Detection in colored non-Gaussian noise using cumulants

Brian M. Sadler, Georgios B. Giannakis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations

Abstract

In this paper we consider detection in colored linear non-Gaussian noise of unknown covariance. Higher order cumulants of non-Gaussian processes are estimated in the presence of unknown deterministic and/or Gaussian signals. This allows either parametric or non-parametric estimation of the covariance of the non-Gaussian process via its cumulants. Our approach to detection is to augment methods based on second-order statistics using cumulants. We propose a solution for detection of deterministic signals based on matched filters which incorporate cumulants, where the resulting solutions are valid under either detection hypothesis. This allows for single record detection and obviates the need for prewhitening using noiseonly training records. We also consider detection of random Gaussian signals in non-Gaussian noise.

Original languageEnglish (US)
Title of host publicationIEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1993
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages204-207
Number of pages4
ISBN (Electronic)0780309464
DOIs
StatePublished - 1993
Externally publishedYes
Event1993 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1993 - Minneapolis, United States
Duration: Apr 27 1993Apr 30 1993

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume4
ISSN (Print)1520-6149

Conference

Conference1993 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1993
Country/TerritoryUnited States
CityMinneapolis
Period4/27/934/30/93

Bibliographical note

Publisher Copyright:
© 1993 IEEE

Fingerprint

Dive into the research topics of 'Detection in colored non-Gaussian noise using cumulants'. Together they form a unique fingerprint.

Cite this