Predicting BCI performance to study BCI illiteracy
Benjamin Blankertz, Claudia Sanelli, Sebastian Halder, Eva-Maria Hammer, Andrea Kübler, Klaus-Robert Müller, Gabriel Curio and Thorsten Dickhaus
In: 7th NFSI & ICBEM 2009(2009).
Brain-Computer Interfaces (BCIs) allow a user to control a computer application just by brain
activity as acquired, e.g., by electroencephalography (EEG). After 30 years of BCI research, the success
of BCI control that may be provided still greatly varies between subjects. For a percentage of about
20% the obtained accuracy does not reach the level criterion, meaning that BCI control is not accurate
enough to control an application. The development of predictors of BCI performance serves two
purposes: a better under-standing of the 'illiterates phenomenon', and avoidance of a costly and
frustrating training procedure for subjects who might not obtain BCI control. Furthermore, such
predictors may lead to approaches to antagonize BCI-illiteracy.
Here, we propose a neurophysiological predictor of BCI performance which can be determined from a
two minutes recording of a relax with eyes open condition using two Laplacian EEG channels. A
correlation of r = 0.53 between the proposed predictor and BCI feedback performance was obtained on
a large data base with N = 80 BCI-naive subjects in their first session with the Berlin Brain-Computer
Interface (BBCI) system which operates on modulations of sensory motor rhythms (SMRs).
|EPrint Type:||Conference or Workshop Item (Paper)|
|Project Keyword:||Project Keyword UNSPECIFIED|
|Subjects:||Brain Computer Interfaces|
|Deposited By:||Stefan Haufe|
|Deposited On:||08 March 2010|