Human Activity Recognition from Triaxial Accelerometer Data - Feature Extraction and Selection Methods for Clustering of Physical Activities

Inês Machado, Ricardo Gomes, Hugo Gamboa, Vítor Paixão

2014

Abstract

The demand for objectivity in clinical diagnosis has been one of the greatest challenges in Biomedical Engineering. The study, development and implementation of solutions that may serve as ground truth in physical activity recognition and in medical diagnosis of chronic motor diseases is ever more imperative. This paper describes a human activity recognition framework based on feature extraction and feature selection techniques where a set of time, statistical and frequency domain features taken from 3-dimensional accelerometer sensors are extracted. In this paper, unsupervised learning is applied to the feature representation of accelerometer data to discover the activities performed by different subjects. A feature selection framework is developed in order to improve the clustering accuracy and reduce computational costs. The features which best distinguish a particular set of activities are selected from a 180th- dimensional feature vector through machine learning algorithms. The implemented framework achieved very encouraging results in human activity recognition: an average person-dependent Adjusted Rand Index (ARI) of 99:29%0:5% and a person-independent ARI of 88:57%4:0% were reached.

References

  1. Ankerst, M., Breunig, M. M., Kriegel, H.-P., and Sander, J. (1999). Optics: ordering points to identify the clustering structure. SIGMOD Rec., 28(2):49-60.
  2. Bandini, L. G., Gleason, J., Curtin, C., Lividini, K., Anderson, S. E., Cermak, S. A., Maslin, M., and Must, A. (2013). Comparison of physical activity between children with autism spectrum disorders and typically developing children. Autism, 17(1):44-54.
  3. Bouten, C. V., Koekkoek, K. T., Verduin, M., Kodde, R., and Janssen, J. D. (1997). A triaxial accelerometer and portable data processing unit for the assessment of daily physical activity. IEEE Transactions on Biomedical Engineering, 44(3):136-147.
  4. Bugané, F., Benedetti, M. G., Casadio, G., Attala, S., Biagi, F., Manca, M., and Leardini, A. (2012). Estimation of spatial-temporal gait parameters in level walking based on a single accelerometer: Validation on normal subjects by standard gait analysis. Comput. Methods Prog. Biomed., 108(1):129-137.
  5. Crockford, D. (2006). The application/json media type for javascript object notation (json). RFC 4627, IETF.
  6. Donalek, C. (2011). Supervised and Unsupervised Learning. (April).
  7. Ester, M., peter Kriegel, H., S, J., and Xu, X. (1996). A density-based algorithm for discovering clusters in large spatial databases with noise. pages 226-231. AAAI Press.
  8. Foerster, F. and Fahrenberg, J. (2000). Motion pattern and posture: correctly assessed by calibrated accelerometers, page 32(3):450457.
  9. Frey, B. J. and Dueck, D. (2007). Clustering by passing messages between data points. Science, 315(5814):972-976.
  10. Gomes, R., Nunes, N., Sousa, J., and Gamboa, H. (2012). Long term biosignals visualization and processing. In BIOSIGNALS, pages 402-405.
  11. Heer, J., Kong, N., and Agrawala, M. (2009). Sizing the horizon: The effects of chart size and layering on the graphical perception of time series visualizations. In ACM Human Factors in Computing Systems (CHI).
  12. I. H. Witten, E. Frank and Hall, M. A. (2011). Data Mining: Practical Machine Learning Tools and Techniques.
  13. Khan, A. M., Lee, Y.-K., Lee, S. Y., and Kim, T.- S. (2010). A triaxial accelerometer-based physicalactivity recognition via augmented-signal features and a hierarchical recognizer. Trans. Info. Tech. Biomed., 14(5):1166-1172.
  14. Liao, L., Fox, D., and Kautz, H. (2005). Location-based activity recognition using relational markov networks. In Proceedings of the 19th international joint conference on Artificial intelligence, IJCAI'05, pages 773- 778, San Francisco, CA, USA. Morgan Kaufmann Publishers Inc.
