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
Hi-index | 0.00 |
“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.