A kernel extension to handle missing data

  • Guillermo Nebot-Troyano
  • Lluís A. Belanche-Muñoz
Conference paper


An extension for univariate kernels that deals with missing values is proposed. These extended kernels are shown to be valid Mercer kernels and can adapt to many types of variables, such as categorical or continuous. The proposed kernels are tested against standard RBF kernels in a variety of benchmark problems showing different amounts of missing values and variable types. Our experimental results are very satisfactory, because they usually yield slight to much better improvements over those achieved with standard methods.


Waste Water Treatment Plant Normalize Root Mean Square Error Kernel Machine Univariate Kernel Kernel Extension 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    R Development Core Team: R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria. (2008)Google Scholar
  2. 2.
    Asuncion, A. and Newman, D.J. (2007). UCI Machine Learning Repository, Irvine, CA: University of California, School of Information and Computer Science.
  3. 3.
    Belanche, LL., Valdés, J.J., Comas, J., Roda, I. and Poch, M. (1999) Towards a Model of Input-Output Behavior of Wastewater Treatment Plants using Soft Computing Techniques. Environmental Modeling & Software, 14: 409-419. Elsevier, 1999.CrossRefGoogle Scholar
  4. 4.
    Berg, C., Christensen, J.P.R. and Ressel, P. Harmonic Analysis on Semigroups: Theory of Positive Definite and Related Functions. Springer-Verlag, 1984.Google Scholar
  5. 5.
    Burges, J.C. A Tutorial on Support Vector Machines for Pattern Recognition. Data Mining and Knowledge Discovery, 2 (1998).Google Scholar
  6. 6.
    Duda, R. and Hart, P. Pattern Classification and Scene Analysis. Wiley (1973).Google Scholar
  7. 7.
    Gower, J.C. A general coefficient of similarity and some of its properties. Biometrics, 22, pp. 882-907 (1971).Google Scholar
  8. 8.
    Horn, R. and Johnson, C.R. Matrix analysis. Cambridge University Press, 1991.Google Scholar
  9. 9.
    Little, R.J.A. and Rubin, D.B. Statistical analysis with missing data. John Wiley, 1987.Google Scholar
  10. 10.
    Mercer, J. (1909). Functions of positive and negative type and their connection with the theory of integral equations. Philos. Trans. Roy. Soc. London, A 209: 415-446.Google Scholar
  11. 11.
    Parzen, E. On estimation of a probability density function and mode. The Annals of Mathematical Statistics, 33(3), pp. 1065-1076 (1962).MATHCrossRefMathSciNetGoogle Scholar
  12. 12.
    Prechelt, L. PROBEN1: A Set of Benchmarks and Benchmarking Rules for Neural Network Training Algorithms. Report 21/94. Fakultät für Informatik, Univ. Karlsruhe, 1994.Google Scholar
  13. 13.
    Rosenblatt, M. Remarks on Some Nonparametric Estimates of a Density Function. The Annals of Mathematical Statistics, 27(3), pp. 832-837 (1956).MATHCrossRefMathSciNetGoogle Scholar
  14. 14.
    Schölkopf, B. Learning with kernels. John Wiley, 2001.Google Scholar
  15. 15.
    Sheather, S. J. and Jones,M.C. A reliable data-based bandwidth selection method for kernel density estimation. Journal of the Royal Statistical Society series B, 53, 683690, 1991.MathSciNetGoogle Scholar
  16. 16.
    Vapnik, V. The nature of Statical Learning Theory. Springer-Verlag, New York, 1995.Google Scholar
  17. 17.
    Vapnik, V. The support vector method of function estimation. Neural networks and machine learning. C. Bishop (Ed.), NATO ASI Series F. Springer, 1998.Google Scholar

Copyright information

© Springer-Verlag London 2010

Authors and Affiliations

  • Guillermo Nebot-Troyano
    • 1
  • Lluís A. Belanche-Muñoz
    • 1
  1. 1.Faculty of Computer Science, Polytechnical University of CataloniaBarcelonaSpain

Personalised recommendations