Signal enumeration in Gaussian and non-Gaussian noise using entropy estimation of eigenvalues

In this paper, a novel method based on the entropy estimation of the observation space eigenvalues is proposed to estimate the number of independent sources impinging on a sensor array. In this method we do not need to know a priori information about the noise model and we can use it in any Gaussian...

Full description

Saved in:
Bibliographic Details
Published in:Digital signal processing 2018-07, Vol.78, p.163-174
Main Authors: Asadi, Hamid, Seyfe, Babak
Format: Article
Language:English
Subjects:
Eigenvalues
Entropy estimation
Kernel function
Non-Gaussian noise
Source enumeration
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, a novel method based on the entropy estimation of the observation space eigenvalues is proposed to estimate the number of independent sources impinging on a sensor array. In this method we do not need to know a priori information about the noise model and we can use it in any Gaussian or non-Gaussian model of observations and noise. Our analytical results show that the proposed algorithm is consistent and an approximation for probability of false alarm and an upper bound for probability of missed detection are derived analytically. The performance of the proposed algorithm is compared with the existing methods in the presence of Gaussian and non-Gaussian noise via the simulations. It is shown that this information theoretic method called EEE, has a better performance than those methods in the literature, especially in non-Gaussian noise environment.
ISSN:1051-2004
1095-4333
DOI:10.1016/j.dsp.2018.03.005