Smart Classifier Selection for Activity Recognition on Wearable Devices

Negar Ghourchian, Doina Precup

2013

Abstract

Activity recognition is a key component of human-machine interaction applications. Information obtained from sensors in smart wearable devices is especially valuable, because these devices have become ubiquitous, and they record large amounts of data. Machine learning algorithms can then be used to process this data. However, wearable devices impose restrictions in terms of computation and energy resources, which need to be taken into account by a learning algorithm. We propose to use a real-time learning approach, which interactively determines the most effective set of modalities (or features) for classification, given the task at hand. Our algorithm optimizes sensor selection, in order to consume less power, while still maintaining good accuracy in classifying sequences of activities. Performance on a large, noisy dataset including four different sensing modalities shows that this is a promising approach.

References

  1. Breiman, L. (2001). Random forests. Machine Learning, 45(1):5-32.
  2. Castanon, D. A. (1997). Approximate dynamic programming for sensor management. In IEEE CDC, pages 1202-1207.
  3. Choudhury, T., Consolvo, S., Harrison, B., Hightower, J., LaMarca, A., LeGrand, L., Rahimi, A., Rea, A., Bordello, G., Hemingway, B., Klasnja, P., Koscher, K., Landay, J., Lester, J., Wyatt, D., and Haehnel, D. (2008). The mobile sensing platform: An embedded activity recognition system. Pervasive Computing, 7(2):32-41.
  4. Clarkson, B. and Pentland, A. (1999). Unsupervised clustering of ambulatory audio and video. In ICASSP, pages 3037-3040.
  5. Kalandros, M., Pao, L. Y., and Chi Ho, Y. (1999). Randomization and super-heuristics in choosing sensor sets for target tracking applications. In IEEE CDC, pages 1803-1808.
  6. Mannini, A. and Sabatini, A. M. (2010). Machine learning methods for classifying human physical activity from on-body accelerometers. Sensors, 10(2):1154-1175.
  7. Settles, B. (2010). Active learning literature survey. Technical Report 1648, University of Wisconsin-Madison.
  8. Subramanya, A. and Raj, A. (2006). Recognizing activities and spatial context using wearable sensors. In UAI.
  9. Zhang, Y. and Ji, Q. (2005). Sensor selection for active information fusion. In AAAI, pages 1229-1234.
Download


Paper Citation


in Harvard Style

Ghourchian N. and Precup D. (2013). Smart Classifier Selection for Activity Recognition on Wearable Devices . In Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-8565-41-9, pages 581-585. DOI: 10.5220/0004269805810585


in Bibtex Style

@conference{icpram13,
author={Negar Ghourchian and Doina Precup},
title={Smart Classifier Selection for Activity Recognition on Wearable Devices},
booktitle={Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2013},
pages={581-585},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004269805810585},
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 - Smart Classifier Selection for Activity Recognition on Wearable Devices
SN - 978-989-8565-41-9
AU - Ghourchian N.
AU - Precup D.
PY - 2013
SP - 581
EP - 585
DO - 10.5220/0004269805810585