Personalized Federated Attention State Space Learning for Wearable Human Activity Recognition
ACM Transactions on Embedded Computing Systems · 31.07.2026 · 25 (4) · 1-34
DOI: 10.1145/3820371 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Embedded Computing Systems, online erschienen am 30.06.2026. Verfasst von Zhiwen Xiao und 2 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Doctoral Innovation Fund Program of Southwest Jiaotong University, Key Laboratory of Detection and Application of Space Effect in Southwest Sichuan at Leshan Normal University, Education Department of Sichuan Province.
Abstract (Originalsprache)
Wearable human activity recognition (HAR) focuses on classifying human activities from multi-sensor data collected by wearable devices and has become increasingly important in pervasive computing. However, existing methods face several challenges: (1) aggregating heterogeneous local models while preserving user-specific data distributions, (2) achieving personalized adaptation of global models to diverse behavioral patterns, and (3) capturing both local and global temporal dependencies inherent in sensor time-series data. To address these challenges, we propose PFLMamba, a personalized federated learning framework integrating an attention-enhanced state-space model (ASSM) for hierarchical temporal feature extraction. PFLMamba employs a server-side personalized attention aggregation mechanism to tailor global models for individual clients, while ASSM captures both local and long-range temporal patterns on the client side. Extensive evaluations on the WISDM and PAMAP2 datasets demonstrate that PFLMamba achieves F 1 scores of 91.83 and 96.01, respectively, outperforming state-of-the-art federated learning baselines such as FCLFD, EFDLS, and FKD. PFLMamba’s effectiveness is further validated on multi-user and heterogeneous-sensor datasets, namely UCI-HAR and UNIMIB-SHAR, confirming its generalization across diverse populations and device types. Beyond predictive accuracy, PFLMamba exhibits a favorable trade-off between efficiency and performance, with lower client-side training overhead than teacher-student-based frameworks and competitive throughput relative to lightweight alternatives. Further experiments on resource-constrained edge devices (i.e., Raspberry Pi 4 and PYNQ-Z2) validate its practical feasibility, highlighting low-latency inference and moderate energy consumption. These results establish PFLMamba as a robust and efficient solution for personalized wearable HAR.
Förderung
- Doctoral Innovation Fund Program of Southwest Jiaotong University
- Key Laboratory of Detection and Application of Space Effect in Southwest Sichuan at Leshan Normal University, Education Department of Sichuan Province
Zitieren
APA
Xiao, Z., Wan, Q., & Tong, H. (2026). Personalized Federated Attention State Space Learning for Wearable Human Activity Recognition. ACM Transactions on Embedded Computing Systems, 25(4), 1-34. https://doi.org/10.1145/3820371
Vancouver
Xiao Z, Wan Q, Tong H. Personalized Federated Attention State Space Learning for Wearable Human Activity Recognition. ACM Transactions on Embedded Computing Systems. 2026;25(4):1-34. doi:10.1145/3820371
BibTeX
@article{Xiao2026,
author = {Xiao, Zhiwen and Wan, Qian and Tong, Huagang},
title = {Personalized Federated Attention State Space Learning for Wearable Human Activity Recognition},
journal = {ACM Transactions on Embedded Computing Systems},
year = {2026},
volume = {25},
number = {4},
pages = {1--34},
doi = {10.1145/3820371}
}
EUVIMED