Robust estimation of the number of sources using an MMSE-based MDL method

Teng Long*, Lei Huang, Erke Mao

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

In this paper, using the mutual information, we bridge the probability density function and the minimum mean-square error (MMSE) between the observed data and the desired signal, and then employ the MMSE to construct an MMSE-based MDL criterion for accurate source enumeration. The presented numerical results demonstrate that the proposed method is superior to the existing MDL methods in detection performance.

Original languageEnglish
Title of host publicationIET International Radar Conference 2009
Edition551 CP
DOIs
Publication statusPublished - 2009
EventIET International Radar Conference 2009 - Guilin, China
Duration: 20 Apr 200922 Apr 2009

Publication series

NameIET Conference Publications
Number551 CP

Conference

ConferenceIET International Radar Conference 2009
Country/TerritoryChina
CityGuilin
Period20/04/0922/04/09

Keywords

  • Eigenvalue decomposition (EVD)
  • Minimum description length (MDL)
  • Sensor array processing
  • Source number estimation

Fingerprint

Dive into the research topics of 'Robust estimation of the number of sources using an MMSE-based MDL method'. Together they form a unique fingerprint.

Cite this