On the blind source separation of human electroencephalogram by approximate joint diagonalization of second order statistics

Over the last ten years blind source separation (BSS) has become a prominent processing tool in the study of human electroencephalography (EEG). Without relying on head modeling BSS aims at estimating both the waveform and the scalp spatial pattern of the intracranial dipolar current responsible of the observed EEG. In this review we begin by placing the BSS linear instantaneous model of EEG within the framework of brain volume conduction theory. We then review the concept and current practice of BSS based on second-order statistics (SOS) and on higher-order statistics (HOS), the latter better known as independent component analysis (ICA). Using neurophysiological knowledge we consider the fitness of SOS-based and HOS-based methods for the extraction of spontaneous and induced EEG and their separation from extra-cranial artifacts. We then illustrate a general BSS scheme operating in the time-frequency domain using SOS only. The scheme readily extends to further data expansions in order to capture experimental source of variations as well. A simple and efficient implementation based on the approximate joint diagonalization of Fourier cospectral matrices is described (AJDC). We conclude discussing useful aspects of BSS analysis of EEG, including its assumptions and limitations.

[1]  Xi-Lin Li,et al.  Nonorthogonal Joint Diagonalization Free of Degenerate Solution , 2007, IEEE Transactions on Signal Processing.

[2]  F. L. D. Silva,et al.  Event-related EEG/MEG synchronization and desynchronization: basic principles , 1999, Clinical Neurophysiology.

[3]  Serge Dégerine,et al.  A Comparative Study of Approximate Joint Diagonalization Algorithms for Blind Source Separation in Presence of Additive Noise , 2007, IEEE Transactions on Signal Processing.

[4]  Ricardo Vigário,et al.  Overlearning in Marginal Distribution-Based ICA: Analysis and Solutions , 2003, J. Mach. Learn. Res..

[5]  A. Pérez-Villalba Rhythms of the Brain, G. Buzsáki. Oxford University Press, Madison Avenue, New York (2006), Price: GB £42.00, p. 448, ISBN: 0-19-530106-4 , 2008 .

[6]  Abdeldjalil Aïssa-El-Bey,et al.  Underdetermined Blind Separation of Nondisjoint Sources in the Time-Frequency Domain , 2007, IEEE Transactions on Signal Processing.

[7]  Jan Beran,et al.  Statistics for long-memory processes , 1994 .

[8]  Fabian J. Theis,et al.  Blind signal separation into groups of dependent signals using joint block diagonalization , 2005, 2005 IEEE International Symposium on Circuits and Systems.

[9]  Christian Jutten,et al.  Space or time adaptive signal processing by neural network models , 1987 .

[10]  Motoaki Kawanabe,et al.  A resampling approach to estimate the stability of one-dimensional or multidimensional independent components , 2002, IEEE Transactions on Biomedical Engineering.

[11]  Dinh-Tuan Pham,et al.  Blind separation of instantaneous mixtures of nonstationary sources , 2001, IEEE Trans. Signal Process..

[12]  Andrzej Cichocki,et al.  Adaptive blind signal and image processing , 2002 .

[13]  El Mostafa Fadaili,et al.  Nonorthogonal Joint Diagonalization/Zero Diagonalization for Source Separation Based on Time-Frequency Distributions , 2007, IEEE Transactions on Signal Processing.

[14]  Arie Yeredor,et al.  Non-orthogonal joint diagonalization in the least-squares sense with application in blind source separation , 2002, IEEE Trans. Signal Process..

[15]  Zhi-Lin Zhang,et al.  Morphologically constrained ICA for extracting weak temporally correlated signals , 2008, Neurocomputing.

[16]  Marco Congedo,et al.  Subspace Projection Filters for Real-Time Brain Electromagnetic Imaging , 2006, IEEE Transactions on Biomedical Engineering.

[17]  Fernando H. Lopes da Silva,et al.  Functional localization of brain sources using EEG and/or MEG data: volume conductor and source models. , 2004 .

[18]  Theo Gasser,et al.  Correction of muscle artefacts in the EEG power spectrum , 2005, Clinical Neurophysiology.

[19]  F. H. Lopes da Silva,et al.  Computer-assisted EEG diagnosis: pattern recognition and brain mapping , 1998 .

[20]  C. Joyce,et al.  Automatic removal of eye movement and blink artifacts from EEG data using blind component separation. , 2004, Psychophysiology.

[21]  Cuntai Guan,et al.  Feature Selection Based on Fisher Ratio and Mutual Information Analyses for Robust Brain Computer Interface , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[22]  Mercedes Atienza,et al.  Muscle Artifact Removal from Human Sleep EEG by Using Independent Component Analysis , 2008, Annals of Biomedical Engineering.

[23]  Terrence J. Sejnowski,et al.  Complex Independent Component Analysis of Frequency-Domain Electroencephalographic Data , 2003, Neural Networks.

