International Journal of Intelligent Systems and Applications (IJISA)
IJISA Vol. 9, No. 10, 8 Oct. 2017
Cover page and Table of Contents: PDF (size: 479KB)
Determination of Structural Parameters of Multilayer Perceptron Designed to Estimate Parameters of Technical Systems
Full Text (PDF, 479KB), PP.57-62
Views: 0 Downloads: 0
Author(s)
Zhengbing Hu
1,*
Igor A. Tereykovskiy
2
Lyudmila O. Tereykovska
3
Volodymyr V. Pogorelov
2
Index Terms
Neuro-network model generalization, Structure of multilayer perceptron, Hidden neuron layer, Hidden neuron, Structure adaptation
Abstract
The paper is dedicated to the problem of efficiency increasing in case of applying multilayer perceptron in context of parameters estimation for technical systems. It is shown that the increase of efficiency is possible by adaptation of structure of the multilayer perceptron to the problem specification set. It is revealed that the structure adaptation lies in the determination the following parameters:
1. The number of hidden neuron layers;
2. The number of neurons within each layer.
In terms of the paper, we introduce mathematical apparatus that allows conducting the structure adaptation for minimization of the relative error of the neuro-network model generalization. A numerical experiment to demonstrate efficiency of the mathematical apparatus was developed and described in terms of the article. Further research in this sphere lies in the development of a method for calculation of optimum relationship between the number of the hidden neuron layers and the number of hidden neurons within each layer.
Cite This Paper
Zhengbing Hu, Igor A. Tereykovskiy, Lyudmila O. Tereykovska, Volodymyr V. Pogorelov, "Determination of Structural Parameters of Multilayer Perceptron Designed to Estimate Parameters of Technical Systems", International Journal of Intelligent Systems and Applications(IJISA), Vol.9, No.10, pp.57-62, 2017. DOI:10.5815/ijisa.2017.10.07
Reference
[1]Ezhov A. A. Neyrokompyuting i ego primeneniya v ekonomike i biznese / A. A. Ezhov, S. A. Shumskiy. – M.: MIFI, 1998. – 224 s.
[2]Korchenko A. Neyrosetevyie modeli, metodyi i sredstva otsenki parametrov bezopasnosti Internet-orientirovannyih informatsionnyih sistem: monografIya / A. Korchenko, I. Tereykovskiy, N. Karpinskiy, S. Tyinyimbaev. – K. : TOV «Nash Format». – 2016. – 275 s.
[3]Tarasenko V. P. Metod zastosuvannia produktsiinykh pravyl dlia podannia ekspertnykh znan v neiromerezhevykh zasobakh rozpiznavannia merezhevykh atak na kompiuterni systemy / V. P. Tarasenko, O. H. Korchenko, I. A. Tereikovskyi // Bezpeka informatsii. – 2013. – T. 19, № 3. – S. 168-174.
[4]Rudenko O.H. Shtuchni neironni merezhi. Navch. posib. / O.H. Rudenko, Ye.V. Bodianskyi. – Kharkiv: TOV "Kompaniia SMIT", 2006. – 404 s.
[5]Tereykovskaya L. Prospects of neural networks in business models [Text] / L. Tereykovskaya, O. Petrov, M. Aleksander // TransComp 2015. 30 November – 3 December, 2015, Zakopanem, Poland. – P. 1539–1545.
[6]Tereikovskyi I. Neironni merezhi v zasobakh zakhystu kompiuternoi informatsii / I. Tereikovskyi. – K. : PolihrafKonsaltynh. – 2007. – 209 s.
[7]Tereikovskyi I. A. Optymizatsiia struktury dvokhsharovoho perseptronu, pryznachenoho dlia rozpiznavannia anomalnykh velychyn ekspluatatsiinykh parametriv kompiuternoi merezhi / I. A. Tereikovskyi // Naukovo-tekhnichnyi zbirnyk «Upravlinnia rozvytkom skladnykh system» Kyiv. nats. un-tu budivnytstva i arkhitektury. – 2011. – Vyp. 5. – S. 128–131.
[8]Zhengbing H. The Analysis and Investigation of Multiplicative Inverse Searching Methods in the Ring of Integers Modulo M / H. Zhengbing, I. A. Dychka, M. Onai, A. Bartkoviak // Intelligent Systems and Applications, 2016, 11, P. 9-18.