A Variational Message Passing Algorithm for Sensor Self-Localization in Wireless Networks
Publikation: Forskning - peer review › Konferenceartikel i proceeding
Standard
A Variational Message Passing Algorithm for Sensor Self-Localization in Wireless Networks. / Pedersen, Claus; Pedersen, Troels; Fleury, Bernard Henri.
IEEE International Symposium on Information Theory Proceedings (ISIT) 2011. IEEE, 2011. s. 2158-2162.Publikation: Forskning - peer review › Konferenceartikel i proceeding
Harvard
APA
CBE
MLA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - A Variational Message Passing Algorithm for Sensor Self-Localization in Wireless Networks
A1 - Pedersen,Claus
A1 - Pedersen,Troels
A1 - Fleury,Bernard Henri
AU - Pedersen,Claus
AU - Pedersen,Troels
AU - Fleury,Bernard Henri
PB - IEEE
PY - 2011/8
Y1 - 2011/8
N2 - We propose a novel algorithm for sensor selflocalization<br/>in cooperative wireless networks where observations<br/>of relative sensor distances are available. The variational message<br/>passing (VMP) algorithm is used to implement a mean field<br/>solution to the estimation of the posterior probabilities of the<br/>sensor positions in an R^2 scenario. Extension to R^3 is straightforward.<br/>Compared to non-parametric methods based on belief<br/>propagation, the VMP algorithm features significantly lower<br/>communication overhead between sensors. This is supported by<br/>performance simulations which show that the estimated mean<br/>localization error of the algorithm stabilizes after approximately<br/>30 iterations.
AB - We propose a novel algorithm for sensor selflocalization<br/>in cooperative wireless networks where observations<br/>of relative sensor distances are available. The variational message<br/>passing (VMP) algorithm is used to implement a mean field<br/>solution to the estimation of the posterior probabilities of the<br/>sensor positions in an R^2 scenario. Extension to R^3 is straightforward.<br/>Compared to non-parametric methods based on belief<br/>propagation, the VMP algorithm features significantly lower<br/>communication overhead between sensors. This is supported by<br/>performance simulations which show that the estimated mean<br/>localization error of the algorithm stabilizes after approximately<br/>30 iterations.
KW - Variational message passing
KW - mean field
KW - localization
KW - wireless sensor network
UR - http://www.isit2011.org
SN - 978-1-4577-0596-0
BT - IEEE International Symposium on Information Theory Proceedings (ISIT) 2011
T2 - IEEE International Symposium on Information Theory Proceedings (ISIT) 2011
SP - 2158
EP - 2162
ER -