Resource-Aware Personalized Federated Learning for Wearable Health Monitoring: A Simulation Study
DOI:
https://doi.org/10.55003/ETH.430402Keywords:
Federated learning, personalized health monitoring, edge computing, privacy preservation, Internet of Things (IoT)Abstract
Continuous health monitoring using wearable sensors promises personalized and proactive healthcare, yet existing cloud-centric learning solutions suffer from critical limitations in privacy, adaptability, and personalization under non-IID user data. To address these challenges, this paper proposes an on-device personalized federated learning (FL) framework that explicitly models user heterogeneity while preserving data privacy and supporting deployment on resource-constrained wearable devices. The proposed framework integrates lightweight deep neural models with a heterogeneity-aware aggregation strategy to capture user-specific physiological variations without centralized data collection. Differentially private model updates protect sensitive information during training, while a dynamic utility-driven client selection mechanism reduces communication overhead and improves convergence efficiency. Personalized fine-tuning further adapts the shared model to individual users, enabling accurate and responsive health monitoring directly on consumer devices. Experimental evaluations on the WESAD and PAMAP2 datasets conducted in a simulated federated learning environment demonstrate that the proposed framework improves classification accuracy by approximately 7–8 percentage points over the FedAvg baseline while reducing communication cost by approximately 25–30%. These findings demonstrate the feasibility of the proposed personalized federated learning framework for future deployment on resource-constrained wearable devices while preserving user privacy through differential privacy mechanisms.
References
[1] M. Chen, Y. Ma, Y. Li, D. Wu, Y. Zhang, and C. -H Youn, “Wearable 2.0: Enabling Human-Cloud Integration in Next Generation Healthcare Systems,” IEEE Communications Magazine, vol. 55, no. 1, pp. 54–61, 2017, doi: 10.1109/MCOM.2017.1600410CM.
[2] Y. Yin, Y. Zeng, X. Chen, and Y. Fan, “The internet of things in healthcare: An overview,” Journal of Industrial Information Integration, vol. 1, pp. 3–13, 2016, doi: 10.1016/j.jii.2016.03.004.
[3] J. Li, Y. Meng, L. Ma, S. Du, H. Zhu, Q. Pei, and X. Shen, “A Federated Learning Based Privacy-Preserving Smart Healthcare System,” IEEE Transactions on Industrial Informatics, vol. 18, no. 3, pp. 2021–2031, 2021, doi: 10.1109/TII.2021.3098010.
[4] H. B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y Arcas, “Communication-efficient learning of deep networks from decentralized data,” in Proc. 20th Int. Conf. Artificial Intelligence and Statistics (AISTATS), Fort Lauderdale, FL, USA, Apr. 20–22, 2017, pp. 1273–1282.
[5] P. Voigt and A. von dem Bussche, “Special data processing activities,” in The EU General Data Protection Regulation (GDPR): A Practical Guide, 1st ed. Cham, Switzerland: Springer International Publishing, 2017, ch. 9, pp. 235–243, doi: 10.1007/978-3-319-57959-7_9.
[6] T. Li, A. K. Sahu, A. Talwalkar, and V. Smith, “Federated Learning: Challenges, Methods, and Future Directions,” IEEE Signal Processing Magazine, vol. 37, no. 3, pp. 50–60, 2020, doi: 10.1109/MSP.2020.2975749.
[7] Q. Wu, X. Chen, Z. Zhou, and J. Zhang, “FedHome: Cloud-Edge Based Personalized Federated Learning for In-Home Health Monitoring,” IEEE Transactions on Mobile Computing, vol. 21, no. 8, pp. 2818–2832, 2022, doi: 10.1109/tmc.2020.3045266.
[8] A. Z. Tan, H. Yu, L. Cui, and Q. Yang, “Towards Personalized Federated Learning,” IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 12, pp. 9587–9603, Dec. 2023, doi: 10.1109/tnnls.2022.3160699.
[9] C. T. Dinh, N. H. Tran, and T. D. Nguyen, “Personalized Federated Learning with Moreau Envelopes,” in 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, BC, Canada, Dec. 6–12, 2020, pp. 21394–21405.
[10] T. Li, A. K. Sahu, M. Zaheer, M. Sanjabi, A. Talwalkar, and V. Smith, “Federated Optimization in Heterogeneous Networks,” in Proc. Machine Learning and Systems 2 (MLSys 2020), Austin, TX, USA, Mar. 2–4, 2020, pp. 1–22.
[11] A. K. Selvaraj, S. B. Prathiba, A. Deepak Kumar, R. Dhanalakshmi, T. R. Gadekallu, and G. Srivastava, “Co-Training-Based Personalized Federated Learning With Generative Adversarial Networks for Enhanced Mobile Smart Healthcare Diagnosis,” IEEE Transactions on Consumer Electronics, vol. 70, no. 3, pp. 6131–6139, 2024, doi: 10.1109/tce.2024.3460469.
[12] M. Guduri, C. Chakraborty, U. Maheswari, and M. Margala, “Blockchain-Based Federated Learning Technique for Privacy Preservation and Security of Smart Electronic Health Records,” IEEE Transactions on Consumer Electronics, vol. 70, no. 1, pp. 2608–2617, 2024, doi: 10.1109/tce.2023.3315415.
[13] Z. Jia, T. Zhou, Z. Yan, J. Hu, and Y. Shi, “Personalized Meta-Federated Learning for IoT-Enabled Health Monitoring,” IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 43, no. 10, pp. 3157–3170, doi: 10.1109/TCAD.2024.3388908.
[14] A. Reiss and D. Stricker, “Introducing a New Benchmarked Dataset for Activity Monitoring,” in 2012 16th International Symposium on Wearable Computers, Newcastle, UK, Jun. 18–22, 2012, pp. 108–109, doi: 10.1109/ISWC.2012.13.
[15] P. Schmidt, A. Reiss, R. Dürichen, C. Marberger, and K. Van Laerhoven, “Introducing WESAD, a Multimodal Dataset for Wearable Stress and Affect Detection,” in Proc. 20th ACM International Conference on Multimodal Interaction, Boulder, CO, USA, Oct. 16–20, 2018, pp. 400–408, doi: 10.1145/3242969.3242985.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 School of Engineering, King Mongkut’s Institute of Technology Ladkrabang

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
The published articles are copyrighted by the School of Engineering, King Mongkut's Institute of Technology Ladkrabang.
The statements contained in each article in this academic journal are the personal opinions of each author and are not related to King Mongkut's Institute of Technology Ladkrabang and other faculty members in the institute.
Responsibility for all elements of each article belongs to each author; If there are any mistakes, each author is solely responsible for his own articles.



