Keywords
intelligent video analytics
IoT
econometric modelling
smart-home security
Information-Quanta architecture
How to Cite
Abstract
Modern surveillance is being transformed by the combination of artificial intelligence and the Internet of Things, especially with intelligent video analytics and pose recognition technologies. This paper will discuss how AI-powered pose recognition in the context of smart-home security systems can work by means of an econometric analysis of the data on how the Guard-N 4.0 platform operates. The study deals with one of the most critical problems that is the accomplishment of a balance between detection accuracy, latency, energy consumption, and bandwidth consumption in privacy-preserving settings. The aim is to measure the effect that the enablement of pose recognition and the quality of pose has on detection performance and system latency. The analytical methodology is a mix of a secondary data. analysis and econometric modelling, which is the Negative Binomial Fixed-Effects, Seemingly Unrelated Regressions, Difference-in-Differences, and Instrumental Variables. It was analyzed on a panel dataset of 18,450 device home day observations on the parameters: alert counts, latency and energy consumption.
References
AI City Challenge. AI City Dataset for Video Analytics; NVIDIA and University of Nebraska–Omaha: Omaha, NE, USA, 2025. Available online: https://www.aicitychallenge.org/ (accessed on 15 October 2025).
Alshamsi, O.; Shaalan, K.; Butt, U. Towards Securing Smart Homes: A Systematic Literature Review of Malware Detection Techniques and Recommended Prevention Approach. Information 2024, 15, 631. https://doi.org/10.3390/info15100631
Dardour, A.; El Haji, E.; Begdouri, M.A. Video Surveillance and Artificial Intelligence for Urban Security in Smart Cities: A Review of a Selection of Empirical Studies from 2018 to 2024. Comput. Sci. Math. Forum 2025, 10, 15. https://doi.org/10.3390/cmsf2025010015
ETSI. Internet of Things and Latency Measurement Framework; European Telecommunications Standards Institute: Sophia Antipolis, France, 2025. Available online: https://www.etsi.org/technologies/internet-of-things (accessed on 15 October 2025).
European Commission, Joint Research Centre (JRC). Smart Grids and IoT Monitoring Data; JRC: Brussels, Belgium, 2025. Available online: https://data.jrc.ec.europa.eu/ (accessed on 15 October 2025).
Ferone, A.; Maratea, A.; Camastra, F.; Ciaramella, A.; Staiano, A.; Lettiero, M.; Polizio, A.; Lombardi, F.; Spoleto, A.J. AiWatch: A Distributed Video Surveillance System Using Artificial Intelligence and Digital Twins Technologies. Technologies 2025, 13, 195. https://doi.org/10.3390/technologies13050195
Gazis, A.; Katsiri, E. Streamline Intelligent Crowd Monitoring with IoT Cloud Computing Middleware. Sensors 2024, 24, 3643. https://doi.org/10.3390/s24113643
Golda, T.; Guaia, D.; Wagner-Hartl, V. Perception of Risks and Usefulness of Smart Video Surveillance Systems. Appl. Sci. 2022, 12, 10435. https://doi.org/10.3390/app122010435
Honarparvar, S.; Saeedi, S.; Liang, S.; Squires, J. Design and Development of an Internet of Smart Cameras Solution for Complex Event Detection in COVID-19 Risk Behaviour Recognition. ISPRS Int. J. Geo-Inf. 2021, 10, 81. https://doi.org/10.3390/ijgi10020081
IEEE DataPort. Human Action Recognition and IoT Performance Datasets; IEEE: New York, NY, USA, 2025. Available online: https://ieee-dataport.org (accessed on 15 October 2025).
Intel Corporation. DevMesh IoT Edge Analytics Performance Logs; Intel Corporation: Santa Clara, CA, USA, 2025. Available online: https://devmesh.intel.com/ (accessed on 15 October 2025).
Kaggle. Human Activity Recognition and Pose Estimation Collections; Google LLC: Mountain View, CA, USA, 2025. Available online: https://www.kaggle.com (accessed on 15 October 2025).
Koldovskiy, A. A Transdisciplinary Approach to Improving the Quality of the Scientific and Educational Process in the Context of Digital Transformation. In Proceedings of the 6th International Scientific and Practical Web Forum: Building a Unified Open Information Space for Lifelong Education, Kyiv–Kharkiv, Ukraine, 2024a.
