Advertisement

Multimedia Tools and Applications

, Volume 66, Issue 1, pp 95–114 | Cite as

Detecting gait-related health problems of the elderly using multidimensional dynamic time warping approach with semantic attributes

  • Bogdan Pogorelc
  • Matjaž Gams
Article

Abstract

We present a health-monitoring system based on the multidimensional dynamic time warping approach with semantic attributes for the detection of health problems in the elderly to prolong their autonomous living. The movement of the elderly 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 of an elderly person. This paper is an extension of our previous study, which proposed four data mining approaches to recognition of health problems, falls and activities of elderly from their motion patterns. The most successful of the four approaches is SMDTW (Multidimensional dynamic time-warping approach with semantic attributes), whose version is used and thoroughly analyzed in this paper. SMDTW is the modification of the DTW algorithm to use with the multidimensional time series with semantic attributes. To test the robustness of the SMDTW approach, this study calculates the DTW on the time series of various lengths. The semantic attributes presented here consist of the joint angles that are able to recognize many types of movement, e.g., health problems, falls and activities, in contrast to the more specific approaches with specific medically defined attributes from the literature. The k-nearest-neighbor classifier using SMDTW as a distance measure classifies movement of an elderly person 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 accuracy of 97.2%, comparable to the more specific approaches.

Keywords

Health-problems detection Human-motion analysis Gait analysis Machine learning Data mining Temporal data mining Time-series data mining Human locomotion Elderly care Ambient assisted living Ambient media Ambient intelligence Ubiquitous computing Pervasive health 

Notes

Acknowledgements

This work is partially financed by the European Union, the European Social Fund. The authors thank Martin Tomšič, Bojan Nemec and Leon Žlajpah for their help with data acquisition, and Anton Gradišek for his medical expertise.

