An EM method for spatio-temporal blind source separation using an AR-MOG source model

Authors:
Kenneth E. Hild;Hagai T. Attias;Srikantan S. Nagarajan
Affiliations:
Dept. of Radiology, University of California at San Francisco, CA;Golden Metallic, San Francisco, CA;Dept. of Radiology, University of California at San Francisco, CA
Venue:
ICA'06 Proceedings of the 6th international conference on Independent Component Analysis and Blind Signal Separation
Year:
2006

Citing 8
Cited 3

An information-maximization approach to blind separation and blind deconvolution

Neural Computation
Independent factor analysis

Neural Computation
An analysis of entropy estimators for blind source separation

Signal Processing
Markovian source separation

IEEE Transactions on Signal Processing
Signal separation by symmetric adaptive decorrelation: stability,convergence, and uniqueness

IEEE Transactions on Signal Processing
Blind separation of mixture of independent sources through aquasi-maximum likelihood approach

IEEE Transactions on Signal Processing
Equivariant adaptive source separation

IEEE Transactions on Signal Processing
Blind source separation-semiparametric statistical approach

IEEE Transactions on Signal Processing

Letters: Neurally plausible, non-combinatorial iterative independent process analysis

Neurocomputing
Letters: Semi-blind source extraction for fetal electrocardiogram extraction by combining non-Gaussianity and time-correlation

Neurocomputing
Independent Component Analysis for Time-dependent Processes Using AR Source Model

Neural Processing Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

A maximum likelihood blind source separation algorithm is developed. The temporal dependencies are explained by assuming that each source is an AR process and the distribution of the associated i.i.d. innovations process is described using a Mixture of Gaussians (MOG). Unlike most maximum likelihood methods the proposed algorithm takes into account both spatial and temporal information, optimization is performed using the Expectation-Maximization method, and the source model is learned along with the demixing parameters.