Development of a Strategy to Predict and Detect Falls Using Wearable Sensors

  • Nuno Ferrete RibeiroEmail author
  • João André
  • Lino Costa
  • Cristina P. Santos
Mobile & Wireless Health
Part of the following topical collections:
  1. Mobile & Wireless Health


Falls are a prevalent problem in actual society. Some falls result in injuries and the cost associated with their treatment is high. This is a complex problem that requires several steps in order to be tackled. Firstly, it is crucial to develop strategies that recognize the locomotion mode, indicating the state of the subject in various situations. This article aims to develop a strategy capable of identifying normal gait, the pre-fall condition, and the fall situation, based on a wearable system (IMUs-based). This system was used to collect data from healthy subjects that mimicked falls. The strategy consists, essentially, in the construction and use of classifiers as tools for recognizing the locomotion modes. Two approaches were explored. Associative Skill Memories (ASMs) based classifier and a Convolutional Neural Network (CNN) classifier based on deep learning. Finally, these classifiers were compared, providing for a tool with a good accuracy in recognizing the locomotion modes. Results have shown that the accuracy of the classifiers was quite acceptable. The CNN presented the best results with 92.71% of accuracy considering the pre-fall step different from normal steps, and 100% when not considering.


Inertial Measurement Units (IMUs) Gait analysis Principal Component Analysis (PCA) Associative Skill Memories (ASMs) Convolutional Neural Network (CNN) Deep learning 



This work has been supported by the FCT - Fundação para a Ciência e Tecnologia - with the scholarship reference PD/BD/141515/2018, by the FEDER funds through the COMPETE 2020 - Programa Operacional Competitividade e Internacionalização (POCI) and P2020 with the Reference Project EML under Grant POCI-01-0247-FEDER-033067, and through the COMPETE 2020 POCI with the Reference Project under Grant POCI-01-0145-FEDER-006941.

Compliance with Ethical Standards

Conflict of interests

The authors declare that they have no conflict of interest.

Ethical approval

All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.

Informed Consent

Informed consent was obtained from all individual participants included in the study.


