Fourier Density Approximation for Belief Propagation in Wireless Sensor Networks

Abstract

Abstract-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.

Anchor Nodes Positioning for Self-localization in Wireless Sensor Networks using Belief Propagation and Evolutionary Algorithms

“…In [10] boxed bounded sampling is used to address the non-efficient sampling of the algorithm. In another research, By sending Fourier series instead of particles, the transmission data is greatly reduced [11]. [12] and [13] pruned extra edges from the graph and algorithm runs in minimum spanning tree.…”