Russian Federation
Russian Federation
This paper addresses the pressing problem of enhancing the autonomy of security systems based on acoustic-vibration pattern recognition. Primary attention is given to the transition from cloud computing to the tiny machine learning (TinyML) paradigm, which enables the transfer of data processing directly to edge devices. The authors analyze methods for reducing the computational load on the microcontroller's central processor through the use of specialized hardware modules for preliminary signal preparation. The article demonstrates the effectiveness of co-design of hardware and software components of the system for minimizing energy consumption while maintaining high accuracy of event classification.
tiny machine learning (TinyML), energy efficiency, acoustic-vibration signals, hardware preprocessing, neural network quantization, microcontrollers, feature extraction, register-transfer level (RTL)
1. Issledovanie sposobov zaschity informacii ot utechki po akusticheskomu i vibroakusticheskomu kanalam / V. K. Zol'nikov, S. A. Sazonova, A. I. Zarevich, S. S. Bashun // Modelirovanie sistem i processov. – 2025. – T. 18, № 2. – S. 27-40. – DOIhttps://doi.org/10.12737/2219-0767-2025-18-2-27-40. – EDN GBWORY.
2. Tehnologiya razrabotki RTL modeli opisaniya izdeliya pri razrabotke programmno-analiticheskogo kompleksa SAPR / D. V. Shehovcov, A. M. Plotnikov, K. V. Zol'nikov, A. I. Zarevich // Modelirovanie sistem i processov. – 2023. – T. 16, № 3. – S. 79-86. – DOIhttps://doi.org/10.12737/2219-0767-2023-16-3-79-86. – EDN MGXEWN.
3. Sazonova, S. A. Issledovanie i razrabotka modeley proektirovaniya mikroshem cifrovoy obrabotki informacii / S. A. Sazonova, K. V. Zol'nikov, V. F. Asminin // Modelirovanie sistem i processov. – 2025. – T. 18, № 3. – S. 89-99. – DOIhttps://doi.org/10.12737/2219-0767-2025-18-3-89-99. – EDN LGIGCI.
4. Ray, P. P. A review on TinyML: State-of-the-art and prospects / P. P. Ray // Journal of King Saud University. Computer and Information Sciences. – 2022. – Vol. 34, No. 4. – P. 1595-1623. – DOIhttps://doi.org/10.1016/j.jksuci.2021.11.019. – EDN ISZGCE.
5. Kwon, J. Hardware/Software Co-Design for TinyML Voice-Recognition Application on Resource Frugal Edge Devices / J. Kwon, D. Park // Applied Sciences (Switzerland). – 2021. – Vol. 11, No. 22. – P. 11073. – DOIhttps://doi.org/10.3390/app112211073. – EDN JZRQXN.
