Determining the Number of Signals by Information Theoretic Criteria.

Abstract

The determination of the number of signals in a wide class of problems, including array processing, harmonic retrieval and pole retrieval, is addressed. A new approach, based on the application of the information theoretic criteria for model identification introduced by Akaike, Schwartz and Rissanen, is presented. It is shown that the criterion introduced by Schwartz and Rissanen yields a consistent estimate of the number of signals, while the criterion introduced by Akaike yields an consistent estimate that tends, in the large sample limit, to overestimate the number of signals. (Author)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 11, 1983
Accession Number
ADA142748

Entities

People

  • M. Wax
  • Thomas Kailath

Organizations

  • Stanford University

Tags

Communities of Interest

  • Materials and Manufacturing Processes
  • Sensors

DTIC Thesaurus Topics

  • Air Force
  • Arrays
  • Contracts
  • Covariance
  • Eigenvalues
  • Eigenvectors
  • Electrical Engineering
  • Engineering
  • Frequency
  • Frequency Domain
  • Identification
  • Information Theory
  • Judgment
  • Noise
  • Observation
  • Probability
  • Signal Processing

Readers

  • Regression Analysis.
  • Speech Processing/Speech Recognition.