CrossHAR: Generalizing Cross-dataset Human Activity Recognition via Hierarchical Self-Supervised Pretraining
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · 13.05.2024 · 8 (2) · 1-26
DOI: 10.1145/3659597 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, online erschienen am 15.05.2024. Verfasst von Zhiqing Hong und 7 weiteren Autor:innen. Die Arbeit wurde bisher 79-mal zitiert (Crossref) und nennt 91 Literaturangaben. Gefördert von: National Science and Technology Major Project.
Abstract (Originalsprache)
The increasing availability of low-cost wearable devices and smartphones has significantly advanced the field of sensor-based human activity recognition (HAR), attracting considerable research interest. One of the major challenges in HAR is the domain shift problem in cross-dataset activity recognition, which occurs due to variations in users, device types, and sensor placements between the source dataset and the target dataset. Although domain adaptation methods have shown promise, they typically require access to the target dataset during the training process, which might not be practical in some scenarios. To address these issues, we introduce CrossHAR, a new HAR model designed to improve model performance on unseen target datasets. CrossHAR involves three main steps: (i) CrossHAR explores the sensor data generation principle to diversify the data distribution and augment the raw sensor data. (ii) CrossHAR then employs a hierarchical self-supervised pretraining approach with the augmented data to develop a generalizable representation. (iii) Finally, CrossHAR fine-tunes the pretrained model with a small set of labeled data in the source dataset, enhancing its performance in cross-dataset HAR. Our extensive experiments across multiple real-world HAR datasets demonstrate that CrossHAR outperforms current state-of-the-art methods by 10.83% in accuracy, demonstrating its effectiveness in generalizing to unseen target datasets.
Förderung
- National Science and Technology Major Project
Zitieren
APA
Hong, Z., Li, Z., Zhong, S., Lyu, W., Wang, H., Ding, Y., He, T., & Zhang, D. (2024). CrossHAR: Generalizing Cross-dataset Human Activity Recognition via Hierarchical Self-Supervised Pretraining. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 8(2), 1-26. https://doi.org/10.1145/3659597
Vancouver
Hong Z, Li Z, Zhong S, Lyu W, Wang H, Ding Y, et al. CrossHAR: Generalizing Cross-dataset Human Activity Recognition via Hierarchical Self-Supervised Pretraining. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies. 2024;8(2):1-26. doi:10.1145/3659597
BibTeX
@article{Hong2024,
author = {Hong, Zhiqing and Li, Zelong and Zhong, Shuxin and Lyu, Wenjun and Wang, Haotian and Ding, Yi and He, Tian and Zhang, Desheng},
title = {CrossHAR: Generalizing Cross-dataset Human Activity Recognition via Hierarchical Self-Supervised Pretraining},
journal = {Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies},
year = {2024},
volume = {8},
number = {2},
pages = {1--26},
doi = {10.1145/3659597}
}
EUVIMED