Human Fall Detection from Acceleration Measurements Using a Recurrent Neural Network

  • T. TheodoridisEmail author
  • V. Solachidis
  • N. Vretos
  • P. Daras
Conference paper
Part of the IFMBE Proceedings book series (IFMBE, volume 66)


In this work, a method for human fall detection is presented based on Recurrent Neural Networks. The ability of these networks to process and encode sequential data, such as acceleration measurements from body-worn sensors, makes them ideal candidates for this task. Furthermore, since such networks can benefit greatly from additional data during training, the use of a data augmentation procedure involving random 3D rotations has been investigated. When evaluated on the publicly available URFD dataset, the proposed method achieved better results compared to other methods.


Human fall detection Recurrent neural network Data augmentation Acceleration 



This work was supported by the European Project: ICT4LIFE Grant no. 690090 within the H2020 Research and Innovation Programme.

Conflict of Interest

The authors declare that they have no conflict of interest.


  1. 1.
    World Health Organization WHO, Falls. Accessed 19 Sep 2017
  2. 2.
    Kalache A, Fu D, Yoshida S, et al (2007) World health organisation global report on falls prevention in older age. World Health OrganisationGoogle Scholar
  3. 3.
    Yuwono M, Moulton BD, Su SW et al (2012) Unsupervised machine-learning method for improving the performance of ambulatory fall-detection systems. Biomed Eng 11:9Google Scholar
  4. 4.
    Bourke AK, Ven P, Gamble M, et al (2010) Assessment of waist-worn tri-axial accelerometer based fall-detection algorithms using continuous unsupervised activities. In: Proceedings of the annual international conference of the IEEE engineering in medicine and biology society, pp 2782–278Google Scholar
  5. 5.
    Liu S-H, Cheng W-C (2012) Fall detection with the support vector machine during scripted and continuous unscripted activities. Sensors 12:12301–12316CrossRefGoogle Scholar
  6. 6.
    Kangas M, Vikman I, Wiklander J et al (2009) Sensitivity and specificity of fall detection in people aged 40 years and over. Gait Posture 29:571–574CrossRefGoogle Scholar
  7. 7.
    Koshmak GA, Linden M, Loutfi A (2013) Evaluation of the android-based fall detection system with physiological data monitoring. In: Proceedings of the annual international conference of the IEEE engineering in medicine and biology society, pp 1164–1168Google Scholar
  8. 8.
    Abbate S, Marco A, Bonatesta F et al (2012) A smartphone-based fall detection system. Perv Mobile Comput 8:883–899CrossRefGoogle Scholar
  9. 9.
    Vishwakarma V, Mandal C, Sural S (2007) Automatic detection of human fall in video. Pattern Recognit Mach Intel 616–623Google Scholar
  10. 10.
    Rougier C, Meunier J, St-Arnaud A et al (2011) Robust video surveillance for fall detection based on human shape deformation. IEEE Trans Circuits Syst Video Technol 21:611–622CrossRefGoogle Scholar
  11. 11.
    Mastorakis G, Makris D (2014) Fall detection system using Kinects infrared sensor. J Real-Time Image Process 9:635–646CrossRefGoogle Scholar
  12. 12.
    Rimminen H, Lindström J, Linnavuo M et al (2010) Detection of falls among the elderly by a floor sensor using the electric near field. IEEE Trans Inf Technol Biomed 14:1475–1476CrossRefGoogle Scholar
  13. 13.
    Alwan M, Rajendran P J, Kell S, et al (2006) A smart and passive floor-vibration based fall detector for elderly. In: Proceedings of information and communication technologies, vol 1, pp 1003–1007Google Scholar
  14. 14.
    Wang Y, Wu K, Ni LM (2017) Wifall: device-free fall detection by wireless networks. IEEE Trans Mob Comput 16:581–594CrossRefGoogle Scholar
  15. 15.
    Bourke AK, Obrien JV, Lyons GM (2007) Evaluation of a threshold-based tri-axial accelerometer fall detection algorithm. Gait Posture 26:194–199CrossRefGoogle Scholar
  16. 16.
    Kwolek B, Kepski M (2014) Human fall detection on embedded platform using depth maps and wireless accelerometer. Comput Methods Programs Biomed 117:489–501CrossRefGoogle Scholar
  17. 17.
    Cippitelli E, Gasparrini S, Gambi E, et al (2016) An integrated approach to fall detection and fall risk estimation based on RGB-depth and inertial sensors. In: Proceedings of the international conference on software development and technologies for enhancing accessibility and fighting info-exclusion, pp 246–253Google Scholar
  18. 18.
    Alzubi H, Ramzan N, Shahriar H, et al (2016) Optimization and evaluation of the human fall detection system. In: Proceedings of SPIE 10008, remote sensing technologies and applications in urban environments, p 1000816Google Scholar
  19. 19.
    Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9:1735–1780CrossRefGoogle Scholar
  20. 20.
    Gers FA, Schmidhuber J, Cummins F (1999) Learning to forget: continual prediction with LSTM. In: Proceedings of international conference on artificial neural networks, pp 850–855Google Scholar
  21. 21.
    UR Fall Detection Dataset. Accessed 19 Sep 2017

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  • T. Theodoridis
    • 1
    Email author
  • V. Solachidis
    • 1
  • N. Vretos
    • 1
  • P. Daras
    • 1
  1. 1.Information Technologies Institute, Centre for Research and Technology HellasThessalonikiGreece

Personalised recommendations