Top > JACIII > Fall Detection Based on Graph Neural Networks with Variable Ti ...

single-jc.php

JACIII Vol.28 No.4 pp. 974-982
doi: 10.20965/jaciii.2024.p0974
(2024)

Research Paper:

Views over last 60 days: 233

Fall Detection Based on Graph Neural Networks with Variable Time Windows

Jiawei Wei*, Junjie Li**, Yuqing Liu*,†, and Hongbin Ma*** ORCID Icon

*Department of Engineering, Shanghai Ocean University
No.999 Hucheng Huan Road, Pudong New Area, Shanghai 201306, China

†Corresponding author

**Department of Information Science and Engineering, Lanzhou University
No.456 Jiayuguan Road, Lanzhou, Gansu 730020, China

***School of Automation, Beijing Institute of Technology
No.5 South Street, Zhongguancun, Haidian District, Beijing 100081, China

Received:
February 8, 2024
Accepted:
April 9, 2024
Published:
July 20, 2024
Creative Commons License
Keywords:
fall detection, graph topologists, wrist-worn IMU sensors data, variable time windows, graph convolution neural network
Abstract

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.

T-GCN model framework

T-GCN model framework

Cite this article as:
J. Wei, J. Li, Y. Liu, and H. Ma, “Fall Detection Based on Graph Neural Networks with Variable Time Windows,” J. Adv. Comput. Intell. Intell. Inform., Vol.28 No.4, pp. 974-982, 2024.
Data files:
References
  1. [1] N. C. Betancourt, M. Flores-Calero, and C. Almeida, “Sudden cardiac death detection by using an hybrid method based on TWA and dictionary learning: A data experimentation,” IEEE Access, Vol.11, pp. 53006-53018, 2023. https://doi.org/10.1109/ACCESS.2023.3277396
  2. [2] A. Martín-Yebra, L. Sörnmo, and P. Laguna, “QT interval adaptation to heart rate changes in atrial fibrillation as a predictor of sudden cardiac death,” IEEE Trans. on Biomedical Engineering, Vol.69, No.10, pp. 3109-3118, 2022. https://doi.org/10.1109/TBME.2022.3161725
  3. [3] M. Mubashir, L. Shao, and L. Seed, “A survey on fall detection: Principles and approaches,” Neurocomputing, Vol.100, pp. 144-152, 2013. https://doi.org/10.1016/j.neucom.2011.09.037
  4. [4] E. Ramanujam, T. Perumal, and S. Padmavathi, “Human activity recognition with smartphone and wearable sensors using deep learning techniques: A review,” IEEE Sensors J., Vol.21, No.12, pp. 13029-13040, 2021. https://doi.org/10.1109/JSEN.2021.3069927
  5. [5] W. Yan, C. Shuang, Y. Hongnian, “A survey on wearable sensor modality centred human activity recognition in health care,” Expert Systems with Applications, Vol.137, pp. 167-190, 2019. https://doi.org/10.1016/j.eswa.2019.04.057
  6. [6] X. Han et al., “The effect of axis-wise triaxial acceleration data fusion in CNN-based human activity recognition,” IEICE Trans. on Information and Systems, Vol.E103-D, No.4, pp. 813-824, 2020. https://doi.org/10.1587/transinf.2018EDP7409
  7. [7] I. Kecskés et al., “Simultaneous calibration of a hexapod robot and an IMU sensor model based on raw measurements,” IEEE Sensors J., Vol.21, No.13, pp. 14887-14898, 2021. https://doi.org/10.1109/JSEN.2021.3074272
  8. [8] C. Li, L. Yu, and S. Fei, “Real-time 3D motion tracking and reconstruction system using camera and IMU sensors,” IEEE Sensors J., Vol.19, No.15, pp. 6460-6466, 2019. https://doi.org/10.1109/JSEN.2019.2907716
  9. [9] N. Siddiqui and R. H. M. Chan, “Multimodal hand gesture recognition using single IMU and acoustic measurements at wrist,” PLOS ONE, Vol.15, No.1, Article No.e0227039, 2020. https://doi.org/10.1371/journal.pone.0227039
  10. [10] T. T. Pham and Y. S. Suh, “Histogram feature-based approach for walking distance estimation using a waist-mounted IMU,” IEEE Sensors J., Vol.20, No.20, pp. 12354-12363, 2020. https://doi.org/10.1109/JSEN.2020.2999930
  11. [11] F. Wittmann, O. Lambercy, and R. Gassert, “Magnetometer-based drift correction during rest in IMU arm motion tracking,” Sensors, Vol.19, No.6, Article No.1312, 2019. https://doi.org/10.3390/s19061312
  12. [12] S. Majumder and M. J. Deen, “Wearable IMU-based system for real-time monitoring of lower-limb joints,” IEEE Sensors J., Vol.21, No.6, pp. 8267-8275, 2021. https://doi.org/10.1109/JSEN.2020.3044800
