Model and Principles for the Implementation of Neural-Like Structures Based on Geometric Data Transformations

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


In this paper, the concept of information modeling based on a new model of geometric transformations is considered. This concept ensures the solutions of the following tasks like pattern recognition, predicting, classification, the principal independent components selection, optimization, recovering of lost data or their consolidation and implementing the information protection and privacy methods. Neural-like structures based on the Geometric Transformations Model as universal approximator implement principles of training and self-training and base on an algorithmic or hardware performing variants using the space and time parallelization principles. Geometric Transformations Model uses a single methodological framework for various tasks and fast non-iterative study with pre-defined number of computation steps, provides repeatability of the training outcomes and the possibility to obtain satisfactory solutions for large and small training samples.


Geometric Transformations Model Neural-like network Training and self-training algorithms Basic properties of the geometric transformations model 


  1. 1.
    Hu, Z., Bodyanskiy, Y.V., Tyshchenko, O.K., Boiko, O.O.: An ensemble of adaptive neuro-fuzzy Kohonen networks for online data stream fuzzy clustering. Int. J. Mod. Educ. Comput. Sci. (IJMECS) 8(5), 12–18 (2016). Scholar
  2. 2.
    Hu, Z., Bodyanskiy, Y.V., Tyshchenko, O.K., Boiko, O.O.: An evolving cascade system based on a set of neo-fuzzy nodes. Int. J. Intell. Syst. Appl. (IJISA) 8(9), 1–7 (2016). Scholar
  3. 3.
    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
  4. 4.
    Bodyanskiy, Y., Vynokurova, O., Savvo, V., Tverdokhlib, T., Mulesa, P.: Hybrid clustering-classification neural network in the medical diagnostics of the reactive arthritis. Int. J. Intell. Syst. Appl. (IJISA) 8(8), 1–9 (2016). Scholar
  5. 5.
    Muller, B.: Neural Networks: An Introduction. Springer, Berlin (1991)Google Scholar
  6. 6.
    Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1999)zbMATHGoogle Scholar
  7. 7.
    Verbenko, I., Tkachenko, R.: Gantry and bridge cranes neuro-fuzzy control by using neural-like structures of geometric transformations. Tech. Trans. Autom. Control Issue 3-AC (11) (2013).
  8. 8.
    Tkachenko, R., Tkachenko, P., Izonin, I., Tsymbal, Y.: Learning-based image scaling using neural-like structure of geometric transformation paradigm. In: Hassanien, A., Oliva, D. (eds.) Advances in Soft Computing and Machine Learning in Image Processing. Studies in Computational Intelligence, vol. 730, no. 1, pp. 537–567. Springer, Cham (2018). Scholar
  9. 9.
    Zajíc, Z., Machlica, L., Müller, L.: Bottleneck ANN: dealing with small amount of data in shift-MLLR adaptation. In: 2012 IEEE 11th International Conference on Signal Processing, Beijing, pp. 507–510 (2012).
  10. 10.
    Tsymbal, Y., Tkachenko, R.: A digital watermarking scheme based on autoassociative neural networks of the geometric transformations model. In: 2016 IEEE First International Conference on Data Stream Mining & Processing (DSMP), Lviv, pp. 231–234 (2016).
  11. 11.
    Ku, W., Storer, R.H., Georgakis, C.: Disturbance detection and isolation by dynamic principal component analysis. Chemometr. Intell. Lab. Syst. 30(1), 179–196 (1995). Scholar
  12. 12.
    Sharma, A., Paliwal, K.K.: Fast principal component analysis using fixed-point algorithm. Pattern Recogn. Lett. 28(10), 1151–1155 (2007). Scholar
  13. 13.
    Xu, H.: An SVD-like matrix decomposition and its applications. Linear Algebra Appl. 368, 1–24 (2003). Scholar
  14. 14.
    Dronyuk, I., Fedevych, O.: Traffic flows Ateb-prediction method with fluctuation modeling using Dirac functions. In: Gaj, P., Kwiecień, A., Sawicki, M. (eds.) Computer Networks, CN 2017, Communications in Computer and Information Science, vol. 718. Springer, Cham (2017)CrossRefGoogle Scholar
  15. 15.
    Picus, L.O., Adamson, F., Montague, W., Owens, M.A.: New Conceptual Framework for Analyzing the Costs of Performance Assessment. Stanford University, Stanford Center for Opportunity Policy in Education, Stanford (2010)Google Scholar
  16. 16.
    Pawson, H., Milligan, V., Phibbs, P., Rowley, S.: Assessing management costs and tenant outcomes in social housing: developing a framework. AHURI Positioning Paper No.160. Australian Housing and Urban, Melbourne (2014)Google Scholar
  17. 17.
    Ivanov, Y., et al.: Adaptive moving object segmentation algorithms in cluttered environments. In: The Experience of Designing and Application of CAD Systems in Microelectronics, Lviv, pp. 97–99 (2015).
  18. 18.
    Kazarian, A., Teslyuk, V., Tsmots, I., Mashevska, M.: Units and structure of automated “smart” house control system using machine learning algorithms. In: 2017 14th International Conference the Experience of Designing and Application of CAD Systems in Microelectronics (CADSM), Lviv, pp. 364–366 (2017).

Copyright information

© Springer International Publishing AG, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Lviv Polytechnic National UniversityLvivUkraine

Personalised recommendations