Discovering the Chances of Health Problems and Falls in the Elderly Using Data Mining

  • Bogdan Pogorelc
  • Matjaž Gams
Part of the Studies in Computational Intelligence book series (SCI, volume 423)


The basis for this work was an invited paper at the International Joint Conference on Artificial Intelligence (IJCAI) workshop on Chance Discovery in 2011 and an additional invitation to submit an extended version of a paper to this book. Here we present a generalized approach to the detection of the chances of health problems and falls in the elderly for the purpose of prolonging their autonomous living using a novel data-mining approach. The movement of the user is captured with a motion-capture system that consists of body-worn tags, whose coordinates are acquired by sensors located in an apartment. The output time series of the coordinates are modeled with the proposed data-mining approach in order to recognize the specific health problem or fall. The approach is general in the sense that it uses a k-nearest-neighbor algorithm and dynamic time warping with the time series of all the measurable joint angles for the attributes instead of a more specific approach with medically defined attributes. It is a two-step approach: in the first step it classifies the person’s activities into five activities, including different types of falls. In the second step it classifies classified walking instances from the first step into five different health states: one healthy and four unhealthy. Even though the new approach is more general and can be used to differentiate other types of activities or health problems, it achieves very high classification accuracies, similar to the more specific approaches described in the literature.


health problems activities falls elderly machine learning data mining 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bourke, A.K., et al.: An optimum accelerometer configuration and simple algorithm for accurately detecting falls. In: Proc. BioMed 2006, pp. 156–160 (2006)Google Scholar
  2. 2.
    Bourke, A.K., O’Brien, J.V., Lyons, G.M.: Evaluation of a threshold-based tri-axial accelerometer fall detection algorithm. Gait & Posture 26, 194–199 (2007)CrossRefGoogle Scholar
  3. 3.
    Confidence Consortium: Ubiquitous Care System to Support Independent Livingd,
  4. 4.
    Craik, R., Oatis, C.: Gait Analysis: Theory and Application. Mosby-Year Book (1995)Google Scholar
  5. 5.
    eMotion: Smart motion capture system,
  6. 6.
    Itakura, F.: Minimum prediction residual principle applied to speech recognition. IEEE Transactions on Acoustics, Speech and Signal Processing 23(1), 67–72 (1975)CrossRefGoogle Scholar
  7. 7.
    Kaluža, B., Mirchevska, V., Dovgan, E., Luštrek, M., Gams, M.: An Agent-Based Approach to Care in Independent Living. In: de Ruyter, B., Wichert, R., Keyson, D.V., Markopoulos, P., Streitz, N., Divitini, M., Georgantas, N., Mana Gomez, A. (eds.) AmI 2010. LNCS, vol. 6439, pp. 177–186. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  8. 8.
    Keogh, E., Ratanamahatana, C.A.: Exact indexing of dynamic time warping. Knowl. Inf. Syst. 7(3), 358–386 (2005)CrossRefGoogle Scholar
  9. 9.
    Lakany, H.: Extracting a diagnostic gait signature. Patt. Recognition 41, 1627–1637 (2008)MATHCrossRefGoogle Scholar
  10. 10.
    Luštrek, M., Kaluža, B.: Fall detection and activity recognition with machine learning. Informatica 33, 2 (2009)Google Scholar
  11. 11.
    Miskelly, F.G.: Assistive technology in elderly care. Age and Ageing 30, 455–458 (2001)CrossRefGoogle Scholar
  12. 12.
    Moore, S.T., et al.: Long-term monitoring of gait in Parkinson’s disease. Gait Posture (2006)Google Scholar
  13. 13.
    Perolle, G., Fraisse, P., Mavros, M., Etxeberria, L.: Automatic fall detection and acivity monitoring for elderly, COOP-005935 — HEBE Cooperative Research Project- CRAFT, Luxembourg (2006)Google Scholar
  14. 14.
    Pogorelc, B., Bosnić, Z., Gams, M.: Automatic recognition of gait-related health problems in the elderly using machine learning. Multimed Tools Appl. (2011), doi:10.1007/s11042-011-0786-1Google Scholar
  15. 15.
    Ribarič, S., Rozman, J.: Sensors for measurement of tremor type joint movements. MIDEM 37(2), 98–104 (2007)Google Scholar
  16. 16.
    Rudel, D.: Zdravje na domu na daljavo za stare osebe. Infor. Med. Slov. 13(2), 19–29 (2008)Google Scholar
  17. 17.
    Sakoe, H., Chiba, S.: Dynamic programming algorithm optimization for spoken word recognition. IEEE Transactions on Acoustics, Speech and Signal Processing 26(1), 43–49 (1978)MATHCrossRefGoogle Scholar
  18. 18.
    Salvador, S., Chan, P.: Toward accurate dynamic time warping in linear time and space. Intell. Data Anal. 11(5), 561–580 (2007)Google Scholar
  19. 19.
    Strle, D., Kempe, V.: MEMS-based inertial systems. MIDEM 37(4), 199–209 (2007)Google Scholar
  20. 20.
    Toyne, S.: Ageing: Europe’s growing problem. BBC News,
  21. 21.
    Trontelj, J., et al.: Safety Margin at mammalian neuromuscular junction-an example of the significance of fine time measurements in neurobiology. MIDEM 38(3), 155–160 (2008)Google Scholar
  22. 22.
    Williams, M.E., Owens, J.E., Parker, B.E., Granata, K.P.: A new approach to assessing function in elderly people. Trans. Am. Clin. Clim. Ass. 114, 203–216 (2003)Google Scholar
  23. 23.
    Dovgan, E., Luštrek, M., Pogorelc, B., Gradišek, A., Burger, H., Gams, M.: Intelligent elderly-care prototype for fall and disease detection from sensor data. Zdrav Vestn 80, 824–831 (2011)Google Scholar
  24. 24.
    Strle, B., Mozina, M., Bratko, I.: Qualitative approximation to Dynamic TimeWarping similarity between time series data. In: Proceedings of the Workshop on Qualitative Reasoning (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Bogdan Pogorelc
    • 1
    • 2
  • Matjaž Gams
    • 1
    • 2
  1. 1.Jožef Stefan InstituteLjubljanaSlovenia
  2. 2.Špica International d.o.o.LjubljanaSlovenia

Personalised recommendations