Integration of Federated Learning and Edge Computing for Privacy-Preserving Predictive Analytics in Smart City Surveillance Networks
Keywords:
Smart cities, federated learning, edge computing, surveillance networks, privacy-preserving analytics, decentralized AI, urban securityAbstract
Smart cities increasingly rely on surveillance networks for real-time data analytics and security operations. However, the integration of such systems raises significant privacy and latency concerns due to the transmission of sensitive visual and sensor data to centralized servers. This paper explores a novel integration of Federated Learning (FL) and Edge Computing (EC) to support decentralized, privacy-preserving predictive analytics within smart surveillance infrastructures. By leveraging edge nodes for local computation and FL for collaborative model training, the framework minimizes privacy risks while ensuring scalable, low-latency analytics. We review literature, propose a hybrid architecture, and provide simulated performance comparisons using bean plots and tables. Our findings highlight the effectiveness of this integration for privacy-conscious, efficient surveillance systems in smart city applications.
References
Bonawitz, Keith, et al. "Towards Federated Learning at Scale: System Design." SysML Conference, 2019.
Brisimi, Theodora S., et al. "Federated Learning of Predictive Models from Federated Electronic Health Records." Scientific Reports, vol. 8, no. 1, 2018, pp. 1–8.
Hard, Andrew, et al. "Federated Learning for Mobile Keyboard Prediction." arXiv preprint arXiv:1811.03604, 2018.
Li, Tian, et al. "Federated Optimization in Heterogeneous Networks." Proceedings of Machine Learning and Systems, vol. 2, 2020, pp. 429–450.
Lim, Wei Yang Bryan, et al. "Federated Learning in Mobile Edge Networks: A Comprehensive Survey." IEEE Communications Surveys & Tutorials, vol. 22, no. 3, 2020, pp. 2031–2063.
McMahan, Brendan, et al. "Communication-Efficient Learning of Deep Networks from Decentralized Data." Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, vol. 54, 2017, pp. 1273–1282.
Nikouei, Saman, et al. "Smart Surveillance as an Edge Network Service: From Harr-Cascade, SVM to a Lightweight CNN." IEEE Access, vol. 7, 2019, pp. 152140–152154.
Shi, Weisong, et al. "Edge Computing: Vision and Challenges." IEEE Internet of Things Journal, vol. 3, no. 5, 2016, pp. 637–646.
Wang, Xiao, et al. "In-Edge AI: Intelligentizing Mobile Edge Computing, Caching and Communication by Federated Learning." IEEE Network, vol. 33, no. 5, 2019, pp. 156–165.
Yang, Qiang, et al. "Federated Machine Learning: Concept and Applications." ACM Transactions on Intelligent Systems and Technology, vol. 10, no. 2, 2019, pp. 1–19.
Zhang, Chaoyun, et al. "Deep Learning in Mobile and Wireless Networking: A Survey." IEEE Communications Surveys & Tutorials, vol. 21, no. 3, 2019, pp. 2224–2287.
Zhao, Yue, et al. "Federated Learning with Non-IID Data." arXiv preprint arXiv:1806.00582, 2018.
Zheng, Zhiyuan, et al. "Smart Surveillance System Based on Edge Computing." IEEE Access, vol. 6, 2018, pp. 25413–25426
Downloads
Published
Issue
Section
License
Copyright (c) 2021 Anita Yeboah (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
