Robust Distributed Estimation Using the Embedded Subgraphs Algorithm

Simple item page
dc.citation.bibtexNamearticleen_US
dc.citation.firstpage2998
dc.citation.issueNumber8en_US
dc.citation.journalTitleIEEE Transactions on Signal Processingen_US
dc.citation.lastpage3010
dc.citation.volumeNumber54en_US
dc.contributor.authorDelouille, Veroniqueen_US
dc.contributor.authorNeelamani, Rameshen_US
dc.contributor.authorBaraniuk, Richard G.en_US
dc.contributor.orgDigital Signal Processing (http://dsp.rice.edu/)en_US
dc.date.accessioned2007-10-31T00:42:41Z
dc.date.available2007-10-31T00:42:41Z
dc.date.issued2006-08-01en
dc.date.modified2006-07-24en_US
dc.date.submitted2006-07-24en_US
dc.descriptionJournal Paperen_US
dc.description.abstractWe propose a new iterative, distributed approach for linear minimum mean-square-error (LMMSE) estimation in graphical models with cycles. The embedded subgraphs algorithm (ESA) decomposes a loopy graphical model into a number of linked embedded subgraphs and applies the classical parallel block Jacobi iteration comprising local LMMSE estimation in each subgraph (involving inversion of a small matrix) followed by an information exchange between neighboring nodes and subgraphs. Our primary application is sensor networks, where the model encodes the correlation structure of the sensor measurements, which are assumed to be Gaussian. The resulting LMMSE estimation problem involves a large matrix inverse, which must be solved in-network with distributed computation and minimal intersensor communication. By invoking the theory of asynchronous iterations, we prove that ESA is robust to temporary communication faults such as failing links and sleeping nodes, and enjoys guaranteed convergence under relatively mild conditions. Simulation studies demonstrate that ESA compares favorably with other recently proposed algorithms for distributed estimation. Simulations also indicate that energy consumption for iterative estimation increases substantially as more links fail or nodes sleep. Thus, somewhat surprisingly, sensor network energy conservation strategies such as low-powered transmission and aggressive sleep schedules could actually prove counterproductive. Our results can be replicated using MATLAB code from www.dsp.rice.edu/software.en_US
dc.description.sponsorshipTexas Instrumentsen_US
dc.description.sponsorshipDefense Advanced Research Projects Agencyen_US
dc.description.sponsorshipOffice of Naval Researchen_US
dc.description.sponsorshipNational Science Foundationen_US
dc.description.sponsorshipAir Force Office of Scientific Researchen_US
dc.identifier.citationV. Delouille, R. Neelamani and R. G. Baraniuk, "Robust Distributed Estimation Using the Embedded Subgraphs Algorithm," <i>IEEE Transactions on Signal Processing,</i> vol. 54, no. 8, 2006.
dc.identifier.doihttp://dx.doi.org/10.1109/TSP.2006.874839en_US
dc.identifier.urihttps://hdl.handle.net/1911/19856
dc.language.isoeng
dc.subjectAsynchronous iterations*
dc.subjectWiener filter*
dc.subjectdistributed estimation*
dc.subjectgraphical models*
dc.subjectmatrix splitting*
dc.subjectsensor networks*
dc.subject.keywordAsynchronous iterationsen_US
dc.subject.keywordWiener filteren_US
dc.subject.keyworddistributed estimationen_US
dc.subject.keywordgraphical modelsen_US
dc.subject.keywordmatrix splittingen_US
dc.subject.keywordsensor networksen_US
dc.subject.otherDSP for Communicationsen_US
dc.titleRobust Distributed Estimation Using the Embedded Subgraphs Algorithmen_US
dc.typeJournal article
dc.type.dcmiText
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Del2006Aug1RobustDist.PDF
Size:
673.92 KB
Format:
Adobe Portable Document Format
Download
Collections
ECE Publications
DSP Publications