[24]  Robert Plonsey,et al.  Bioelectromagnetism: Principles and Applications of Bioelectric and Biomagnetic Fields , 1995 .

[25]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[26]  A. Yeredor Blind separation of Gaussian sources via second-order statistics with asymptotically optimal weighting , 2000, IEEE Signal Processing Letters.

[27]  Andrzej Cichocki,et al.  Adaptive Blind Signal and Image Processing - Learning Algorithms and Applications , 2002 .

[28]  F. H. Lopes da Silva,et al.  Event-related potentials: methodology and quantification , 1998 .

[29]  Matthew T. Sutherland,et al.  Reliable detection of bilateral activation in human primary somatosensory cortex by unilateral median nerve stimulation , 2006, NeuroImage.

[30]  L. Fety,et al.  New methods for signal separation , 1988 .

[31]  J. Gotman,et al.  Removal of EMG and ECG artifacts from EEG based on wavelet transform and ICA , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[32]  Jean-Franois Cardoso High-Order Contrasts for Independent Component Analysis , 1999, Neural Computation.

[33]  Ernst Fernando Lopes Da Silva Niedermeyer,et al.  Electroencephalography, basic principles, clinical applications, and related fields , 1982 .

[34]  P. Welch The use of fast Fourier transform for the estimation of power spectra: A method based on time averaging over short, modified periodograms , 1967 .

[35]  Antoine Souloumiac,et al.  Blind source detection and separation using second order non-stationarity , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[36]  Matthew T. Sutherland,et al.  Validation of SOBI components from high-density EEG , 2005, NeuroImage.

[37]  J.C. Mosher,et al.  Multiple dipole modeling and localization from spatio-temporal MEG data , 1992, IEEE Transactions on Biomedical Engineering.

[38]  Klaus Obermayer,et al.  Quadratic optimization for simultaneous matrix diagonalization , 2006, IEEE Transactions on Signal Processing.

[39]  P. Rossini,et al.  Functional source separation from magnetoencephalographic signals , 2006, Human brain mapping.

[40]  R. Greenblatt,et al.  Local linear estimators for the bioelectromagnetic inverse problem , 2005, IEEE Transactions on Signal Processing.

[41]  Armando Malanda,et al.  Independent Component Analysis as a Tool to Eliminate Artifacts in EEG: A Quantitative Study , 2003, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[42]  Andrzej Cichocki,et al.  Blind noise reduction for multisensory signals using ICA and subspace filtering, with application to EEG analysis , 2002, Biological Cybernetics.

[43]  Yimin Zhang,et al.  Blind Separation of Nonstationary Sources Based on Spatial Time-Frequency Distributions , 2006, EURASIP J. Adv. Signal Process..

[44]  Arie Yeredor,et al.  A fast approximate joint diagonalization algorithm using a criterion with a block diagonal weight matrix , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[45]  G.F. Inbar,et al.  An improved P300-based brain-computer interface , 2005, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[46]  Christopher J. James,et al.  Temporally constrained ICA: an application to artifact rejection in electromagnetic brain signal analysis , 2003, IEEE Transactions on Biomedical Engineering.

[47]  Adel Belouchrani,et al.  A one step time-frequency blind identification , 2003, Seventh International Symposium on Signal Processing and Its Applications, 2003. Proceedings..

[48]  Rémi Gribonval,et al.  A survey of Sparse Component Analysis for blind source separation: principles, perspectives, and new challenges , 2006, ESANN.

[49]  S P Fitzgibbon,et al.  Removal of EEG Noise and Artifact Using Blind Source Separation , 2007, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[50]  B. Thompson Canonical Correlation Analysis , 1984 .

[51]  Lang Tong,et al.  BLIND ESTIMATION OF CORRELATED SOURCE SIGNALS , 1990, 1990 Conference Record Twenty-Fourth Asilomar Conference on Signals, Systems and Computers, 1990..

[52]  H. Sebastian Seung,et al.  Algorithms for Non-negative Matrix Factorization , 2000, NIPS.

[53]  J. Cardoso,et al.  Blind beamforming for non-gaussian signals , 1993 .

[54]  Barry D. Van Veen,et al.  MEG and EEG source localization in beamspace , 2006, IEEE Transactions on Biomedical Engineering.

[55]  Paul Van de Heyninga,et al.  Correlation between Independent Components of scalp EEG and intracranial EEG ( iEEG ) time series , 2007 .

[56]  Klaus-Robert Müller,et al.  Enhancing the signal-to-noise ratio of ICA-based extracted ERPs , 2006, IEEE Transactions on Biomedical Engineering.

[57]  Dinh Tuan Pham,et al.  Blind separation of instantaneous mixture of sources via the Gaussian mutual information criterion , 2000, 2000 10th European Signal Processing Conference.

