Near optimal detection of complex signals with unknown parameters

Author

Hanson, Grant A. ; Iltis, Ronald A.

Author_Institution

Weapons Div., Naval Air Warfare Center, China Lake, CA, USA

Volume

1

fYear

1997

fDate

2-5 Nov. 1997

Firstpage

530

Abstract

We consider the problem of detecting complex signals with uncertain parameters including amplitude and phase. For one class of problems the optimal solution is a three-layer neural network with an infinite number of intermediate nodes. We investigate several finite size structures which approximate the output of the optimal detector and deliver near optimal detection performance with reduced complexity. Training these structures is shown to have an interpretation in terms of minimizing cross entropy.

Keywords

Gaussian distribution; approximation theory; minimum entropy methods; neural nets; optimisation; signal detection; amplitude; circular Gaussian distribution; complex signals; cross entropy minimisation; finite size structures; function approximation; intermediate nodes; near optimal detection; optimal detector; optimal solution; phase; reduced complexity; three-layer neural network; unknown parameters; Communication networks; Detectors; Laboratories; Lakes; Minimax techniques; Neural networks; Phase detection; Radar detection; Signal detection; Weapons;

fLanguage

English

Publisher

ieee

Conference_Titel

Signals, Systems & Computers, 1997. Conference Record of the Thirty-First Asilomar Conference on

Conference_Location

Pacific Grove, CA, USA

ISSN

1058-6393

Print_ISBN

0-8186-8316-3

Type

conf

DOI

10.1109/ACSSC.1997.680434

Filename

680434