Adaptive GMDH classifiers system

Authors

  • Нина Владимировна Кондрашова International Research and Training Center for Information Technologies and Systems of the National Academy of Sciences and Ministry of Education and Science of Ukraine Glushkov av. 40, Kiev, Ukraine, 03680, Ukraine
  • Павлов Александр Владимирович National Technical University of Ukraine "KPI" Pobeda ave., 37, Kyiv, Ukraine, 03056, Ukraine
  • Андрей Владимирович Павлов International Research and Training Center for Information Technologies and Systems of the National Academy of Sciences and Ministry of Education and Science of Ukraine Glushkov av. 40, Kiev, Ukraine, 03680, Ukraine
  • Владимир Анатольевич Павлов National Technical University of Ukraine "KPI" Pobeda ave., 37, Kyiv, Ukraine, 03056, Ukraine

DOI:

https://doi.org/10.15587/2313-8416.2014.27392

Keywords:

generalized relaxation iterative algorithm (GRIA), multilayer algorithm with combinatorial selection of variables (MACSoV)

Abstract

It is shown that the self-organization models, built by generalized relaxation iterative algorithm (GRIA), are the most accurate when examining the classifiers on new data. The maximum classification accuracy depends on the target sample, the type of model and external criterion of GMDH and classifiers system. Known multilayer algorithm with combinatorial selection of variables (MACSoV) has more flexible accuracy adjustment on different parts of sample compared with GRIA, but much lower speed operation in solving the classification problem.  

Author Biographies

Нина Владимировна Кондрашова, International Research and Training Center for Information Technologies and Systems of the National Academy of Sciences and Ministry of Education and Science of Ukraine Glushkov av. 40, Kiev, Ukraine, 03680

candidate of science, senior staff scientist

Department of information technology and inductive modeling

Павлов Александр Владимирович, National Technical University of Ukraine "KPI" Pobeda ave., 37, Kyiv, Ukraine, 03056

Ph.D., (assistant) lecturer

Department of Descriptive Geometry, Engineering and Computer Graphics

Андрей Владимирович Павлов, International Research and Training Center for Information Technologies and Systems of the National Academy of Sciences and Ministry of Education and Science of Ukraine Glushkov av. 40, Kiev, Ukraine, 03680

Ph.D., scientific associate

Department of information technology and inductive modeling

Владимир Анатольевич Павлов, National Technical University of Ukraine "KPI" Pobeda ave., 37, Kyiv, Ukraine, 03056

Candidate of science, Associate Professor

Department of Biomedical Cybernetics

References

1. Ivakhnenko, A. G., Stepashko, V. S. (1985). Pomehoustojchivost' modelirovanija [Simulation noise immunity]. Kyiv, USSR :Naukova dumka, 214.

2. Stevens, S. S. (1946). On the Theory of Scales of Measurement. Science, 2684 (103), 677–680.

3. Kondrashova, N. V., Pavlov, V. A., Pavlov, A. V. (2013). Reshenie zadachi medicinskoj diagnostiki linejnym diskriminantnym analizom i MGUA [Problem solution of medical diagnosis by linear discriminant analysis and GMDH]. USiM, 244 (2), 79–88.

4. Yenyukov, I. S. (Ed.) (1989). Faktornyj, diskriminantnyj i klasternyj analiz [Factorial, Discriminant and Cluster analyses]. Moscow, USSR : Finance and Statistics, 215.

5. Sarychev, A. P. (1991). Diskriminantnyj analiz s obuchajushhimi i proverochnymi podvyborkami nabljudenij [Discriminant analysis with training, and check the subsample of observations]. Avtomatika, 2, 55–59.

6. Sarychev, A. P. (2008). Reshenie zadachi diskriminantnogo analiza v uslovijah strukturnoj neopredelennosti na osnovanii MGUA [Problem solution of discriminant analysis in the conditions of structural uncertainty based on GMDH]. Problemy upravleniya i informatiki, 3, 100–112.

7. Sarychev, A. P., Sarycheva, L. V. (2010). GMDH-Based Criterion for Optimal Set Features Determination in Nonlinear Discriminant Analysis. Proc. of 3d International Conference on Inductive Modeling, ICIM’2010. Yevpatoria (Ukraine), 40–43.

8. Ivakhnenko, A. G. (1971). Sistemy jevristicheskoj samoorganizacii v tehnicheskoj kibernetike [Systems of heuristic self-organization in technical cybernetics]. Kyiv, USSR, Tehnika, 364.

9. Klecka, W. R. (1980). Discriminant analysis. Quantitative Applications in the Social Sciences Series, Thousand Oaks, CA: Sage Publications. http://dx.doi.org/10.4135/9781412983938

10. Sarychev, A. P. (1988). Iteracionnyj algoritm MGUA dlja sinteza razdeljajushhej funkcii v zadache diskriminantnogo analiza [Iterative GMDH algorithm for synthesis separating function in problem of discriminant analysis]. Avtomatika, 2, 20–24.

11. Pavlov, O. V. (2006). Algorytmy samoorganizacii' v zadachah pidvyshhennja informatyvnosti geometrychnyh modelej procesiv, zadanyh tochkovym karkasom [Algorithms for self-organization in problems of increasing informativity geometric models for the processes specified with help of points framework]. Kyiv, 197.

12. Pavlov, A. V. (2011). Obobshhjonnyj relaksacionnyj iteracionnyj algoritm MGUA [Generalized relaxation iterative algorithm of GMDH]. Inductive Modelling of complex Systems. Kyiv: IRTC IT&S, 2, 95–108.

13. Kondrashova, N. V., Pavlov, V. A., Pavlov, A. V. (2006). Mnogorjadnyj algoritm veernyh reshenij [Multilayered algorithm of fan solutions]. herald National Technical Univ. ’KPI’. Informatics, Management and Computer Science, 45, 218–227.

Published

2014-10-14

Issue

Section

Physics and mathematics