Imbalance Data Classification via Neural-Like Structures of Geometric Transformations Model: Local and Global Approaches

  • Roman Tkachenko
  • Anastasiya Doroshenko
  • Ivan Izonin
  • Yurii Tsymbal
  • Bohdana Havrysh
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 754)


The classification task is one of the most widespread among the tasks of Data Mining - spam detection, medical diagnosis, ad targeting, risk assessment and image classification. However, all these tasks have a common feature - training dataset can be unbalanced, the number of instances of the target class can be less than one percent of all data. In this article, we compare the results of solving one of these problems using the most common classification methods (Random Forest Leaner, Logistic Regression, SVM). The article describes a new classification method based on neural-like structures of Geometric Transformations Model (local and global approaches) and compares their result with the obtained results.


Classification Imbalance data Neural-like structures  Data unevenness Geometric transformations model Machine learning 


  1. 1.
    Ting, K.M.: Encyclopedia of Machine Learning. Springer, Boston. ISBN 978-0-387-30164-8 (2011)Google Scholar
  2. 2.
    Bodyanskiy, Y.V., Vynokurova, O.A., Dolotov, A.I.: Self-learning cascade spiking neural network for fuzzy clustering based on group method of data handling. J. Autom. Inf. Sci. 45, 23–33 (2013)CrossRefGoogle Scholar
  3. 3.
    Pozzolo, A.D., Caelen, O., Johnson, R.A., Bontempi, G.: Calibrating probability with underdamping for unbalanced classification. In: Proceedings of the 2015 IEEE Symposium Series on Computational Intelligence, Cape Town, pp. 159–166 (2015)Google Scholar
  4. 4.
    Keilwagen, J., Grosse, I., Grau, J.: Area under precision–recall curves for weighted and unweighted data. PLoS ONE 9(3), 92209 (2014)CrossRefGoogle Scholar
  5. 5.
    Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer, New York (1995). Scholar
  6. 6.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)Google Scholar
  7. 7.
    Kutucu, H., Almryad, A.: Modeling of solar energy potential in Libya using an artificial neural network model. In: Proceedings of the 2016 IEEE First International Conference on Data Stream Mining & Processing (DSMP), Lviv, pp. 356–359 (2016)Google Scholar
  8. 8.
    Hu, Z., Bodyanskiy, Y.V., Tyshchenko, O.K., Samitova, V.O.: Possibilistic fuzzy clustering for categorical data arrays based on frequency prototypes and dissimilarity measures. Int. J. Intell. Syst. Appl. (IJISA) 9(5), 55–61 (2017). Scholar
  9. 9.
    Bodyanskiy, Y.V., Tyshchenko, A.K., Deineko, A.A.: An evolving radial basis neural network with adaptive learning of its parameters and architecture. Autom. Control Comput. Sci. 49(5), 255–260 (2015)CrossRefGoogle Scholar
  10. 10.
    Hu, Z., Bodyanskiy, Y.V., Tyshchenko, O.K., Boiko, O.O.: A neuro-fuzzy Kohonen network for data stream possibilistic clustering and its online self-learning procedure. Appl. Soft Comput. 14, 252–258 (2017)Google Scholar
  11. 11.
    Hu, Z., Bodyanskiy, Y.V., Tyshchenko, O.K., Tkachov, V.M.: Fuzzy clustering data arrays with omitted observations. Int. J. Intell. Syst. Appl. (IJISA) 9(6), 24–32 (2017). Scholar
  12. 12.
    Bodyanskiy, Y.V., Tyshchenko, O.K., Kopaliani, D.S.: An evolving connectionist system for data stream fuzzy clustering and its online learning. Neurocomputing 262, 41–56 (2017)CrossRefGoogle Scholar
  13. 13.
    Bodyanskiy, Y., Vynokurova, O., Setlak, G., Peleshko, D., Mulesa, P.: Adaptive multivariate hybrid neuro-fuzzy system and its on-board fast learning. Neurocomputing 230, 409–416 (2017)CrossRefGoogle Scholar
  14. 14.
    Fawcett, Tom: An introduction to ROC analysis. Pattern Recognit. Lett. 27(8), 861–874 (2006)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995)zbMATHGoogle Scholar
  16. 16.
    Tkachenko, R., Tkachenko, P., Izonin, I., Tsymbal, Y.: Learning-based image scaling using neural-like structure of geometric transformation paradigm. In: Studies in Computational Intelligence, vol. 730, pp. 537–565. Springer, Heidelberg (2018)Google Scholar
  17. 17.
    Polishchuk, U., Tkachenko, P., Tkachenko, R., Yurchak, I.: Features of the auto-associative neuro like structures of the geometrical transformation machine (GTM). In: Proceedings of the 2009 5th International Conference on Perspective Technologies and Methods in MEMS Design, Zakarpattya, pp. 66–67 (2009)Google Scholar
  18. 18.
    Medykovskyy, M., Tsmots, I., Tsymbal, Y., Doroshenko, A.: Development of a regional energy efficiency control system on the basis of intelligent components. In: Proceedings of the 2016 XIth International Scientific and Technical Conference Computer Sciences and Information Technologies (CSIT), Lviv, pp. 18–20 (2016)Google Scholar
  19. 19.
    Hu, Z., Bodyanskiy, Y.V., Tyshchenko, O.K., Samitova, V.O.: Fuzzy clustering data given on the ordinal scale based on membership and likelihood functions sharing. Int. J. Intell. Syst. Appl. (IJISA) 9(2), 1–9 (2017). Scholar
  20. 20.
    Hu, Z., Bodyanskiy, Y.V., Tyshchenko, O.K., Samitova, V.O.: Fuzzy clustering data given in the ordinal scale. Int. J. Intell. Syst. Appl. (IJISA) 9(1), 67–74 (2017). Scholar
  21. 21.
    Hu, Z., Ye, V., Bodyanskiy, O.K., Tyshchenko, A.: Deep cascade neuro-fuzzy system for high-dimensional online fuzzy clustering. In: Proceedings of the 2016 IEEE First International Conference on Data Stream Mining and Processing (DSMP 2016), Lviv, Ukraine, pp. 318–322, 23–27 August 2017Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2019

Authors and Affiliations

  • Roman Tkachenko
    • 1
  • Anastasiya Doroshenko
    • 1
  • Ivan Izonin
    • 1
  • Yurii Tsymbal
    • 1
  • Bohdana Havrysh
    • 2
  1. 1.Lviv Polytechnic National UniversityLvivUkraine
  2. 2.Ukrainian Graphic Arts AcademyLvivUkraine

Personalised recommendations