Optimal detection of non-Gaussian random signals in Gaussian noise

Reviewed and analyzed issues related to Polyustrovsky naguszewski representation of random signals and noises in the PA-dilinjah aerospace systems. It is shown that real signals and non-Gaussian noise can be represented by the corresponding poly-Gaussian processes. The properties of poly-Gaussian random processes are considered and analyzed. The relationship between the parameters of the mixture of signals and noise and their components is analyzed.

Download Full-text

CONSTRUCTIVE ACTION OF ADDITIVE NOISE IN OPTIMAL DETECTION

International Journal of Bifurcation and Chaos ◽

10.1142/s0218127405013824 ◽

2005 ◽

Vol 15 (09) ◽

pp. 2985-2994 ◽

Cited By ~ 14

Author(s):

FRANÇOIS CHAPEAU-BLONDEAU ◽

DAVID ROUSSEAU

Keyword(s):

Information Processing ◽

White Noise ◽

Stochastic Resonance ◽

Gaussian Noise ◽

Additive Noise ◽

Optimal Detection ◽

Processing Conditions ◽

Noise Optimization ◽

Additive White Noise ◽

Non Gaussian

The optimal detection of a signal of known form hidden in additive white noise is examined in the framework of stochastic resonance and noise-aided information processing. Conditions are exhibited where the performance in the optimal detection increases when the level of the additive (non-Gaussian bimodal) noise is raised. On the additive signal–noise mixture, when a threshold quantization is performed prior to the optimal detection, another form of improvement by noise can be obtained, with subthreshold signals and Gaussian noise. Optimization of the quantization threshold shows that even in symmetric detection settings, the optimal threshold can be away from the center of symmetry and in subthreshold configuration of the signals. These properties concerning non-Gaussian noise and nonlinear preprocessing in optimal detection, are meaningful to the current exploration of the various modalities and potentialities of stochastic resonance.

Download Full-text

Optimal detection in colored non-Gaussian noise with unknown parameters

10.1109/icassp.1987.1169781 ◽

2005 ◽

Cited By ~ 4

Author(s):

S. Kay ◽

D. Sengupta

Keyword(s):

Gaussian Noise ◽

Optimal Detection ◽

Unknown Parameters ◽

Non Gaussian

Download Full-text

Analysis of the Transformation of Random Signals and Noise Using Poly-Gaussian Models

Journal of Physics Conference Series ◽

10.1088/1742-6596/2096/1/012137 ◽

2021 ◽

Vol 2096 (1) ◽

pp. 012137

Author(s):

V M Artyushenko ◽

V I Volovach

Keyword(s):

Linear System ◽

Gaussian Noise ◽

Nonlinear Element ◽

Gaussian Models ◽

Series Connection ◽

Output Response ◽

Information Measuring ◽

Gaussian Representation ◽

Random Signals ◽

Non Gaussian

Abstract Analysis performed transformation of random signals and noise in linear and nonlinear systems based on the use of poly-Gaussian models and multidimensional PDF of the output paths of information-measuring and radio systems. The classification of elements of these systems, as well as expressions describing the input action and output response of the system are given. It is shown that the analysis of information-measuring and systems can be carried out using poly-Gaussian models. The analysis is carried out with a series connection of a linear system and a nonlinear element, a series connection of a nonlinear element and a linear system, as well as with a parallel connection of the named links. The output response in all cases will be a mixture of a poly-Gaussian distribution with a number of components. An example of the analysis of signal transmission through an intermediate frequency amplifier and a linear detector against a background of non-Gaussian noise is given. The resulting probability density distribution of the sum of the signal and non-Gaussian noise at the output of the detector will be poly-Rice. The multidimensional probability distribution density of the output processes of the nonlinear signal envelope detector is also obtained. The results of modeling the found distribution densities are presented. It is shown that the use of the poly-Gaussian representation of signals and noise, as well as the impulse response of the system, makes it possible to effectively analyze inertial systems in the time domain.

Download Full-text