Multidimensional independent component analysis

Author

Cardoso, Jean-François

Author_Institution

CNRS, Paris, France

Volume

4

fYear

1998

fDate

12-15 May 1998

Firstpage

1941

Abstract

This paper proposes to generalize the notion of independent component analysis (ICA) to the notion of multidimensional independent component analysis (MICA). We start from the ICA or blind source separation (BSS) model and show that it can be uniquely identified provided it is properly parameterized in terms of one-dimensional subspaces. From this standpoint, the BSS/ICA model is generalized to multidimensional components. We discuss how ICA standard algorithms can be adapted to MICA decomposition. The relevance of these ideas is illustrated by a MICA decomposition of ECG signals

Keywords

electrocardiography; matrix algebra; medical signal processing; BSS/ICA mode; ECG signals; ICA standard algorithms; MICA decomposition; blind source separation model; independent component analysis; matrices; multidimensional independent component analysis; one-dimensional subspaces; Algorithm design and analysis; Blind source separation; Electrocardiography; Independent component analysis; Matrix decomposition; Multidimensional systems; Principal component analysis; Signal processing; Source separation; State estimation;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on

Conference_Location

Seattle, WA

ISSN

1520-6149

Print_ISBN

0-7803-4428-6

Type

conf

DOI

10.1109/ICASSP.1998.681443

Filename

681443