Some Imputation Algorithms for Restoration of Missing Data

  • Vladimir Ryazanov
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7042)

Abstract

The problem of reconstructing the feature values in samples of objects given in terms of numerical features is considered. The three approaches, not involving the use of probability models and a priori information, are considered. The first approach is based on the organization of the iterative procedure for successive elaboration of missing values of attributes. In this case, the analysis of local information for each object with missing data is fulfilled. The second approach is based on solving an optimization problem. We calculate such previously unknown feature values for which there is maximum correspondence of metric relations between objects in subspaces of known partial values and found full descriptions. The third approach is based on solving a series of recognition tasks for each missing value. Comparisons of these approaches on simulated and real problems are presented.

Keywords

missing data imputation feature pattern recognition feature values restoration 

References

  1. 1.
    Little, R.J.A., Rubin, D.B.: Statistical Analysis with Missing Data. Wiley, New York (1987)MATHGoogle Scholar
  2. 2.
    Zloba, E.: Statistical methods of reproducing of missing data. J. Computer Modelling & New Technologies 6(1), 51–61 (2002)Google Scholar
  3. 3.
    Morin, R.L., Raeside, D.E.: A reappraisal of distance-weighted k-nearest neighbor classification for pattern recognition with missing data. IEEE Transactions on Systems, Man and Cybernetics, 241–243 (1981)Google Scholar
  4. 4.
    Zhang, S.: Parimputation: From imputation and null-imputation to partially imputation. IEEE Intelligent Informatics Bulletin 9(1), 32–38 (2008)Google Scholar
  5. 5.
    Delavallade, T., Dang, T.H.: Using Entropy to Impute Missing Data in a Classification Task. In: IEEE International Conference on Fuzzy Systems, London, pp. 1–6 (2007)Google Scholar
  6. 6.
    Honghai, F., Guoshun, C., Cheng, Y., Bingru, Y., Yumei, C.: A SVM Regression Based Approach to Filling in Missing Values. In: Khosla, R., Howlett, R.J., Jain, L.C. (eds.) KES 2005. LNCS (LNAI), vol. 3683, pp. 581–587. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  7. 7.
    Zhuravlev, Y.I., Nikiforov, V.V.: Recognition Algorithms based on Estimate Evaluation. J. Kibernetika 3, 1–11 (1971) (in Russian)Google Scholar
  8. 8.
    Zhuravlev, Y.I., Ryazanov, V.V., Senko, O.V.: Recognition. Mathematical methods. Programm. System. Applications, Fazis, Moscow (2006) (in Russian)Google Scholar
  9. 9.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn. Wiley interscience (2001)Google Scholar
  10. 10.
    Ryazanov, V.V.: Logical Regularities in Pattern Recognition (Parametric Approach). Computational Mathematics and Mathematical Physics 47(10), 1720–1735 (2007); ©Pleiades Publishing, Ltd., Original Russian Text ©V.V. Ryazanov, published in Zhurnal Vychislitel’noi Matematiki i Matematicheskoi Fiziki 47(10), 1793–1808 (2007)Google Scholar
  11. 11.
    Fausett, L.: Fundamentals of Neural Networks. Prentice-Hall (1994)Google Scholar
  12. 12.
    Vapnik, V.: The Nature of Statistical Learning Theory. Springer, Heidelberg (1995)CrossRefMATHGoogle Scholar
  13. 13.
    Ishodzhanov, T.R., Ryazanov, V.V.: A gradient search for logical regularities of classes with a linear dependence. In: 14th All-Russian Conference on Mathematical Methods for Pattern Recognition: 14 All-Russian Conference, pp. 123–124. MAKS Press, Vladimir region (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Vladimir Ryazanov
    • 1
  1. 1.Dorodnicyn Computing Centre of RASInstitution of Russian Academy of SciencesMoscowRussia

Personalised recommendations