Physics-guided contrastive learning for wearable fall detection: towards low-latency on-device inference
Journal of Edge Computing · 20.11.2026
DOI: 10.55056/jec.1262 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Edge Computing, online erschienen am 20.11.2026. Verfasst von Bowen Zuo und 4 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Fall detection on wearable edge devices requires high sensitivity within tight latency, memory and energy budgets. We propose PhyCL-Net, a time-domain network without an explicit spectral feature branch. It combines a physics-guided dynamic kernel (PDK), which adapts temporal receptive fields to local signal dynamics, with jerk-aware fall-aware attention (FAA), which emphasises transient segments. A hierarchical dual-view contrastive regulariser is used only during training, and its auxiliary heads are removed for deployment. On SisFall with 12-fold leave-one-subject-out (LOSO) validation, PhyCL-Net achieves 98.21 ± 0.10% accuracy and 98.16 ± 0.10% Macro-F1 across five seeds, with 1.049M parameters and 0.15 GFLOPs. Compared with a matched spectral baseline, its median single-thread CPU latency is 31.6% lower (125.99 ms). On the empirical ROC curve, the false-positive rate (FPR) at a 95% true-positive rate (TPR) is 0.72%, but the TPR at 1% FPR is 2.73 percentage points lower than that of the spectral baseline.
Zitieren
APA
Zuo, B., Xie, J., Wang, S., Liu, S., & Luo, X. (2026). Physics-guided contrastive learning for wearable fall detection: towards low-latency on-device inference. Journal of Edge Computing. https://doi.org/10.55056/jec.1262
Vancouver
Zuo B, Xie J, Wang S, Liu S, Luo X. Physics-guided contrastive learning for wearable fall detection: towards low-latency on-device inference. Journal of Edge Computing. 2026. doi:10.55056/jec.1262
BibTeX
@article{Zuo2026,
author = {Zuo, Bowen and Xie, Junhui and Wang, Siqi and Liu, Sihan and Luo, Xiaojuan},
title = {Physics-guided contrastive learning for wearable fall detection: towards low-latency on-device inference},
journal = {Journal of Edge Computing},
year = {2026},
doi = {10.55056/jec.1262}
}
EUVIMED