• DocumentCode
    1319863
  • Title

    A generalized ICA algorithm

  • Author

    Stoll, Benoit ; Moreau, Eric

  • Author_Institution
    ISITV, MS-GESSY, La Valette du Var, France
  • Volume
    7
  • Issue
    4
  • fYear
    2000
  • fDate
    4/1/2000 12:00:00 AM
  • Firstpage
    90
  • Lastpage
    92
  • Abstract
    In this paper, we consider the source separation problem through a block algorithm based on the maximization of contrast functions. We propose a new contrast with parameterized cross-cumulants. It allows us to put three classical contrasts in a common framework. Following the same spirit of the independent component analysis (ICA) algorithm, we derive the analytical solution for the case of two sources. Finally, a computer simulation is performed to illustrate the behavior of a Jacobi-like algorithm for the maximization of the new contrast.
  • Keywords
    higher order statistics; signal processing; Jacobi-like algorithm; block algorithm; computer simulation; contrast functions maximization; cumulants; generalized ICA algorithm; independent component analysis; source separation problem; Algorithm design and analysis; Computer simulation; Independent component analysis; Jacobian matrices; Matrix decomposition; Reactive power; Source separation; Statistical analysis; Statistics; Vectors;
  • fLanguage
    English
  • Journal_Title
    Signal Processing Letters, IEEE
  • Publisher
    ieee
  • ISSN
    1070-9908
  • Type

    jour

  • DOI
    10.1109/97.833006
  • Filename
    833006