Automation and Remote Control

, Volume 79, Issue 10, pp 1854–1862 | Cite as

Recurrent Algorithms of Structural Classification Analysis for Complex Organized Information

  • A. A. Dorofeyuk
  • E. V. BaumanEmail author
  • Yu. A. Dorofeyuk
  • A. L. Chernyavskii
Problems of Optimization and Simulation at Control of Development of Large-Scale Systems


For the structural classification analysis of complex organized information, we propose to use recurrent algorithms of stochastic approximation type. We introduce classification quality functionals that depend on non-normalized and zero moments of probability distribution functions for the probability of sample objects appearing in the classes, as well as the type of optimal classification. We propose a new classification algorithm for this type of classification quality criteria and prove a theorem about its convergence that ensures the stationary value of the corresponding functional. We show that the proposed algorithm can be used to solve a wide class of problems in structural classification analysis.


structural classification analysis of information fuzzy classification recurrent algorithms stochastic approximation fuzziness types parameter structuring cluster analysis piecewise approximation of complex functions 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Dorofeyuk, A.A., Dorofeyuk, Yu.A., Pokrovskaya, I.V., and Chernyavskii, A.L., Recurrent Algorithms of Intelligent Information Analysis in Complex Measurement and Control Systems, Datch. Sist., 2016, no. 12, pp. 3–10.Google Scholar
  2. 2.
    Robbins, N. and Monro, S., A Stochastic Approximation Method, Ann. Math. Stat., 1951, vol. 22, no. 1, pp. 400–407.MathSciNetCrossRefzbMATHGoogle Scholar
  3. 3.
    Kiefer, J. and Wolfowitz, J., Stochastic Estimation of the Maximum of a Regression Function, Ann. Math. Statist., 1952, vol. 23, no. 3, pp. 462–466.MathSciNetCrossRefzbMATHGoogle Scholar
  4. 4.
    Nevel’son, M.B. and Khas’minskii, R.Z., Stokhasticheskaya approksimatsiya i rekurrentnoe otsenivanie (Stochastic Approximation and Recurrent Estimation), Moscow: Nauka, 1972.Google Scholar
  5. 5.
    Bharath, B. and Borkar, V.S., Stochastic Approximation Algorithms: Overview and Recent Trends, Sadhana, 1999, no. 24, pp. 425–452.MathSciNetCrossRefzbMATHGoogle Scholar
  6. 6.
    Kushner, H. and Yin, G., Stochastic Approximation and Recursive Algorithms and Applications, in Stochastic Modelling and Applied Probability, vol. 35, New York: Springer, 2003.Google Scholar
  7. 7.
    Tsypkin, Ya.Z. and Kel’mans, G.K., Recurrent Self-Learning Algorithms, Tekh. Kibern., 1967, no. 5, pp. 78–87.Google Scholar
  8. 8.
    Braverman, E.M. and Muchnik, I.B., Strukturnye metody obrabotki empiricheskikh dannykh (Structural Methods of Processing Empirical Data), Moscow: Nauka, 1983.Google Scholar
  9. 9.
    Braverman, E.M., Dorofeyuk, A.A., Lumel’skii, V.Ya., and Muchnik, I.B., Diagonalization of the Communication Matrix and Extraction of Latent Factors, in Problemy rasshireniya vozmozhnostei avtomatov (Problems of Expanding the Capabilities of Automata), Moscow: IAT, 1971, no.1.Google Scholar
  10. 10.
    Pokrovskaya, I.V., Goldovskaya, M.D., Dorofeyuk, Yu.A., and Kiseleva, N.E., Intellectual Methods of Processing Qualitative Data, Mash. Obuchen. Analiz Dannykh, 2014, vol. 1, no. 10, pp. 1396–1406.Google Scholar
  11. 11.
    Bauman, E.V., Dorofeyuk, A.A., Dorofeyuk, Yu.A., and Pokrovskaya, I.V., Structural Classification Methods for the Identification Problem for Complex Control Objects, in Proc. 5th Intl. Conf. “Management of Large-Scale Development” (MLSD’2011), Moscow: Inst. Probl. Upravlen., 2011, vol. II.Google Scholar
  12. 12.
    Bezdek, J.C., Pattern Recognition with Fuzzy Objective Function Algorithms, New York: Springer, 1981.CrossRefzbMATHGoogle Scholar
  13. 13.
    Kiseleva, N.E., Dorofeyuk, A.A., Dorofeyuk, Yu.A., and Pokrovskaya, I.V., Program and Algorithmic Complex of Intelligent Analysis for Weakly Formalized Data, Datch. Sist., 2014, no. 6, pp. 48–53.Google Scholar
  14. 14.
    Spiro, A.G., Dorofeyuk, A.A., Dorofeyuk, Yu.A., Alperovich, Eug., and Alperovich, M., Forecasting of the Range of Values for Stock Prices on a Stock Market, in Proc. 8th Intl. Conf. “Managing the Development for Large-Scale Systems” (MLSD’2015), Moscow: Inst. Probl. Upravlen., 2015, vol. 2, pp. 388–390.Google Scholar
  15. 15.
    Guchuk, V.V., Desova, A.A., Dorofeyuk, A.A., and Anokhin, A.M., An Objectivization Procedure for Expert Classification of the Characterics of Biological Signals for Medical and Diagnostic Complexes, Datch. Sist., 2014, no. 2, pp. 2–7.Google Scholar
  16. 16.
    Kuznetsov, E.N., Anashkina, A.A., Esipova, N.G., and Tumanyan, V.G., Cluster Analysis of Amino Acid Protein Residues Based on the Structure of their Spatial Contacts with DNA Nucleotides, in Proc. 8th Intl. Conf.“Management of Large-Scale Development” (MLSD’2015, Moscow). Moscow: Inst. Probl. Upravlen., 2015, vol. 2, pp. 382–385.Google Scholar
  17. 17.
    Dorofeyuk, Yu.A., Dorofeyuk, A.A., and Chernyavskii, A.L., A Method for Intelligent Analysis of Parameter Estimates for Monitoring of Large-Scale Socio-Economic Systems for Non-Representative Samples, in Proc. 8th Intl. Conf.“Management of Large-Scale Development” (MLSD’2015), Moscow: Inst. Probl. Upravlen., 2015, vol. 2, pp. 372–375.Google Scholar
  18. 18.
    Mandel, A., Bordukov, D., Dorofeyuk, A., Dorofeyuk, J., and Chernyavsky, A., A Structural Prediction Concept for Railway State Forecasting Problem, in 15 IFAC Sympos. Inform. Control Probl. Manufactur. (INCOM 2015), IFAC–PapersOnLine, vol. 48, no. 3, Canada: Ottawa Elsevier, 2015, pp. 1338–1342.Google Scholar

Copyright information

© Pleiades Publishing, Ltd. 2018

Authors and Affiliations

  • A. A. Dorofeyuk
    • 1
  • E. V. Bauman
    • 1
    Email author
  • Yu. A. Dorofeyuk
    • 2
  • A. L. Chernyavskii
    • 2
  1. 1.Markov Processes InternationalNew YorkUSA
  2. 2.Trapeznikov Institute of Control SciencesRussian Academy of SciencesMoscowRussia

Personalised recommendations