Control Systems and Computers

https://doi.org/10.15407/csc.2021.05-06.045

Control Systems and Computers, 2021, Issue 5-6 (295-296), pp. 45-54.

UDC 6:004.8

O.H. Moroz, senior research scientist, Department for Technologies of Inductive Modelling, International Research and Training Center for Information Technologies and Systems of the NAS and MES of Ukraine, Glushkov Ave., 40, Kyiv, 03187, Ukraine, olhahryhmoroz@gmail.com

The problem of constructing the GMDH neural networks with active neurons

Characteristics of the existing neural networks of GMDH with active neurons are given and their main advantages and disadvantages are analyzed. An approach to increasing the efficiency of inductive construction of complex system models from statistical data based on the creation of a new class of GMDH neural networks with active neurons using methods of computational intelligence is proposed.

Download full text! (In English)

Keywords: GMDH neural network, computational intelligence, genetic algorithms, active neurons, inductive modeling.

1. Stepashko V.S., Bulgakova O.S., Zosimov V.V., 2018. Iterative algorithms for inductive modeling. Kyiv: Naukova dumka, 190 p. (In Ukrainian).
2. Stepashko V.S., Bulgakova O.S., 2013. “Generalized iterative algorithm of the Group Method of Data Handling”. Upravlyayushchie Sistemy i Mashiny, pp. 5-17 (In Russian).
3. Stepashko V., Bulgakova O., “Generalized Iterative Algorithm GIA GMDH,” Proceedings of the 4th International Conference on Inductive Modelling ICIM-2013, Kyiv, IRTC ITS NASU, pp. 119-123.
4. Stepashko V.S., 2017. “Developments and prospects of GMDH-based inductive modeling”. Conference on Computer Science and Information Technologies, pp. 474-491.
   https://doi.org/10.1007/978-3-319-70581-1_34
5. Moroz O.H., Stepashko V.S., 2021. Comparative features of MIA GMDH and deep feed-forward neural networks. Cybernetics and computer engineering, 4 (206), pp. 5-20.
   https://doi.org/10.15407/kvt206.04.005
6. Moroz O.H., Stepashko V.S., 2021. “ The sorting algorithms of inductive modeling with genetic operators”. Kyiv, Osvita Ukrayiny, 216 p. (In Ukrainian).
7. Kondo T, Ueno J., 2007. “Feedback GMDH-Type Neural Network Self-Selecting Optimum Neural Network Architecture and its Application to 3-Dimensional Medical Image Recognition of the Lungs”. Proc. of the II Int. Workshop on Inductive Modelling IWIM-2007, 19-23 Sept. 2007, Prague: Czech Technical University, pp. 63-70.
8. Ivakhnenko A.G., Ivakhnenko G.A., Mueller J.A., 1995. “Self-organization of neuronets with Active Neurons”. Pattern Recognition and Image Analysis, 4 (4), pp. 177-188.
9. Ivakhnenko A.G., Mueller J.-A., 1995. “Self-organization of Nets of Active Neurons”. System Analysis Modeling Simulation, 20, pp. 93-106.
10. Ivakhnenko G.A., 2003. “Algorithm for complexing analogs for self-organization of double multi-row neural networks”, Upravlyayushchie Sistemy i Mashiny, 2, pp. 100 -106 (In Russian).
11. Kordik P., 2006. Fully automated knowledge extraction using group of adaptive model evolution: PhD thesis / Electrical Engineering and Information Technology. Prague: CTU, 150 p.
12. Kovarik O, Kordik P., 2008. ”Optimizing Models Using Continuous Ant Algorithms”. Proc. of the 2nd Int. Conf. on Inductive Modelling ICIM-2008. K.: IRTC ITS NANU, pp. 124-128.
13. Lemke F., 2008. “Parallel Self-Organizing Modeling”. Proc. of the 2nd Int. Conf. on Inductive Modelling ICIM-2008. K.: IRTC ITS NANU, pp. 176-184.
14. Bodyanskiy Ye.V., Zaychenko Yu.P, Pavlikovskaya Ye., 2009. “The Neo-Fuzzy Neural Network Structure Optimization Using the GMDH for the Solving Forecasting and Classification Problems”. Proc. of the 3rd Int. Workshop on Inductive Modelling IWIM-2009, 14-19 Sept. 2009, Krynica, Poland. Prague: Czech Technical University, pp. 100-107.
15. Stepashko V.S., Bulgakova O.S., Zosimov V.V., 2010. “ Hybrid algorithms for self-organization of models for predicting complex processes”. Inductive modeling of complex systems. Collected research papers, Issue 2, Kyiv: IRTC ITS NASU, pp. 236-246 (In Ukrainian).
16. Ivakhnenko A.G., Wunsh D., Ivakhnenko G.A., 1999. “Inductive sorting-out GMDH algorithms with polynomial complexity for active neurons of neural networks”. Proceedings of the International Joint Conference on Neural Networks, IEEE, Piscataway, New Jersey, pp. 1169-1173.
17. Müller J.-A., Lemke F., 1999. Self-organizing Data Mining. 220 p.
18. Ivakhnenko G.A. Model-Free Analogues as Active Neurons for Neural Network Self-organization. [online] Available at: <http://www.gmdh.net/articles/algor/analogue.pdf> (Accessed09.2021).
19. Stepashko V.S., Bulgakova O.S., Zosimov V.V., 2018. “Construction and research of the generalized iterative GMDH algorithm with active neurons,” Advances in Intelligent Systems and Computing, Vol. 689, pp. 492-510.
    https://doi.org/10.1007/978-3-319-70581-1_35
20. Ivakhnenko A.G., Kovalishyn V.V., Tetko I.V., Luik A.I., Ivakhnenko G.A., Ivakhnenko N.A., 1999. “Application of Self-Organizing Neural Networks with Active Neurons for Prediction of Bioactivity of Chemical Compounds by the Analogues Search Algorithm”. Journal of Automation and Information Sciences, 31 (7-9), pp. 51-58. 
    https://doi.org/10.1615/JAutomatInfScien.v31.i7-9.90
21. Ivakhnenko G.A., 1995. “Self-organization of Neuronet with Active Neurons for Effects of Nuclear Tests Explosions Forecasting”. System Analysis Modeling Simulation SAMS, 20, pp.107-116.
22. Kovalishyn V.V., Tetko I. V., Luik A.I., Ivakhnenko A.G., 2000. “Application of Self-Organizing Neural Networks with Active Neurons for QSAR Studies”. Molecular Modeling and Prediction of Bioactivity, pp. 444-445.
    https://doi.org/10.1007/978-1-4615-4141-7_112
23. Lukosch H.K., 2017. “Simulation gaming. Applications for sustainable cities and smart infrastructures”. Proc. of 48th international simulation and gaming association conference, pp. 10-14.
    https://doi.org/10.1007/978-3-319-91902-7
24. Marchev A., Motzev M. and Müller, J-A., 1985. “Applications of Self-Organization Procedures for Business System Models Building”, Automatics, Vol. 1, pp. 37-44.

Received 28.11.2021