Journal Home
Login
Register
Open Access Journal
Submit a Paper
Propose a Special lssue
Open Access
ARTICLE
Federated Learning–Driven Intelligence for Autonomous and Medical Cyber-Physical Systems: Integrative Architectures, Privacy Preservation, and Deployment Challenges
Issue Vol. 2 No. 01 (2025): Volume 02 Issue 01 --- Section Articles
PDF
Abstract
The rapid proliferation of data-intensive cyber-physical systems has fundamentally altered how intelligence is designed, trained, and deployed across domains such as autonomous transportation, smart healthcare, and medical image analysis. Traditional centralized machine learning paradigms, while historically dominant, increasingly face structural limitations related to privacy leakage, regulatory compliance, communication overhead, and domain heterogeneity. Federated learning has emerged as a transformative alternative that distributes model training across decentralized data silos while preserving local data ownership. This research article presents a comprehensive and theoretically grounded investigation into federated learning as an enabling intelligence paradigm for autonomous driving systems and medical imaging applications, with a particular emphasis on self-driving vehicles and brain tumor classification. Drawing on foundational surveys of autonomous vehicle intelligence (Badue et al., 2021) and hybrid deep learning models for medical diagnosis (Biswas & Islam, 2021; Biswas & Islam, 2023), the study situates federated learning within the broader evolution of machine learning architectures.
The article advances an integrative analytical framework that unifies insights from vehicular intelligence, Internet of Things infrastructures, medical imaging pipelines, and privacy-preserving computation. Rather than presenting experimental benchmarks, the study adopts an interpretive methodology grounded in cross-domain synthesis of existing empirical findings. The analysis elucidates how federated learning architectures address non-independent and identically distributed data, system heterogeneity, and adversarial vulnerabilities in both autonomous mobility and healthcare settings. Particular attention is given to hierarchical aggregation strategies, blockchain-enabled coordination, homomorphic encryption, and explainable artificial intelligence as mechanisms that enhance trust and robustness.
The results reveal that federated learning is not merely a technical optimization but a socio-technical reconfiguration of intelligence production, redistributing power, responsibility, and risk across stakeholders. In autonomous driving, federated learning enables collaborative perception and decision-making across fleets without compromising proprietary or personal data, complementing the perception-planning-control pipeline outlined in self-driving system surveys (Badue et al., 2021). In medical imaging, federated architectures support scalable diagnostic intelligence across institutions while mitigating ethical and legal barriers associated with centralized patient data repositories (Biswas & Islam, 2023). The discussion critically examines unresolved challenges, including convergence instability, communication efficiency, fairness, and regulatory alignment, and articulates a forward-looking research agenda that bridges engineering rigor with societal accountability.
Keywords
References
1. Aledhari, M., Razzak, R., Parizi, R. M., & Saeed, F. (2020). Federated learning: a survey on enabling technologies, protocols, and applications. IEEE Access, 8, 140699–140725.
2. Biswas, A., & Islam, M. S. (2023). A hybrid deep CNN-SVM approach for brain tumor classification. Journal of Information Systems Engineering & Business Intelligence, 9(1).
3. Pandya, S., Srivastava, G., Jhaveri, R., et al. (2023). Federated learning for smart cities: A comprehensive survey. Sustainable Energy Technologies and Assessments, 55, 102987.
4. Badue, C., Guidolini, R., Carneiro, R. V., et al. (2021). Self-driving cars: A survey. Expert Systems with Applications, 165, 113816.
5. Rahman, A., Hossain, M. S., Muhammad, G., et al. (2023). Federated learning-based AI approaches in smart healthcare. Cluster Computing, 26, 2271–2311.
6. Biswas, A., & Islam, M. S. (2021). Brain tumor types classification using k-means clustering and ANN approach. In Proceedings of the 2nd International Conference on Robotics, Electrical and Signal Processing Techniques. IEEE.
7. Du, Z., Wu, C., Yoshinaga, T., et al. (2020). Federated learning for vehicular internet of things. IEEE Open Journal of the Computer Society, 1, 45–61.
8. Gecer, M., &Garbinato, B. (2024). Federated learning for mobility applications. ACM Computing Surveys, 56, 133.
9. Truong, N., Sun, K., Wang, S., et al. (2021). Privacy preservation in federated learning. Computers & Security, 110, 102402.
10. Fang, H., & Qian, Q. (2021). Privacy preserving machine learning with homomorphic encryption and federated learning. Future Internet, 13, 94.
11. Chehimi, M., & Saad, W. (2022). Quantum federated learning with quantum data. In ICASSP 2022 Proceedings. IEEE.
12. Briggs, C., Fan, Z., & Andras, P. (2020). Federated learning with hierarchical clustering of local updates. In International Joint Conference on Neural Networks. IEEE.
13. Jagarlamudi, G. K., Yazdinejad, A., Parizi, R. M., &Pouriyeh, S. (2023). Exploring privacy measurement in federated learning. Journal of Supercomputing, 80, 10511–10551.
14. Savazzi, S., Nicoli, M., Bennis, M., et al. (2021). Opportunities of federated learning in connected and automated industrial systems. IEEE Communications Magazine, 59(2), 16–21.
