 10–13.10.1109/ICCSNT.2013.6967053Search in Google Scholar
[42] Wu, Y., Liu, J., and Ge, Y. H. (2016). “Comparison of Total Least Squares and Least Squares for Four- and Seven-parameter Model Coordinate Transformation.” Journal of Applied Geodesy, 10(4), 259–266.10.1515/jag-2016-0015Search in Google Scholar
[43] Xu, P. (2016). “The effect of errors-in-variables on variance component estimation.” Journal of Geodesy, Springer Berlin Heidelberg, 90(8), 681–701.10.1007/s00190-016-0902-0Search in Google Scholar
[44] Xu, P. (2019). “Improving the weighted least squares estimation of parameters in errors-in-variables models.” Journal of the Franklin Institute, Elsevier Ltd, 356(15), 8785–8802.10.1016/j.jfranklin.2019.06.016Search in Google Scholar
[45] Xu, P., and Liu, J. (2014). “Variance components in errors-in-variables models: Estimability, stability and bias analysis.” Journal of Geodesy, 88(8), 719–734.10.1007/s00190-014-0717-9Search in Google Scholar
[46] Xu, P., Liu, J., and Shi, C. (2012). “Total least squares adjustment in partial errors-in-variables models: Algorithm and statistical analysis.” Journal of Geodesy, 86(8), 661–675.10.1007/s00190-012-0552-9Search in Google Scholar
[47] Xu, P., Liu, J., Zeng, W., and Shen, Y. (2014). “Effects of errors-in-variables on weighted least squares estimation.” Journal of Geodesy, 88(7), 705–716.10.1007/s00190-014-0716-xSearch in Google Scholar
[48] Zhang, S., Zhang, K., Han, J., and Tong, X. (2017). “Total least norm solution for linear structured EIV model.” Applied Mathematics and Computation, 304(7), 58–64.10.1016/j.amc.2017.01.006Search in Google Scholar
[49] Zhao, J. (2017). “Efficient weighted total least-squares solution for partial errors-in-variables model.” Survey Review, 49(356), 346–354.10.1080/00396265.2016.1180753Search in Google Scholar
[50] Zhou, Y., and Deng, C. (2012). “Weighted and Unweighted Total Least Square Methods and Applications to Heteroscedastic 3D Coordinate Transformation.” Geomatics and Information Science of Wuhan University, 37(8), 976–979.Search in Google Scholar
[51] Zhou, Y., Kou, X., Li, J., and Fang, X. (2016). “Comparison of Structured and Weighted Total Least-Squares Adjustment Methods for Linearly Structured Errors-in-Variables Models.” Journal of Surveying Engineering, 143(1), 04016019.10.1061/(ASCE)SU.1943-5428.0000190Search in Google Scholar
© 2022 Walter de Gruyter GmbH, Berlin/Boston
