Fourier Density Approximation for Belief Propagation in Wireless Sensor Networks

  • Chongning Na
  • Hui Wang
  • Dragan Obradovic
  • Uwe D. Hanebeck
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 35)


Many distributed inference problems in wireless sensor networks can be represented by probabilistic graphical models, where belief propagation, an iterative message passing algorithm provides a promising solution. In order to make the algorithm efficient and accurate, messages which carry the belief information from one node to the others should be formulated in an appropriate format. This paper presents two belief propagation algorithms where non-linear and non-Gaussian beliefs are approximated by Fourier density approximations, which significantly reduces power consumptions in the belief computation and transmission. We use self-localization in wireless sensor networks as an example to illustrate the performance of this method.


Density approximation Belief propagation Distributed inference Wireless sensor network 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Gharavi, H., Kumar, S. (Eds.): Special issue on sensor networks and applications. In Proceedings of the IEEE, vol.91, no.8, Aug. 2003Google Scholar
  2. 2.
    Kumar, S., Zhao, F., Shepherd, D. (Eds.): Special issue on collaborative information processing. In IEEE Signal Processing Magazine, vol.19, no.2, Mar. 2002Google Scholar
  3. 3.
    Ihler, A., Fisher, J., Moses, R., Willsky, A.: Nonparametric belief propagation for self-calibration in sensor networks. In Proceedings of IPSN 2004Google Scholar
  4. 4.
    Kronmal, R., Tarter, M.: The estimation of probability densities and cumulatives by Fourier series methods. In Journal of the American Statistical Association, vol.63, no.323, pp.925–952, Sep. 1968Google Scholar
  5. 5.
    Brunn, D., Sawo, F., Hanebeck, U.D.: Efficient nonlinear Bayesian estimation based on Fourier densities. In Proceedings of the 2006 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI 2006), Germany 2006Google Scholar
  6. 6.
    Brunn, D., Sawo, F., Hanebeck, U.D.: Nonlinear multidimensional Bayesian estimation with Fourier densities. In Proceedings of the 2006 IEEE Conference on Decision and Control (CDC 2006), pp.1303–1308, San Diego, California, Dec. 2006Google Scholar
  7. 7.
    Lauritzen, S.L.: Graphical Models. Oxford University Press, Oxford, 1996Google Scholar
  8. 8.
    Clifford, P.: Markov random fields in statistics. In Grimmett, G.R., Welsh, D.J.A. (Eds.) Disorder in Physical Systems, pp.19C32. Oxford University Press, Oxford, 1990Google Scholar
  9. 9.
    Paskin, M., Guestrin, C.: A robust architecture for distributed inference in sensor networks. Intel Research, Technical Report IRB-TR-03-039, 2004.Google Scholar
  10. 10.
    Aji, S.M., McEliece, R.J.: The generalized distributive law. IEEE Transactions on Information Theory vol.46, pp.325–343, Mar. 2000Google Scholar
  11. 11.
    Murphy, K., Weiss, Y., Jordan, M.: Loopy-belief propagation for approximate inference: An empirical study. In Uncertainty in Artificial Intelligence vol.15, pp.467–475, Jul. 1999Google Scholar
  12. 12.
    Kschischang, F.R., Frey, B.J., Loeliger, H.A.: Factor graph and the sum-product algorithm. IEEE Transactions Information Theory, vol.47, no.2, pp.498–518, Feb. 2001.Google Scholar
  13. 13.
    Hanebeck, U.D.: Progressive Bayesian estimation for nonlinear discrete-time systems: the measurement step. In Proceedings of the 2003 IEEE Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI 2003), pp.173–178, Tokyo, Japan, Jul. 2003.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Chongning Na
    • 1
  • Hui Wang
    • 2
  • Dragan Obradovic
    • 1
  • Uwe D. Hanebeck
    • 3
  1. 1.Siemens AG, Corporate Technology, Information and CommunicationsMunichGermany
  2. 2.Information and Communications, Corporate Technology, Siemens AGMunichGermany
  3. 3.Intelligent Sensor-Actuator-Systems Laboratory (ISAS), Institute of Computer Science and Engineering, Universitaet Karlsruhe (TH)KarlsruheGermany

Personalised recommendations