Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2012 Jan:2012:1-6.
doi: 10.1109/COMSNETS.2012.6151376.

Wearable Networked Sensing for Human Mobility and Activity Analytics: A Systems Study

Bo Dong  1 , Subir Biswas  1
Affiliations

Wearable Networked Sensing for Human Mobility and Activity Analytics: A Systems Study

Bo Dong et al. Int Conf Commun Syst Netw. 2012 Jan.

Abstract

This paper presents implementation details, system characterization, and the performance of a wearable sensor network that was designed for human activity analysis. Specific machine learning mechanisms are implemented for recognizing a target set of activities with both out-of-body and on-body processing arrangements. Impacts of energy consumption by the on-body sensors are analyzed in terms of activity detection accuracy for out-of-body processing. Impacts of limited processing abilities in the on-body scenario are also characterized in terms of detection accuracy, by varying the background processing load in the sensor units. Through a rigorous systems study, it is shown that an efficient human activity analytics system can be designed and operated even under energy and processing constraints of tiny on-body wearable sensors.

Keywords: Activity Analytics; Machine Learning; Neural Network; On-body Processing; Wearable Sensor Network.

PubMed Disclaimer

Figures

Fig. 1
Fig. 1. Wearable sensor network for activity analysis
Fig. 2
Fig. 2. TDMA MAC layer for on- and off-body communication
Fig. 3
Fig. 3. Acceleration data streams for three representative activities
Fig. 4
Fig. 4. Entropy streams for the representative activities
Fig. 5
Fig. 5. Principal Component Analysis for 10 dynamic activities
Fig. 6
Fig. 6. Hierarchical classifier layering
Fig. 7
Fig. 7. Confusion matrix for the dynamic activity classification
Fig. 8
Fig. 8. Classification accuracy vs. sampling interval
Fig. 9
Fig. 9. Power monitoring arrangement
Fig. 10
Fig. 10. Power consumption traces for different sampling rates
Fig. 11
Fig. 11. Activity recognition as function of power consumption
Fig. 12
Fig. 12. On-body processing model
Fig. 13
Fig. 13. Loss of detection accuracy due to limited processing cycles
See this image and copyright information in PMC

References

    1. Wu WH, Bui AA, Batalin MA, Liu D, Kaiser WJ. Incremental Diagnosis Method for Intelligent Wearable Sensor Systems. IEEE Transactions on Information Technology in Biomedicine. 2007 Sep;11(no. 5):553–562. - PubMed
    1. Wu W, Bui A, Batalin M, Au L, Binney J, Kaiser w. MEDIC: Medical embedded device for individualized care. Artif Intell Med. 2008 Feb;42(no. 2):137–152. - PubMed
    1. Hung K, Zhang YT, Tai B. Wearable medical devices for tele-home healthcare. 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2004 IEMBS ′04; 2004. pp. 5384–5387. - PubMed
    1. Quwaider M, Rao J, Biswas S. Transmission power assignment with postural position inference for on-body wireless communication links. ACM Transactions on Embedded Computing Systems. 2010 Aug;10:1–27.
    1. Maurer U, Smailagic A, Siewiorek DP, Deisher M. Activity Recognition and Monitoring Using Multiple Sensors on Different Body Positions. :113–116.

LinkOut - more resources