Towards User-Generalizable Wearable-Sensor-Based Human Activity Recognition: A Multi-Task Contrastive Learning Approach
Sensors · 2025
DOI: 10.3390/s25226988 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Pengyu Guo und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronic Engineering and Information Systems, The University of Tokyo, Tokyo 113-8654, Japan. Hauptthemen laut MEDLINE: Wearable Electronic Devices, Human Activities. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Human Activity Recognition (HAR) using wearable sensors has shown great potential for personalized health management and ubiquitous computing. However, existing deep learning-based HAR models often suffer from poor user-level generalization, which limits their deployment in real-world scenarios. In this work, we propose a novel multi-task contrastive learning framework that jointly optimizes activity classification and supervised contrastive objectives to enhance generalization across unseen users. By leveraging both activity and user labels to construct semantically meaningful contrastive pairs, our method improves representation learning while maintaining user-agnostic inference at test time. We evaluate the proposed framework on three public HAR datasets using cross-user splits, achieving comparable results to both supervised and self-supervised baselines. Extensive ablation studies further confirm the effectiveness of our design choices, including multi-task training and the integration of user-aware contrastive supervision. These results highlight the potential of our approach for building more generalizable and scalable HAR systems.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Electronic Engineering and Information Systems, The University of Tokyo, Tokyo 113-8654, Japan.
- Information Technology Center, The University of Tokyo, Tokyo 113-8654, Japan.
Zitieren
APA
Guo, P., & Nakayama, M. (2025). Towards User-Generalizable Wearable-Sensor-Based Human Activity Recognition: A Multi-Task Contrastive Learning Approach. Sensors. https://doi.org/10.3390/s25226988
Vancouver
Guo P, Nakayama M. Towards User-Generalizable Wearable-Sensor-Based Human Activity Recognition: A Multi-Task Contrastive Learning Approach. Sensors. 2025. doi:10.3390/s25226988
BibTeX
@article{Guo2025,
author = {Guo, Pengyu and Nakayama, Masaya},
title = {Towards User-Generalizable Wearable-Sensor-Based Human Activity Recognition: A Multi-Task Contrastive Learning Approach},
journal = {Sensors},
year = {2025},
doi = {10.3390/s25226988}
}
EUVIMED