An Ensemble Dynamic Time Warping Classifier with Application to Activity Recognition

Conference paper


This paper proposes a new ensemble classifier based on Dynamic Time Warping (DTW), and demonstrates how it can be used to combine information from multiple time-series sensors, to relate them to the activities of the person wearing them. The training data for the system comprises a set of short time samples for each sensor and each activity, which are used as templates for DTW, and time series for each sensor are classified by assessing their similarity to these templates. To arrive at a final classification, results from separate classifiers are combined using a voting ensemble. The approach is evaluated on data relating to six different activities of daily living (ADLs) from the MIT Placelab dataset, using hip, thigh and wrist sensors. It is found that the overall average accuracy in recognising all six activities ranges from 45.5% to 57.2% when using individual sensors, but this increases to 84.3% when all three sensors are used together in the ensemble. The results compare well with other published results in which different classification algorithms were used, indicating that the ensemble DTW classification approach is a promising one.


Window Size Activity Recognition Confusion Matrix Dynamic Time Warping Ensemble Classifier 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    S. S. Intille, K. Larson, E. Munguia Tapia, J. Beaudin, P. Kaushik, J. Nawyn, and R. Rockinson, "Using a live-in laboratory for ubiquitous computing research," in Proceedings of PERVASIVE 2006, Berlin Heidelberg: Springer -Verlag, 2006, pp. 349-365.Google Scholar
  2. 2.
    E.M. Tapia: “Using Machine Learning for Real-time Activity Recognition and Estimation of Energy Expenditure”, Ph.D. Thesis, Massachusetts Institute of Technology, 2008.Google Scholar
  3. 3.
    R. Clark, J.F. Van Nostrand, J.M. Wiener and R.J. Hanley: “Measuring the Activities of Daily Living: Comparisons Across National Surveys”. For U.S. Department of Health and Human Services, 1990.Google Scholar
  4. 4.
    Kevin Kinsella and Wan He, “An Ageing World: 2008. International Population Report”. For the US Census Bureau, June 2009.Google Scholar
  5. 5.
    Laing Buisson Consulting: “Demand for places in elderly care homes projected to increase”. In Care of the Elderly Market Survey, 2006.Google Scholar
  6. 6.
    H. Sakoe & S. Chiba: “Dynamic programming algorithm optimization for spoken word recognition”, IEEE Transactions on Acoustics, Speech, and Signal Processing 26 (1) (1978) 43-49.MATHCrossRefGoogle Scholar
  7. 7.
    E.J. Keogh, M.J. Pazzani. “Derivative Dynamic Time Warping”. First SIAM International Conference on Data Mining (SDM'2001), 2001.Google Scholar
  8. 8.
    D. Lemire: “Faster Retrieval with a Two-Pass Dynamic-Time-Warping Lower Bound”, Pattern Recognition, Vol. 42, Issue 9, pp. 2169-2180, Sep. 2009.MATHCrossRefGoogle Scholar
  9. 9.
    C.A. Ratanamahatana and E. Keogh: “Three Myths about Dynamic Time Warping Data Mining.” In Proceedings of SIAM International Conference on Data Mining (SDM '05), Newport Beach, CA, April 2005.Google Scholar
  10. 10.
    N. Ravi, N. Dandekar, P. Mysore, and M. Littman, “Activity Recognition from Accelerometer Data”. In Proceedings of American Association of Artificial Intelligence, 2005.Google Scholar
  11. 11.
    L. Bao and S. Intille, “Activity Recognition from User-Annotated Acceleration Data.” In Proceedings of PERVASIVE 2004, Vienna, Austria, April 2004.Google Scholar
  12. 12.
    Xi Long, Bin Yin, and Ronald M. Aarts: “Single-Accelerometer-Based Daily Physical Activity Classification.” In 31st Annual International Conference of the IEEE EMBS, Minneapolis, Minnesota, USA, September 2-6, 2009.Google Scholar

Copyright information

© Springer-Verlag London Limited 2011

Authors and Affiliations

  1. 1.National University of Ireland, GalwayGalwayIreland

Personalised recommendations