Integer-Coded Genetic Algorithm for Trimmed Estimator of Multivariate Linear Errors in Variables Model

Abstract:

The multivariate linear errors-in-variables (EIV) model is frequently used in computer vision for model fitting tasks. As well known, when sample data is contaminated by large numbers of awkwardly placed outliers, the least squares estimator isn’t robust. To obtain robust estimators of multivariate linear EIV model, orthogonal least trimmed square and orthogonal least trimmed absolute deviation estimators based on the subset of h cases(out of n)are proposed. However, these robust estimators possessing the exact fit property are NP-hard to compute. To tackle this problem, an integer-coded genetic algorithm that is applicable to trimmed estimators is presented. The trimmed estimators of multivariate linear EIV model on real data are provided and the results show that the integer-coded genetic algorithm is correct and effective.

• Periodical: Advanced Materials Research (Volumes 457-458)
• Pages: 1223-1229
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.457-458.1223
• Online since: January 2012
• Authors: Hui Rong Cao, Fu Chang Wang
• Keywords: C-Step, Integer-Coded Genetic Algorithm, Linear Error-in-Variable Model, Orthogonal Least Trimmed Absolute Deviation (OLTAD), Orthogonal Least Trimmed Squares (OLTS)

References

[1] B. Matei and P. Meer, A General Method for Errors-in-Variables Problems in Computer Vision, In Proceedings, CVPR 2000, IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Vol. 2(2000), p.18 – 25.

DOI: 10.1109/cvpr.2000.854727

[2] A. Choukroun and V. Charvillat, Bucketing Techniques in Robust Regression for Computer Vision, Lecture Notes in Computer Science, 13th Scandinavian Conference, SCIA 2003 Halmstad, Sweden, June, 2003, Proceedings 2003, Vol2749(2003), p.737–748.

DOI: 10.1007/3-540-45103-x_81

[3] M.L. Brown, Robust line estimation with errors in both variables, Journal of the American Statistical Association. Vol. 77(1982), pp.71-79.

DOI: 10.1080/01621459.1982.10477768

[4] R.H. Zamar, Robust estimation in the errors-in-variables model, Biometrika. Vol. 76(1989), p.149–160.

DOI: 10.1093/biomet/76.1.149

[5] R.H. Zamar, Bias robust estimation in the orthogonal regression, The annals of statistics. Vol. 20(1992), p.1875–1888.

DOI: 10.1214/aos/1176348893

[6] M. Fekri and A. Ruiz-Gazen, Robust weighted orthogonal regression in the errors-in-variables model, Journal of Multivariate Analysis. Vol. 88(2004), pp.89-108.

DOI: 10.1016/s0047-259x(03)00057-5

[7] Croux , M. Fekri and A. Ruiz-Gazen, Fast and robust estimation of the multivariate errors in variables model, TEST . Vol. 19(2009), pp.286-303.

DOI: 10.1007/s11749-009-0155-9

[8] T. Hu and H.J. Cui, t-type estimators for a class of linear errors-in-variables models, Statistica Sinica . Vol. 19(2009), pp.1013-1036.

[9] C. Croux and G. Haesbroeck. Principal component analysis based on robust estimators of the covariance or correlation matrix: Influence functions and efficiencies, Biometrika. Vol. 87(2000), pp.603-618.

DOI: 10.1093/biomet/87.3.603

[10] Y. Dodge. Statistical data analysis based on the L1-norm and related methods, Boston, Basel, Berlin: Birkhäuser, 2002, pp.109-123.

[11] I. Wegener, in: Complexity Theory, Springer, Berlin Heidelberg, (2005).

[12] J. van der Geer, J.A.J. Hanraads, R.A. Lupton, The art of writing a scientific article, J. Sci. Commun. 163 (2000) 51-59.

[13] S. Chatterjeea, M. Laudatoa and L. A. Lynchb, Genetic algorithms and their statistical applications: an introduction, Computational Statistics & Data Analysis, Vol. 22(1996), pp.633-651.

[14] P.J. Rousseeuw and A.M. Leroy, Robust Regression and Outliers Detection, John Wiley and Son(1987).