Predicting Fall Events by a Spatio-Temporal Topological Network with Multiple Wearable Sensors

Xiaohu Li, Jiawei Liu, Guorui Liao, Mingrui Yin, Shu Wang, Guoxin Su, Jun Liao, Li Liu

Abstract

A key challenge in sensor-based fall prediction is the fact that a fall event can often occur in various configurations of fall poses together with their own spatio-temporal dependencies. This leads us to define a spatio-temporal model to explicitly characterize these internal configurations of poses. In particular, we introduce a graph neural network with spatio-temporal topological structure to encode such latent relations among poses by capturing representative patterns in fall events. Moreover, a human body orientation estimator is devised to capture human low limbs information, and as a result, separate pose dependencies are globally consistent. Empirical evaluations on two benchmark datasets and one in-house dataset suggest our approach significantly outperforms the state-of-the-art methods.
BibTeX
@inproceedings{li2024predicting,
  author = {Xiaohu Li and Jiawei Liu and Guorui Liao and Mingrui Yin and Shu Wang and Guoxin Su and Jun Liao and Li Liu},
  title = {{Predicting Fall Events by a Spatio-Temporal Topological Network with Multiple Wearable Sensors}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2024},
  doi = {10.1109/icassp48485.2024.10446493},
}

Loading related content...

Figure