Predicting Mental Imagery-Based BCI Performance from Personality, Cognitive Profile and Neurophysiological Patterns

Mental-Imagery based Brain-Computer Interfaces (MI-BCIs) allow their users to send commands to a computer using their brain-activity alone (typically measured by ElectroEncephaloGraphy—EEG), which is processed while they perform specific mental tasks. While very promising, MI-BCIs remain barely used outside laboratories because of the difficulty encountered by users to control them. Indeed, although some users obtain good control performances after training, a substantial proportion remains unable to reliably control an MI-BCI. This huge variability in user-performance led the community to look for predictors of MI-BCI control ability. However, these predictors were only explored for motor-imagery based BCIs, and mostly for a single training session per subject. In this study, 18 participants were instructed to learn to control an EEG-based MI-BCI by performing 3 MI-tasks, 2 of which were non-motor tasks, across 6 training sessions, on 6 different days. Relationships between the participants’ BCI control performances and their personality, cognitive profile and neurophysiological markers were explored. While no relevant relationships with neurophysiological markers were found, strong correlations between MI-BCI performances and mental-rotation scores (reflecting spatial abilities) were revealed. Also, a predictive model of MI-BCI performance based on psychometric questionnaire scores was proposed. A leave-one-subject-out cross validation process revealed the stability and reliability of this model: it enabled to predict participants’ performance with a mean error of less than 3 points. This study determined how users’ profiles impact their MI-BCI control ability and thus clears the way for designing novel MI-BCI training protocols, adapted to the profile of each user.

[1]  F.R.H. Zijlstra,et al.  Efficiency in work behaviour: A design approach for modern tools , 1993 .

[2]  Klaus-Robert Müller,et al.  Neurophysiological predictor of SMR-based BCI performance , 2010, NeuroImage.

[3]  Dennis J. McFarland,et al.  Brain–computer interfaces for communication and control , 2002, Clinical Neurophysiology.

[4]  L. DeStefano.  Bruininks-Oseretsky Test of Motor Proficiency , 2008 .

[5]  Christa Neuper,et al.  Neurofeedback Training for BCI Control , 2009 .

[6]  K. Müller,et al.  Psychological predictors of SMR-BCI performance , 2012, Biological Psychology.

[7]  Benjamin Blankertz,et al.  Visuo-motor coordination ability predicts performance with brain-computer interfaces controlled by modulation of sensorimotor rhythms (SMR) , 2014, Front. Hum. Neurosci..

[8]  D. McFarland,et al.  An auditory brain–computer interface (BCI) , 2008, Journal of Neuroscience Methods.

[9]  Clemens Brunner,et al.  Better than random? A closer look on BCI results , 2008 .

[10]  N Birbaumer,et al.  Behavioural treatment of slow cortical potentials in intractable epilepsy: neuropsychological predictors of outcome. , 1993, Journal of neurology, neurosurgery, and psychiatry.

[11]  Brendan Z. Allison,et al.  Brain-Computer Interfaces , 2010 .

[12]  Steven E. Poltrock,et al.  Individual Differences in visual imagery and spatial ability , 1984 .

[13]  Robert P Freckleton,et al.  Why do we still use stepwise modelling in ecology and behaviour? , 2006, The Journal of animal ecology.

[14]  M. Moore.  Learner Autonomy: The Second Dimension of Independent Learning. , 1972 .

[15]  S. Vandenberg,et al.  Mental Rotations, a Group Test of Three-Dimensional Spatial Visualization , 1978, Perceptual and motor skills.

[16]  N. Birbaumer,et al.  Predictors of successful self control during brain-computer communication , 2003, Journal of neurology, neurosurgery, and psychiatry.

[17]  Sung Chan Jun,et al.  High Theta and Low Alpha Powers May Be Indicative of BCI-Illiteracy in Motor Imagery , 2013, PloS one.

[18]  Raymond B. Cattell,et al.  Personality Structure and the New Fifth Edition of the 16PF , 1995 .

[19]  C. Spielberger,et al.  Manual for the State-Trait Anxiety Inventory , 1970 .

[20]  J. H. Hong,et al.  Gamma band activity associated with BCI performance: simultaneous MEG/EEG study , 2013, Front. Hum. Neurosci..

[21]  L. Cohen,et al.  Brain–machine interface in chronic stroke rehabilitation: A controlled study , 2013, Annals of neurology.

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

[23]  Guillaume Gibert,et al.  OpenViBE: An Open-Source Software Platform to Design, Test, and Use BrainComputer Interfaces in Real and Virtual Environments , 2010, PRESENCE: Teleoperators and Virtual Environments.

[24]  Jerome H. Friedman,et al.  On Bias, Variance, 0/1—Loss, and the Curse-of-Dimensionality , 2004, Data Mining and Knowledge Discovery.

[25]  S. Coyle,et al.  Brain–computer interfaces: a review , 2003 .

