Feature selection on movement imagery discrimination and attention detection

Noninvasive brain–computer interfaces (BCI) translate subject’s electroencephalogram (EEG) features into device commands. Large feature sets should be down-selected for efficient feature translation. This work proposes two different feature down-selection algorithms for BCI: (a) a sequential forward selection; and (b) an across-group variance. Power rar ratios (PRs) were extracted from the EEG data for movement imagery discrimination. Event-related potentials (ERPs) were employed in the discrimination of cue-evoked responses. While center-out arrows, commonly used in calibration sessions, cued the subjects in the first experiment (for both PR and ERP analyses), less stimulating arrows that were centered in the visual field were employed in the second experiment (for ERP analysis). The proposed algorithms outperformed other three popular feature selection algorithms in movement imagery discrimination. In the first experiment, both algorithms achieved classification errors as low as 12.5% reducing the feature set dimensionality by more than 90%. The classification accuracy of ERPs dropped in the second experiment since centered cues reduced the amplitude of cue-evoked ERPs. The two proposed algorithms effectively reduced feature dimensionality while increasing movement imagery discrimination and detected cue-evoked ERPs that reflect subject attention.

[1]  W. R. Dillon,et al.  On the Use of Component Scores in the Presence of Group Structure , 1989 .

[2]  G. Pfurtscheller,et al.  Conversion of EEG activity into cursor movement by a brain-computer interface (BCI) , 2004, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[3]  Yu-Te Wu,et al.  Brain computer interface using flash onset and offset visual evoked potentials , 2008, Clinical Neurophysiology.

[4]  Dan Wu,et al.  Combining Spatial Filters for the Classification of Single-Trial EEG in a Finger Movement Task , 2007, IEEE Transactions on Biomedical Engineering.

[5]  S. Schiff,et al.  Interplay of Electroencephalogram Phase and Auditory-Evoked Neural Activity , 2003, The Journal of Neuroscience.

[6]  P.M. Mendes,et al.  Feature down-selection in Brain-Computer Interfaces , 2009, 2009 4th International IEEE/EMBS Conference on Neural Engineering.

[7]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[8]  Steven J. Schiff,et al.  Neuronal spatiotemporal pattern discrimination: The dynamical evolution of seizures , 2005, NeuroImage.

[9]  T. Mergner,et al.  Selecting relevant electrode positions for classification tasks based on the electro-encephalogram , 2006, Medical and Biological Engineering and Computing.

[10]  Yijun Wang,et al.  Predicting Intended Movement Direction Using EEG from Human Posterior Parietal Cortex , 2009, HCI.

[11]  Steven J. Schiff,et al.  Dangerous phase , 2007, Neuroinformatics.

[12]  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.

[13]  G.E. Birch,et al.  A New Design of the Asynchronous Brain Computer Interface Using the Knowledge of the Path of Features , 2005, Conference Proceedings. 2nd International IEEE EMBS Conference on Neural Engineering, 2005..

[14]  David G. Stork,et al.  Pattern Classification , 1973 .

[15]  Febo Cincotti,et al.  Human Movement-Related Potentials vs Desynchronization of EEG Alpha Rhythm: A High-Resolution EEG Study , 1999, NeuroImage.

[16]  E. W. Sellers,et al.  Toward enhanced P300 speller performance , 2008, Journal of Neuroscience Methods.

[17]  E Wascher,et al.  The interaction of stimulus- and response-related processes measured by event-related lateralizations of the EEG. , 1996, Electroencephalography and clinical neurophysiology.

[18]  Jens Haueisen,et al.  Independent component analysis: comparison of algorithms for the investigation of surface electrical brain activity , 2009, Medical & Biological Engineering & Computing.

[19]  Bernhard Graimann,et al.  A comparison approach toward finding the best feature and classifier in cue-based BCI , 2007, Medical & Biological Engineering & Computing.

[20]  Gary E. Birch,et al.  Automatic user customization for improving the performance of a self-paced brain interface system , 2006, Medical and Biological Engineering and Computing.

[21]  Huan Liu,et al.  Efficient Feature Selection via Analysis of Relevance and Redundancy , 2004, J. Mach. Learn. Res..

[22]  Jonathan R. Wolpaw,et al.  Brain-computer interfaces (BCIs) for communication and control , 2007, Assets '07.

[23]  G. Pfurtscheller,et al.  Rapid prototyping of an EEG-based brain-computer interface (BCI) , 2001, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[24]  Scott T. Grafton,et al.  Premotor Cortex Activation during Observation and Naming of Familiar Tools , 1997, NeuroImage.

[25]  B. Thompson,et al.  Use of Structure Coefficients in Published Multiple Regression Articles: β is not Enough , 2001 .

[26]  Gert Pfurtscheller,et al.  Motor imagery and direct brain-computer communication , 2001, Proc. IEEE.

[27]  I. Jolliffe.  Principal Component Analysis , 2002 .

[28]  Febo Cincotti,et al.  Relevant EEG features for the classification of spontaneous motor-related tasks , 2002, Biological Cybernetics.

[29]  E. Vogel,et al.  Sensory gain control (amplification) as a mechanism of selective attention: electrophysiological and neuroimaging evidence. , 1998, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[30]  Bernard D. Flury,et al.  Why Multivariate Statistics , 1997 .

[31]  Bernhard Schölkopf,et al.  Support vector channel selection in BCI , 2004, IEEE Transactions on Biomedical Engineering.

[32]  Xiaorong Gao,et al.  A brain–computer interface using motion-onset visual evoked potential , 2008, Journal of neural engineering.