Title
A new expression of the asymptotic performances of Maximum Likelihood DOA estimation method with modeling errors
Abstract
This paper provides a new analytic expression of the RMS (Root Mean Square) error and bias of the Maximum Likelihood (ML) Direction Of Arrival (DOA) estimator in the presence of steering vectors modeling errors. The reference [4] proposes a first order approximation of these performances which is adapted to small modeling errors. In order to take into account larger modeling errors and provide tools for designing experimental set-up, a more accurate and easily usable derivation of these performances is necessary For such an investigation, the DOA estimation errors are written as an hermitean form with a stochastic vector composed by the modeling errors. Finally, a closed form expression between the performances (bias and RMS error) and statistical moments of the model error are deduced from the statistics of the hermitean form. Simulations confirm the theoretical results.
Year
Venue
Keywords
2004
EUSIPCO
direction-of-arrival estimation,error analysis,maximum likelihood estimation,mean square error methods,doa estimation error,ml direction of arrival estimator,rms error,asymptotic performance,closed form expression,hermitean form,maximum likelihood doa estimation method,root mean square error,statistical moment,steering vector modeling error,stochastic vector,signal processing
Field
DocType
ISBN
Errors-in-variables models,Mathematical optimization,Direction of arrival,Algorithm,Closed-form expression,Root mean square,Root-mean-square deviation,Maximum likelihood sequence estimation,Mathematics,Estimator,Method of moments (statistics)
Conference
978-320-0001-65-7
Citations 
PageRank 
References 
1
0.42
0
Authors
3
Name
Order
Citations
PageRank
A. Ferreol130525.51
Pascal Larzabal253564.76
M. Viberg3917188.13