Title :
Joint DOA, frequency and model order estimation in additive α-stable noise
Author :
Kannan, B. ; Fitzgerald, W.J. ; Kuruoglu, E.E.
Author_Institution :
Dept. of Eng., Cambridge Univ., UK
fDate :
6/22/1905 12:00:00 AM
Abstract :
Many classes of noise encountered in real-life exhibit outliers that will not fit into a Gaussian noise model. α-stable distributions are among the most important non-Gaussian models that can be used to accurately model impulsive noise environments. We introduce an algorithm that can be used to jointly estimate DOA (direction of arrival), frequency and model order in α-stable noise. Approximating α-stable noise by a Gaussian mixture, we use Bayesian principles to define a posterior density on the signal and noise parameter space. We describe an efficient stochastic algorithm called reversible jump RCMC (Markov chain Monte Carlo) that is used to evaluate our posterior density
Keywords :
Bayes methods; Markov processes; Monte Carlo methods; approximation theory; array signal processing; direction-of-arrival estimation; frequency estimation; impulse noise; stability; stochastic processes; α-stable distributions; Bayesian principles; DOA estimation; Gaussian mixture; Markov chain Monte Carlo algorithm; additive α-stable noise; antenna array processing; direction of arrival estimation; discrete Gaussian mixture approximation; efficient stochastic algorithm; frequency estimation; impulsive noise environments; joint estimation; model order estimation; noise parameter space; nonGaussian models; outliers; posterior density; reversible jump RCMC; signal parameter space; Additive noise; Array signal processing; Bayesian methods; Direction of arrival estimation; Frequency estimation; Gaussian noise; Laboratories; Monte Carlo methods; Narrowband; Noise level;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2000. ICASSP '00. Proceedings. 2000 IEEE International Conference on
Print_ISBN :
0-7803-6293-4
DOI :
10.1109/ICASSP.2000.860230