[26]  C. Neuper,et al.  Whatever Works: A Systematic User-Centered Training Protocol to Optimize Brain-Computer Interfacing Individually , 2013, PloS one.

[27]  Weiqiang Dong.  On Bias , Variance , 0 / 1-Loss , and the Curse of Dimensionality RK April 13 , 2014 .

[28]  W. Klimesch.  EEG alpha and theta oscillations reflect cognitive and memory performance: a review and analysis , 1999, Brain Research Reviews.

[29]  Cuntai Guan,et al.  Learning from other subjects helps reducing Brain-Computer Interface calibration time , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[30]  Cuntai Guan,et al.  Brain-Computer Interface in Stroke Rehabilitation , 2013, J. Comput. Sci. Eng..

[31]  Fabien Lotte,et al.  How Well Can We Learn With Standard BCI Training Approaches? A Pilot Study. , 2014 .

[32]  Jacqueline Bourdeau,et al.  Advances in Intelligent Tutoring Systems , 2010 .

[33]  G. Pfurtscheller,et al.  Imagery of motor actions: differential effects of kinesthetic and visual-motor mode of imagery in single-trial EEG. , 2005, Brain research. Cognitive brain research.

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

[35]  G. Pfurtscheller,et al.  How many people are able to operate an EEG-based brain-computer interface (BCI)? , 2003, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[36]  Christa Neuper,et al.  Control beliefs can predict the ability to up-regulate sensorimotor rhythm during neurofeedback training , 2013, Front. Hum. Neurosci..

[37]  N. Birbaumer,et al.  The Influence of Psychological State and Motivation on Brain–Computer Interface Performance in Patients with Amyotrophic Lateral Sclerosis – a Longitudinal Study , 2010, Front. Neuropharma..

[38]  Anton Nijholt,et al.  Guest Editorial: Brain/neuronal - Computer game interfaces and interaction , 2013, IEEE Trans. Comput. Intell. AI Games.

[39]  G. Pfurtscheller,et al.  Optimal spatial filtering of single trial EEG during imagined hand movement. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[40]  Michitaka Hirose,et al.  Brain-Computer Interfaces, Virtual Reality, and Videogames , 2008, Computer.

[41]  D. Berch,et al.  The Corsi Block-Tapping Task: Methodological and Theoretical Considerations , 1998, Brain and Cognition.

[42]  William Stafford Noble,et al.  How does multiple testing correction work? , 2009, Nature Biotechnology.

[43]  Cuntai Guan,et al.  The predictive role of pre-cue EEG rhythms on MI-based BCI classification performance , 2014, Journal of Neuroscience Methods.

[44]  H. Levenson.  Activism and Powerful Others: Distinctions within the Concept of Internal-External Control , 1974 .

[45]  D. F. Marks,et al.  Mental imagery and creativity: a meta-analytic review study. , 2003, British journal of psychology.

[46]  M. Finlayson,et al.  Neuropsychological significance of variations in patterns of academic performance: Verbal and visual-spatial abilities , 1978, Journal of abnormal child psychology.

[47]  Christian Mühl,et al.  Flaws in current human training protocols for spontaneous Brain-Computer Interfaces: lessons learned from instructional design , 2013, Front. Hum. Neurosci..

[48]  H. Keselman,et al.  Backward, forward and stepwise automated subset selection algorithms: Frequency of obtaining authentic and noise variables , 1992 .

[49]  R. Felder,et al.  Learning and Teaching Styles in Engineering Education. , 1988 .

[50]  Bernhard Schölkopf,et al.  Causal influence of gamma oscillations on the sensorimotor rhythm , 2011, NeuroImage.

[51]  D. Wechsler,et al.  Wechsler Adult Intelligence Scale—Fourth Edition (WAIS-IV) , 2010 .

[52]  Brendan Z. Allison,et al.  Brain-Computer Interfaces: A Gentle Introduction , 2009 .

[53]  N. Hara.  STUDENT DISTRESS IN A WEB-BASED DISTANCE EDUCATION COURSE , 2000 .

[54]  Brendan Z. Allison,et al.  Could Anyone Use a BCI? , 2010, Brain-Computer Interfaces.

[55]  Jeanine A. Verbunt,et al.  Motor imagery in patients with a right hemisphere stroke and unilateral neglect , 2011, Brain injury.

[56]  L. Aftanas,et al.  Human anterior and frontal midline theta and lower alpha reflect emotionally positive state and internalized attention: high-resolution EEG investigation of meditation , 2001, Neuroscience Letters.

[57]  Karim Jerbi,et al.  Exceeding chance level by chance: The caveat of theoretical chance levels in brain signal classification and statistical assessment of decoding accuracy , 2015, Journal of Neuroscience Methods.

[58]  Fabien Lotte,et al.  Brain-Computer Interfaces: Beyond Medical Applications , 2012, Computer.

[59]  M. Bradley,et al.  Measuring emotion: the Self-Assessment Manikin and the Semantic Differential. , 1994, Journal of behavior therapy and experimental psychiatry.