Abstract
We present a framework for the automated generation of power-efficient state detection in wearable sensor nodes. The core of the framework is a decision tree classifier, which dynamically adjusts the activation and sampling rate of the sensors (termed groggy wakeup), such that only the data necessary to determine the system state is collected at any given time. This classifier can be tuned to trade-off accuracy and power in a structured fashion. Use of a sensor set which measures the phenomena of interest in multiple fashions and with various accuracies further improves the savings by increasing the possible choices for the above decision process.
An application based on a wearable gait monitor provides quantitative results. Comparing the decision tree classifier to a Support Vector Machine, it is shown that groggy wakeup allows the system to achieve the same detection accuracy for less average power. A simulation of real-time operation demonstrates that our multi-tiered system detects states as accurately as a single-trigger (binary) wakeup system, drawing substantially less power with only a negligible increase in latency.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
J. P. DiMarco. Inplantable cardioverter-defibrillators. New England Journal of Medicine, 349(19): 1836–1847, 2003.
Brian Clarkson. Life Patterns: structure from wearable sensors. PhD thesis, MIT, 2002.
Ari Y. Benbasat, Stacy J. Morris, and Joseph A. Paradiso. A wireless modular sensor architecture and its application in on-shoe gait analysis. IEEE Sensors 2003.
P. Dutta et al. Design of a wireless sensor network platform for detecting rare, random and ephemeral events. IPSN 2005.
P. Dutta, University of Calfornia Berkeley. IPSN’ 05 talk.
K. Van Laerhoven, H.W. Gellersen, and Y.G. Malliaris. Long-term activity monitoring with a wearable sensor node. BSN 2006.
A. Jain and E. Chang. Adaptive sampling for sensor networks. Data Management for Sensor Networks 2004.
A. Gelb, editor. Applied Optimal Estimation. MIT Press, 1974.
Ari Y. Benbasat and Joseph A. Paradiso. A compact modular wireless sensor platform. IPSN 2005.
Stacy J Morris. A Shoe-Integrated Sensor System for Wireless Gait Analysis and Real-TimeTherapeutic Feedback. ScD thesis, MIT, 2004.
Lily Lee. Gait Analysis for Classification. PhD thesis, MIT, 2002.
A. Webb. Statistical Pattern Recognition. Wiley, 2002.
L. Breiman et al. Classification and Regression Trees. Wadsworth, 1984.
H. Zhu, J. Wertsch, et al. Foot pressure distribution during walking and shuffling. Arch Phys Med Rehabil, 72:390–397, May 1991.
D.E. Krebs et al. Biomotion community-wearable human activity monitor: Total knee replacement and healthy control subjects. BSN 2006.
R. Duda, P. Hart, and D. Stork. Pattern Classification. Wiley, 2001.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 International Federation for Medical and Biological Engineering
About this paper
Cite this paper
Benbasat, A.Y., Paradiso, J.A. (2007). Groggy Wakeup - Automated Generation of Power-Efficient Detection Hierarchies for Wearable Sensors. In: Leonhardt, S., Falck, T., Mähönen, P. (eds) 4th International Workshop on Wearable and Implantable Body Sensor Networks (BSN 2007). IFMBE Proceedings, vol 13. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-70994-7_10
Download citation
DOI: https://doi.org/10.1007/978-3-540-70994-7_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-70993-0
Online ISBN: 978-3-540-70994-7
eBook Packages: EngineeringEngineering (R0)