EXPERIMENTAL INVESTIGATION OF METHOD FOR THE SYNTHESIS OF NEURO-FUZZY MODELS IN A PARALLEL COMPUTER SYSTEM

Authors

  • S. Yu. Skrupsky Zaporizhzhia National Technical University, Zaporizhzhia, Ukraine, Ukraine

DOI:

https://doi.org/10.15588/1607-3274-2016-2-7

Keywords:

synthesis of model, parallel system, resource planning, neural network, mean-squared error.

Abstract

The article deals with the problem of the development of the non-linear model describing dependences between the characteristics of a
system, in which synthesis of neuro-fuzzy networks is realized, the parameters of the investigated method and the time spent on execution of
the models synthesis. The object of research is a synthesis of neuro-fuzzy models for individual prediction of the hypertensive patient state.
The subject of research is a parallel computer system that performs the method of neuro-fuzzy networks synthesis. The purpose of the work
is to improve the efficiency of parallel computer systems solving the problems of medical direction. A non-linear model to predict the time
used by a parallel system to perform the method of neuro-fuzzy network synthesis and thus to execute a rational choice of the computer system
resources has been proposed. The software that implements the proposed model has been developed. Experiments confirming the adequacy of the proposed model have been executed. The experimental results allow us to recommend the application of the developed model in practice.

References

Лашкул З. В. Особливості епідеміології артеріальної гіпертензії та її ускладнень на регіональному рівні з 1999 по 2013 роки / З. В. Лашкул // Сучаснi медичнi технології. – 2014, № 2. – С. 134–141. 2. Sergey Subbotin Individual prediction of the hypertensive patient condition based on computational intelligence / Sergey Subbotin, Andrii Oliinyk, Stepan Skrupsky – Information and Digital Technologies 2015 ISBN 978-1-4673-7185-8, 7–9 july 2015, Zilina, Slovakia. – P. 336–344 3. Oliinyk A. O. Experimental Investigation with Analyzing the Training Method Complexity of Neuro-Fuzzy Networks Based on Parallel Random Search / Andrii Oliinyk, Stepan Skrupsky, Sergey Subbotin // Automatic Control and Computer Sciences ISSN 0146-4116. – 2015. Vol. 49, No. 1. – P. 11–20. DOI: 10.3103/S0146411615010071 4. Субботін С. О. Подання й обробка знань у системах штучного інтелекту та підтримки прийняття рішень : навч. посібник / С. О. Субботін. – Запоріжжя : ЗНТУ, 2008. – 341 с. 5. Oliinyk A. O. Using Parallel Random Search to Train Fuzzy Neural Networks / A. O. Oliinyk, S. Yu. Skrupsky, S. A. Subbotin // Automatic Control and Computer Sciences. – 2014. – Vol. 48, Issue 6. – P. 313–323. DOI: 10.3103/S0146411614060078 6. Характеристики ГРІД-вузла НАНУ. – Режим доступа: URL: http://www.ipme.kiev.ua/ukr/grid_vuzol/charakter-g.html. – Загл. з екрану. 7. Introduction to GPUs. – Режим доступа: URL: https://www.cs.u texa s.edu /~pinga l i /CS37 8 /20 1 5 sp/ lect u res/IntroGPUs.pdf. – Загл. з екрану. 8. Sulistio A. Simulation of Parallel and Distributed Systems:A Taxonomy - and Survey of Tools / A. Sulistio, C. S. Yeo, R. Buyya // International Journal of Software Practice and Experience. Wiley Press. – 2002. – P. 1–19. 9. Методы и модели планирования ресурсов в GRID-системах : монография / [В. С. Пономаренко, С. В. Листровой, С. В. Минухин, С. В. Знахур]. – X. : ИД ИНЖЭК», 2008. – 408 с. 10. Петренко А. І. Комп’ютерне моделювання ГРІД-систем / А. I. Петренко // Электроника и связь 5' Тематический выпуск «Электроника и нанотехнологии». – 2010. – С. 40–48.

Downloads

How to Cite

Skrupsky, S. Y. (2016). EXPERIMENTAL INVESTIGATION OF METHOD FOR THE SYNTHESIS OF NEURO-FUZZY MODELS IN A PARALLEL COMPUTER SYSTEM. Radio Electronics, Computer Science, Control, (2). https://doi.org/10.15588/1607-3274-2016-2-7

Issue

No. 2 (2016): Radio Electronics, Computer Science, Control

Section

Neuroinformatics and intelligent systems

License

Copyright (c) 2016 S. Yu. Skrupsky

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Creative Commons Licensing Notifications in the Copyright Notices

The journal allows the authors to hold the copyright without restrictions and to retain publishing rights without restrictions.

The journal allows readers to read, download, copy, distribute, print, search, or link to the full texts of its articles.

The journal allows to reuse and remixing of its content, in accordance with a Creative Commons license СС BY -SA.

Authors who publish with this journal agree to the following terms:

  • Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License CC BY-SA that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.

  • Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.

  • Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.