Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Machine-learning based co-adaptive calibration: A perspective to fight BCI illiteracy

: Vidaurre, C.; Sannelli, C.; Müller, K.-R.; Blankertz, B.


Corchado Rodriguez, E.S.:
Hybrid artificial intelligent systems. 5th international conference, HAIS 2010. Vol.1 : San Sebastian, Spain, June 23-25, 2010; proceedings
Berlin: Springer, 2010 (Lecture Notes in Artificial Intelligence 6076)
ISBN: 3-642-13768-7
ISBN: 978-3-642-13768-6
ISSN: 0302-9743
International Conference on Hybrid Artificial Intelligent Systems (HAIS) <5, 2010, San Sebastián>
Conference Paper
Fraunhofer FIRST ()

"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.