  13. [13] L. Chen et al., “Intelligent fall detection method based on accelerometer data from a wrist-worn smart watch,” Measurement, Vol.140, pp. 215-226, 2019. https://doi.org/10.1016/j.measurement.2019.03.079
  14. [14] Y. Tian et al., “Robust human activity recognition using single accelerometer via wavelet energy spectrum features and ensemble feature selection,” Systems Science & Control Engineering, Vol.8, No.1, pp. 83-96, 2020. https://doi.org/10.1080/21642583.2020.1723142
  15. [15] T. de Quadros, A. E. Lazzaretti, and F. K. Schneider, “A movement decomposition and machine learning-based fall detection system using wrist wearable device,” IEEE Sensors J., Vol.18, No.12, pp. 5082-5089, 2018. https://doi.org/10.1109/JSEN.2018.2829815
  16. [16] E. Kanjo, E. M. G. Younis, and C. S. Ang, “Deep learning analysis of mobile physiological, environmental and location sensor data for emotion detection,” Information Fusion, Vol.49, pp. 46-56, 2019. https://doi.org/10.1016/j.inffus.2018.09.001
  17. [17] P. Wang, E. Fan, and P. Wang, “Comparative analysis of image classification algorithms based on traditional machine learning and deep learning,” Pattern Recognition Letters, Vol.141, pp. 61-67, 2021. https://doi.org/10.1016/j.patrec.2020.07.042
  18. [18] M. Martinez and P. L. De Leon, “Falls risk classification of older adults using deep neural networks and transfer learning,” IEEE J. of Biomedical and Health Informatics, Vol.24, No.1, pp. 144-150, 2020. https://doi.org/10.1109/JBHI.2019.2906499
  19. [19] G. Şengül et al., “Deep learning based fall detection using smartwatches for healthcare applications,” Biomedical Signal Processing and Control, Vol.71, Part B, Article No.103242, 2022. https://doi.org/10.1016/j.bspc.2021.103242
  20. [20] S. Dong, P. Wang, and K. Abbas, “A survey on deep learning and its applications,” Computer Science Review, Vol.40, Article No.100379, 2021. https://doi.org/10.1016/j.cosrev.2021.100379
  21. [21] J. Zhou et al., “Graph neural networks: A review of methods and applications,” AI Open, Vol.1, pp. 57-81, 2020. https://doi.org/10.1016/j.aiopen.2021.01.001
  22. [22] Z. Lai et al., “Multiscale wavelet-driven graph convolutional network for blade icing detection of wind turbines,” IEEE Sensors J., Vol.22, No.22, pp. 21974-21985, 2022. https://doi.org/10.1109/JSEN.2022.3211079
  23. [23] X. Li et al., “A fault diagnosis method for rotating machinery with semi-supervised graph convolutional network and images converted from vibration signals,” IEEE Sensors J., Vol.23, No.11, pp. 11946-11955, 2023. https://doi.org/10.1109/JSEN.2023.3267427
  24. [24] Y. Shi et al., “A fast pearson graph convolutional network combined with electronic nose to identify the origin of rice,” IEEE Sensors J., Vol.21, No.19, pp. 21175-21183, 2021. https://doi.org/10.1109/JSEN.2021.3079424
  25. [25] Y. Liu et al., “Graph convolutional network enabled two-stream learning architecture for diabetes classification based on flash glucose monitoring data,” Biomedical Signal Processing and Control, Vol.69, Article No.102896, 2021. https://doi.org/10.1016/j.bspc.2021.102896
  26. [26] Y. Li et al., “Identification of Mild cognitive impairment based on quadruple GCN model constructed with multiple features from higher-order brain connectivity,” Expert Systems with Applications, Vol.230, Article No.120575, 2023. https://doi.org/10.1016/j.eswa.2023.120575
  27. [27] S. Dastjerdi, B. Akgöz, and Ö. Civalek, “On the effect of viscoelasticity on behavior of gyroscopes,” Int. J. of Engineering Science, Vol.149, Article No.103236, 2020. https://doi.org/10.1016/j.ijengsci.2020.103236
  28. [28] S. Gupta, “Deep learning based human activity recognition (HAR) using wearable sensor data,” Int. J. of Information Management Data Insights, Vol.1, No.2, Article No.100046, 2021. https://doi.org/10.1016/j.jjimei.2021.100046

Creative Commons License  This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Dec. 06, 2024