Computing R.O.C. for Quadratic Detectors.

Abstract

After defining a broad class of nonlinear detectors--those whose outputs are quadratic forms in terms of their inputs, exact probability distributions are derived when time samples are independent for three important sub-classes: coherent power (sum and square), correlator, and incoherent power (square and sum) detectors. An asymptotic method is used to obtain the distributions of the more general class of detector, including dependent time samples. Computer programs, example calculations, and many graphical results are included; the emphasis is on imparting a methodology which has been successful in computing R.O.C. for the detectors modeled, for both Gaussian and deterministic signals. (Author)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 10, 1976
Accession Number
ADA050477

Entities

People

  • L. E. Miller

Organizations

  • Naval Ordnance Laboratory

Tags

Communities of Interest

  • C4I
  • Energy and Power Technologies
  • Materials and Manufacturing Processes
  • Weapons Technologies

DTIC Thesaurus Topics

  • Applied Mathematics
  • Asymptotic Series
  • Computer Programs
  • Correlators
  • Data Science
  • Detection
  • Detectors
  • False Alarms
  • Gaussian Distributions
  • Information Science
  • Information Theory
  • Power
  • Probability
  • Probability Density Functions
  • Probability Distributions
  • Random Variables
  • Warning Systems

Fields of Study

  • Physics

Readers

  • Image Processing and Computer Vision.
  • Statistical inference.
  • Theoretical Analysis.