Implementation of a Modular Growing When Required Neural Gas Architecture for Recognition of Falls

  • Frederico B. Klein
  • Karla Štěpánová
  • Angelo Cangelosi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9947)


In this paper we aim for the replication of a state of the art architecture for recognition of human actions using skeleton poses obtained from a depth sensor. We review the usefulness of accurate human action recognition in the field of robotic elderly care, focusing on fall detection. We attempt fall recognition using a chained Growing When Required neural gas classifier that is fed only skeleton joints data. We test this architecture against Recurrent SOMs (RSOMs) to classify the TST Fall detection database ver. 2, a specialised dataset for fall sequences. We also introduce a simplified mathematical model of falls for easier and faster bench-testing of classification algorithms for fall detection.

The outcome of classifying falls from our mathematical model was successful with an accuracy of \( 97.12 \pm 1.65\,\%\) and from the TST Fall detection database ver. 2 with an accuracy of \(90.2 \pm 2.68\,\%\) when a filter was added.


Action recognition Falls Neural networks Neural gas Topological classifiers Socially assistive robotics 


  1. 1.
    Arlot, S., Celisse, A.: A survey of cross-validation procedures for model selection. Stat. Surv. 4, 40–79 (2010). doi:10.1214/09-SS054 MathSciNetCrossRefMATHGoogle Scholar
  2. 2.
    Burman, P.: A comparative study of ordinary cross-validation, v-fold cross-validation and the repeated learning-testing methods. Biometrika 76(3), 503–514 (1989)MathSciNetCrossRefMATHGoogle Scholar
  3. 3.
    Chan, M., Estéve, D., Escriba, C., Campo, E.: A review of smart homes-present state and future challenges. Comput. Methods Prog. Biomed. 91, 55–81 (2008). doi:10.1016/j.cmpb.2008.02.001 CrossRefGoogle Scholar
  4. 4.
    Fernandez-Granero, M.A., Sanchez-Morillo, D., Leon-Jimenez, A.: Computerised analysis of telemonitored respiratory sounds for predicting acute exacerbations of copd. Sensors (Basel) 15, 26978–26996 (2015). doi:10.3390/s151026978 CrossRefGoogle Scholar
  5. 5.
    Flodgren, G., Rachas, A., Farmer, A.J., Inzitari, M., Shepperd, S.: Interactive telemedicine: effects on professional practice and health care outcomes. In: Cochrane Database of Systematic Reviews. Wiley (2015)Google Scholar
  6. 6.
    Furao, S., Hasegawa, O.: An incremental network for on-line unsupervised classification and topology learning. Neural Netw. 19, 90–106 (2006). doi:10.1016/j.neunet.2005.04.006 CrossRefMATHGoogle Scholar
  7. 7.
    Gasparrini, S., Cippitelli, E., Gambi, E., Spinsante, S., Wåhslén, J., Orhan, I., Lindh, T.: Proposal and experimental evaluation of fall detection solution basedon wearable and depth data fusion. In: Loshkovska, S., Koceski, S. (eds.) ICTInnovations 2015, Advances in Intelligent Systems and Computing, pp. 99–108. Springer International Publishing, Switzerland (2016)Google Scholar
  8. 8.
    Ho, T.-W., Huang, C.-T., Chiu, H.-C., Ruan, S.-Y., Tsai, Y.-J., Yu, C.-J., Lai, F.: Effectiveness of telemonitoring in patients with chronic obstructive pulmonary disease in Taiwan-a randomized controlled Trial. Sci. Rep. 6 (2016). doi:10.1038/srep23797
  9. 9.
    Jauch, E.C., Saver, J.L., Demaerschalk, B.M., Khatri, P., McMullan Jr., P.W., Qureshi, A.I., Rosenfield, K., Scott, P.A., Summers, D.R., Wang, D.Z.: AHA/ASA Guideline. Stroke (2013)Google Scholar
  10. 10.
    JointType enumeration [WWW Document], n.d. Accessed 14 May 16
  11. 11.
    Koppula, H.S., Saxena, A.: Anticipating human activities using object affordances for reactive robotic response. IEEE Trans. Pattern Anal. Mach. Intell. 38, 14–29 (2016)CrossRefGoogle Scholar
  12. 12.
    Martinetz, T.M., Schulten, K.J.: A “Neural Gas” networklearns topologies. In: Kohonen, T., Mäkisara, K., Simula, O., Kangas, J. (eds.) Proceedings of the International Conference on Artificial Neural Networks 1991, Espoo, Finland, pp. 397–402, Amsterdam, North-Holland, New York (1991)Google Scholar
  13. 13.
    Marsland, S., Shapiro, J., Nehmzow, U.: A self-organising network that grows when required. Neural Netw. 15, 1041–1058 (2002)CrossRefGoogle Scholar
  14. 14.
    Parisi, G., Wermter, S., others.: Hierarchical SOM-based detection of novel behavior for 3D human tracking. In: The 2013 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2011)Google Scholar
  15. 15.
    Parisi, G.I., Weber, C., Wermter, S.: Self-organizing neural integration of pose-motion features for human action recognition. Front. Neurorobotics 9, (2015). doi:10.3389/fnbot.2015.00003
  16. 16.
    Peacock, T., Hadjiconstantinou, N.: Course materials for 2.003J/1.053J dynamics and control I, Spring (2007). MIT OpenCourseWare (, Massachusetts Institute of Technology. Accessed 13 May 2016
  17. 17.
    Prime sensor\(^{\text{TM}}\) NITE 1.3 framework programmer’s guide - NITE.pdf. Accessed 14 May 2016
  18. 18.
    Rabbitt, S.M., Kazdin, A.E., Scassellati, B.: Applications and recommendations for expanded use. Clin. Psychol. Rev. 35, 35–46. doi:10.1016/j.cpr.2014.07.001
  19. 19.
    Valenzuela, T.D., Roe, D.J., Cretin, S., Spaite, D.W., Larsen, M.P.: Estimating effectiveness of cardiac arrest interventions: a logistic regression survival model. Circulation 96, 3308–3313 (1997). doi:10.1161/01.CIR.96.10.3308 CrossRefGoogle Scholar
  20. 20.
    Wilkinson, T.M.A., Donaldson, G.C., Hurst, J.R., Seemungal, T.A.R., Wedzicha, J.A.: Early therapy improves outcomes of exacerbations of chronic obstructive pulmonary disease. Am. J. Respir. Crit. Care Med. 169, 1298–1303 (2004). doi:10.1164/rccm.200310-1443OC CrossRefGoogle Scholar
  21. 21.
    Yongli, G., Yin, O.S., Han, P.Y.: State of the art: a study on fall detection. World Acad. Sci. Eng. Technol. 62, 294–298 (2012)Google Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Frederico B. Klein
    • 1
  • Karla Štěpánová
    • 2
  • Angelo Cangelosi
    • 1
  1. 1.School of Computing, Electronics and MathematicsPlymouth UniversityPlymouthUK
  2. 2.Department of CyberneticsCzech Technical UniversityPragueCzech Republic

Personalised recommendations