DOI QR코드

DOI QR Code

Threshold-based Pre-impact Fall Detection and its Validation Using the Real-world Elderly Dataset

임계값 기반 충격 전 낙상검출 및 실제 노인 데이터셋을 사용한 검증

  • Dongkwon Kim (Department of Biomedical Engineering and Institute of Medical Engineering, Yonsei University) ;
  • Seunghee Lee (Department of Biomedical Engineering and Institute of Medical Engineering, Yonsei University) ;
  • Bummo Koo (Department of Biomedical Engineering and Institute of Medical Engineering, Yonsei University) ;
  • Sumin Yang (Department of Biomedical Engineering and Institute of Medical Engineering, Yonsei University) ;
  • Youngho Kim (Department of Biomedical Engineering and Institute of Medical Engineering, Yonsei University)
  • 김동권 (연세대학교 의공학과, 연세대학교 의료공학연구소) ;
  • 이승희 (연세대학교 의공학과, 연세대학교 의료공학연구소) ;
  • 구범모 (연세대학교 의공학과, 연세대학교 의료공학연구소) ;
  • 양수민 (연세대학교 의공학과, 연세대학교 의료공학연구소) ;
  • 김영호 (연세대학교 의공학과, 연세대학교 의료공학연구소)
  • Received : 2023.10.24
  • Accepted : 2023.11.14
  • Published : 2023.12.31

Abstract

Among the elderly, fatal injuries and deaths are significantly attributed to falls. Therefore, a pre-impact fall detection system is necessary for injury prevention. In this study, a robust threshold-based algorithm was proposed for pre-impact fall detection, reducing false positives in highly dynamic daily-living movements. The algorithm was validated using public datasets (KFall and FARSEEING) that include the real-world elderly fall. A 6-axis IMU sensor (Movella Dot, Movella, Netherlands) was attached to S2 of 20 healthy adults (aged 22.0±1.9years, height 164.9±5.9cm, weight 61.4±17.1kg) to measure 14 activities of daily living and 11 fall movements at a sampling frequency of 60Hz. A 5Hz low-pass filter was applied to the IMU data to remove high-frequency noise. Sum vector magnitude of acceleration and angular velocity, roll, pitch, and vertical velocity were extracted as feature vector. The proposed algorithm showed an accuracy 98.3%, a sensitivity 100%, a specificity 97.0%, and an average lead-time 311±99ms with our experimental data. When evaluated using the KFall public dataset, an accuracy in adult data improved to 99.5% compared to recent studies, and for the elderly data, a specificity of 100% was achieved. When evaluated using FARSEEING real-world elderly fall data without separate segmentation, it showed a sensitivity of 71.4% (5/7).

Keywords

Acknowledgement

본 연구는 산업통상자원부와 한국산업기술진흥원의 "R&D재발견프로젝트"의 지원을 받아 수행된 연구결과이며(과제번호: P0026060) 또한 2023년도 교육부의 재원으로 한국연구재단의 지원을 받아 수행된 지자체-대학 협력기반 지역혁신 사업의 결과입니다(2022RIS-005).

