Title :
Robust estimation of a reception region from location fingerprints
Author_Institution :
Tampere Univ. of Technol., Tampere, Finland
Abstract :
A method for fitting an ellipse-shaped reception region to a set of location-stamped radio signal reception reports, or location fingerprints, is presented. Reports are modelled as having a multivariate Student distribution. The method is less sensitive to outliers than existing smallest-enclosing ellipse and Normal-distribution based methods. A Gibbs sampling algorithm and an Expectation-Maximisation algorithm to compute ellipse parameters are presented.
Keywords :
estimation theory; expectation-maximisation algorithm; radio direction-finding; statistical distributions; Gibbs sampling algorithm; ellipse parameters; expectation-maximisation algorithm; location fingerprints; location-stamped radio signal reception; multivariate student distribution; normal-distribution based methods; reception region; robust estimation; smallest-enclosing ellipse; Atmospheric modeling; Bayesian methods; Computational modeling; Data models; Databases; Robustness; Shape;
Conference_Titel :
Localization and GNSS (ICL-GNSS), 2011 International Conference on
Conference_Location :
Tampere
Print_ISBN :
978-1-4577-0186-3
Electronic_ISBN :
978-1-4577-0187-0
DOI :
10.1109/ICL-GNSS.2011.5955261
