Investigation of a Neural Network Decomposition by Proteus Design Suite

Authors

DOI:

https://doi.org/10.17072/1993-0550-2022-2-73-80

Keywords:

Circuit Simulation, Microcontroller, Neural Network, Proteus

Abstract

The division of a monolithic neural network into blocks with their implementation on programmable logic within the framework of the Fog computing concept is considered. It is assumed that considering possible reconfiguration the implementation of blocks is performed on programmable logic: field-programmable gate array, FPGA (complex programmable logic device, CPLD), System-on-a-Chip, SoC or System-in-Package, SiP. The article explores such an implementation in the Proteus Design Suite based on ATMega32 microcontrollers. Modeling confirms the efficiency of the developed decomposition method. The research was carried out under the RFBR grant 20-37-90036 (Method of synthesizing neural network recognition devices for implementing the Fog computing mode).

Author Biography

Sergey F. Tyurin , Perm National Research Polytechnic University; Russia Perm State University

Sergey F. Tyurin (Perm, Russian Federation) is an Honored Inventor of the Russian Federation, Doctor of Technical Sciences, Professor, Professor at the Department of Automation and Telemechanics Perm National Research Polytechnic University (614990, Perm, 29, Komsomolsky pr., e-mail: tyurinsergfeo@yandex.ru), Professor at the Department of Software Computing Systems Perm State University (614990, Perm, 15, Bukireva str.).

References

Кузнецов О.П. Дискретная математика для инженера. Сер. Учебники для вузов. Специальная литература (3-е изд., перераб. и доп.). СПб. [и др.], 2009.

Руднев В.А. Применение микроконтроллеров для реализации нейронных сетей // Вестник Южно-Уральского государственного университета. Серия: компьютерные технологии, управление, радиоэлектроника, 2012. № 23. С. 181–183.

Novac P.E. et al. Quantization and deploy ment of deep neural networks on microcon trollers. Sensors, 2021. Т. 21, № 9. С. 2984. DOI: 10.3390/s21092984.

Cotton N.J., Wilamowski B.M., Dundar G. A neural network implementation on an inex pensive eight-bit microcontroller. 2008 Inter national Conference on Intelligent Engineer ing Systems, 2008. С. 109–114. DOI: 10.1109/INES.2008.4481278.

Tu Y. et al. A power efficient neural network implementation on heterogeneous FPGA and GPU devices. 2019 IEEE 20th International Conference on Information Reuse and Inte gration for Data Science (IRI), 2019. С. 193–199. DOI: 10.1109/IRI.2019.00040.

Goudarzi M. et al. An application placement technique for concurrent IoT applications in edge and fog computing environments. IEEE Transactions on Mobile Computing, 2020. Т. 20, № 4. С. 1298–1311, DOI: 10.1109/TMC.2020.2967041.

Угрюмов Е.П. Цифровая схемотехника: учеб. пособие для вузов. Санкт-Петербург: БХВ-Петербург, 2010. 797 с.

Proteus Downloads. URL: https://www.labcenter.com/downloads/ (дата обращения: 23.03.2022).

Тюрин C.Ф., Ковыляев Д.А., Данилова Е.Ю., Городилов А.Ю. Программирование микроконтроллеров с использованием IDE: учеб. пособие / под ред. С.Ф. Тюрина. Пермь: Изд-во Перм. нац. исслед. политех. ун-та, 2021. 100 с.

Тюрин С.Ф. Вычислительная техника и информационные технологии / Рук-во к лаборат. работам в системе Proteus 7.2. Пермь: Из-во Перм. гос. техн. ун-та, 2010. 135 с.

Тюрин С.Ф., Ковыляев Д.А., Данилова Е.Ю., Городилов А.Ю. Изучение программирования микроконтроллеров в САПР PROTEUS // Вестник Пермского университета. Математика. Механика. Информатика. 2021. Вып. 2(53). С. 69–74.

Published

2022-07-05

How to Cite

Bahtin В. В., Podlesnykh И. А. ., & Tyurin С. Ф. . (2022). Investigation of a Neural Network Decomposition by Proteus Design Suite. BULLETIN OF PERM UNIVERSITY. MATHEMATICS. MECHANICS. COMPUTER SCIENCE, (2 (57), 73–80. https://doi.org/10.17072/1993-0550-2022-2-73-80