Machine-Learning based co-adaptive calibration: a perspective to fight BCI illiteracy

Authors:
Carmen Vidaurre;Claudia Sannelli;Klaus-Robert Müller;Benjamin Blankertz
Affiliations:
Computer Science Faculty, Machine Learning department, Berlin Institute of Technology, Berlin, Germany;Computer Science Faculty, Machine Learning department, Berlin Institute of Technology, Berlin, Germany;Computer Science Faculty, Machine Learning department, Berlin Institute of Technology, Berlin, Germany;Computer Science Faculty, Machine Learning department, Berlin Institute of Technology, Berlin, Germany
Venue:
HAIS'10 Proceedings of the 5th international conference on Hybrid Artificial Intelligence Systems - Volume Part I
Year:
2010

Citing 3
Cited 0

A well-conditioned estimator for large-dimensional covariance matrices

Journal of Multivariate Analysis
Covariate Shift Adaptation by Importance Weighted Cross Validation

The Journal of Machine Learning Research
2009 Special Issue: Time Domain Parameters as a feature for EEG-based Brain-Computer Interfaces

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

“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.