Paper Info
Title
RSS-based sensor network localization in contaminated Gaussian measurement noise
Abstract
We study received signal strength-based cooperative localization in wireless sensor networks. We assume that the measurement noise fits a contaminated Gaussian model so as to take into account some outlier conditions. In addition, some environment-dependent parameters are assumed to be unknown. We propose an expectation-maximization based algorithm for robust centralized network localization without offline training. As benchmark for comparison, we express the best achievable localization accuracy in terms of the Cramér-Rao bound. Experimental results demonstrate the advantages of the proposed algorithm as compared to some representative algorithms.
Year
DOI
Venue
2013
10.1109/CAMSAP.2013.6714022
CAMSAP
Keywords
Field
DocType
cooperative localization,received signal strength (rss),expectation-maximisation algorithm,rss-based sensor network localization,cramer-rao bound,expectation-maximization based algorithm,centralized network localization,localization accuracy,expectation-maximization (em),cramér-rao bound (crb),received signal strength,wireless sensor networks,gaussian noise,contaminated gaussian measurement noise,sensor placement,non-gaussian noise,control engineering
Computer science,Algorithm,Outlier,Gaussian,Gaussian network model,Signal strength,Artificial intelligence,RSS,Wireless sensor network,Gaussian noise,Machine learning
Conference
ISBN
Citations 
PageRank 
978-1-4673-3144-9
2
0.37
References 
Authors
4
5
Name
Order
Citations
PageRank
Feng Yin112714.30
Ang Li220.37
Abdelhak M. Zoubir31036148.03
Carsten Fritsche415714.72
Fredrik Gustafsson52287281.33