Machine-Learning Based Co-adaptive Calibration: A Perspective to Fight BCI Illiteracy

“BCI illiteracy” is one of the biggest problems and challenges in BCI research It means that BCI control cannot be achieved by a non-negligible number of subjects (estimated 20% to 25%) There are two main causes for BCI illiteracy in BCI users: either no SMR idle rhythm is observed over motor areas, or this idle rhythm is not attenuated during motor imagery, resulting in a classification performance lower than 70% (criterion level) already for offline calibration data In a previous work of the same authors, the concept of machine learning based co-adaptive calibration was introduced This new type of calibration provided substantially improved performance for a variety of users Here, we use a similar approach and investigate to what extent co-adapting learning enables substantial BCI control for completely novice users and those who suffered from BCI illiteracy before.

[1]  J. Wolpaw,et al.  Brain-computer communication: unlocking the locked in. , 2001, Psychological bulletin.

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

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

[4]  K. Jellinger.  Toward Brain-Computer Interfacing , 2009 .

[5]  N. Birbaumer,et al.  Predictability of Brain-Computer Communication , 2004 .

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

[7]  Porto Carras.  Heart rate and heart-rate variability during hypnotic responding , 1994 .

[8]  Reinhold Scherer,et al.  A fully on-line adaptive BCI , 2006, IEEE Transactions on Biomedical Engineering.

[9]  Klaus-Robert Müller,et al.  The Berlin Brain-Computer Interface: Accurate performance from first-session in BCI-naive subjects , 2008, IEEE Transactions on Biomedical Engineering.

[10]  Klaus-Robert Müller,et al.  The non-invasive Berlin Brain–Computer Interface: Fast acquisition of effective performance in untrained subjects , 2007, NeuroImage.

[11]  Klaus-Robert Müller,et al.  Covariate Shift Adaptation by Importance Weighted Cross Validation , 2007, J. Mach. Learn. Res..

[12]  Nicole Krämer,et al.  Time Domain Parameters as a feature for EEG-based Brain-Computer Interfaces , 2009, Neural Networks.

[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]  K. Müller,et al.  Predicting BCI performance to study BCI illiteracy , 2009, BMC Neuroscience.

[15]  Christa Neuper,et al.  14 Human Brain-Computer Interface , 2005 .

[16]  K.-R. Muller,et al.  Linear and nonlinear methods for brain-computer interfaces , 2003, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[17]  Masashi Sugiyama,et al.  Dimensionality Reduction of Multimodal Labeled Data by Local Fisher Discriminant Analysis , 2007, J. Mach. Learn. Res..

[18]  K.-R. Muller,et al.  Optimizing Spatial filters for Robust EEG Single-Trial Analysis , 2008, IEEE Signal Processing Magazine.

[19]  Klaus-Robert Müller,et al.  Machine learning for real-time single-trial EEG-analysis: From brain–computer interfacing to mental state monitoring , 2008, Journal of Neuroscience Methods.

[20]  A. Riehle,et al.  Motor Cortex in Voluntary Movements , 2004 .

[21]  Klaus-Robert Müller,et al.  Boosting bit rates in noninvasive EEG single-trial classifications by feature combination and multiclass paradigms , 2004, IEEE Transactions on Biomedical Engineering.

[22]  Olivier Ledoit,et al.  A well-conditioned estimator for large-dimensional covariance matrices , 2004 .

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

[24]  B. Blankertz,et al.  Towards a cure for BCI illiteracy: machine learning based co-adaptive learning , 2009, BMC Neuroscience.