  1. 1.
    Rueterbories, J., Spaich, E. G., Larsen, B., and Andersen, O. K., Methods for gait event detection and analysis in ambulatory systems. Med. Eng. Phys. 32(6):545–552, 2010. Scholar
  2. 2.
    Fish, D. J., Pathology forum: Characteristic gait patterns in neuromuscular pathologies. Journal of Prosthetics and Orthotics 9(2):163–167, 1997.CrossRefGoogle Scholar
  3. 3.
    Amboni, M., Iuppariello, L., Iavarone, A., Fasano, A., Palladino, R., Rucco, R., Picillo, M., Lista, I., Varriale, P., Vitale, C., Cesarelli, M., Sorrentino, G., and Barone, P., Step length predicts executive dysfunction in Parkinson’s disease: a 3-year prospective study. J. Neurol. 265(10):2211–2220, 2018. Scholar
  4. 4.
    Liparoti, M., Della Corte, M., Rucco, R., Sorrentino, P., Sparaco, M., Capuano, R., Minino, R., Lavorgna, L., Agosti, V., Sorrentino, G., and Bonavita, S., Gait abnormalities in minimally disabled people with multiple sclerosis: a 3D-motion analysis study. Mult. Scler. Relat. Disord. 29:100–107, 2019. Scholar
  5. 5.
    Rucco, R., Agosti, V., Jacini, F., Sorrentino, P., Varriale, P., De Stefano, M., Milan, G., Montella, P., and Sorrentino, G., Spatio-temporal and kinematic gait analysis in patients with Frontotemporal dementia and Alzheimer’s disease through 3D motion capture. Gait Posture 52:312–317, 2017. Scholar
  6. 6.
    Sorrentino, P., Barbato, A., Del Gaudio, L., Rucco, R., Varriale, P., Sibilio, M., Strazzullo, P., Sorrentino, G., and Agosti, V., Impaired gait kinematics in type 1 Gaucher’s disease. J. Park. Dis. 6(1): 191–195, 2016. Scholar
  7. 7.
    Barone, P., Aarsland, D., Burn, D., Emre, M., Kulisevsky, J., and Weintraub, D.: Cognitive impairment in nondemented Parkinson’s disease., 2011
  8. 8.
    Chen, P. H., Wang, R. L., Liou, D. J., and Shaw, J. S.: Gait disorders in Parkinson’s disease: Assessment and management., 2013
  9. 9.
    Thompson, A.J., Toosy, A.T., and Ciccarelli, O., Pharmacological management of symptoms in multiple sclerosis: current approaches and future directions. Lancet Neurol. 9(12):1182–1199, 2010. Scholar
  10. 10.
    Braak, H., Thal, D. R., Ghebremedhin, E., and Del Tredici, K., Stages of the pathologic process in alzheimer disease: Age categories from 1 to 100 years. J. Neuropathol. Exp. Neurol. 70(11):960–969, 2011. Scholar
  11. 11.
    Brady, R. O., Kanfer, J. N., and Shapiro, D., Metabolism of glucocerebrosides II. Evidence of an enzymatic deficiency in Gaucher’s disease. Biochem. Biophys. Res. Commun. 18(2):221–225, 1965. Scholar
  12. 12.
    Muro-de-la Herran, A., García-Zapirain, B., and Méndez-Zorrilla, A., Gait analysis methods: an overview of wearable and non-wearable systems, highlighting clinical applications. Sensors (Switzerland) 14(2):3362–3394, 2014. Scholar
  13. 13.
    Berry, S. D., and Miller, R., Falls: Epidemiology, pathophysiology, and relationship to fracture. Curr. Osteoporos. Rep. 6(4):149–154, 2008.CrossRefGoogle Scholar
  14. 14.
    Medicine, I., and Prevention, D.: The second fifty years: Promoting health and preventing disability national academies press, 1992Google Scholar
  15. 15.
    Khusainov, R., Azzi, D., Achumba, I. E., and Bersch, S. D., Real-time human ambulation, activity, and physiological monitoring: taxonomy of issues, techniques, applications, challenges and limitations. Sensors (Basel, Switzerland) 13(10):12852–12902, 2013. Scholar
  16. 16.
    Hsieh, C. Y., Liu, K. C., Huang, C. N., Chu, W. C., and Chan, C. T.: Novel hierarchical fall detection algorithm using a multiphase fall model. Sensors (Switzerland) 17(2)., 2017
  17. 17.
    Burns, E. R., Stevens, J. A., and Lee, R., The direct costs of fatal and non-fatal falls among older adults — United States. J. Safety Res. 58:99–103, 2016. Scholar
  18. 18.
    Cates, B., Sim, T., Heo, H. M., Kim, B., Kim, H., and Mun, J. H.: A novel detection model and its optimal features to classify falls from low- and high-acceleration activities of daily life using an insole sensor system. Sensors (Switzerland) 18(4)., 2018
  19. 19.
    SENSO 2012: SENSO supports, 2012Google Scholar
  20. 20.
    Tunstall Healthcare: iVi intelligent pendant, 2017Google Scholar
  21. 21.
    Tamura, T., Yoshimura, T., Sekine, M., Uchida, M., and Tanaka, O., A wearable airbag to prevent fall injuries. IEEE Trans. Inf. Technol. Biomed. 13(6):910–914, 2009. Scholar
  22. 22.
    Ribeiro, N. F., and Santos, C. P.: An intuitive visual interface for a real-time monitoring system for human gait using imus. In: 2017 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)., pp. 153–158, 2017.
  23. 23.
    Macedo, P., Afonso, J. A., Rocha, L. A., and Simoes, R.: A telerehabilitation system based on wireless motion capture sensors. In: PhyCS - Proceedings of the International Conference on Physiological Computing Systems., pp. 55–62, 2014.
  24. 24.
    Ribeiro, N. F., and Santos, C. P.: Inertial measurement units: a brief state of the art on gait analysis. In: 2017 IEEE 5th Portuguese Meeting on Bioengineering (ENBENG)., pp. 1–4, 2017.
  25. 25.
    Igual, R., Medrano, C., and Plaza, I., Challenges, issues and trends in fall detection systems. BioMedical Engineering OnLine 12(1):66, 2013. Scholar
  26. 26.
    Rucco, R., Sorriso, A., Liparoti, M., Ferraioli, G., Sorrentino, P., Ambrosanio, M., and Baselice, F.: Type and location of wearable sensors for monitoring falls during static and dynamic tasks in healthy elderly: a review., 2018
  27. 27.
    Kangas, M., Konttila, A., Winblad, I., and Jamsa, T.: Determination of simple thresholds for accelerometry-based parameters for fall detection. In: 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society., pp. 1367–1370, 2007.
