Abstract : Blind techniques are born in the eighties, when first adaptive equalizers have been designed for digital communications. The problem was to compensate for the effects of an unknown linear single input single output (SISO) stationary channel, without knowing the input. The scientific community used the word ``blind'' for denoting all identification or inversion methods based on output observations only. In fact, blind techniques in digital communications aimed at working when the ``eye was closed'', hence the terminology. At the beginning, the word ``unsupervised'' was sometimes used (for instance in French the wording autodidacte), but it seems now better to be consistent with the worldwide terminology, even if this one is not ideal, and comprehensible only in the context of digital communications. The problem of blind source separation (BSS) differs from blind equalization, adressed previously by Sato, Godard and Benveniste, by the fact that the unknown linear system consists of a several inputs and outputs: such a system is referred to as multiple inputs multiple outputs (MIMO). Although initially the BSS problem was restricted to memoryless channels, it now encompasses all linear or nonlinear MIMO mixtures, with or without memory. The BSS problem has been first formulated in 1984, even if theoretical principles, which drive source separation methods, have been understood later. In this chapter, we briefly introduce the principles and main notations used in this book. A few ideas which contributed to the development of this research domain from its birth are reviewed. The present chapter is ending with a short description of each of the twenty subsequent chapters.
Complete list of metadatas
Contributor : Christian Jutten <>
Submitted on : Monday, March 1, 2010 - 8:10:49 PM
Last modification on : Tuesday, July 9, 2019 - 1:21:26 AM


  • HAL Id : hal-00460655, version 1


Christian Jutten, Pierre Comon. Introduction. Pierre Comon, Christian Jutten. Handbook of blind source separation. Independent component analysis and applications, Academic Press (Elsevier), pp.1-22, 2010. ⟨hal-00460655⟩



Record views