Preditas — Software package for solving pattern recognition and diagnostic problems

  • P. Pudil
  • S. Bláha
  • J. Novoičová
Statistical Pattern Recognition
Part of the Lecture Notes in Computer Science book series (LNCS, volume 301)


A general purpose software package "PREDITAS" is presented, aimed at solving a wide range of pattern recognition and diagnostic problems with respect to constraints and requirements imposed by practice. The theoretical background of the feature selection technique and stepwise decision rule employed in the PREDITAS system is outlined, together with the reasons for the necessity to combine theoretically based procedures with heuristic ones at some stages of the global solution.


Feature Selection Decision Rule Feature Subset Diagnostic Problem Feature Selection Technique 
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).
    Anderson T., Bahadur R.: Classification into two multivariate normal distributions with different covariance matrices. The Annals of Math. Statistics, Vol.33, 420–431, 1962.Google Scholar
  2. (2).
    Bláha S., Pudil P.: The PREDITAS system and its use for computer-aided medical decision making. In: Medical Decision Making: Diagnostic Strategies and Expert Systems, edited by J.H. Van Bemmel, F. Grémy, J. Zvárová. North-Holland, Amsterdam 1985 (Proceedings of the IFIP-IMIA International Conference).Google Scholar
  3. (3).
    Bláha S., Pudil P.: PREDITAS — User Manual (in Czech), Research Report No. 1331, Prague 1987.Google Scholar
  4. (4).
    Bláha S., Novoičová J., Pudil P.: PREDITAS — Theory and practice of diagnostic task solving (to appear)Google Scholar
  5. (5).
    Devijver P.A. and Kittler J.: Pattern Recognition — A Statistical Approach. Prentice-Hall, Englewood Cliffs, New Jersey 1982.Google Scholar
  6. (6).
    Foley D.: Considerations of sample and feature size. IEEE Trans. Inf. Theory, Vol. IT-18, 618–626, (1972).CrossRefGoogle Scholar
  7. (7).
    Kanal L., Chandrasekar B.: On dimensionality and sample size in statistical pattern classification. Pattern Recognition, Vol. 3, 225–234, 1971.CrossRefGoogle Scholar
  8. (8).
    Kanal L.: Patterns in pattern recognition 1968–1974. IEEE Trans. on Pat. Recog. IT-20, 697–722, 1974.Google Scholar
  9. (9).
    Pecinovský R., Pudil P., Bláha S.: The algorithms for sequential feature selection based on the measure of discriminative power. Proceedings of DIANA Symposium, Liblice 1982.Google Scholar
  10. (10).
    Pudil P., Bláha S.: Evaluation of effectiveness of features selected by discriminant analysis methods. Pattern Recognition, Vol. 14, Nos 1–6, 700–703, 1981. (Special Issue: Proceedings of 1980 Pattern Recognition Conference, Oxford).CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1988

Authors and Affiliations

  • P. Pudil
    • 1
  • S. Bláha
    • 1
  • J. Novoičová
    • 1
  1. 1.Institute of Information Theory and AutomationCzechoslovak Academy of SciencesPrague 8

Personalised recommendations