Evaluation of Brain Source Separation for MEG Data Applying JADE, Fast-ICA and Natural Gradient-Based Algorithm with Robust Pre-Whitening Technique

Independent component analysis (ICA) has been applied to magnetoencephalographic (MEG) data to determine the behavior and localization of brain sources. In this work, both nonaveraged single-trial data and averaged multiple-trial data are analyzed, in order to study the relationship between the performance of decomposition and the number of averages across data trials. To evaluate the performance of source decomposition, 1) the ratio of source decomposition, which indicates whether source components will be decomposed or not, 2) the power of decomposed components, which is calculated as the covariance of decomposed components, and 3) the accuracy of source estimation, are demonstrated. In addition, a number of existing ICA algorithms such as JADE, Fast-ICA, and the natural gradient-based algorithm with a robust pre-whitening technique are used to decompose MEG data. Our results show the relationship between the accuracy of source decomposition and the number of averages and, by applying the ICA approach, the number of averages can be reduced.

[1]  Terrence J. Sejnowski,et al.  Independent Component Analysis Using an Extended Infomax Algorithm for Mixed Subgaussian and Supergaussian Sources , 1999, Neural Computation.

[2]  Takayuki Arai,et al.  Visualization of Brain Activities of Single-Trial and Averaged Multiple-Trials MEG Data , 2003, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

[3]  Shiro Ikeda,et al.  Independent component analysis for noisy data -- MEG data analysis , 2000, Neural Networks.

[4]  Tzyy-Ping Jung,et al.  Independent Component Analysis of Electroencephalographic Data , 1995, NIPS.

[5]  Marissa Westerfield,et al.  INDEPENDENT COMPONENT ANALYSIS OF SINGLE-TRIAL EVENT-RELATED POTENTIALS , 1999 .

[6]  Erkki Oja,et al.  Independent component approach to the analysis of EEG and MEG recordings , 2000, IEEE Transactions on Biomedical Engineering.

[7]  Terrence J. Sejnowski,et al.  An Information-Maximization Approach to Blind Separation and Blind Deconvolution , 1995, Neural Computation.

[8]  Schuster,et al.  Separation of a mixture of independent signals using time delayed correlations. , 1994, Physical review letters.

[9]  Barak A. Pearlmutter,et al.  A Context-Sensitive Generalization of ICA , 1996 .

[10]  Andrzej Cichocki,et al.  A New Learning Algorithm for Blind Signal Separation , 1995, NIPS.

[11]  Andrzej Cichocki,et al.  Independent component analysis for unaveraged single-trial MEG data decomposition and single-dipole source localization , 2002, Neurocomputing.

[12]  Andrzej Cichocki,et al.  A robust approach to independent component analysis of signals with high-level noise measurements , 2003, IEEE Trans. Neural Networks.

[13]  Andreas Ziehe,et al.  Artifact Reduction in Magnetoneurography Based on Time-Delayed Second Order Correlations , 1998 .

[14]  Aapo Hyvärinen,et al.  A Fast Fixed-Point Algorithm for Independent Component Analysis , 1997, Neural Computation.

[15]  Antoine Souloumiac,et al.  Jacobi Angles for Simultaneous Diagonalization , 1996, SIAM J. Matrix Anal. Appl..