[58]  Soo-Young Lee Blind Source Separation and Independent Component Analysis: A Review , 2005 .

[59]  Miguel Angel Mañanas,et al.  A comparative study of automatic techniques for ocular artifact reduction in spontaneous EEG signals based on clinical target variables: A simulation case , 2008, Comput. Biol. Medicine.

[60]  Matthew T. Sutherland,et al.  Recovery of correlated neuronal sources from EEG: The good and bad ways of using SOBI , 2005, NeuroImage.

[61]  Lang Tong,et al.  Indeterminacy and identifiability of blind identification , 1991 .

[62]  T. Sejnowski,et al.  Removal of eye activity artifacts from visual event-related potentials in normal and clinical subjects , 2000, Clinical Neurophysiology.

[63]  P. Nunez,et al.  Source analysis of EEG oscillations using high-resolution EEG and MEG. , 2006, Progress in brain research.

[64]  C.J. James,et al.  On the use of Spectrally Constrained ICA applied to single-channel Ictal EEG recordings within a Dynamical Embedding Framework , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[65]  Lucas C. Parra,et al.  Blind Source Separation via Generalized Eigenvalue Decomposition , 2003, J. Mach. Learn. Res..

[66]  Lars Kai Hansen,et al.  Model Selection for Convolutive ICA with an Application to Spatiotemporal Analysis of EEG , 2007, Neural Computation.

[67]  Andreas Ziehe,et al.  Blind Source Separation Techniques for Decomposing Event-Related Brain Signals , 2004, Int. J. Bifurc. Chaos.

[68]  Kiyotoshi Matsuoka,et al.  A neural net for blind separation of nonstationary signals , 1995, Neural Networks.

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

[70]  Andrzej Cichocki,et al.  Second Order Nonstationary Source Separation , 2002, J. VLSI Signal Process..

[71]  Gwen A. Frishkoff,et al.  Automated protocol for evaluation of electromagnetic component separation (APECS): Application of a framework for evaluating statistical methods of blink extraction from multichannel EEG , 2007, Clinical Neurophysiology.

[72]  Steven G. Johnson,et al.  The Design and Implementation of FFTW3 , 2005, Proceedings of the IEEE.

[73]  R N Vigário,et al.  Extraction of ocular artefacts from EEG using independent component analysis. , 1997, Electroencephalography and clinical neurophysiology.

[74]  Franca Tecchio,et al.  Functional source separation applied to induced visual gamma activity , 2008, Human brain mapping.

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

[76]  R. Fisher,et al.  Epileptic seizure disorders , 1985, Journal of Neurology.

[77]  S. J. Roberts,et al.  Independent Component Analysis: Source Assessment Separation, a Bayesian Approach , 1998 .

[78]  M. Corbetta,et al.  Electrophysiological signatures of resting state networks in the human brain , 2007, Proceedings of the National Academy of Sciences.

[79]  Andreas Ziehe,et al.  A Fast Algorithm for Joint Diagonalization with Non-orthogonal Transformations and its Application to Blind Source Separation , 2004, J. Mach. Learn. Res..

[80]  F. H. Lopes da Silva,et al.  Biophysical aspects of EEG and magnetoencephalogram generation , 1998 .

[81]  Yan Wang,et al.  Contrasting single-trial ERPs between experimental manipulations: Improving differentiability by blind source separation , 2006, NeuroImage.

[82]  Christian Jutten,et al.  Blind separation of sources, part I: An adaptive algorithm based on neuromimetic architecture , 1991, Signal Process..

[83]  Peter F. Driessen,et al.  Independent component analysis and clustering improve signal-to-noise ratio for statistical analysis of event-related potentials , 2007, Clinical Neurophysiology.

[84]  Moeness G. Amin,et al.  Blind source separation based on time-frequency signal representations , 1998, IEEE Trans. Signal Process..

[85]  Eric Moulines,et al.  A blind source separation technique using second-order statistics , 1997, IEEE Trans. Signal Process..

[86]  Christopher J. James,et al.  Extracting Rhythmic Brain Activity for Brain-Computer Interfacing through Constrained Independent Component Analysis , 2007, Comput. Intell. Neurosci..

[87]  I F Gorodnitsky,et al.  Neuromagnetic source imaging with FOCUSS: a recursive weighted minimum norm algorithm. , 1995, Electroencephalography and clinical neurophysiology.

[88]  Christopher J. James,et al.  On Semi-Blind Source Separation Using Spatial Constraints With Applications in EEG Analysis , 2006, IEEE Transactions on Biomedical Engineering.

[89]  Yuanqing Li,et al.  Blind estimation of channel parameters and source components for EEG signals: a sparse factorization approach , 2006, IEEE Transactions on Neural Networks.

[90]  Lang Tong,et al.  Waveform-preserving blind estimation of multiple independent sources , 1993, IEEE Trans. Signal Process..

