Dimensionality Reduction Using External Context in Pattern Recognition Problems with Ordered Labels

  • Ewa Skubalska-Rafajłowicz
  • Adam Krzyżak
  • Ewaryst Rafajłowicz
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7267)

Abstract

Our aim is to propose a new look at the dimensionality reduction in pattern recognition problems by extracting part of variables that are further called external context variables. We show how to incorporate them into the Bayes classification scheme with loss functions that depend on class labels that are ordered. Then, the general form of the optimal context sensitive classifier is derived and the learning method that is based on kernel approximation is proposed.

Keywords

Dimensionality Reduction Class Label Context Variable Learning Sequence Random Projection 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ciskowski, P., Rafajłowicz, E.: Context-Dependent Neural Nets–Structures and Learning. IEEE Trans. Neural Networks 15, 1367–1377 (2004)CrossRefGoogle Scholar
  2. 2.
    Davies, E.R.: Machine Vision. Morgan Kaufmann, San Francisco (2005)Google Scholar
  3. 3.
    Devroye, L., Györfi, L., Lugosi, G.: Probabilistic Theory of Pattern Recognition. Springer, New York (1996)MATHGoogle Scholar
  4. 4.
    Eden, M.: Handwriting and Pattern Recognition. IRE Transactions on Information Theory, 100–166 (February 1962)Google Scholar
  5. 5.
    Elman, J.L.: Finding structure in time. Cognitive Sci. 15(2), 179–211 (1990)MathSciNetGoogle Scholar
  6. 6.
    Greblicki, W.: Asymptotically Optimal Pattern Recognition Procedures with Density Estimates. IEEE Trans. Information Theory IT 24, 250–251 (1978)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Gyorfi, L., Kohler, M., Krzyżak, A., Walk, H.: A Distribution-Free Theory of Nonparametric Regression. Springer, New York (2002)CrossRefGoogle Scholar
  8. 8.
    Krzyżak, A., Rafajłowicz, E.: Pattern Recognition with Linearly Structured Labels Using Recursive Kernel Estimator. In: Rutkowski, L., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2010. LNCS (LNAI), vol. 6113, pp. 422–429. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  9. 9.
    Kurzyński, M.: On the identity of optimal strategies for multistage classifiers. Pattern Recognition Letters 10, 39–46 (1989)MATHCrossRefGoogle Scholar
  10. 10.
    Lee, K.T.: Context-dependent phonetic hidden Markov models for speaker-independent continuous speech recognition. IEEE Transactions on Acoustics, Speech and Signal Processing 38(4), 599–609 (1990)CrossRefGoogle Scholar
  11. 11.
    Rafajłowicz, E.: Classifiers sensitive to external context – theory and applications to video sequences. Expert Systems (2011), doi:10.1111/j.1468-0394.2010.00564Google Scholar
  12. 12.
    Rafajłowicz, E.: Context-dependent neural nets – Problem statement and examples. In: Proceedings 3rd Conference on Neural Networks Applications, Zakopane, Poland, pp. 557–562 (May 1999)Google Scholar
  13. 13.
    Rafajłowicz, E.: Learning context dependent neural nets. In: Proceedings 3rd Conference on Neural Networks Applications, Zakopane, Poland, pp. 551–556 (May 1999)Google Scholar
  14. 14.
    Rafajłowicz, E., Skubalska-Rafajłowicz, E.: MAD Loss in Pattern Recognition and RBF Learning. In: Rutkowski, L., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2008. LNCS (LNAI), vol. 5097, pp. 671–680. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  15. 15.
    Raviv, J.: Decision Making in Markov Chains Applied to the Problem of Pattern Recognition. IEEE Transactions on Information Theory IT-3(4), 536–551 (1967)CrossRefGoogle Scholar
  16. 16.
    Skubalska-Rafajłowicz, E.: Clustering of Data and Nearest Neighbors Search for Pattern Recognition with Dimensionality Reduction Using Random Projections. In: Rutkowski, L., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2010. LNCS (LNAI), vol. 6113, pp. 462–470. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  17. 17.
    Skubalska-Rafajłowicz, E.: Neural networks with sigmoidal activation functions-dimension reduction using normal random projection. Nonlinear Analysis, Theory, Methods & Applications. Series A, Theory and Methods 71(12), 1255–1263 (2009)CrossRefGoogle Scholar
  18. 18.
    Skubalska-Rafajłowicz, E.: Pattern recognition algorithms based on space-filling curves and orthogonal expansions. IEEE Transactions on Information Theory 47(5), 1915–1927 (2001)MATHCrossRefGoogle Scholar
  19. 19.
    Turney, P.: The identification of context-sensitive features: A formal definition of context for concept learning. In: Proceedings 13th Int. Conf. Machine Learning (ICML 1996), Bari, Italy, pp. 53–59 (1996)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Ewa Skubalska-Rafajłowicz
    • 1
  • Adam Krzyżak
    • 2
  • Ewaryst Rafajłowicz
    • 1
  1. 1.Institute of Computer Engineering, Control & RoboticsWrocław University of TechnologyWrocławPoland
  2. 2.Department of Computer Science and Software EngineeringConcordia UniversityMontrealCanada

Personalised recommendations