Abstract
Designing power-aware signal processing algorithms for activity recognition is challenging as special care needs to be taken to maintain acceptable classification accuracy while minimizing the energy consumption. This paper utilizes the theory of distributed random projection and joint sparse representation to develop a simultaneous dimension reduction and classification approach for multi-sensor activity recognition in BSNs. Both temporal and spatial correlations of sensing data among the multiple sensors are exploited for the purpose of compression and classification. Activity recognition with multiple sensors is formulated as a multi-task joint sparse representation model to combine the strength of multiple sensors for improving the classification accuracy. This method is validated on the WARD dataset using inertial sensors placed on various locations on a human body. Experimental result shows that the proposed DRP-JSR approach achieves better classification performance that is competitive with traditional classifier.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Seeger, C., Buchmann, A., Laerhoven, K.V.: MyHealthAssistant: A phone-based Body sensor network that captures the wearer’s exercises throughout the Day. In: 6th IEEE International Conference on Body Area Networks, pp. 181–189. IEEE Press, New York (2011)
Yang, C.C., Hsu, Y.L.: A review of acclerometry-based wearable motion detector for physical activity monitoring. Sensors 10, 7772–7788 (2010)
Reichardt, D., Miglietta, M., Moretti, L., Morsink, P., Schulz, W.C.: CarTALK 2000: safe and comfortable driving based upon inter-vehicle-communication. In: IEEE Intelligent Vehicle Symposium, pp. 545–550. IEEE Press, Piscataway (2002)
Ghasemzadeh, H., Jarari, R.: Physical movement monitoring using body sensor networks: a phonological approach to construct spatial decision trees. IEEE Transactions on Industrial Informatics 7(1), 66–77 (2011)
Donoho, D.L.: Compressed sensing. IEEE Trans. on Information Theory 52(4), 1289–1306 (2006)
Barson, D., Wakin, M.B., Duate, M.F., Sarvotham, S., Baraniuk, R.G.: Distributed compressed sensing (November 2005) (preprint)
Wright, J., Yang, A., Ganesh, A., Sastry, S.S., Ma, Y.: Robust face recognition via sparse representation. IEEE Trans. on Pattern Anal. Mach. Intell. 31(2), 210–227 (2009)
Yuan, X.P., Liu, X., Yan, S.: Visual classification with multitask joint sparse representation. IEEE Trans. on Image Processing 21(10), 4349–4360 (2012)
Zhang, H., Nasrabadi, N.M., Zhang, Y., Huang, T.S.: Joint dynamic sparse representation for multi-view face recognition. Pattern Recognition 45, 1290–1298 (2012)
Baraniuk, R., Davenport, M., Devore, R., Wakin, M.: A simple proof of the restricted isometry property for random matrices. Constr. Approx. 28(3), 253–263 (2008)
Ji, S., Dunson, D., Carin, L.: Multitask compressive sensing. IEEE Trans. on Signal Processing 57(1), 92–106 (2009)
Yang, A., Kuryloski, P., Bajcsy, R.: WARD: a wearable action recognition database (2009), http://www.eecs.berkeley.edu/~yang/software/WAR/
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Xiao, L., Li, R., Luo, J., Duan, M. (2014). Activity Recognition via Distributed Random Projection and Joint Sparse Representation in Body Sensor Networks. In: Sun, L., Ma, H., Hong, F. (eds) Advances in Wireless Sensor Networks. CWSN 2013. Communications in Computer and Information Science, vol 418. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-54522-1_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-54522-1_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-54521-4
Online ISBN: 978-3-642-54522-1
eBook Packages: Computer ScienceComputer Science (R0)