[91]  Yannick Deville,et al.  Temporal and time-frequency correlation-based blind source separation methods. Part I: Determined and underdetermined linear instantaneous mixtures , 2007, Signal Process..

[92]  Fabian J. Theis,et al.  On the use of joint diagonalization in blind signal processing , 2006, 2006 IEEE International Symposium on Circuits and Systems.

[93]  Wim Van Paesschen,et al.  Canonical Correlation Analysis Applied to Remove Muscle Artifacts From the Electroencephalogram , 2006, IEEE Transactions on Biomedical Engineering.

[94]  E. Whitham,et al.  Scalp electrical recording during paralysis: Quantitative evidence that EEG frequencies above 20Hz are contaminated by EMG , 2007, Clinical Neurophysiology.

[95]  M. Wax,et al.  A least-squares approach to joint diagonalization , 1997, IEEE Signal Processing Letters.

[96]  F. H. Lopes da Silva,et al.  Functional localization of brain sources using EEG and/or MEG data: volume conductor and source models. , 2004, Magnetic resonance imaging.

[97]  L. Trahms,et al.  Single evoked somatosensory MEG responses extracted by time delayed decorrelation , 2005, IEEE Transactions on Signal Processing.

[98]  Patrick Berg,et al.  Artifact Correction of the Ongoing EEG Using Spatial Filters Based on Artifact and Brain Signal Topographies , 2002, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[99]  J. Cardoso On the Performance of Orthogonal Source Separation Algorithms , 1994 .

[100]  Fabian J. Theis,et al.  Uniqueness of complex and multidimensional independent component analysis , 2004, Signal Process..

[101]  Andreas Ziehe,et al.  TDSEP — an efficient algorithm for blind separation using time structure , 1998 .

[102]  Arie Yeredor,et al.  Asymptotically Optimal Blind Separation of Parametric Gaussian Sources , 2004, ICA.

[103]  Ramesh Srinivasan,et al.  Identification of wave‐like spatial structure in the SSVEP: Comparison of simultaneous EEG and MEG , 2007, Statistics in medicine.

[104]  Ignace Lemahieu,et al.  Removing Ocular Movement Artefacts by a Joint Smoothened Subspace Estimator , 2007, Comput. Intell. Neurosci..

[105]  P. Comon,et al.  Ica: a potential tool for bci systems , 2008, IEEE Signal Processing Magazine.

[106]  T. Ens,et al.  Blind signal separation : statistical principles , 1998 .

[107]  J. Sarvas Basic mathematical and electromagnetic concepts of the biomagnetic inverse problem. , 1987, Physics in medicine and biology.

[108]  Serge Dégerine,et al.  Second-order blind separation of sources based on canonical partial innovations , 2000, IEEE Trans. Signal Process..

[109]  Fabian J. Theis,et al.  Pivot Selection Strategies in Jacobi Joint Block-Diagonalization , 2007, ICA.

[110]  Dinh Tuan Pham,et al.  Joint Approximate Diagonalization of Positive Definite Hermitian Matrices , 2000, SIAM J. Matrix Anal. Appl..

[111]  Aapo Hyvärinen,et al.  Fast and robust fixed-point algorithms for independent component analysis , 1999, IEEE Trans. Neural Networks.

[112]  G. Darmois,et al.  Analyse générale des liaisons stochastiques: etude particulière de l'analyse factorielle linéaire , 1953 .

[113]  Wei Lu,et al.  Approach and applications of constrained ICA , 2005, IEEE Transactions on Neural Networks.

[114]  D. Pham,et al.  Exploiting source non stationary and coloration in blind source separation , 2002, 2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628).

[115]  Bhaskar D. Rao,et al.  Sparse solutions to linear inverse problems with multiple measurement vectors , 2005, IEEE Transactions on Signal Processing.

[116]  Jean-François Cardoso,et al.  Multidimensional independent component analysis , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[117]  Patrick Suppes,et al.  Single-Trial Classification of MEG Recordings , 2007, IEEE Transactions on Biomedical Engineering.

[118]  Pierre Comon,et al.  Independent component analysis, A new concept? , 1994, Signal Process..

[119]  Lei Ding,et al.  Motor imagery classification by means of source analysis for brain–computer interface applications , 2004, Journal of neural engineering.

[120]  Joep J. M. Kierkels,et al.  A model-based objective evaluation of eye movement correction in EEG recordings , 2006, IEEE Transactions on Biomedical Engineering.

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

[122]  A. Cichocki,et al.  Blind separation of nonstationary sources in noisy mixtures , 2000 .

[123]  Wolfgang Rosenstiel,et al.  Online Artifact Removal for Brain-Computer Interfaces Using Support Vector Machines and Blind Source Separation , 2007, Comput. Intell. Neurosci..