PNF and Movement

Korea Proprioceptive Neuromuscular Facilitation Association (대한고유수용성신경근촉진법학회)
권호 표지
DOI QR코드

DOI QR Code

Vest-type System on Machine Learning-based Algorithm to Detect and Predict Falls

  • Ho-Chul Kim (Department of Radiological Science, College of Health Science, Eulji University) ;
  • Ho-Seong Hwang (Research Institute of Machine Intelligence Convergence System, EulJi University) ;
  • Kwon-Hee Lee (Department of Bio-Medical Science, Korea University) ;
  • Min-Hee Kim (Department of Physical therapy, College of Health Science, Eulji University)
  • Received : 2024.03.06
  • Accepted : 2024.03.22
  • Published : 2024.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

Purpose: Falls among persons older than 65 years are a significant concern due to their frequency and severity. This study aimed to develop a vest-type embedded artificial intelligence (AI) system capable of detecting and predicting falls in various scenarios. Methods: In this study, we established and developed a vest-type embedded AI system to judge and predict falls in various directions and situations. To train the AI, we collected data using acceleration and gyroscope values from a six-axis sensor attached to the seventh cervical and the second sacral vertebrae of the user, considering accurate motion analysis of the human body. The model was constructed using a neural network-based AI prediction algorithm to anticipate the direction of falls using the collected pedestrian data. Results: We focused on developing a lightweight and efficient fall prediction model for integration into an embedded AI algorithm system, ensuring real-time network optimization. Our results showed that the accuracy of fall occurrence and direction prediction using the trained fall prediction model was 89.0% and 78.8%, respectively. Furthermore, the fall occurrence and direction prediction accuracy of the model quantized for embedded porting was 87.0 % and 75.5 %, respectively. Conclusion: The developed fall detection and prediction system, designed as a vest-type with an embedded AI algorithm, offers the potential to provide real-time feedback to pedestrians in clinical settings and proactively prepare for accidents.

Keywords

Acknowledgement

This research was funded by the National Research Foundation of Korea (NRF) grant funded by the Eulji government Ministry of Science, ICT & Future Planning, grant number 2016R1C1B2012888. The funding source had no role in the collection, analyses, or interpretation of data; in the writing of the manuscript, or in the decision to publish the results.

References

  1. Ajerla D, Mahfuz S, Zulkernine F. A real-time patient monitoring framework for fall detection. Wireless Communications and Mobile Computing. 2019;1-13.
  2. Angal Y, Jagtap A. Fall detection system for older adults. Institute of Electrical and Electronics Engineers Conference. 2016;262-266.
  3. Babiuch M, Foltynek P, Smutny P. Using the ESP32 microcontroller for data processing. Institute of Electrical and Electronics Engineers Conference. 2019;1-6.
  4. Cook RL. Stochastic sampling in computer graphics. ACM Transactions on Graphics. 1986;5(1):51-72. https://doi.org/10.1145/7529.8927
  5. Cucchiara R, Prati A, Vezzani R. A multi-camera vision system for fall detection and alarm generation. Expert Systems. 2007;24(5):334-345. https://doi.org/10.1111/j.1468-0394.2007.00438.x
  6. Gupta HP, Chudgar HS, Mukherjee S, et al. A Continuous Hand Gestures Recognition Technique for Human-Machine Interaction Using Accelerometer and Gyroscope Sensors. IEEE Sensors Journal. 2016;16:6425-6432. https://doi.org/10.1109/JSEN.2016.2581023
  7. Huynh QT, Nguyen UD, Irazabal LB, et al. Optimization of an accelerometer and gyroscope-based fall detection algorithm. Journal of Sensors. 2015;1-8.
  8. Kerdegari H, Samsudin K, Rahman Ramli A, et al. Development of wearable human fall detection system using multilayer perceptron neural network. International Journal of Computational Intelligence Systems. 2013;6(1):127-136. https://doi.org/10.1080/18756891.2013.761769
  9. Kwolek B, Kepski M. Improving fall detection by the use of depth sensor and accelerometer. Neurocomputing. 2015;168:637-645. https://doi.org/10.1016/j.neucom.2015.05.061
  10. Mascret Q, Bielmann M, Fall C-L, et al. Real-time human physical activity recognition with low latency prediction feedback using raw IMU data. Institute of Electrical and Electronics Engineers Conference. 2018;239-242.
  11. Moncada LVV, & Mire LG. Preventing Falls in Older Persons. American Family Physician. 2017;96(4):240-247.
  12. Musci M, De Martini D, Blago N, et al. Online fall detection using recurrent neural networks on smart wearable devices. IEEE Transactions on Emerging Topics in Computing. 2020;9(3):1276-1289.
  13. Ren L, Peng Y. Research of Fall Detection and Fall Prevention Technologies: A Systematic Review. IEEE Access. 2019;7:77702-77722. https://doi.org/10.1109/ACCESS.2019.2922708
  14. Shi J, Chen D, Wang M. Pre-impact fall detection with CNN-based class activation mapping method. Sensors. 2020;20(17):4750.
  15. Usmani S, Saboor A, Haris M, et al. Latest Research Trends in Fall Detection and Prevention Using Machine Learning: A Systematic Review. Sensors (Basel). 2021;21(15):5134.
  16. Wang Y, Wu K, Ni LM. WiFall: Device-free fall detection by wireless networks. IEEE Transactions on Mobile Computing. 2016(2);581-594.
  17. Xu T, Zhou Y, Zhu J. New Advances and Challenges of Fall Detection Systems: A Survey. Applied Sciences. 2018;8(3):418.
  18. Zheng L, Zhao J, Dong F, et al. Fall Detection Algorithm Based on Inertial Sensor and Hierarchical Decision. Sensors (Basel). 2022;23(1):107.