EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Human Activity Recognition via Attention-Augmented TCN-BiGRU Fusion

Ji-Long He, Jian-Hong Wang iD, Chih-Min Lo iD, Zhaodi Jiang

Sensors · 16.09.2025 · 25 (18) · 5765

DOI: 10.3390/s25185765 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 16.09.2025. Verfasst von Ji-Long He und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Shandong University of Technology, Zibo 255000, China. Hauptthemen laut MEDLINE: Human Activities, Attention. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the widespread application of wearable sensors in health monitoring and human–computer interaction, deep learning-based human activity recognition (HAR) research faces challenges such as the effective extraction of multi-scale temporal features and the enhancement of robustness against noise in multi-source data. This study proposes the TGA-HAR (TCN-GRU-Attention-HAR) model. The TGA-HAR model integrates Temporal Convolutional Neural Networks and Recurrent Neural Networks by constructing a hierarchical feature abstraction architecture through cascading Temporal Convolutional Network (TCN) and Bidirectional Gated Recurrent Unit (BiGRU) layers for complex activity recognition. This study utilizes TCN layers with dilated convolution kernels to extract multi-order temporal features. This study utilizes BiGRU layers to capture bidirectional temporal contextual correlation information. To further optimize feature representation, the TGA-HAR model introduces residual connections to enhance the stability of gradient propagation and employs an adaptive weighted attention mechanism to strengthen feature representation. The experimental results of this study demonstrate that the model achieved test accuracies of 99.37% on the WISDM dataset, 95.36% on the USC-HAD dataset, and 96.96% on the PAMAP2 dataset. Furthermore, we conducted tests on datasets collected in real-world scenarios. This method provides a highly robust solution for complex human activity recognition tasks.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Human ActivitiesAttentionHumansNeural Networks, ComputerDeep LearningAlgorithmsWearable Electronic DevicesMonitoring, Physiologic

Stichwörter der Autor:innen

attention mechanismbidirectional gated recurrent unithuman activity recognitionsensor data sequencestemporal convolutional network

Autor:innen und Institutionen

  • School of Computer Science and Technology, Shandong University of Technology, Zibo 255000, China.
  • Department of Digital Multimedia Design, School of Innovative Design and Management, National Taipei University of Business, No. 321, Sec. 1, Jinan Rd., Zhongzheng District, Taipei City 100025, Taiwan.

ORCID-Profile: Jian-Hong Wang, Chih-Min Lo

Zitieren

APA

He, J. L., Wang, J. H., Lo, C. M., & Jiang, Z. (2025). Human Activity Recognition via Attention-Augmented TCN-BiGRU Fusion. Sensors, 25(18), 5765. https://doi.org/10.3390/s25185765

Vancouver

He JL, Wang JH, Lo CM, Jiang Z. Human Activity Recognition via Attention-Augmented TCN-BiGRU Fusion. Sensors. 2025;25(18):5765. doi:10.3390/s25185765

BibTeX
@article{He2025,
  author = {He, Ji-Long and Wang, Jian-Hong and Lo, Chih-Min and Jiang, Zhaodi},
  title = {Human Activity Recognition via Attention-Augmented TCN-BiGRU Fusion},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {18},
  pages = {5765},
  doi = {10.3390/s25185765}
}
Kostenlos starten →