Accession Number:

ADA123454

Title:

Alternatives to Optimal Detection.

Descriptive Note:

Technical rept. no. 8, Feb 81-Oct 82,

Corporate Author:

PRINCETON UNIV NJ INFORMATION SCIENCES AND SYSTEMS LAB

Report Date:

1982-11-01

Pagination or Media Count:

125.0

Abstract:

In this report, signal detection in non-Gaussian noise is considered. This work can be divided roughly into two parts. The essential purpose of the first part is to investigate the existence and design of some sub-optimal detectors which are modifications of the sample mean detector. The method used here is based on orthogonal series expansions in terms of the Gaussian distribution and the moments of the noise distribution. The second part is concerned with signal detection in bounded noise. Both the known signal case and the unknown signal case are studied. An algorithm of a sequential nature is devised.

Subject Categories:

  • Theoretical Mathematics
  • Cybernetics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE