An open vibration and pressure platform for fall prevention with a reinforcement learning agent

Abstract

The risk of falls among the elderly population is one that may lead to dire consequences. It can significantly affect the quality of life of the victims and even lead to their premature death. Many technological tools have been proposed in the literature to detect falls, but little effort has been done regarding their prevention. In this paper, our research team proposes an inexpensive open vibration platform equipped with pressure sensors. The platform is built from easily available electronic components to be used as a tool by physiotherapists in order to help them in their evaluation of the postural control of individuals at risk of postural imbalance. The platform has been built to be easily reproducible by the scientific community. Moreover, the computer code necessary to make it work is fully open source and can be used in any non-commercial applications. A first version of the platform was tested with 7 healthy human participants. A simple reinforcement learning agent was deployed and tested to automatically calibrate the vibration motors for optimal stimulation. The agent exploited computer vision to capture the data from a force platform commercially available and use it as ground truth. Finally, a second version of the platform was built and is presented in the paper. That version is currently being validated clinically with both healthy and impaired human participants. The preliminary data are presented in this paper.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Notes

  1. 1.

    https://github.com/LIARALab

  2. 2.

    https://www.arduino.cc/en/Guide/Introduction

  3. 3.

    https://redbear.cc/product/wifi-ble/redbear-duo.html

  4. 4.

    www.autodesk.com/products/eagle/overview

  5. 5.

    www.voltera.io

  6. 6.

    https://www.autodesk.com/products/fusion-360/overview

  7. 7.

    www.lulzbot.com/store/printers/lulzbot-taz-6

  8. 8.

    www.mathworks.com/products/matlab.html

References

  1. 1.

    Roberts KL, Allen HA (2016) Perception and cognition in the ageing brain: a brief review of the short-and long-term links between perceptual and cognitive decline. Front Aging Neurosci 8:39

    Google Scholar 

  2. 2.

    Schmidt L, Kerkhoff G, Utz KS (2016) Sensory stimulation in post-stroke postural imbalance: a novel treatment approach? Clin Neurophysiol 127(1):21–22

    Google Scholar 

  3. 3.

    Najafi B, Talal TK, Grewal GS, Menzies R, Armstrong DG, Lavery LA (2017) Using plantar electrical stimulation to improve postural balance and plantar sensation among patients with diabetic peripheral neuropathy: a randomized double blinded study. J Diabetes Sci Technol 11(4):693–701

    Google Scholar 

  4. 4.

    Timar B, Timar R, Gaițua L, Oancea C, Levai C, Lungeanu D (2016) The impact of diabetic neuropathy on balance and on the risk of falls in patients with type 2 diabetes mellitus: a cross-sectional study. PLoS One 11(4):e0154654

    Google Scholar 

  5. 5.

    Melzer I, Benjuya N, Kaplanski J (2004) Postural stability in the elderly: a comparison between fallers and non-fallers. Age Ageing 33(6):602–607

    Google Scholar 

  6. 6.

    Lapierre N, Neubauer N, Miguel-Cruz A, Rincon AR, Liu L, Rousseau J (2018) The state of knowledge on technologies and their use for fall detection: a scoping review. Int J Med Inform 111:58–71

    Google Scholar 

  7. 7.

    Rajagopalan R, Litvan I, Jung T-P (2017) Fall prediction and prevention systems: recent trends, challenges, and future research directions. Sensors 17(11):2509

    Google Scholar 

  8. 8.

    Farshchian BA, Dahl Y (2015) The role of ICT in addressing the challenges of age-related falls: a research agenda based on a systematic mapping of the literature. Pers Ubiquit Comput 19(3–4):649–666

    Google Scholar 

  9. 9.

    Brenton-Rule A et al (2012) Reliability of the TekScan MatScan®system for the measurement of postural stability in older people with rheumatoid arthritis. J Foot Ankle Res 5(1):21

    Google Scholar 

  10. 10.

    de Oliveira MR, da Silva RA, Dascal JB, Teixeira DC (2014) Effect of different types of exercise on postural balance in elderly women: a randomized controlled trial. Arch Gerontol Geriatr 59(3):506–514

    Google Scholar 

  11. 11.

    Oliveira MR et al (2018) One-legged stance sway of older adults with and without falls. PLoS One 13(9):e0203887

    Google Scholar 

  12. 12.

    Nguyen U-SDT, Kiel DP, Li W, Galica AM, Kang HG, Casey VA, Hannan MT (2012) Correlations of clinical and laboratory measures of balance in older men and women. Arthritis Care Res 64(12):1895–1902

    Google Scholar 

  13. 13.

    Rhea CK et al (2011) Noise and complexity in human postural control: interpreting the different estimations of entropy. PLoS One 6(3):e17696

    Google Scholar 

  14. 14.

    Toosizadeh N, Ehsani H, Miramonte M, Mohler J (2018) Proprioceptive impairments in high fall risk older adults: the effect of mechanical calf vibration on postural balance. Biomed Eng Online 17(1):51

    Google Scholar 

  15. 15.

    Roll R, Kavounoudias A, Roll J-P (2002) Cutaneous afferents from human plantar sole contribute to body posture awareness. Neuroreport 13(15):1957–1961

    Google Scholar 

  16. 16.

    Kavounoudias A, Roll R, Roll J-P (2001) Foot sole and ankle muscle inputs contribute jointly to human erect posture regulation. J Physiol 532(3):869–878

    Google Scholar 

  17. 17.

    Zarkou A, Lee SCK, Prosser LA, Jeka JJ (2020) Foot and ankle somatosensory deficits affect balance and motor function in children with cerebral palsy. Front Hum Neurosci 14

  18. 18.

    Lafontaine V, Bouchard K, Gagnon JM, Dallaire M, Gaboury S, da Silva RA, Beaulieu LD (2019) An open vibration platform to evaluate postural control using a simple reinforcement learning agent. Procedia Comput Sci 151:194–201

    Google Scholar 

  19. 19.

    Littman ML (2015) Reinforcement learning improves behaviour from evaluative feedback. Nature 521(7553):445

    Google Scholar 

  20. 20.

    Puterman ML (2014) Markov decision processes: discrete stochastic dynamic programming. John Wiley & Sons

  21. 21.

    Auer P, Cesa-Bianchi N, Fischer P (2002) Finite-time analysis of the multiarmed bandit problem. Mach Learn 47(2–3):235–256

    MATH  Google Scholar 

  22. 22.

    Pulli K, Baksheev A, Kornyakov K, Eruhimov V (2012) Real-time computer vision with OpenCV. Commun ACM 55(6):61–69

    Google Scholar 

  23. 23.

    Fontecha J, Navarro FJ, Hervás R, Bravo J (2013) Elderly frailty detection by using accelerometer-enabled smartphones and clinical information records. Pers Ubiquit Comput 17(6):1073–1083

    Google Scholar 

Download references

Acknowledgments

We thank the Canadian Foundation for Innovation (CFI) whose contribution provided the necessary equipment to build the prototypes.

Funding

The authors received grants from the Fondation de l’UQAC and to the Centre Intersectoriel en Santé Durable (CISD) that enabled them to conduct this research.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Kevin Bouchard.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Lafontaine, V., Lapointe, P., Bouchard, K. et al. An open vibration and pressure platform for fall prevention with a reinforcement learning agent. Pers Ubiquit Comput 25, 7–19 (2021). https://doi.org/10.1007/s00779-020-01416-0

Download citation

Keywords

  • Sensors
  • Vibration motors
  • Force platform
  • Postural control
  • Reinforcement learning
  • Technology for health