Advertisement

The Procedure for Defining the Best Recognition Module of the Algorithms for Calculating Estimates

  • Kamilov Mirzoyan
  • Hudayberdiev Mirzaakbar
  • Khamroev Alisher
Conference paper

Abstract

We have considered the problem of finding the optimal procedure for constructing improved results in some sense, the algorithms for calculating estimates. Such a procedure has been carried out by the selection of optimal values of the parameters of extreme algorithms. This serves to reduce the number of calculations in the algorithms for calculating estimates (ACE) and to increase the quality of the recognition process.

Keywords

Pattern recognition ACE Parameter Training set Simple set 

Notes

Acknowledgments

This work was supported partly by the Grant А-5-004 of the Committee of Sciences and Technologies of the Republic of Uzbekistan.

References

  1. 1.
    Zhuravlev YI (1998) Selected scientific works. Magistr, Moscow (in Russian)Google Scholar
  2. 2.
    Gurevich IB, Nefedov AV (2001) An efficient technique for calculating proximity functions in the 2D family of algorithms based on estimate calculations with rectangular support sets. Pattern Recognit Image Anal 11(1):175–178Google Scholar
  3. 3.
    Dukukin AA (2006) A method for constructing an optimal algorithm estimates calculations. J Comput Math Math Phys 46:755–762 (in Russian)Google Scholar
  4. 4.
    Vetrov DP (2003) On the stability of pattern recognition algorithms. Pattern Recognit Image Anal 13(3):470–475 (in Russian)Google Scholar
  5. 5.
    Deaprtment of Russian Academy of Sciences, Institute of Mathematics Named After S. L. Sobolev (2009) All-Russian conference with international participators. Knowl – Ontol – Theory-2009 1:35–41 (in Russian)Google Scholar
  6. 6.
    Zhuravlev YI, Ryazanov VV, Senko OV. Recognition mathematical methods. Software system. Practical applications. Publishing FAZIS, Moscow (in Russian)Google Scholar
  7. 7.
    Kamilov MM, Minglikulov ZB, Khamroev ASH (2014) Application of genetic algorithm for determining epsilon thresholds in the algorithms for calculating estimates. Eighth World Conference on Intelligent Systems for industrial automation (WCIS-2014), pp 27–30, TashkentGoogle Scholar
  8. 8.
    Alisher K (2017) An algorithm for constructing feature relations between the classes in the training set. Orig Res Article Procedia Comput Sci 103:244–247.  https://doi.org/10.1016/j.procs.2017.01.094CrossRefGoogle Scholar
  9. 9.
    Hudayberdiev MK, Akhatov AR, Hamroev AS (2011) On a model of forming the optimal parameters of the recognition algorithms. Int J KIMICS 9(5):607–609, KoreaGoogle Scholar
  10. 10.
    Kamilov MM, Khamroev ASH (2016) About methods for defining the threshold values of elements of quantitative features of objects in database DBTulipa. X International IEEE Scientific and Technical Conference “Dynamics of Systems, Mechanisms and Machines”. T.4. –pp 21–25, Omsk, RussiaGoogle Scholar
  11. 11.
    Kamilov MM, Hudayberdiev MK (2018) Formation of a qualitative description of the training set in solving the recognition problem. ISJ: Theor Appl Sci 01(57):33–37.  https://doi.org/10.15863/TAS.2018.01.57.6CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Kamilov Mirzoyan
    • 1
  • Hudayberdiev Mirzaakbar
    • 1
  • Khamroev Alisher
    • 1
  1. 1.Scientific and Innovation Center of Information and Communication TechnologiesTashkentUzbekistan

Personalised recommendations