tspd - Distributed Detection in Sensor Networks with Packet...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Distributed Detection in Sensor Networks with Packet Losses and Finite Capacity Links * Venkatesh Saligrama Murat Alanyali Onur Savas † Abstract We consider the problem of classifying among a set of M hypotheses via distributed noisy sensors. The sensors can collaborate over a communication network and the task is to arrive at a consensus about the event after exchanging messages. We apply a variant of belief propagation as a strategy for collaboration to arrive at a solution to the distributed classification problem. We show that the message evolution can be re-formulated as the evolution of a linear dynamical system, which is primarily characterized by network connectivity. We show that a consensus to the centralized MAP estimate can almost always reached by the sensors for any arbitrary network. We then extend these results in several directions. First, we demonstrate that these results continue to hold with quantization of the messages, which is appealing from the point of view of finite bit rates supportable between links. We then demonstrate robustness against packet losses, which implies that optimal decisions can be achieved with asynchronous transmissions as well. Next, we present an account of energy requirements for distributed detection and demonstrate significant improvement over conventional decentralized detection. Finally, extensions to distributed estimation are described. 1 Introduction Recent advances in computing and communication technologies provide impetus for deploying massive net- works of tiny sensors capable of measuring, processing and exchanging data over a wireless medium. In typical applications energy limitation of individual sensors is a primary bottleneck as it entails further constraints in communication bandwidth, reliability and connectivity. Information processing models that account for such * This research was supported by ONR Young Investigator Award N00014-02-100362, PECASE Award and NSF CAREER Program under grants ANI-0238397, ECS-0449194 and NSF programs CCF-0430983, and CNS-0435353. † The authors are affiliated with the Department of Electrical and Computer Engineering at Boston University. E-mail: { srv,alanyali,savas } @bu.edu. 1 limitations have recently received much attention within the networking, signal processing and information- theory communities. In this paper we address this issue from a distributed viewpoint and consider a collection of sensors observing a single phenomena through noisy measurements. The sensors can only collaborate through a network defined by a connectivity graph in which messages may be subject to quantization or random losses. The task is to exchange messages in order to arrive at a consensus that reflects the classification of the event by a hypothetical node that has access to all observations and observation models....
View Full Document

This note was uploaded on 11/03/2009 for the course COMPUTERS CS537 taught by Professor Salman during the Spring '09 term at Texas A&M University–Commerce.

Page1 / 30

tspd - Distributed Detection in Sensor Networks with Packet...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online