EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multimodal Fall Detection Using Spatial–Temporal Attention and Bi-LSTM-Based Feature Fusion

Jungpil Shin, Abu Saleh Musa Miah, Rei Egawa, Najmul Hassan, Koki Hirooka, Yoichi Tomioka

Future Internet · 15.04.2025 · 17 (4) · 173

DOI: 10.3390/fi17040173 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Future Internet, online erschienen am 15.04.2025. Verfasst von Jungpil Shin und 5 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Japan Society for the Promotion of Science (JSPS) KAKENHI.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human fall detection is a significant healthcare concern, particularly among the elderly, due to its links to muscle weakness, cardiovascular issues, and locomotive syndrome. Accurate fall detection is crucial for timely intervention and injury prevention, which has led many researchers to work on developing effective detection systems. However, existing unimodal systems that rely solely on skeleton or sensor data face challenges such as poor robustness, computational inefficiency, and sensitivity to environmental conditions. While some multimodal approaches have been proposed, they often struggle to capture long-range dependencies effectively. In order to address these challenges, we propose a multimodal fall detection framework that integrates skeleton and sensor data. The system uses a Graph-based Spatial-Temporal Convolutional and Attention Neural Network (GSTCAN) to capture spatial and temporal relationships from skeleton and motion data information in stream-1, while a Bi-LSTM with Channel Attention (CA) processes sensor data in stream-2, extracting both spatial and temporal features. The GSTCAN model uses AlphaPose for skeleton extraction, calculates motion between consecutive frames, and applies a graph convolutional network (GCN) with a CA mechanism to focus on relevant features while suppressing noise. In parallel, the Bi-LSTM with CA processes inertial signals, with Bi-LSTM capturing long-range temporal dependencies and CA refining feature representations. The features from both branches are fused and passed through a fully connected layer for classification, providing a comprehensive understanding of human motion. The proposed system was evaluated on the Fall Up and UR Fall datasets, achieving a classification accuracy of 99.09% and 99.32%, respectively, surpassing existing methods. This robust and efficient system demonstrates strong potential for accurate fall detection and continuous healthcare monitoring.

Förderung

  • Japan Society for the Promotion of Science (JSPS) KAKENHI

Zitieren

APA

Shin, J., Miah, A. S. M., Egawa, R., Hassan, N., Hirooka, K., & Tomioka, Y. (2025). Multimodal Fall Detection Using Spatial–Temporal Attention and Bi-LSTM-Based Feature Fusion. Future Internet, 17(4), 173. https://doi.org/10.3390/fi17040173

Vancouver

Shin J, Miah ASM, Egawa R, Hassan N, Hirooka K, Tomioka Y. Multimodal Fall Detection Using Spatial–Temporal Attention and Bi-LSTM-Based Feature Fusion. Future Internet. 2025;17(4):173. doi:10.3390/fi17040173

BibTeX
@article{Shin2025,
  author = {Shin, Jungpil and Miah, Abu Saleh Musa and Egawa, Rei and Hassan, Najmul and Hirooka, Koki and Tomioka, Yoichi},
  title = {Multimodal Fall Detection Using Spatial–Temporal Attention and Bi-LSTM-Based Feature Fusion},
  journal = {Future Internet},
  year = {2025},
  volume = {17},
  number = {4},
  pages = {173},
  doi = {10.3390/fi17040173}
}
Kostenlos starten →