Analysis and online realization of the CCA approach for blind source separation

Wei Liu, Danilo P. Mandic, Andrzej Cichocki

Research output: Contribution to journalArticlepeer-review

40 Citations (SciVal)

Abstract

A critical analysis of the canonical correlation analysis (CCA) approach in blind source separation (BSS) is provided. It is proved that by maximizing the autocorrelation functions of the recovered signals we can separate the source signals successfully. It is further shown that the CCA approach represents the same class of generalized eigenvalue decomposition (GEVD) problems as the matrix pencil method. Finally, online realizations of the CCA approach are discussed with a linear-predictor-based algorithm studied as an example.

Original languageEnglish
Pages (from-to)1505-1510
Number of pages6
JournalIEEE Transactions on Neural Networks
Volume18
Issue number5
DOIs
Publication statusPublished - Sep 2007
Externally publishedYes

Keywords

  • Blind source separation (BSS)
  • Canonical correlation analysis (CCA)
  • Linear predictor
  • Matrix pencil
  • Second-order statistics (SOS)

Fingerprint

Dive into the research topics of 'Analysis and online realization of the CCA approach for blind source separation'. Together they form a unique fingerprint.

Cite this