Robust estimation of event-related potentials via particle filter

BACKGROUND AND OBJECTIVE In clinical examinations and brain-computer interface (BCI) research, a short electroencephalogram (EEG) measurement time is ideal. The use of event-related potentials (ERPs) relies on both estimation accuracy and processing time. We tested a particle filter that uses a large number of particles to construct a probability distribution. METHODS We constructed a simple model for recording EEG comprising three components: ERPs approximated via a trend model, background waves constructed via an autoregressive model, and noise. We evaluated the performance of the particle filter based on mean squared error (MSE), P300 peak amplitude, and latency. We then compared our filter with the Kalman filter and a conventional simple averaging method. To confirm the efficacy of the filter, we used it to estimate ERP elicited by a P300 BCI speller. RESULTS A 400-particle filter produced the best MSE. We found that the merit of the filter increased when the original waveform already had a low signal-to-noise ratio (SNR) (i.e., the power ratio between ERP and background EEG). We calculated the amount of averaging necessary after applying a particle filter that produced a result equivalent to that associated with conventional averaging, and determined that the particle filter yielded a maximum 42.8% reduction in measurement time. The particle filter performed better than both the Kalman filter and conventional averaging for a low SNR in terms of both MSE and P300 peak amplitude and latency. For EEG data produced by the P300 speller, we were able to use our filter to obtain ERP waveforms that were stable compared with averages produced by a conventional averaging method, irrespective of the amount of averaging. CONCLUSIONS We confirmed that particle filters are efficacious in reducing the measurement time required during simulations with a low SNR. Additionally, particle filters can perform robust ERP estimation for EEG data produced via a P300 speller.

[1]  Hulusi Kececi,et al.  Habituation and Dishabituation of P300 , 2006, Cognitive and behavioral neurology : official journal of the Society for Behavioral and Cognitive Neurology.

[2]  G. G. Stokes "J." , 1890, The New Yale Book of Quotations.

[3]  Keum-Shik Hong,et al.  Real-time feature extraction of P300 component using adaptive nonlinear principal component analysis , 2011, Biomedical engineering online.

[4]  Zhihua Huang,et al.  A novel single-trial event-related potential estimation method based on compressed sensing , 2013, Neuroscience Bulletin.

[5]  D O Walter,et al.  Biological processing. , 1984, The American journal of physiology.

[6]  Kaiquan Shen,et al.  The Synergy between Complex Channel-Specific FIR Filter and Spatial Filter for Single-Trial EEG Classification , 2013, PloS one.

[7]  G Zouridakis,et al.  Estimation of individual evoked potential components using iterative independent component analysis , 2007, Physics in medicine and biology.

[8]  Saeid Sanei,et al.  The application of particle filters in single trial event-related potential estimation , 2009, Physiological measurement.

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

[11]  Giuseppe De Nicolao,et al.  A multi-task learning approach for the extraction of single-trial evoked potentials , 2013, Comput. Methods Programs Biomed..

[12]  Chee-Ming Ting,et al.  Artifact Removal from Single-Trial ERPs using Non-Gaussian Stochastic Volatility Models and Particle Filter , 2014, IEEE Signal Processing Letters.

[13]  A. Kübler,et al.  Motivation modulates the P300 amplitude during brain–computer interface use , 2010, Clinical Neurophysiology.

[14]  E. Donchin,et al.  Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials. , 1988, Electroencephalography and clinical neurophysiology.

[15]  Chee-Ming Ting,et al.  Modeling and estimation of single-trial event-related potentials using partially observed diffusion processes , 2015, Digit. Signal Process..

[16]  D. Goodin,et al.  Electrophysiological differences between subtypes of dementia. , 1986, Brain : a journal of neurology.

[17]  Carsten Thomsen,et al.  A comparative study between a simplified Kalman filter and Sliding Window Averaging for single trial dynamical estimation of event-related potentials , 2010, Comput. Methods Programs Biomed..

[18]  T. Fukami,et al.  Effects of Button Pressing and Mental Counting on N100, N200, and P300 of Auditory-Event-Related Potential Recording , 2014 .

[19]  Chee-Ming Ting,et al.  Spectral Estimation of Nonstationary EEG Using Particle Filtering With Application to Event-Related Desynchronization (ERD) , 2011, IEEE Transactions on Biomedical Engineering.

[20]  J. Polich,et al.  P300 topography and modality effects from a single-stimulus paradigm. , 1996, Psychophysiology.

[21]  G. Baselli,et al.  Single sweep analysis of visual evoked potentials through a model of parametric identification , 1987, Biological Cybernetics.

[22]  Shigenobu Nakamura,et al.  Objective evaluation of fatigue by event-related potentials , 1998, Journal of the Neurological Sciences.