ABSTRACT

This chapter introduces basic concepts, criteria, and algorithms for Blind signal separation (BSS) and blind deconvolution and explores relationships between the BSS and blind deconvolution tasks. The chapter considers open issues and challenges within these related fields. BSS is sometimes used interchangeably with independent component analysis (ICA), technically, BSS and ICA are different tasks. BSS is most appropriate in situations where a linear mixture model is plausible. BSS offers the potential of extracting coherent and identifiable signal features that can be more easily tied to specific bodily functions or ailments. Two formulations of BSS task have been extensively explored: those that use spatial independence and non-Gaussianity, and those that use spatial decorrelation and temporal correlation. Density matching BSS methods rely heavily on concepts in information theory, a half-century-young field with applications in numerous fields including communications, economics, neuro-science, and physics. The chapter outlines spatio-temporal extensions of BSS and blind deconvolution, namely, the multichannel blind deconvolution and convolutive BSS tasks, respectively.