Task-dependent signal variations in EEG error-related potentials for brain–computer interfaces

OBJECTIVE A major difficulty of brain-computer interface (BCI) technology is dealing with the noise of EEG and its signal variations. Previous works studied time-dependent non-stationarities for BCIs in which the user's mental task was independent of the device operation (e.g., the mental task was motor imagery and the operational task was a speller). However, there are some BCIs, such as those based on error-related potentials, where the mental and operational tasks are dependent (e.g., the mental task is to assess the device action and the operational task is the device action itself). The dependence between the mental task and the device operation could introduce a new source of signal variations when the operational task changes, which has not been studied yet. The aim of this study is to analyse task-dependent signal variations and their effect on EEG error-related potentials. APPROACH The work analyses the EEG variations on the three design steps of BCIs: an electrophysiology study to characterize the existence of these variations, a feature distribution analysis and a single-trial classification analysis to measure the impact on the final BCI performance. RESULTS AND SIGNIFICANCE The results demonstrate that a change in the operational task produces variations in the potentials, even when EEG activity exclusively originated in brain areas related to error processing is considered. Consequently, the extracted features from the signals vary, and a classifier trained with one operational task presents a significant loss of performance for other tasks, requiring calibration or adaptation for each new task. In addition, a new calibration for each of the studied tasks rapidly outperforms adaptive techniques designed in the literature to mitigate the EEG time-dependent non-stationarities.

[1]  Derek Greene,et al.  Unsupervised Learning and Clustering , 2008, Machine Learning Techniques for Multimedia.

[2]  Jonathan R Wolpaw,et al.  Control of a two-dimensional movement signal by a noninvasive brain-computer interface in humans. , 2004, Proceedings of the National Academy of Sciences of the United States of America.

[3]  N. Birbaumer,et al.  BCI2000: a general-purpose brain-computer interface (BCI) system , 2004, IEEE Transactions on Biomedical Engineering.

[4]  Rajesh P. N. Rao,et al.  Towards adaptive classification for BCI , 2006, Journal of neural engineering.

[5]  Todd C. Handy,et al.  Event-related potentials : a methods handbook , 2005 .

[6]  Javier Minguez,et al.  Real-time recognition of feedback error-related potentials during a time-estimation task , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[7]  R. Oostenveld,et al.  Independent EEG Sources Are Dipolar , 2012, PloS one.

[8]  Iñaki Iturrate,et al.  A Noninvasive Brain-Actuated Wheelchair Based on a P300 Neurophysiological Protocol and Automated Navigation , 2009, IEEE Transactions on Robotics.

[9]  H. Bekkering,et al.  Modulation of activity in medial frontal and motor cortices during error observation , 2004, Nature Neuroscience.

[10]  J. Hohnsbein,et al.  ERP components on reaction errors and their functional significance: a tutorial , 2000, Biological Psychology.

[11]  Motoaki Kawanabe,et al.  Toward Unsupervised Adaptation of LDA for Brain–Computer Interfaces , 2011, IEEE Transactions on Biomedical Engineering.

[12]  Iñaki Iturrate,et al.  Robot reinforcement learning using EEG-based reward signals , 2010, 2010 IEEE International Conference on Robotics and Automation.

[13]  José del R. Millán,et al.  Noninvasive brain-actuated control of a mobile robot by human EEG , 2004, IEEE Transactions on Biomedical Engineering.

[14]  R D Pascual-Marqui,et al.  Standardized low-resolution brain electromagnetic tomography (sLORETA): technical details. , 2002, Methods and findings in experimental and clinical pharmacology.

[15]  Ricardo Chavarriaga,et al.  A supervised recalibration protocol for unbiased BCI , 2011 .

[16]  T. Sejnowski,et al.  Dynamic Brain Sources of Visual Evoked Responses , 2002, Science.

[17]  B. Rockstroh,et al.  Biofeedback of slow cortical potentials. I. , 1980, Electroencephalography and clinical neurophysiology.

[18]  D. Yarnitsky,et al.  Neurophysiology of the cortical pain network: revisiting the role of S1 in subjective pain perception via standardized low-resolution brain electromagnetic tomography (sLORETA). , 2008, Journal of Pain.

