Robust Decentralized Source Localization via Averaging

Published 4 October 2006

Michael Rabbat, Robert Nowak, J.A. Bucklew

DOI10.1109/icassp.2005.1416489

Citations84

TL;DR

A new approach to localizing an isotropic energy source using measurements from distributed sensors based on kernel averaging techniques and suggests that the proposed estimator is much more robust and exhibits better performance characteristics than the popular least squares estimator.

Abstract

We present a new approach to localizing an isotropic energy source using measurements from distributed sensors based on kernel averaging techniques. The location estimate is easily and efficiently calculated in a decentralized fashion. Statistical properties are derived for a very general measurement model. Experiments suggest that the proposed estimator is much more robust and exhibits better performance characteristics than the popular least squares estimator under a variety of conditions.

Keywords

Computer ScienceEngineering

Systems & Control LettersFast linear iterations for distributed averaging

2,722 Citations2004Lin Xiao, Stephen Boyd

IEEE Transactions on Signal ProcessingRelative location estimation in wireless sensor networks

1,877 Citations2003Neal Patwari, Alfred O. Hero +3 more

This work derives CRBs and maximum-likelihood estimators (MLEs) under Gaussian and log-normal models for the TOA and RSS measurements, respectively for sensor location estimation when sensors measure received signal strength or time-of-arrival between themselves and neighboring sensors.

Wireless Sensor Networks: An Information Processing Approach

970 Citations2004Feng Zhao, Leonidas Guibas

This paper presents a meta-modelling framework that automates and automates the very labor-intensive and therefore time-heavy and expensive process of manually cataloging and cataloging sensor networks.

Consensus protocols for networks of dynamic agents

894 Citations2004R.O. Saber, Richard M. Murray

It turns out that the connectivity of the network is the key in reaching a consensus in networks of dynamic agents, and a tight upper bound is found on the maximum fixed time-delay that can be tolerated in the network.

IEEE Signal Processing MagazineSource localization and beamforming

554 Citations2002J.C. Chen, Kung Yao +1 more

Information-Driven Dynamic Sensor Collaboration for Tracking Applications

438 Citations2002Feng Zhao, Jaewon Shin +1 more

The main idea is for a network to determine participants in a "sensor collaboration" by dynamically optimizing the information utility of data for a given cost of communication and computation.

IEEE Journal on Selected Areas in CommunicationsQuantized incremental algorithms for distributed optimization

416 Citations2005Michael Rabbat, Robert D. Nowak

The main conclusion is that as the number of sensors in the network grows, in-network processing will always use less energy than a centralized algorithm, while maintaining a desired level of accuracy.

Entropy-based sensor selection heuristic for target localization

314 Citations2004Hanbiao Wang, Kung Yao +2 more

An entropy-based sensor selection heuristic for localization that greedily selects one sensor in each step without retrieving any actual sensor observations is proposed and is more effective when the optimal candidate sensor is more informative.

View PDF

Minds at UW (University of Wisconsin)Decentralized source localization and tracking

144 Citations2004Michael Rabbat, Robert D. Nowak

A fast, easy-toimplement algorithm for localizing a source using received signal strength measurements is presented, based on incremental subgradient optimization methods, that is much lower than that used by other schemes, especially as network size grows.

View PDF

Distributed Bayesian hypothesis testing in sensor networks

100 Citations2004Murat Alanyali, S. Venkatesh +2 more

It is shown that the message evolution can be re-formulated as the evolution of a linear dynamical system, which is primarily characterized by network connectivity, which leads to a fundamental understanding of as to which network topologies naturally lend themselves to consensus building and conflict avoidance.