References

  1. World Health Organization. Step safely: strategies for preventing and managing falls across the life-course. 2021. 
  2. Vieira ER, Palmer RC, Chaves PH. Prevention of falls in older people living in the community. Bmj, 2016;353. 
  3. Dionyssiotis Y, Dontas IA, Economopoulos D, Lyritis GP. Rehabilitation after falls and fractures. J Musculoskelet Neuronal Interact. 2008;8(3):244-250. 
  4. Schacht E, Richy F, Reginster J. The therapeutic effects of alfacalcidol on bone strength, muscle metabolism and prevention of falls and fractures. Journal of Musculoskeletal and Neuronal Interactions. 2005;5(3):273. 
  5. Hanssens L, Reginster JY. Relevance of bone mineral density, bone quality and falls in reduction of vertebral and non-vertebral fractures. Journal of Musculoskeletal and Neuronal Interactions. 2003;3(3):189-193. 
  6. Elliott S, Painter J, Hudson S. Living alone and fall risk factors in community-dwelling middle age and older adults. Journal of community health. 2009;34:301-310.  https://doi.org/10.1007/s10900-009-9152-x
  7. Noury N, Herve T, Rialle V, Virone G, Mercier E, Morey G, Porcheron T. Monitoring behavior in home using a smart fall sensor and position sensors. In 1st Annual International IEEE-EMBS Special Topic Conference on Microtechnologies in Medicine and Biology. 2000;607-610. 
  8. Williams G, Doughty K, Cameron K, Bradley DA. A smart fall and activity monitor for telecare applications. In Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol. 20 Biomedical Engineering Towards the Year 2000 and Beyond. 1998;3:1151-1154. 
  9. Parker MJ, Gillespie WJ, Gillespie LD. Effectiveness of hip protectors for preventing hip fractures in elderly people: systematic review. Bmj. 2006;332(7541):571-574.  https://doi.org/10.1136/bmj.38753.375324.7C
  10. Derler S, Spierings AB, Schmitt KU. Anatomical hip model for the mechanical testing of hip protectors. Medical engineering & physics. 2005;27(6):475-485.  https://doi.org/10.1016/j.medengphy.2005.02.001
  11. Van Thanh P, Tran DT, Nguyen DC, Duc Anh N. Nhu Dinh D, El-Rabaie S, Sandrasegaran K. Development of a real-time, simple and high-accuracy fall detection system for elderly using 3-DOF accelerometers. Arabian Journal for Science and Engineering. 2019;44:3329-3342.  https://doi.org/10.1007/s13369-018-3496-4
  12. Zhong Z, Chen F, Zhai Q, Fu Z, Ferreira JP, Liu Y, Liu T. A real-time pre-impact fall detection and protection system. In 2018 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM). 2018;1039-1044. 
  13. Ahn S, Choi D, Kim J, Kim S, Jeong Y, Jo M, Kim Y. Optimization of a pre-impact fall detection algorithm and development of hip protection airbag system. Sens. Mater. 2018;30(8):1743-1752.  https://doi.org/10.18494/SAM.2018.1876
  14. Kim S, Kim Y, Kwon T, Kim D, Kim N. Dynamic Characterization of Fall for Development of Fracture Prevention System. Journal of Biomedical Engineering Research. 2007;28(6):811-816.  https://doi.org/10.9718/JBER.2007.28.6.811
  15. Tamura T, Yoshimura T, Sekine M, Uchida M, Tanaka O. A wearable airbag to prevent fall injuries. IEEE Transactions on Information Technology in Biomedicine. 2009;13(6):910-914.  https://doi.org/10.1109/TITB.2009.2033673
  16. Jung H, Koo B, Kim J, Kim T, Nam Y, Kim Y. Enhanced algorithm for the detection of preimpact fall for wearable airbags. Sensors. 2020;20(5):1277. 
  17. Yu X, Jang J, Xiong S. A large-scale open motion dataset (KFall) and benchmark algorithms for detecting pre-impact fall of the elderly using wearable inertial sensors. Frontiers in Aging Neuroscience. 2021;13:692865. 
  18. Sucerquia A, Lopez JD, Vargas-Bonilla JF, SisFall: A fall and movement dataset. Sensors. 2017;17(1):198. 
  19. Ketcham CJ, Seidler RD, Van Gemmert AW, Stelmach GE. Age-related kinematic differences as influenced by task difficulty, target size, and movement amplitude. The Journals of Gerontology Series B: Psychological Sciences and Social Sciences. 2002;57(1):P54-P64.  https://doi.org/10.1093/geronb/57.1.P54
  20. Alizadeh J, Bogdan M, Classen J, Fricke C. Support vector machine classifiers show high generalizability in automatic fall detection in older adults. Sensors. 2021;21(21):7166. 
  21. Klenk J, Schwickert L, Palmerini L, Mellone S, Bourke A, Ihlen EA, FARSEEING Consortium. The FARSEEING realworld fall repository: a large-scale collaborative database to collect and share sensor signals from real-world falls. European review of aging and physical activity. 2016;13:1-7.  https://doi.org/10.1186/s11556-016-0168-9
  22. Lee JK. Study on vertical velocity-based pre-impact fall detection. Journal of Sensor Science and Technology. 2014;23(4):251-258.  https://doi.org/10.5369/JSST.2014.23.4.251
  23. Degen T, Jaeckel H, Rufer M, Wyss S. SPEEDY: A Fall Detector in a Wrist Watch. In ISWC. 2003;3:184-187.  https://doi.org/10.1109/ISWC.2003.1241410
  24. Bourke AK, O'Donovan KJ, Nelson J, OLaighin GM. Fall-detection through vertical velocity thresholding using a triaxial accelerometer characterized using an optical motion-capture system. In 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 2008;2832-2835. 
  25. Kim Y, Jung H, Koo B, Kim J, Kim T, Nam Y. Detection of pre-impact falls from heights using an inertial measurement unit sensor. 2020;Sensors, 20(18):5388.