Features of the application of artificial intelligence in Internet of Things systems
DOI:
https://doi.org/10.34121/1028-9763-2026-2-3-13Keywords:
Internet of Things, big data, artificial intelligence, machine learning, TinyMAbstract
The article analyzes the features of the application of artificial intelligence (AI) for Big Data (BD) processing in IoT (Internet of Things) systems (BD-IoT). The construction of modern multi-tier IoT systems has been studied, and a comparison of BD processing in traditional cloud services and at the IoT edge has been carried out. The possibilities of using the latest cellular network standards for building IoT systems are shown. Modern network intrusion detection methods (NIDS) are studied, enabling optimization of traffic analysis and increasing the level of security in IoT systems based on BD network processing. The TinyML approach for distributing system processing between devices has also been considered to evaluate its applicability in BD-IoT systems. The analysis has shown that the transition from traditional cloud architecture to distributed ones using AI increases the horizontal scalability of the BD-IoT network and minimizes the load on the cloud in conditions of limited computing and network resources. It is substantiated that the use of 5G and 6G standards is a necessary requirement for scaling a BD-IoT system with a large number of sensors and ensuring stable operation in conditions of geographical expansion based on increasing network bandwidth using AI. The feasibility of distributing NIDS functions between higher levels of BD-IoT systems is determined, in accordance with the volume of data and the required speed of response when using AI. The use of feature selection at the edge computing levels provides high speed processing of critical data and interpretation results, while feature extraction in cloud environments allows the identification of complex concealed attacks on large data sets. It is shown that the use of TinyML approaches is a promising direction for distributing computational load in BD-IoT systems. The implementation of machine learning models at the end-device level significantly reduces the amount of data transmitted to the cloud infrastructure, increases the energy efficiency of the system, and enables making critical decisions in real time. Таbl.: 2. Figs.: 2. Refs.: 19 titles.
References
1. Hassebo A., Tealab M. Global Models of Smart Cities and Potential IoT Applications: A Review. IoT. 2023. Vol. 4, N 3. P. 366–411. DOI: https://doi.org/10.3390/iot4030017.
2. Коваленко О.Є. Ситуаційні моделі обробки інформації в системах інтернету речей. Математичні машини і системи. 2025. № 2. С. 15–23. DOI: https://doi.org/10.34121/1028-9763-2025-2-15-23.
3. ITU-T Rec. Y.2060 (06/2012). Overview of the Internet of things. DOI: https://www.itu.int/rec/T-REC Y.2060-201206-I.
4. Lee K. The Internet of Things (IoT): Applications, investments, and challenges for enterprises. Business Horizons. 2015. Vol. 58, Issue 4. P. 431–440. DOI: https://doi.org/ 10.1016/j.bushor.2015.03.008.
5. ITU-R M.[IMT-2020.TECH PERF REQ] — Minimum Requirements Related to Technical Performance for IMT–2020 Radio Interface(s), document ITU-R M.2410-0. International Telecommunication Union — Recommendations. 2017. Nov. [Online]. URL: https://www.itu.int/pub/R-REP-M.2410-2017.
6. Ren R., Wang J., Yu J., Zhu X., Wan X., Lu H. Joint Resource Allocation for Multiplexing eMBB, URLLC and mMTC Traffics Based on DRL. IEEE 99th Vehicular Technology Conference (VTC2024-Spring). Singapore, Singapore, 2024. P. 1–5. DOI: https://doi.org/10.1109/VTC2024-Spring62846.2024.10683585.
7. Robin Ch., Nankya M., Akl R. 6G Networks and the AI Revolution — Exploring Technologies, Applications, and Emerging Challenges. Sensors. 2024. N 6. P. 1888. DOI: https://doi.org/ 10.3390/s24061888.
8. ITU-R. Requirements related to technical performance for IMT-Advanced radio interface(s). Report ITU-R M.2134. 2008. URL: https://www.itu.int/pub/R-REP-M.2134-2008.
9. ITU-R. IMT Vision — Framework and overall objectives of the future development of IMT for 2020 and beyond. Recommendation ITU-R M.2083-0. 2015. URL: https://www.itu.int/rec/R-REC-M.2083/en.
10. 3GPP. Service requirements for the 5G system. 3rd Generation Partnership Project (3GPP), TS 22.261 V15.0.0. 2018. URL: https://portal.3gpp.org/desktopmodules/Specifications/SpecificationDetails.aspx?specificationId=2933.
11. El Morr C., Ali-Hassan H. Descriptive, Predictive, and Prescriptive Analytics. Analytics in Healthcare. SpringerBriefs in Health Care Management and Economics. Springer, Cham. 2019. https://doi.org/10.1007/978-3-030-04506-7_3.
12. Коваленко О.Є. Інтелектуалізація граничних обчислень інтернету речей. Математичні машини і системи. 2024. № 3–4. С. 50–68. DOI: https://doi.org/10.34121/1028-9763-2024-3-4-50-68.
13. Ficili I., Giacobbe M., Tricomi G., Puliafito A. From Sensors to Data Intelligence: Leveraging IoT, Cloud, and Edge Computing with AI. Sensors. 2025. Vol. 25 (6). P. 1763. https://doi.org/10.3390/s25061763.
14. Marjani M., Nasaruddin F., Gani A. et al. Big IoT Data Analytics: Architecture, Opportunities, and Open Research Challenges. IEEE Access. 2017. Vol. 5. P. 5247–5261. DOI: https://doi.org/10.1109/ACCESS.2017.2689040.
15. Nguyen D.C., Ding M., Pathirana P.N. et al. 6G Internet of Things: A Comprehensive Survey. IEEE Internet of Things Journal. 2022. Vol. 9, N 1. P. 359–383. DOI: https://doi.org/10.1109/JIOT.2021.3103320.
16. Yahyati C., Lamaakal I., Maleh Y. et al. A Systematic Review of State-of-the-Art TinyML Applications in Healthcare, Education, and Transportation. IEEE Access. 2025. Vol. 13. P. 204513204562. DOI: https://doi.org/10.1109/ACCESS.2025.3633575.
17. DFRobot. Top 8 TinyML Frameworks and Compatible Hardware Platforms. 2024. Jul 12. URL: https://www.dfrobot.com/blog-13921.html.
18. Li, J., Othman M.S., Chen H. et al. Optimizing IoT intrusion detection system: feature selection versus feature extraction in machine learning. Journal of Big Data. 2024. Vol. 11. P. 36. DOI: https://doi.org/10.1186/s40537-024-00892-y.
19. Mishra P., Varadharajan V., Tupakula U., Pilli E. A detailed investigation and analysis of using machine learning techniques for intrusion detection. IEEE Communications Surveys & Tutorials. 2019. Vol. 21, N 1. P. 686–728. DOI: https://doi.org/10.1109/COMST.2018.2847722.
147
70
