Title :
Source number estimation in non-Gaussian noise
Author :
Anand, G.V. ; Nagesha, P.V.
Author_Institution :
Dept. of Electron. & Commun. Eng., PES Univ., Bangalore, India
Abstract :
In this paper a new method of source number estimation in non-Gaussian noise is presented. The proposed signal sub-space identification (SSI) method involves estimation of the array signal correlation matrix and determining the number of positive eigenvalues of the estimated correlation matrix. The SSI method is applied to the problem of estimating the number of plane wave narrowband signals impinging on a uniform linear array. It is shown that the performance of the SSI method in non-Gaussian heavy-tailed noise is significantly better than that of the widely used minimum description length (MDL) method and the recently proposed entropy estimation of eigenvalues (EEE) method based on random matrix theory.
Keywords :
array signal processing; correlation methods; eigenvalues and eigenfunctions; estimation theory; matrix algebra; EEE method based; MDL method; SSI method; array signal correlation matrix estimation; entropy estimation of eigenvalues method; minimum description length method; nonGaussian noise; plane wave narrowband signals; positive eigenvalues; random matrix theory; signal subspace identification method; source number estimation; uniform linear array; Arrays; Correlation; Eigenvalues and eigenfunctions; Estimation; Signal to noise ratio; Vectors; Non-Gaussian noise; noise variance estimation; signal subspace identification; source number estimation;
Conference_Titel :
Signal Processing Conference (EUSIPCO), 2014 Proceedings of the 22nd European
Conference_Location :
Lisbon
