EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

STJA-GCN: A Multi-Branch Spatial–Temporal Joint Attention Graph Convolutional Network for Abnormal Gait Recognition

Ziming Yin, Yi Jiang, Jianli Zheng, Hongliu Yu

Applied Sciences · 26.03.2023 · 13 (7) · 4205

DOI: 10.3390/app13074205 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 26.03.2023. Verfasst von Ziming Yin und 3 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Early recognition of abnormal gait enables physicians to determine a prompt rehabilitation plan for patients for the most effective treatment and care. The Kinect depth sensor can easily collect skeleton data describing the position of joints in the human body. However, the default human skeleton model of Kinect includes an excessive number of many joints, which limits the accuracy of the gait recognition methods and increases the computational resources required. In this study, we propose an optimized human skeleton model for the Kinect system and streamline the joints using a center-of-mass calculation. We integrate several techniques to propose an end-to-end, spatial–temporal, joint attention graph convolutional network (STJA-GCN) architecture. We conducted experiments with a fivefold cross-validation on two common datasets of information on abnormal gaits to evaluate the performance of the proposed method. The results show that the STJA-GCN achieved 93.17 and 92.08% accuracy on the two datasets, and compared to the original spatial–temporal graph convolutional network (ST-GCN), the recognition accuracy increases by 9.22 and 20.65%, respectively. Overall, the results demonstrate that the STJA-GCN can accurately recognize abnormal gaits and, thus, can support low-cost rehabilitation assessments at community hospitals or in patients’ homes.

Förderung

  • National Key R&D Program of China

Zitieren

APA

Yin, Z., Jiang, Y., Zheng, J., & Yu, H. (2023). STJA-GCN: A Multi-Branch Spatial–Temporal Joint Attention Graph Convolutional Network for Abnormal Gait Recognition. Applied Sciences, 13(7), 4205. https://doi.org/10.3390/app13074205

Vancouver

Yin Z, Jiang Y, Zheng J, Yu H. STJA-GCN: A Multi-Branch Spatial–Temporal Joint Attention Graph Convolutional Network for Abnormal Gait Recognition. Applied Sciences. 2023;13(7):4205. doi:10.3390/app13074205

BibTeX
@article{Yin2023,
  author = {Yin, Ziming and Jiang, Yi and Zheng, Jianli and Yu, Hongliu},
  title = {STJA-GCN: A Multi-Branch Spatial–Temporal Joint Attention Graph Convolutional Network for Abnormal Gait Recognition},
  journal = {Applied Sciences},
  year = {2023},
  volume = {13},
  number = {7},
  pages = {4205},
  doi = {10.3390/app13074205}
}
Kostenlos starten →