Skip to main content

Advertisement

SpringerLink
Log in

A comparison of accuracy of fall detection algorithms (threshold-based vs. machine learning) using waist-mounted tri-axial accelerometer signals from a comprehensive set of falls and non-fall trials

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

Falls are the leading cause of injury-related morbidity and mortality among older adults. Over 90 % of hip and wrist fractures and 60 % of traumatic brain injuries in older adults are due to falls. Another serious consequence of falls among older adults is the ‘long lie’ experienced by individuals who are unable to get up and remain on the ground for an extended period of time after a fall. Considerable research has been conducted over the past decade on the design of wearable sensor systems that can automatically detect falls and send an alert to care providers to reduce the frequency and severity of long lies. While most systems described to date incorporate threshold-based algorithms, machine learning algorithms may offer increased accuracy in detecting falls. In the current study, we compared the accuracy of these two approaches in detecting falls by conducting a comprehensive set of falling experiments with 10 young participants. Participants wore waist-mounted tri-axial accelerometers and simulated the most common causes of falls observed in older adults, along with near-falls and activities of daily living. The overall performance of five machine learning algorithms was greater than the performance of five threshold-based algorithms described in the literature, with support vector machines providing the highest combination of sensitivity and specificity.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

References

  1. Albert MV, Kording K, Herrmann M, Jayaraman A (2012) Fall classification by machine learning using mobile phones. PLoS One 7(5):e36556

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  2. Arnold CM, Faulkner RA (2007) The history of falls and the association of the timed up and go test to falls and near-falls in older adults with hip osteoarthritis. BMC Geriatr 7:17

    Article  PubMed  PubMed Central  Google Scholar 

  3. Aziz O, Park EJ, Mori G, Robinovitch SN (2012) Distinguishing near-falls from daily activities with wearable accelerometers and gyroscopes using support vector machines. In: Conference proceedings of IEEE engineering in medicine biology society 2012, pp 5837–5840

  4. Aziz O, Park EJ, Mori G, Robinovitch SN (2014) Distinguishing the causes of falls in humans using an array of wearable tri-axial accelerometers. Gait Posture 39(1):506–512

    Article  PubMed  Google Scholar 

  5. Aziz O, Robinovitch SN (2011) An analysis of the accuracy of wearable sensors for classifying the causes of falls in humans. IEEE Trans Neural Syst Rehabil Eng 19(6):670–676

    Article  PubMed  PubMed Central  Google Scholar 

  6. Bagala F, Becker C, Cappello A, Chiari L, Aminian K, Hausdorff JM, Zijlstra W, Klenk J (2012) Evaluation of accelerometer-based fall detection algorithms on real-world falls. PLoS One 7(5):e37062

    Article  PubMed  PubMed Central  Google Scholar 

  7. Bourke AK, O'Brien JV, Lyons GM (2007) Evaluation of a threshold-based tri-axial accelerometer fall detection algorithm. Gait Posture 26(2):194–199

    Article  CAS  PubMed  Google Scholar 

  8. Bourke AK, O'Donovan KJ, Olaighin G (2008) The identification of vertical velocity profiles using an inertial sensor to investigate pre-impact detection of falls. Med Eng Phys 30(7):937–946

    Article  CAS  PubMed  Google Scholar 

  9. Bourke AK, Scanaill CN, Culhane KM, Brien JVO, Lyons GM (2006) An optimum accelerometer configuration and simple algorithm for accurately detecting falls. In: Proceedings of the 24th IASTED international conference on Biomedical engineering. ACTA Press, Innsbruck

  10. Bourke AK, van de Ven P, Gamble M, O'Connor R, Murphy K, Bogan E, McQuade E, Finucane P, Olaighin G, Nelson J (2010) Evaluation of waist-mounted tri-axial accelerometer based fall-detection algorithms during scripted and continuous unscripted activities. J Biomech 43(15):3051–3057

    Article  CAS  PubMed  Google Scholar 

  11. Bourke AK, van de Ven PW, Chaya AE, GM OL, Nelson J (2008) Testing of a long-term fall detection system incorporated into a custom vest for the elderly. In: Conference Proceedings of IEEE engineering in medicine and biology society 2008, pp 2844–2847

  12. Boyle J, Karunanithi M (2008) Simulated fall detection via accelerometers. In: Conference Proceedings of IEEE engineering in medicine and biology society 2008, pp 1274–1277

  13. Chao PK, Chan HL, Tang FT, Chen YC, Wong MK (2009) A comparison of automatic fall detection by the cross-product and magnitude of tri-axial acceleration. Physiol Meas 30(10):1027–1037

    Article  PubMed  Google Scholar 

  14. Chen J, Kwong K, Chang D, Luk J, Bajcsy R (2005) Wearable sensors for reliable fall detection. In: Conference proceedings of IEEE engineering in medicine and biology society 4, pp 3551–3554

  15. Diaz A, Prado M, Roa LM, Reina-Tosina J, Sanchez G (2004) Preliminary evaluation of a full-time falling monitor for the elderly. In: Conference proceedings of IEEE engineering in medicine and biology society 3, pp 2180–2183

  16. Herman M, Gallagher E, Scott VJ (2006) The evolution of seniors falls prevention in British Columbia. BC Ministry of Health Services, Victoria

    Google Scholar 

  17. Kangas M, Konttila A, Lindgren P, Winblad I, Jamsa T (2008) Comparison of low-complexity fall detection algorithms for body attached accelerometers. Gait Posture 28(2):285–291

