Semi-supervised Discovery of Time-series Templates for Gesture Spotting in Activity Recognition

Héctor F. Satizábal, Julien Rebetez, Andres Perez-Uribe

Abstract

In human activity recognition, gesture spotting can be achieved by comparing the data from on-body sensors with a set of known gesture templates. This work presents a semi-supervised approach to template discovery in which the Dynamic Time Warping distance measure has been embedded in a classic clustering technique. Clustering is used to find a set of template candidates in an unsupervised manner, which are then evaluated by means of a supervised assessment of their classification performance. A cross-validation test over a benchmark dataset showed that our approach yields good results with the advantage of using a single sensor.

References

  1. Berndt, D. J. and Clifford, J. (1994). Using Dynamic Time Warping to Find Patterns in Time Series. In Proc. of KDD-94: AAAI Workshop on Knowledge Discovery in Databases, pages 359-370.
  2. Frank, A. and Asuncion, A. (2010). UCI machine learning repository.
  3. Kaufman, L. and Rousseeuw, P. J. (1987). Clustering by means of medoids. Statistical Data Analysis Based on the L1-Norm and Related Methods, pages 405-416.
  4. Ko, M. H. et al. (2005). Online context recognition in multisensor systems using dynamic time warping. In Proc. of the International Conference on Intelligent Sensors, Sensors Networks and Information Processing., pages 283 - 288.
  5. Lara, O. D. et al. (2012). Centinela: A human activity recognition system based on acceleration and vital sign data. Pervasive and Mobile Computing, 8(5):717-729.
  6. MacQueen, J. B. (1967). Some methods for classification and analysis of multivariate observations. In Proc. of the fifth Berkeley Symposium on Mathematical Statistics and Probability, volume 1, pages 281-297.
  7. Mathie, M. et al. (2003). Detection of daily physical activities using a triaxial accelerometer. Medical and Biological Engineering and Computing, 41:296-301.
  8. Rijsbergen, C. J. V. (1979). Information Retrieval. Butterworth-Heinemann, 2nd edition.
  9. Roggen, D. et al. (2010). Collecting complex activity datasets in highly rich networked sensor environments. In 2010 Seventh International Conference on Networked Sensing Systems, pages 233-240.
  10. Sagha, H. et al. (2011). Benchmarking classification techniques using the Opportunity human activity dataset. In IEEE International Conference on Systems, Man, and Cybernetics.
  11. Stiefmeier, T. et al. (2008). Wearable activity tracking in car manufacturing. Pervasive Computing, IEEE, 7(2):42- 50.
Download


Paper Citation


in Harvard Style

F. Satizábal H., Rebetez J. and Perez-Uribe A. (2013). Semi-supervised Discovery of Time-series Templates for Gesture Spotting in Activity Recognition . In Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-8565-41-9, pages 573-576. DOI: 10.5220/0004268805730576


in Bibtex Style

@conference{icpram13,
author={Héctor F. Satizábal and Julien Rebetez and Andres Perez-Uribe},
title={Semi-supervised Discovery of Time-series Templates for Gesture Spotting in Activity Recognition},
booktitle={Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2013},
pages={573-576},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004268805730576},
isbn={978-989-8565-41-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Semi-supervised Discovery of Time-series Templates for Gesture Spotting in Activity Recognition
SN - 978-989-8565-41-9
AU - F. Satizábal H.
AU - Rebetez J.
AU - Perez-Uribe A.
PY - 2013
SP - 573
EP - 576
DO - 10.5220/0004268805730576