References

  1. 1.
    Bourke AK, Scanaill CNi, Culhane KM, O'Brien JV, Lyons GM (2006) An optimum accelerometer configuration and simple algorithm for accurately detecting falls. In Proceedings of the 24th IASTED international conference on Biomedical engineering 156–160Google Scholar
  2. 2.
    Bourke AK, O'Brien JV, Lyons GM (2007) Evaluation of a threshold-based tri-axial accelerometer fall detection algorithm. Gait&Posture 26:194–199Google Scholar
  3. 3.
    Confidence (2012) Ubiquitous Care System to Support Independent Living. http://www.confidence-eu.org. Accessed 12 May 2012
  4. 4.
    Craik R, Oatis CA (1995) Gait Analysis: Theory and Application. Mosby, St. Louis, MO, USAGoogle Scholar
  5. 5.
    Dovgan E, Luštrek M, Pogorelc B, Gradišek A, Burger H, Gams M (2011) Intelligent elderly-care prototype for fall and disease detection. Zdrav Vestn - Slovenian Medical Journal 80:824–831Google Scholar
  6. 6.
    eMotion (2012) Smart motion capture system. http://www.btsbioengineering.com/BTSBioengineering/Kinematics/BTSSMARTD/BTS_SMARTD.html. Accessed 16 July 2012
  7. 7.
    Itakura F (1975) Minimum prediction residual principle applied to speech recognition. Acoustics, Speech and Signal Processing, IEEE Transactions on 23(1):67–72CrossRefGoogle Scholar
  8. 8.
    Kaluža B, Mirchevska V, Dovgan E, Luštrek M, Gams M (2010) An Agent-based Approach to Care in Independent Living. Lecture notes in computer science 6439:177–186Google Scholar
  9. 9.
    Keogh E, Ratanamahatana CA (2005) Exact indexing of dynamic time warping. Knowl Inf Syst 7(3):358–386CrossRefGoogle Scholar
  10. 10.
    Kononenko I, Kukar M (2007) Machine learning and data mining. In textbook, Horwood Publishing LtdGoogle Scholar
  11. 11.
    Lakany H (2008) Extracting a diagnostic gait signature. Patt Recognition 41:1627–1637MATHCrossRefGoogle Scholar
  12. 12.
    Luštrek M, Kaluža B (2009) Fall detection and activity recognition with machine learning. Informatica 33:205–212Google Scholar
  13. 13.
    Microsoft (2012) Kinect. http://www.xbox.com/en-US/kinect. Accessed 3 June 2012
  14. 14.
    Miskelly FG (2001) Assistive technology in elderly care. Age Ageing 30:455–458CrossRefGoogle Scholar
  15. 15.
    Moore ST, MacDougall HG, Gracies JM, Cohen HS, Ondo WG (2006) Long-term monitoring of gait in Parkinson’s disease. Gait & Posture 26:200–207Google Scholar
  16. 16.
    Perolle G, Fraisse P, Mavros M, Etxeberria L (2006) Automatic fall detection and acivity monitoring for elderly. COOP-005935 – HEBE Cooperative Research Project- CRAFT. LuxembourgGoogle Scholar
  17. 17.
    Pogorelc B, Gams M (2012) Home-based health monitoring of the elderly through gait recognition. Journal of Ambient Intelligence and Smart Environments 4:415–428Google Scholar
  18. 18.
    Pogorelc B, Bosnic Z, Gams M (2012) Automatic recognition of gait-related health problems in the elderly using machine learning. Multimed Tools Appl 58:333–354. doi: 10.1007/s11042-011-0786-1
  19. 19.
    Ribarič S, Rozman J (2007) Sensors for measurement of tremor type joint movements. MIDEM 37(2):98–104Google Scholar
  20. 20.
    Rudel D (2008) Health at home for elderly by telecare and tele-health services. Infor Med Slov 13(2):19–29Google Scholar
  21. 21.
    Sakoe H, Chiba S (1978) Dynamic programming algorithm optimization for spoken word recognition. Acoustics, Speech and Signal Processing, IEEE Transactions on 26(1):43–49MATHCrossRefGoogle Scholar
  22. 22.
    Salvador S, Chan P (2007) Toward accurate dynamic time warping in linear time and space. Intell Data Anal 11(5):561–580Google Scholar
  23. 23.
    Stojmenova E, Debevc M, Zebec L, Imperl B (2012) Assisted living solutions for the elderly through interactive TV. Multimed Tools Appl. doi: 10.1007/s11042-011-0972-1
  24. 24.
    Stone E, Skubic M (2011) Evaluation of an inexpensive depth camera for in-home gait assessment. Journal of Ambient Intelligence and Smart Environments 3(4):349–361Google Scholar
  25. 25.
    Strle D, Kempe V (2007) MEMS-based inertial systems. MIDEM 37(4):199–209Google Scholar
  26. 26.
    Strle B, Mozina M, Bratko I (2009) Qualitative approximation to Dynamic Time Warping similarity between time series data. In Proceedings of the 23rd International Workshop on Qualitative Reasoning 104–110Google Scholar
  27. 27.
    ten Holt GA, Reinders MJT, Hendriks EA (2007) Multi-dimensional dynamic time warping for gesture recognition. In: Thirteenth annual conference of the Advanced School for Computing and Imaging 1–8Google Scholar
  28. 28.
    Toyne S (2012) Ageing: Europe's growing problem. BBC News, http://news.bbc.co.uk/2/hi/business/2248531.stm. Accessed 4 April 2012
  29. 29.
    Trontelj J, Trontelj J, Trontelj I (2008) Safety Margin at mammalian neuromuscular junction – an example of the significance of fine time measurements in neurobiology. MIDEM 38(3):155–160Google Scholar
  30. 30.
    Vatavu RD (2012) Presence bubbles: supporting and enhancing human-human interaction with ambient media. Multimed Tools Appl 58(2):371–383Google Scholar
  31. 31.
    Vatavu RD (2012) Point & click mediated interactions for large home entertainment displays. Multimed Tools Appl 59(1):113–128Google Scholar
  32. 32.
    Vatavu RD (2012) Nomadic gestures: a technique for reusing gesture commands for frequent ambient interactions. Journal of Ambient Intelligence and Smart Environments 4(2):79–93Google Scholar
  33. 33.
    XantaCross (2012) Dynamic Time Warping, http://creativecommons.org/licenses/by-sa/3.0. Accessed 29 August 2012
  34. 34.
    Williams ME, Owens JE, Parker BE, Granata KP (2003) A new approach to assessing function in elderly people. Trans Am Clin Clim Ass 114:203–216Google Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  1. 1.Jožef Stefan Institute, Department of Intelligent SystemsLjubljanaSlovenia
  2. 2.Jozef Stefan International Postgraduate SchoolLjubljanaSlovenia
  3. 3.Špica International d. o. o.LjubljanaSlovenia

Personalised recommendations