    Article  PubMed  Google Scholar 

  18. Kau LJ, Chen CS (2015) A smart phone-based pocket fall accident detection, positioning, and rescue system. IEEE J Biomed Health Inform 19(1):44–56

    Article  PubMed  Google Scholar 

  19. Kern N, Schiele B, Schmidt A (2007) Recognizing context for annotating a live life recording. Personal Ubiquitous Comput. 11(4):251–263

    Article  Google Scholar 

  20. King MB, Tinetti ME (1995) Falls in community-dwelling older persons. J Am Geriatr Soc 43(10):1146–1154

    Article  CAS  PubMed  Google Scholar 

  21. Lee JK, Robinovitch SN, Park EJ (2015) Inertial sensing-based pre-impact detection of falls involving near-fall scenarios. IEEE Trans Neural Syst Rehabil Eng 23(2):258–266

    Article  PubMed  Google Scholar 

  22. Lindemann U, Hock A, Stuber M, Keck W, Becker C (2005) Evaluation of a fall detector based on accelerometers: a pilot study. Med Biol Eng Comput 43(5):548–551

    Article  CAS  PubMed  Google Scholar 

  23. Mallinson WJ, Green MF (1985) Covert muscle injury in aged patients admitted to hospital following falls. Age Ageing 14(3):174–178

    Article  CAS  PubMed  Google Scholar 

  24. Nevitt MC, Cummings SR, Kidd S, Black D (1989) Risk factors for recurrent nonsyncopal falls. A prospective study. JAMA 261(18):2663–2668

    Article  CAS  PubMed  Google Scholar 

  25. Noury N, Galay A, Pasquier J, Ballussaud M (2008) Preliminary investigation into the use of autonomous fall detectors. In: Conference proceedings of IEEE engineering in medicine and biology society 2008, pp 2828–2831

  26. Noury N, Rumeau P, Bourke AK, ÓLaighin G, Lundy JE (2008) A proposal for the classification and evaluation of fall detectors. IRBM 29(6):340–349

    Article  Google Scholar 

  27. Robinovitch SN, Feldman F, Yang Y, Schonnop R, Leung PM, Sarraf T, Sims-Gould J, Loughin M (2013) Video capture of the circumstances of falls in elderly people residing in long-term care: an observational study. Lancet 381(9860):47–54

    Article  PubMed  Google Scholar 

  28. Srygley JM, Herman T, Giladi N, Hausdorff JM (2009) Self-report of missteps in older adults: a valid proxy of fall risk? Arch Phys Med Rehabil 90(5):786–792

    Article  PubMed  PubMed Central  Google Scholar 

  29. Tinetti ME, Williams CS (1998) The effect of falls and fall injuries on functioning in community-dwelling older persons. J Gerontol A Biol Sci Med Sci 53(2):M112–M119

    Article  CAS  PubMed  Google Scholar 

  30. Vellas B, Cayla F, Bocquet H, de Pemille F, Albarede JL (1987) Prospective study of restriction of activity in old people after falls. Age Ageing 16(3):189–193

    Article  CAS  PubMed  Google Scholar 

  31. Weiss A, Shimkin I, Giladi N, Hausdorff JM (2010) Automated detection of near falls: algorithm development and preliminary results. BMC Res Notes 3:62

    Article  PubMed  PubMed Central  Google Scholar 

  32. Weiss GM, Provost F (2003) Learning when training data are costly: the effect of class distribution on tree induction. J Artif Intell Res 19(1):315–354

    Google Scholar 

  33. Wild D, Nayak US, Isaacs B (1981) How dangerous are falls in old people at home? Br Med J (Clin Res Ed) 282(6260):266–268

    Article  CAS  Google Scholar 

Download references

Acknowledgments

This work was supported by team grants from the Canadian Institutes of Health Research (Funding Reference Numbers: AMG-100487 and TIR-103945). SNR was also supported by the Canada Research Chairs program. The funding agency had no direct role in the design and conduct of the study; the collection, management, analysis, and interpretation of the data; or the preparation, review, or approval of the manuscript.

Author information

Authors and Affiliations

  1. Injury Prevention and Mobility Laboratory, Simon Fraser University, Burnaby, BC, Canada

    Omar Aziz & Stephen N. Robinovitch

  2. Department of Biomedical Physiology and Kinesiology, Simon Fraser University, Burnaby, BC, Canada

    Stephen N. Robinovitch

  3. School of Engineering Science, Simon Fraser University, Burnaby, BC, Canada

    Omar Aziz & Stephen N. Robinovitch

  4. School of Computing Science, Simon Fraser University, Burnaby, BC, Canada

    Greg Mori

  5. School of Mechatronic Systems Engineering, Simon Fraser University, Surrey, BC, Canada

    Omar Aziz, Magnus Musngi & Edward J. Park

Authors
  1. Omar Aziz
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Magnus Musngi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Edward J. Park
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Greg Mori
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Stephen N. Robinovitch
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Omar Aziz.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Aziz, O., Musngi, M., Park, E.J. et al. A comparison of accuracy of fall detection algorithms (threshold-based vs. machine learning) using waist-mounted tri-axial accelerometer signals from a comprehensive set of falls and non-fall trials. Med Biol Eng Comput 55, 45–55 (2017). https://doi.org/10.1007/s11517-016-1504-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-016-1504-y

Keywords

Search

Navigation