Resource-Aware Personalized Federated Learning for Wearable Health Monitoring: A Simulation Study
Engineering and Technology Horizons · 2026-11-20 · 43 (4)
DOI: 10.55003/eth.430402 ↗At a glance
Journal article in Engineering and Technology Horizons, published online on 2026-11-20. Written by Parijata Majumdar.
Abstract (original language)
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.
Cite
APA
Majumdar, P. (2026). Resource-Aware Personalized Federated Learning for Wearable Health Monitoring: A Simulation Study. Engineering and Technology Horizons, 43(4). https://doi.org/10.55003/eth.430402
Vancouver
Majumdar P. Resource-Aware Personalized Federated Learning for Wearable Health Monitoring: A Simulation Study. Engineering and Technology Horizons. 2026;43(4). doi:10.55003/eth.430402
BibTeX
@article{Majumdar2026,
author = {Majumdar, Parijata},
title = {Resource-Aware Personalized Federated Learning for Wearable Health Monitoring: A Simulation Study},
journal = {Engineering and Technology Horizons},
year = {2026},
volume = {43},
number = {4},
doi = {10.55003/eth.430402}
}
EUVIMED