Accession Number:

ADA175508

Title:

Statistically/Computationally Efficient Detection in Incompletely Characterized Colored Non-Gaussian Noise via Parametric Modeling

Descriptive Note:

Rept. no. 6, Aug 1984-Jul 1986

Corporate Author:

RHODE ISLAND UNIV KINGSTON DEPT OF ELECTRICAL ENGINEERING

Personal Author(s):

Report Date:

1986-08-01

Pagination or Media Count:

41.0

Abstract:

A generalized likelihood ratio test is known to be able to reliably detect a signal known except for amplitude incompletely characterized colored non-gaussian noise, although it is computationally intensive. A Rao efficient score test shares all the asymptotic properties of the generalized likelihood ratio test for large data records and small signal amplitudes. Its detection performance is asymptotically equivalent to that obtained for a similar detector designed with a priori knowledge of the unknown noise parameters. Computer simulations of the performance of the Rao detector support the theoretical results. A Rao detector built with the knowledge of the true form of the noise PDF is shown to significantly outperform a detector which assumes the noise to be Gaussian.

Subject Categories:

  • Statistics and Probability

Distribution Statement:

APPROVED FOR PUBLIC RELEASE