ICA of correlated sources mismodeled as uncorrelated: Performance analysis

Dana Lahat*, Hagit Messer, Jean François Cardoso

*Corresponding author for this work

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

Abstract

In this contribution we present closed-form performance analysis for the problem of blind separation of correlated sources when the separation algorithm is ignorant of the source model, and assumes only scalar sources. Our data model is of one scalar source and one multidimensional source. We obtain a closed-form analytical expression for applying joint diago-nalization on correlated sources. The obtained expression is different from the optimal expression (in the minimal mean square error (MMSE) sense), obtained by joint block diago-nalization. Numerical evaluations quantify the loss of performance due to mismodeling.

Original languageEnglish
Title of host publication2009 IEEE/SP 15th Workshop on Statistical Signal Processing, SSP '09
Pages489-492
Number of pages4
DOIs
StatePublished - 2009
Event2009 IEEE/SP 15th Workshop on Statistical Signal Processing, SSP '09 - Cardiff, United Kingdom
Duration: 31 Aug 20093 Sep 2009

Publication series

NameIEEE Workshop on Statistical Signal Processing Proceedings

Conference

Conference2009 IEEE/SP 15th Workshop on Statistical Signal Processing, SSP '09
Country/TerritoryUnited Kingdom
CityCardiff
Period31/08/093/09/09

Keywords

  • Blind source separation
  • Independent component analysis
  • Joint diagonalization
  • Mismodeling

Fingerprint

Dive into the research topics of 'ICA of correlated sources mismodeled as uncorrelated: Performance analysis'. Together they form a unique fingerprint.

Cite this