The application of particle filters in single trial event-related potential estimation

In this paper, an approach for the estimation of single trial event-related potentials (ST-ERPs) using particle filters (PFs) is presented. The method is based on recursive Bayesian mean square estimation of ERP wavelet coefficients using their previous estimates as prior information. To enable a performance evaluation of the approach in the Gaussian and non-Gaussian distributed noise conditions, we added Gaussian white noise (GWN) and real electroencephalogram (EEG) signals recorded during rest to the simulated ERPs. The results were compared to that of the Kalman filtering (KF) approach demonstrating the robustness of the PF over the KF to the added GWN noise. The proposed method also outperforms the KF when the assumption about the Gaussianity of the noise is violated. We also applied this technique to real EEG potentials recorded in an odd-ball paradigm and investigated the correlation between the amplitude and the latency of the estimated ERP components. Unlike the KF method, for the PF there was a statistically significant negative correlation between amplitude and latency of the estimated ERPs, matching previous neurophysiological findings.

[1]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[2]  Jian Li,et al.  ASEO: A Method for the Simultaneous Estimation of Single-Trial Event-Related Potentials and Ongoing Brain Activities , 2009, IEEE Transactions on Biomedical Engineering.

[3]  Fetsje Bijma,et al.  A maximum-likelihood estimator for trial-to-trial variations in noisy MEG/EEG data sets , 2004, IEEE Transactions on Biomedical Engineering.

[4]  S. Haykin,et al.  Adaptive Filter Theory , 1986 .

[5]  Anirban DasGupta.  Maximum Likelihood Estimates , 2008 .

[6]  M. Rugg,et al.  Electrophysiology of Mind. , 1996 .

[7]  Tom Eichele,et al.  Tracking pattern learning with single-trial event-related potentials , 2006, Clinical Neurophysiology.

[8]  Mingzhou Ding,et al.  Estimation of single-trial multicomponent ERPs: Differentially variable component analysis (dVCA) , 2003, Biological Cybernetics.

[9]  J. Kaipio,et al.  Subspace regularization method for the single-trial estimation of evoked potentials , 1999, IEEE Transactions on Biomedical Engineering.

[10]  D.H. Lange,et al.  Segmented matched filtering of single event related evoked potentials , 1995, IEEE Transactions on Biomedical Engineering.

[11]  G. Kitagawa.  Monte Carlo Filter and Smoother for Non-Gaussian Nonlinear State Space Models , 1996 .

[12]  P. Jaskowski,et al.  Amplitudes and latencies of single-trial ERP's estimated by a maximum-likelihood method , 1999, IEEE Transactions on Biomedical Engineering.

[13]  D. H. Lange,et al.  Modeling and estimation of single evoked brain potential components , 1997, IEEE Transactions on Biomedical Engineering.

[14]  Hamid Reza Mohseni,et al.  Single trial estimation of event-related potentials using particle filtering , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[15]  Maarten Jansen,et al.  Noise Reduction by Wavelet Thresholding , 2001 .

[16]  D.H. Lange,et al.  A robust parametric estimator for single-trial movement related brain potentials , 1996, IEEE Transactions on Biomedical Engineering.

[17]  Nando de Freitas,et al.  Sequential Monte Carlo Methods in Practice , 2001, Statistics for Engineering and Information Science.

[18]  T. Gasser,et al.  Variable latencies of noisy signals: Estimation and testing in brain potential data , 1987 .

[19]  Hamid Reza Mohseni,et al.  Preprocrssing of Event-Related Potential Signals via Kalman Filtering and Smoothing , 2007, 2007 15th International Conference on Digital Signal Processing.

[20]  T. Sejnowski,et al.  Analysis and visualization of single‐trial event‐related potentials , 2001, Human brain mapping.

[21]  Robi Polikar,et al.  Comparative multiresolution wavelet analysis of ERP spectral bands using an ensemble of classifiers approach for early diagnosis of Alzheimer's disease , 2007, Comput. Biol. Medicine.

[22]  Hamid Reza Mohseni,et al.  A beamforming particle filter for EEG dipole source localization , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[23]  S Cerutti,et al.  Analysis of visual evoked potentials through Wiener filtering applied to a small number of sweeps. , 1987, Journal of biomedical engineering.

[24]  Jun S. Liu,et al.  Metropolized independent sampling with comparisons to rejection sampling and importance sampling , 1996, Stat. Comput..

[25]  Jari P. Kaipio,et al.  Single-trial estimation of multichannel evoked-potential measurements , 2003, IEEE Transactions on Biomedical Engineering.

[26]  Piotr J. Durka,et al.  Single evoked potential reconstruction by means of wavelet transform , 2004, Biological Cybernetics.

[27]  P. KREJCfR.  A MAXIMUM LIKELIHOOD ESTIMATOR , 2009 .

[28]  Clare D. McGillem,et al.  Measurements of Signal Components in Single Visualy Evoked Brain Potentials , 1977, IEEE Transactions on Biomedical Engineering.

[29]  Kristine L. Bell,et al.  A Tutorial on Particle Filters for Online Nonlinear/NonGaussian Bayesian Tracking , 2007 .

[30]  R. Quian Quiroga,et al.  Single-trial event-related potentials with wavelet denoising , 2003, Clinical Neurophysiology.

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

[32]  Mika P. Tarvainen,et al.  Single-trial dynamical estimation of event-related potentials: a Kalman filter-based approach , 2005, IEEE Transactions on Biomedical Engineering.

[33]  S. Sanei,et al.  Sequential monte carlo techniques for EEG dipole placing and tracking , 2008, 2008 5th IEEE Sensor Array and Multichannel Signal Processing Workshop.

[34]  M. von Spreckelsen,et al.  Estimation of single-evoked cerebral potentials by means of parametric modeling and Kalman filtering , 1988, IEEE Transactions on Biomedical Engineering.

[35]  Andrew P. Bagshaw,et al.  Single trial variability of EEG and fMRI responses to visual stimuli , 2007, NeuroImage.

[36]  S. Mallat.  A wavelet tour of signal processing , 1998 .