Optimization techniques for independent component analysis with applications to EEG data

Authors:
Pando Georgiev;Andrzej Cichocki;Hovagim Bakardjian
Affiliations:
Laboratory for Advanced Brain Signal Processing, Brain Science Institute, The Institute of Physical and Chemical Research (RIKEN), Wako-shi, Saitama 351-0198, Japan;Laboratory for Advanced Brain Signal Processing, Brain Science Institute, The Institute of Physical and Chemical Research (RIKEN), Wako-shi, Saitama 351-0198, Japan;Laboratory for Advanced Brain Signal Processing, Brain Science Institute, The Institute of Physical and Chemical Research (RIKEN), Wako-shi, Saitama 351-0198, Japan
Venue:
Quantitative neuroscience
Year:
2004

Citing 8
Cited 1

Optimal control

Optimal control
Adaptive blind separation of independent sources: a deflation approach

Signal Processing
A fast fixed-point algorithm for independent component analysis

Neural Computation
High-order contrasts for independent component analysis

Neural Computation
Robust Blind Source Separation Utilizing Second and Fourth Order Statistics

ICANN '02 Proceedings of the International Conference on Artificial Neural Networks
Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications

Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications
A blind source separation technique using second-order statistics

IEEE Transactions on Signal Processing
A matrix-pencil approach to blind separation of colorednonstationary signals

IEEE Transactions on Signal Processing

Complex blind source extraction from noisy mixtures using second-order statistics

IEEE Transactions on Circuits and Systems Part I: Regular Papers

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a survey and generalizations of some methods for ICA like maximization of kurtosis and algebraic cumulant methods for a combination of second and fourth order statistics by joint diagonalization of covariance and cumulant matrices depending on time delays. We describe an experiment with EEG data showing that the combination of second and fourth order statistics gives better results for detecting of eye movements.