Current Source Density Estimation Enhances the Performance of Motor-Imagery-Related Brain–Computer Interface

The objective is to evaluate the impact of EEG referencing schemes and spherical surface Laplacian (SSL) methods on the classification performance of motor-imagery (MI)-related brain–computer interface systems. Two EEG referencing schemes: common referencing and common average referencing and three surface Laplacian methods: current source density (CSD), finite difference method, and SSL using realistic head model were implemented separately for pre-processing of the EEG signals recorded at the scalp. A combination of filter bank common spatial filter for features extraction and support vector machine for classification was used for both pairwise binary classifications and four-class classification of MI tasks. The study provides three major outcomes: 1) the CSD method performs better than CR, providing a significant improvement of 3.02% and 5.59% across six binary classification tasks and four-class classification task, respectively; 2) the combination of a greater number of channels at the pre-processing stage as compared with the feature extraction stage yields better classification accuracies for all the Laplacian methods; and 3) the efficiency of all the surface Laplacian methods reduced significantly in the case of a fewer number of channels considered during the pre-processing.

[1]  Febo Cincotti,et al.  High-resolution EEG techniques for brain–computer interface applications , 2008, Journal of Neuroscience Methods.

[2]  F. Perrin,et al.  Spherical splines for scalp potential and current density mapping. , 1989, Electroencephalography and clinical neurophysiology.

[3]  Martin Luessi,et al.  Real-Time MEG Source Localization Using Regional Clustering , 2015, Brain Topography.

[4]  H. Flor,et al.  A spelling device for the paralysed , 1999, Nature.

[5]  J R Wolpaw,et al.  Spatial filter selection for EEG-based communication. , 1997, Electroencephalography and clinical neurophysiology.

[6]  Gert Pfurtscheller,et al.  Characterization of four-class motor imagery EEG data for the BCI-competition 2005 , 2005, Journal of neural engineering.

[7]  Hubert Cecotti,et al.  Convolutional Neural Networks for P300 Detection with Application to Brain-Computer Interfaces , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Cuntai Guan,et al.  Cortical Source Localization for Analysing Single-Trial Motor Imagery EEG , 2015, 2015 IEEE International Conference on Systems, Man, and Cybernetics.

[9]  Paul L. Nunez,et al.  The surface laplacian, high resolution EEG and controversies , 2005, Brain Topography.

[10]  Dennis J McFarland,et al.  The advantages of the surface Laplacian in brain-computer interface research. , 2015, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[11]  Guofa Shou,et al.  Detection of EEG Spatial–Spectral–Temporal Signatures of Errors: A Comparative Study of ICA-Based and Channel-Based Methods , 2014, Brain Topography.

[12]  Jürgen Kayser,et al.  Issues and considerations for using the scalp surface Laplacian in EEG/ERP research: A tutorial review. , 2015, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[13]  G. Prasad,et al.  Single-trial effective brain connectivity patterns enhance discriminability of mental imagery tasks , 2017, Journal of neural engineering.

[14]  Girijesh Prasad,et al.  EWMA model based shift-detection methods for detecting covariate shifts in non-stationary environments , 2015, Pattern Recognit..

[15]  W. A. Sarnacki,et al.  Electroencephalographic (EEG) control of three-dimensional movement , 2010, Journal of neural engineering.

[16]  Yijun Wang,et al.  Improving Brain–Computer Interfaces Using Independent Component Analysis , 2012 .

[17]  Ramesh Srinivasan,et al.  Improved Surface Laplacian Estimates of Cortical Potential Using Realistic Models of Head Geometry , 2012, IEEE Transactions on Biomedical Engineering.

[18]  Rabab K Ward,et al.  A survey of signal processing algorithms in brain–computer interfaces based on electrical brain signals , 2007, Journal of neural engineering.

[19]  Ad Aertsen,et al.  Review of the BCI Competition IV , 2012, Front. Neurosci..

[20]  J. Fermaglich.  Electric Fields of the Brain: The Neurophysics of EEG , 1982 .

[21]  Bin He,et al.  Noninvasive Brain-Computer Interfaces Based on Sensorimotor Rhythms , 2015, Proceedings of the IEEE.

[22]  G. Pfurtscheller,et al.  The BCI competition III: validating alternative approaches to actual BCI problems , 2006, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[23]  Olivier Bertrand,et al.  Scalp Current Density Mapping: Value and Estimation from Potential Data , 1987, IEEE Transactions on Biomedical Engineering.