  15. Liu, A. D. (2013). The Effect of Sensor Mass, Sensor Location, and Delamination Location Of. PhD thesis, California Polytechnic State University.
  16. LLoyd, S. P. (1982). Least squares quantization in pcm. IEEE Transactions on Information Theory, 28:129- 137.
  17. Mannini, A., Intille, S. S., Rosenberger, M., Sabatini, A. M., and Haskell, W. (2013). Activity recognition using a single accelerometer placed at the wrist or ankle. Med Sci Sports Exerc.
  18. Mannini, A. and Sabatini, A. (2010). Machine learning methods for classifying human physical activities from on-body sensors.
  19. Mathie, M. (2003). Monitoring and interpreting human movement patterns using a triaxial accelerometer.
  20. Oliphant, T. (2006). Guide to Numpy. Tregol Publishing.
  21. Palmerini, L., Mellone, S., Avanzolini, G., Valzania, F., and Chiari, L. (2013). Classification of early-mild subjects with parkinson's disease by using sensor-based measures of posture, gait, and transitions. In AIME, pages 176-180.
  22. Peeters, G. (2004). A large set of audio features for sound description (similarity and classification) in the CUIDADO project.
  23. Phillips, S. M. and McAuley, E. (2013). Physical activity and fatigue in breast cancer survivors: A panel model examining the role of self-efficacy and depression. Cancer Epidemiology Biomarkers & Prevention, 22(5):773-781.
  24. Pour, G., Troped, P., and Evans, J. (2013). Environment feature extraction and classification for context aware physical activity monitoring. In Sensors Applications Symposium (SAS), 2013 IEEE, pages 123-128.
  25. Santos, J. M. and Embrechts, M. (2009). On the use of the adjusted rand index as a metric for evaluating supervised classification. In Alippi, C., Polycarpou, M. M., Panayiotou, C. G., and Ellinas, G., editors, ICANN (2), volume 5769 of Lecture Notes in Computer Science, pages 175-184. Springer.
  26. Simon, B. J., Errico, J. P., and Raffle, J. T. (2013). Noninvasive magnetic or electrical nerve stimulation to treat or prevent autism spectrum disorders and other disorders of psychological development. US Patent App. 13/783,319.
  27. Smeja, J. F. F. F. M. and Muller, W. (1997). Assessment of posture and motion by multichannel piezoresistive accelerometer recordings. Psychophysiology, page 34(5):607612.
  28. Song, M. R., Lee, Y.-S., Baek, J.-D., and Miller, M. (2012). Physical activity status in adults with depression in the national health and nutrition examination survey, 2005-2006. Public Health Nursing, 29(3):208-217.
  29. Wren, C. R. and Tapia, E. M. (2006). Toward scalable activity recognition for sensor networks. In In Lecture Notes in Computer Science, pages 168-185. Springer.
  30. Z. Ghahramani (2004). Unsupervised learning. Gatsby Computational Neuroscience Unit, University College London.
  31. Zheng, Y., Wong, W.-K., Guan, X., and Trost, S. (2013). Physical activity recognition from accelerometer data using a multi-scale ensemble method.
Download


Paper Citation


in Harvard Style

Machado I., Gomes R., Gamboa H. and Paixão V. (2014). Human Activity Recognition from Triaxial Accelerometer Data - Feature Extraction and Selection Methods for Clustering of Physical Activities . In Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2014) ISBN 978-989-758-011-6, pages 155-162. DOI: 10.5220/0004749801550162


in Bibtex Style

@conference{biosignals14,
author={Inês Machado and Ricardo Gomes and Hugo Gamboa and Vítor Paixão},
title={Human Activity Recognition from Triaxial Accelerometer Data - Feature Extraction and Selection Methods for Clustering of Physical Activities},
booktitle={Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2014)},
year={2014},
pages={155-162},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004749801550162},
isbn={978-989-758-011-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2014)
TI - Human Activity Recognition from Triaxial Accelerometer Data - Feature Extraction and Selection Methods for Clustering of Physical Activities
SN - 978-989-758-011-6
AU - Machado I.
AU - Gomes R.
AU - Gamboa H.
AU - Paixão V.
PY - 2014
SP - 155
EP - 162
DO - 10.5220/0004749801550162