TY - JOUR
T1 - Fall Detection Based on Graph Neural Networks with Variable Time Windows
AU - Wei, Jiawei
AU - Li, Junjie
AU - Liu, Yuqing
AU - Ma, Hongbin
N1 - Publisher Copyright:
© 2024 Fuji Technology Press. All rights reserved.
PY - 2024/7
Y1 - 2024/7
N2 - The precise detection of falls is essential for promptly providing first aid to individuals who are at risk of accidental injury. Presently, the predominant approach for detecting falls is through inertial measurement unit (IMU) sensors, which can capture the real-time motion of an object. However, it is difficult for the current approach to face the challenges in attaining the anticipated performance in real-world applications, owing to the diverse nature of human behavior. To tackle this concern, a fall detection approach that uses a graph convolutional neural network (GCN) with variable time windows (T-GCN) is introduced. The proposed method uses well-designed graph topologies to effectively mitigate the impact of inconsistent data dimensions. Meanwhile, variable time windows are designed to capture keyframe data and to enhance their validity. To evaluate the effectiveness of the T-GCN method, a dataset Dhard containing 12 suspected falls and four real falls is built. The experimental results show that the T-GCN method achieves an accuracy of 91.3% and a precision of 92.5%, surpassing the average accuracy and precision of conventional fall detection methods.
AB - The precise detection of falls is essential for promptly providing first aid to individuals who are at risk of accidental injury. Presently, the predominant approach for detecting falls is through inertial measurement unit (IMU) sensors, which can capture the real-time motion of an object. However, it is difficult for the current approach to face the challenges in attaining the anticipated performance in real-world applications, owing to the diverse nature of human behavior. To tackle this concern, a fall detection approach that uses a graph convolutional neural network (GCN) with variable time windows (T-GCN) is introduced. The proposed method uses well-designed graph topologies to effectively mitigate the impact of inconsistent data dimensions. Meanwhile, variable time windows are designed to capture keyframe data and to enhance their validity. To evaluate the effectiveness of the T-GCN method, a dataset Dhard containing 12 suspected falls and four real falls is built. The experimental results show that the T-GCN method achieves an accuracy of 91.3% and a precision of 92.5%, surpassing the average accuracy and precision of conventional fall detection methods.
KW - fall detection
KW - graph convolution neural network
KW - graph topologists
KW - variable time windows
KW - wrist-worn IMU sensors data
UR - http://www.scopus.com/inward/record.url?scp=85199413404&partnerID=8YFLogxK
U2 - 10.20965/jaciii.2024.p0974
DO - 10.20965/jaciii.2024.p0974
M3 - Article
AN - SCOPUS:85199413404
SN - 1343-0130
VL - 28
SP - 974
EP - 982
JO - Journal of Advanced Computational Intelligence and Intelligent Informatics
JF - Journal of Advanced Computational Intelligence and Intelligent Informatics
IS - 4
ER -