[24]  B. Rockstroh,et al.  Mapping EEG-potentials on the surface of the brain: A strategy for uncovering cortical sources , 2005, Brain Topography.

[25]  G. Huiskamp.  Difference formulas for the surface Laplacian on a triangulated surface , 1991 .

[26]  Cuntai Guan,et al.  Filter Bank Common Spatial Pattern Algorithm on BCI Competition IV Datasets 2a and 2b , 2012, Front. Neurosci..

[27]  Hubert Cecotti,et al.  A Self-Paced and Calibration-Less SSVEP-Based Brain–Computer Interface Speller , 2010, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[28]  Girijesh Prasad,et al.  Adaptive learning with covariate shift-detection for motor imagery-based brain–computer interface , 2015, Soft Computing.

[29]  Wei Wu.  Probabilistic Common Spatial Patterns for Multichannel EEG Analysis , 2015 .

[30]  Cuntai Guan,et al.  High performance P300 speller for brain-computer interface , 2004, IEEE International Workshop on Biomedical Circuits and Systems, 2004..

[31]  A. van Oosterom,et al.  The surface Laplacian of the potential: theory and application , 1996, IEEE Transactions on Biomedical Engineering.

[32]  Bin He,et al.  EEG Source Imaging Enhances the Decoding of Complex Right-Hand Motor Imagery Tasks , 2016, IEEE Transactions on Biomedical Engineering.

[33]  Claudio Carvalhaes,et al.  The surface Laplacian technique in EEG: Theory and methods. , 2014, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[34]  C. Tenke,et al.  Response- and Stimulus-Related ERP Asymmetries in a Tonal Oddball Task: A Laplacian Analysis , 2004, Brain Topography.

[35]  D. Tucker,et al.  Spatial sampling and filtering of EEG with spline Laplacians to estimate cortical potentials , 2005, Brain Topography.

[36]  D. Tucker,et al.  EEG coherency. I: Statistics, reference electrode, volume conduction, Laplacians, cortical imaging, and interpretation at multiple scales. , 1997, Electroencephalography and clinical neurophysiology.

[37]  C. Tenke,et al.  Generator localization by current source density (CSD): Implications of volume conduction and field closure at intracranial and scalp resolutions , 2012, Clinical Neurophysiology.

[38]  O Bertrand,et al.  A theoretical justification of the average reference in topographic evoked potential studies. , 1985, Electroencephalography and clinical neurophysiology.

[39]  Nelson L. Max,et al.  Weights for Computing Vertex Normals from Facet Normals , 1999, J. Graphics, GPU, & Game Tools.

[40]  Michal Niezabitowski,et al.  Elimination of bioelectrical source overlapping effects from the EEG measurements , 2016, 2016 17th International Carpathian Control Conference (ICCC).

[41]  B. Hjorth.  An on-line transformation of EEG scalp potentials into orthogonal source derivations. , 1975, Electroencephalography and clinical neurophysiology.

[42]  Wei Wu,et al.  RSTFC: A Novel Algorithm for Spatio-Temporal Filtering and Classification of Single-Trial EEG , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[43]  M. Peters,et al.  Volume conduction effects in EEG and MEG. , 1998, Electroencephalography and clinical neurophysiology.

[44]  P. Nunez,et al.  High-resolution EEG using spline generated surface Laplacians on spherical and ellipsoidal surfaces , 1993, IEEE Transactions on Biomedical Engineering.

[45]  D J McFarland,et al.  An EEG-based brain-computer interface for cursor control. , 1991, Electroencephalography and clinical neurophysiology.

[46]  Robert Oostenveld,et al.  FieldTrip: Open Source Software for Advanced Analysis of MEG, EEG, and Invasive Electrophysiological Data , 2010, Comput. Intell. Neurosci..

[47]  Gert Pfurtscheller,et al.  Brain-computer interface: a new communication device for handicapped persons , 1993 .

[48]  Franck Vidal,et al.  Linking EEG signals, brain functions and mental operations: Advantages of the Laplacian transformation. , 2015, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[49]  Kenneth J. Pope,et al.  Surface Laplacian of Central Scalp Electrical Signals is Insensitive to Muscle Contamination , 2013, IEEE Transactions on Biomedical Engineering.

[50]  Gregor Strobbe,et al.  EEG beamforming to extract better features of motor imagery in a two-class real-time BCI , 2013 .

[51]  Michael X. Cohen,et al.  Comparison of different spatial transformations applied to EEG data: A case study of error processing. , 2015, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.