  28. 28.
    Boissy, P., Choquette, S., Hamel, M., and Noury, N., User-based motion sensing and fuzzy logic for automated fall detection in older adults. Telemedicine Journal and E-Health: the Official Journal of the American Telemedicine Association 13(6):683–693, 2007. Scholar
  29. 29.
    Lai, C. F., Chang, S. Y., Chao, H. C., and Huang, Y. M., Detection of cognitive injured body region using multiple triaxial accelerometers for elderly falling. IEEE Sensors J. 11(3):763–770, 2011. Scholar
  30. 30.
    Bianchi, F., Redmond, S.J., Narayanan, M.R., Cerutti, S., and Lovell, N.H., Barometric pressure and triaxial accelerometry-based falls event detection. IEEE Trans. Neural Syst. Rehabil. Eng. 18(6):619–627, 2010. Scholar
  31. 31.
    Klucken, J., Barth, J., Kugler, P., Schlachetzki, J., Henze, T., Marxreiter, F., Kohl, Z., Steidl, R., Hornegger, J., Eskofier, B., and Winkler, J., Unbiased and mobile gait analysis detects motor impairment in Parkinson’s disease. PLOS ONE 8(2):1–9, 2013. Scholar
  32. 32.
    Kim, E.A.N., Mordiffi, S.Z., Bee, W.H., Devi, K., and Evans, D., Evaluation of three fall-risk assessment tools in an acute care setting. J. Adv. Nurs. 60(4):427–435, 2007. Scholar
  33. 33.
    Leone, A., Rescio, G., Caroppo, A., and Siciliano, P., A wearable EMG-based system pre-fall detector. Procedia Engineering 120:455–458, 2015. Scholar
  34. 34.
    Andrė, J., Santos, C., and Costa, L., Skill memory in biped locomotion: Using perceptual information to predict task outcome. Journal of Intelligent and Robotic Systems: Theory and Applications 82(3-4):379–397, 2016. Scholar
  35. 35.
    Jimenez, A. R., Seco, F., Prieto, C., and Guevara, J.: A comparison of pedestrian dead-reckoning algorithms using a low-cost mems imu. In: 2009 IEEE International Symposium on Intelligent Signal Processing., pp. 37–42, 2009.
  36. 36.
    InvenSense: MPU-6000 and MPU-6050 Product specification. Tech. Rep. 408 InvenSense Inc, 2013Google Scholar
  37. 37.
    Honeywell: 3-Axis Digital Compass IC HMC5883L. Tech. rep., Honeywell International Inc, 2011Google Scholar
  38. 38.
    Ribeiro, N. F., Ferreira, C., Reis, L. P., Silva, H., Macedo, P., Rocha, L., and Santos, C. P.: Validation of a knee angle measurement system based on IMUs. In: CLAWAR 2017 - The 20th International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines., pp. 645–652. World Scientific, Porto, 2017.
  39. 39.
    Kavanagh, J. J., and Menz, H.B., Accelerometry: a technique for quantifying movement patterns during walking. Gait Posture 28(1):1–15, 2008. Scholar
  40. 40.
    Lockhart, T. E., Soangra, R., Zhang, J., and Wu, X., Wavelet based automated postural event detection and activity classification with single IMU. Biomed. Sci. Instrum. 49(Cdc 2010):224–233, 2013. Scholar
  41. 41.
    Jolliffe, I. T., Principal Component Analysis. 2 ed. Berlin: Springer, 2002. Scholar
  42. 42.
    Wei-min, L., and Chein-I, C.: Variants of principal components analysis. In: 2007 IEEE International Geoscience and Remote Sensing Symposium, pp. 1083–1086, 2007.
  43. 43.
    Ijspeert, A. J., Nakanishi, J., Hoffmann, H., Pastor, P., and Schaal, S., Dynamical movement primitives: Learning attractor models for motor behaviors. Neural Comput. 25(2):328–373, 2013. PMID: 23148415.CrossRefPubMedGoogle Scholar
  44. 44.
    Pastor, P., Kalakrishnan, M., Meier, F., Stulp, F., Buchli, J., Theodorou, E., and Schaal, S., From dynamic movement primitives to associative skill memories. Robot. Auton. Syst. 61(4):351–361, 2013. Scholar
  45. 45.
    Pastor, P., Kalakrishnan, M., Righetti, L., and Schaal, S.: Towards associative skill memories. In: IEEE-RAS International Conference on Humanoid Robots, pp. 309–315, 2012.
  46. 46.
    Hubel, H., and Wiesel, T., Receptive fields of single neurones in the cat’s striate cortex. J. Physiol. 148: 574–591, 1959. Scholar
  47. 47.
    MathWorks: Deep learning: 3 things you need to know, 2017Google Scholar
  48. 48.
    Murphy, K.P., Machine learning: a Probabilistic Perspective. Cambridge: MIT Press, 2012. Scholar
  49. 49.
    Birenbaum, A., and Greenspan, H., Multi-view longitudinal CNN for multiple sclerosis lesion segmentation. Eng. Appl. Artif. Intel. 65:111–118, 2017. Scholar
  50. 50.
    Ahmad, J., Muhammad, K., Lee, M.Y., and Baik, S.W., Endoscopic image classification and retrieval using clustered convolutional features. J. Med. Syst. 41(12):196, 2017. Scholar
  51. 51.
    Ramos-Pollán, R., Guevara-López, M. Á, and Oliveira, E., A software framework for building biomedical machine learning classifiers through grid computing resources. J. Med. Syst. 36(4):2245–2257, 2012. Scholar
  52. 52.
    Garty, H.: hagaygarty/mdCNN, 2017Google Scholar
  53. 53.
    Zhang, J., Lockhart, T.E., and Soangra, R., Classifying lower extremity muscle fatigue during walking using machine learning and inertial sensors. Ann. Biomed. Eng. 42(3):600–612, 2014. Scholar
  54. 54.
    Muniz, A.M.S., Liu, H., Lyons, K.E., Pahwa, R., Liu, W., Nobre, F.F., and Nadal, J., Comparison among probabilistic neural network, support vector machine and logistic regression for evaluating the effect of subthalamic stimulation in Parkinson disease on ground reaction force during gait. J. Biomech. 43(4):720–726, 2010. Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Center for MicroElectroMechanical Systems (CMEMS)University of MinhoGuimarãesPortugal
  2. 2.Production and Systems DepartmentUniversity of MinhoGuimarãesPortugal

Personalised recommendations