Presentation of Data on the State of the Population and Training of an Artificial Neural Network in the Problem of Controlling the Operation of a Genetic Algorithm

Authors

  • David A. Petrosov Financial University under the Government of the Russian Federation
  • Nikita A. Andriyanov Financial University under the Government of the Russian Federation
  • Alexander N. Alyunov Financial University under the Government of the Russian Federation
  • Evgeniy V. Nezhdanov Financial University under the Government of the Russian Federation

DOI:

https://doi.org/10.52575/2712-746X-2023-50-4-924-935

Keywords:

simulation modeling, recurrent class of networks, evolutionary procedures, structural-parametric synthesis, modeling, deep learning, business processes

Abstract

The article discusses the possibility of using a recurrent artificial neural network to solve the problem of controlling a genetic algorithm in the structural-parametric synthesis of simulation models of business processes. As inputs for the selected class of networks, the value of the fitness function of individuals in the population grouped by the number of identical values is considered. This kind of approach allows us to standardize the dimension of neural network inputs for populations of different dimensions. The paper presents examples of data obtained during the work of structural-parametric synthesis of simulation models of business processes of a genetic algorithm, adapted to the solution of the problem, and their visualization, which were used to train an artificial neural network. Based on the data from the computational experiment, several types of artificial neural networks were trained in order to determine a class of networks capable of determining the state of the population of a genetic algorithm in the process of searching for solutions. The paper presents the results of training various artificial neural networks using modern deep learning methods.

 

Acknowledgements
The work was carried out with the financial support of the Russian Science Foundation (project No. 23-31-00127)

Downloads

Download data is not yet available.

Author Biographies

David A. Petrosov, Financial University under the Government of the Russian Federation

Candidate of Technical Sciences, Associate Professor, Associate Professor of the Department of Data Analysis and Machine Learning, Financial University under the Government of the Russian Federation,
Moscow, Russia

Nikita A. Andriyanov, Financial University under the Government of the Russian Federation

Candidate of Technical Sciences, Associate Professor of the Department of Data Analysis and Machine Learning, Financial University under the Government of the Russian Federation,
Moscow, Russia

Alexander N. Alyunov, Financial University under the Government of the Russian Federation

Candidate of Technical Sciences, Associate Professor, Associate Professor of the Department of Data Analysis and Machine Learning, Financial University under the Government of the Russian Federation,
Moscow, Russia

Evgeniy V. Nezhdanov, Financial University under the Government of the Russian Federation

Deputy Director of the Digital Economy Competence Center, Financial University under the Government of the Russian Federation,
Moscow, Russia

References

Андриянов Н.А. 2014. Дискретные дважды стохастические авторегрессионные модели случайных полей. Современные проблемы проектирования, производства и эксплуатации радиотехнических систем,1(9): 69-71.

Васильев К.К. 2014. Авторегрессии с кратными корнями характеристических уравнений. Радиотехника, 11: 74–78.

Голышин А.Е. 2018. Настройка параметров нечеткого контроллера с помощью генетического алгоритма при управлении динамическим объектом. Актуальные проблемы авиации и космонавтики, 4(14): 21-23.

Давронов, Ш. Р. 2023. Обзор современных генетических алгоритмов и их применение на практике. Молодой ученый, 36 (483):15-18.

Денисов М.А., Сопов Е.А. 2021. Генетический алгоритм условной оптимизации для проектирования информативных признаков в задачах классификации. Сибирский аэрокосмический журнал, 1: 18-31.

Дрозин А.Ю. 2023. Генетический алгоритм построения маршрутов выполнения этапов работ в конвейерной системе. Системный администратор,5 (246): 94-95

Петросов Д.А., Зеленина А.Н. 2020. Модель искусственной нейронной сети для решения задачи управления генетическим алгоритмом с применением математического аппарата теории сетей Петри. Моделирование, оптимизация и информационные технологии, 4(31).

Сапрыкина А.О. 2022а. Настройка параметров эволюционных операторов генетического алгоритма для повышения эффективности поиска решения задачи. Современные научные исследования и инновации, 12 (141): 12-19.

Сапрыкина А.О. 2022б. Эволюционные операторы и принцип работы генетического алгоритма. Современные научные исследования и инновации, 11 (139):34-41.

Софронова Е.А. 2023. Вариационный генетический алгоритм и его применение к управлению транспортными потоками в городской среде. International Journal of Open Information Technologies, 4:3-13.

Чеканин В.А., Куликова М.Ю. 2017. Адаптивная настройка параметров генетического алгоритма. Вестник МГТУ «Станкин», 3(42): 85-89.

Шегай М.В., Попова Н.Н. 2023. Генетический алгоритм оптимизации путеводных деревьев. Вестник Московского университета. Серия 15: Вычислительная математика и кибернетика,1:54-61.

Шишкова Н.А. 2017. Генетический алгоритм как метод оптимизации. Проблемы науки, 5(18): 28-30.

Andriyanov N.A., Sluzhivyi M.N. 2019. Solution for the problem of the parameters identification for autoregressions with multiple roots of characteristic equations. CEUR Workshop Proceedings, 2391:1-7.

Hahn Y., Langer T., Meyes R., Meisen T. 2023. Time Series Dataset Survey for Forecasting with Deep Learning. Forecasting, 5: 315-335. https://doi.org/10.3390/forecast5010017

Kalayc T.A., Asan U. 2022. Improving Classification Performance of Fully Connected Layers by Fuzzy Clustering in Transformed Feature Space. Symmetry, 14: 658. https://doi.org/10.3390/sym14040658

Petrosov D.A., Lomazov V.A., Petrosova N.V. 2021.Model of an Artificial Neural Network for Solving the Problem of Controlling a Genetic Algorithm Using the Mathematical Apparatus of the Theory of Petri Nets. Applied Sciences, 11: 3899.

Valerian G., Sutrisno T., Herwindiati D.E. 2020. Image clustering using genetic algorithm with tournament selection and uniform crossover. IOP Conf. Series: Materials Science and Engineering. doi:10.1088/1757–899X/852/1/012043.

Zhang J., Zhu F., Chen H. 2023. Two-Threshold-Variable Integer-Valued Autoregressive Model. Mathematics, 11: 3586. https://doi.org/10.3390/math11163586

Zhang X., Zhong Z., Jianjun Z., Ting W., Wing W.Y. 2023. Robust recurrent neural networks for time series forecasting. Neurocomputing, 526: 143-157.


Abstract views: 58

Share

Published

2023-12-29

How to Cite

Petrosov, D. A., Andriyanov, N. A., Alyunov, A. N., & Nezhdanov, E. V. (2023). Presentation of Data on the State of the Population and Training of an Artificial Neural Network in the Problem of Controlling the Operation of a Genetic Algorithm. Economics. Information Technologies, 50(4), 924-935. https://doi.org/10.52575/2712-746X-2023-50-4-924-935

Issue

Section

SYSTEM ANALYSIS AND PROCESSING OF KNOWLEDGE