[19]  Stefan Haufe,et al.  Single-trial analysis and classification of ERP components — A tutorial , 2011, NeuroImage.

[20]  Wolfgang Rosenstiel,et al.  Online use of error-related potentials in healthy users and people with severe motor impairment increases performance of a P300-BCI , 2012, Clinical Neurophysiology.

[21]  Fusheng Yang,et al.  BCI competition 2003-data set IIb: enhancing P300 wave detection using ICA-based subspace projections for BCI applications , 2004, IEEE Transactions on Biomedical Engineering.

[22]  Cuntai Guan,et al.  Unsupervised Brain Computer Interface Based on Intersubject Information and Online Adaptation , 2009, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[23]  Motoaki Kawanabe,et al.  Robust common spatial filters with a maxmin approach , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[24]  K. Müller,et al.  Finding stationary subspaces in multivariate time series. , 2009, Physical review letters.

[25]  C. C. Duncan,et al.  Event-related potentials in clinical research: Guidelines for eliciting, recording, and quantifying mismatch negativity, P300, and N400 , 2009, Clinical Neurophysiology.

[26]  Klaus-Robert Müller,et al.  Co-adaptive calibration to improve BCI efficiency , 2011, Journal of neural engineering.

[27]  Giancarlo Diana,et al.  Cross-validation methods in principal component analysis: A comparison , 2002 .

[28]  Jdel.R. Millan,et al.  On the need for on-line learning in brain-computer interfaces , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[29]  H. Flor,et al.  The thought translation device (TTD) for completely paralyzed patients. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[30]  G. Pfurtscheller,et al.  Brain-Computer Interfaces for Communication and Control. , 2011, Communications of the ACM.

[31]  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.

[32]  Javier Minguez,et al.  A Telepresence Mobile Robot Controlled With a Noninvasive Brain–Computer Interface , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[33]  J. Millán,et al.  Spatio-temporal filtering for EEG error related potentials. , 2011 .

[34]  Markus Ullsperger,et al.  Event-Related Potential Correlates of Performance-Monitoring in a Lateralized Time-Estimation Task , 2011, PloS one.

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

[36]  Luis Montesano,et al.  Single trial recognition of error-related potentials during observation of robot operation , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[37]  C. Neuper,et al.  Combining Brain–Computer Interfaces and Assistive Technologies: State-of-the-Art and Challenges , 2010, Front. Neurosci..

[38]  K.-R. Muller,et al.  Boosting bit rates and error detection for the classification of fast-paced motor commands based on single-trial EEG analysis , 2003, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[39]  Benjamin Blankertz,et al.  Towards a Cure for BCI Illiteracy , 2009, Brain Topography.

[40]  Aapo Hyvärinen,et al.  Validating the independent components of neuroimaging time series via clustering and visualization , 2004, NeuroImage.

[41]  José del R. Millán,et al.  Error-Related EEG Potentials Generated During Simulated Brain–Computer Interaction , 2008, IEEE Transactions on Biomedical Engineering.

[42]  R. Ward,et al.  EMG and EOG artifacts in brain computer interface systems: A survey , 2007, Clinical Neurophysiology.

[43]  Scott Makeig,et al.  Information-based modeling of event-related brain dynamics. , 2006, Progress in brain research.

[44]  G Calhoun,et al.  Brain-computer interfaces based on the steady-state visual-evoked response. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[45]  Clay B. Holroyd,et al.  Reinforcement-related brain potentials from medial frontal cortex: origins and functional significance , 2004, Neuroscience & Biobehavioral Reviews.

[46]  R Chavarriaga,et al.  Learning From EEG Error-Related Potentials in Noninvasive Brain-Computer Interfaces , 2010, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[47]  E. Oja,et al.  Independent Component Analysis , 2013 .

[48]  José del R. Millán,et al.  Brain-controlled telepresence robot by motor-disabled people , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[49]  Dezhong Yao,et al.  Spatio-temporal dynamics of visual selective attention identified by a common spatial pattern decomposition method , 2009, Brain Research.

[50]  A. Engel,et al.  Trial-by-Trial Coupling of Concurrent Electroencephalogram and Functional Magnetic Resonance Imaging Identifies the Dynamics of Performance Monitoring , 2005, The Journal of Neuroscience.