Prefallkd: Pre-Impact Fall Detection Via CNN-ViT Knowledge Distillation

Fall accidents are critical issues in an aging and aged society. Recently, many researchers developed "pre-impact fall detection systems" using deep learning to support wearable-based fall protection systems for preventing severe injuries. However, most works only employed simple neural ne...

Full description

Saved in:
Bibliographic Details
Main Authors: Chi, Tin-Han, Liu, Kai-Chun, Hsieh, Chia-Yeh, Tsao, Yu, Chan, Chia-Tai
Format: Conference Proceeding
Language:English
Subjects:
Aging
Computational modeling
Fall detection
Inertial measurement units
Knowledge distillation
Pre-impact fall detection
Reliability
System performance
Transformers
Usability
Vision transformer
Wearable sensors
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Fall accidents are critical issues in an aging and aged society. Recently, many researchers developed "pre-impact fall detection systems" using deep learning to support wearable-based fall protection systems for preventing severe injuries. However, most works only employed simple neural network models instead of complex models considering the usability in resource-constrained mobile devices and strict latency requirements. In this work, we propose a novel pre-impact fall detection via CNN-ViT knowledge distillation, namely PreFallKD, to strike a balance between detection performance and computational complexity. The proposed PreFallKD transfers the detection knowledge from the pre-trained teacher model (vision transformer) to the student model (lightweight convolutional neural networks). Additionally, we apply data augmentation techniques to tackle issues of data imbalance. We conduct the experiment on the KFall public dataset and compare PreFallKD with other state-of-the-art models. The experiment results show that PreFallKD could boost the student model during the testing phase and achieves reliable F1-score (92.66%) and lead time (551.3 ms).
ISSN:2379-190X
DOI:10.1109/ICASSP49357.2023.10094979