Koldovskiy, A. Strategic Infrastructure Transformation: Revolutionizing Financial Sector Management for Enhanced Success. Acta Academiae Beregsasiensis. Economics 2024b, 5, 323–332. https://doi.org/10.58423/2786-6742/2024-5-323-332.
Kulbacki, M.; Segen, J.; Chaczko, Z.; Rozenblit, J.W.; Kulbacki, M.; Klempous, R.; Wojciechowski, K. Intelligent Video Analytics for Human Action Recognition: The State of Knowledge. Sensors 2023, 23, 4258. https://doi.org/10.3390/s23094258
Lu, Y.; Zhou, L.; Zhang, A.; Zha, S.; Zhuo, X.; Ge, S. Application of Deep Learning and Intelligent Sensing Analysis in Smart Home. Sensors 2024, 24, 953. https://doi.org/10.3390/s24030953
NIST. Smart Home Testbed Dataset; National Institute of Standards and Technology: Gaithersburg, MD, USA, 2025. Available online: https://www.nist.gov/el/smart-home (accessed on 15 October 2025).
NREL. Residential Energy Consumption Data Center; National Renewable Energy Laboratory: Golden, CO, USA, 2025. Available online: https://data.nrel.gov/ (accessed on 15 October 2025).
OpenCV Foundation. OpenCV Zoo Benchmark and Calibration Data; OpenCV Foundation: Redwood City, CA, USA, 2025. Available online: https://opencv.org/opencv-zoo/ (accessed on 15 October 2025).
Prokopenko, O.; Chechel, A.; Koldovskiy, A.; Kldiashvili, M. Innovative Models of Green Entrepreneurship: Social Impact on Sustainable Development of Local Economies. Economics Ecology Socium 2024, 8, 89–111. https://doi.org/10.61954/2616-7107/2024.8.1-8.
Prokopenko, O.; Ivliіeva, O.; Korshevniuk, T.; Koldovskiy, A.; Shostak, I. The Role of Digital Technologies in Ensuring the Inclusivity of Distance Education. Rev. Conrado 2025, 20(103), e4431. https://lib.iitta.gov.ua/id/eprint/745198/1/%D0%A1%D1%82%D0%B0%D1%82%D1%82%D1%8F%20WoS.pdf
Rahim, A.; Zhong, Y.; Ahmad, T.; Ahmad, S.; Pławiak, P.; Hammad, M. Enhancing Smart Home Security: Anomaly Detection and Face Recognition in Smart Home IoT Devices Using Logit-Boosted CNN Models. Sensors 2023, 23, 6979. https://doi.org/10.3390/s23156979
Ravindran, A. A. Edge Computing Systems for Streaming Video Analytics : Trail Behind and the Paths Ahead. Preprints 2023, 2023080383. https://doi.org/10.20944/preprints202308.0383.v1
Sabit, H. Artifical Intelligence-Based Smart Security System Using Internet of Things for Smart Home Applications. Electronics 2025, 14, 608. https://doi.org/10.3390/electronics14030608
Shalan, M.; Hasan, M.R.; Bai, Y.; Li, J. Enhancing Smart Home Security: Blockchain-Enabled Federated Learning with Knowledge Distillation for Intrusion Detection. Smart Cities 2025, 8, 35. https://doi.org/10.3390/smartcities8010035
Torres-Hernandez, C.M.; Garduño-Aparicio, M.; Rodriguez-Resendiz, J. Smart Homes: A Meta-Study on Sense of Security and Home Automation. Technologies 2025, 13, 320. https://doi.org/10.3390/technologies13080320
Torres-Hernandez, C.M.; Garduño-Aparicio, M.; Rodriguez-Resendiz, J. Smart Homes: A Meta-Study on Sense of Security and Home Automation. Technologies 2025, 13, 320. https://doi.org/10.3390/technologies13080320
UCI Machine Learning Repository. Smart Home Dataset; University of California, Irvine: Irvine, CA, USA, 2025. Available online: https://archive.ics.uci.edu/ml/index.php (accessed on 15 October 2025).
Vardakis, G.; Hatzivasilis, G.; Koutsaki, E.; Papadakis, N. Review of Smart-Home Security Using the Internet of Things. Electronics 2024, 13, 3343. https://doi.org/10.3390/electronics13163343
Yin, H., Sinnott, R.O. & Jayaputera, G.T. A survey of video-based human action recognition in team sports. Artif Intell Rev 57, 293 2024. https://doi.org/10.1007/s10462-024-10934-9
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright (c) 2025 Yevhen Petrov