Human Activity Recognition Based on Novel Accelerometry Features and Hidden Markov Models Application

Ana Luísa Gomes, Vítor Paixão, Hugo Gamboa

Abstract

The Human Activity Recognition (HAR) systems require objective and reliable methods that can be used in the daily routine and must offer consistent results according to the performed activities. In this work, a framework for human activity recognition in accelerometry (ACC) based on our previous work and with new features and techniques was developed. The new features set covered wavelets, the CUIDADO features implementation and the Log Scale Power Bandwidth creation. The Hidden Markov Models were also applied to the clustering output. The Forward Feature Selection chose the most suitable set from a 423th dimensional feature vector in order to improve the clustering performances and limit the computational demands. K-means, Affinity Propagation, DBSCAN and Ward were applied to ACC databases and showed promising results in activity recognition: from 73.20% 7.98% to 89.05% +/- 7.43% and from 70.75% +/- 10.09% to 83.89% +/- 13.65% with the Hungarian accuracy (HA) for the FCHA and PAMAP databases, respectively. The Adjust Rand Index (ARI) was also applied as clustering evaluation method. The developed algorithm constitutes a contribution for the development of reliable evaluation methods of movement disorders for diagnosis and treatment applications.

References

  1. (January 2014). Pamap, http://www.pamap.org/demo.html.
  2. (September 2014). Clustering, http://scikitlearn.org/stable/modules/clustering.html.
  3. A. M. Khan, Y.-K. Lee, S. Y. L. and Kim, T.-S. (2010). a triaxial accelerometer-based physical-activity recognition via augmented-signal features and a hierarchical recognizer. 14(4):11661172.
  4. Adrian Ball, David Rye, F. R. and Velonaki, M. (2011). A comparison of unsupervised learning algorithms for gesture clustering. pages 111-112.
  5. Demetrio Labate, G. W. and Wilson, E. (2013). Wavelets. 60(1):66-76.
  6. Fosler-Lussier, E. (1998). Markov models and hidden markov models - a brief tutorial.
  7. Galka, J. and Ziólko, M. (2008). Wavelets in speech segmentation.
  8. Ghahramani, Z. (2004). Unsupervised learning. pages 3-4.
  9. Godfrey, R. Conway, D. M. and O Laighin, G. (2008). Direct measurement of human movement by accelerometry. Elsevier, 30(10):1364-1386.
  10. Ineˆs Prata Machado, Ricardo Gomes, H. G. V. P. a. (2014). Human activity recognition from triaxial accelerometer data feature extraction and selection methods for clustering of physical activities.
  11. Ittay Eyal, I. K. and Rom, R. (2011). Distributed data clustering in sensor networks. 24(5):207222.
  12. Jani Mantyjarvi, J. H. and Seppanen., T. (2001). Recognizing human motion with multiple acceleration sensors. 2:747 - 752.
  13. Kuhn, H. W. (2009). the hungarian method for the assignment problem. 2:83-97.
  14. Liao, T. (2005). Clustering of time series data - a survey. 38(11):1857 - 1874.
  15. Lin, R.-S. and Chen, L.-H. (2005). A new approach for audio classification and segmentation using gabor wavelets and fisher linear discriminator. 19(6):807- 822.
  16. Nishkam Ravi, Nikhil Dandekar, P. M. and Littman, M. L. (2005). Activity recognition from accelerometer data. 3:1541-1546.
  17. Nunes, N. F. M. (2011). Algorithms for time series clustering. Master's thesis, Physics Department, Faculty of Sciences and Technology, New University of Lisbon and Plux, Wireless Biosignals, Portugal.
  18. Peeters, G. (2004). A large set of audio features for sound description (similarity and classification) in the CUIDADO project.
  19. Ping Guo, Zhenjiang Miao, X.-P. Z. Y. S. and Wang, S. (2012). Coupled observation decomposed hidden markov model for multiperson activity recognition. 22(9):1306 - 1320.
  20. Ricardo Gomes, Neuza Nunes, J. S. and Gamboa, H. (2012). Long term biosignals visualization and processing.
  21. Trabelsi, D., Samer Mohammed, Faicel Chamroukhi, L. O., and Amirat, Y. (2013). An unsupervised approach for automatic activity recognition based on hidden markov model regression. 10(3):829 - 835.
  22. Uwe Maurer, Asim Smailagic, D. P. S. and Deisher, M. (2006). Activity recognition and monitoring using multiple sensors on different body positions. pages 113-116.
  23. Walter, S. F. (2007). Clustering by affinity propagation. Master's thesis, Department of Physics, ETH Zurich, Switzerland.
Download


Paper Citation


in Harvard Style

Luísa Gomes A., Paixão V. and Gamboa H. (2015). Human Activity Recognition Based on Novel Accelerometry Features and Hidden Markov Models Application . In Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2015) ISBN 978-989-758-069-7, pages 76-85. DOI: 10.5220/0005215800760085


in Bibtex Style

@conference{biosignals15,
author={Ana Luísa Gomes and Vítor Paixão and Hugo Gamboa},
title={Human Activity Recognition Based on Novel Accelerometry Features and Hidden Markov Models Application},
booktitle={Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2015)},
year={2015},
pages={76-85},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005215800760085},
isbn={978-989-758-069-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2015)
TI - Human Activity Recognition Based on Novel Accelerometry Features and Hidden Markov Models Application
SN - 978-989-758-069-7
AU - Luísa Gomes A.
AU - Paixão V.
AU - Gamboa H.
PY - 2015
SP - 76
EP - 85
DO - 10.5220/0005215800760085