On optimal channel configurations for SMR-based brain-computer interfaces
via nonparametric multiple comparisons
Brain-computer interfaces (BCIs) based on sensorimotor rhythms (SMRs) make use of brain activity modulated during motor imagery tasks, e.g., left-hand versus right-hand imagery, to control a device and / or provide a communication tool. Usually, activity is thereby measured by multi-channel electroencephalogram (EEG) and translated into commands by a computer program. For example, with the output of a classifier operating on such EEG data, control of an application like a moving cursor on a screen becomes possible. In order to enhance the convenience of use of such a BCI system, small channel setups with few electrodes are favorable due to EEG cap montage time and signal stability. However, a tradeoff with information loss is necessary, because removing channels is likely to deteriorate classification accuracy. We tackle this problem from a statistical point of view and formulate the task of comparing different (standard) electrode layouts as a multiple hypotheses testing problem. Moreover, nonparametric multiple comparisons methods for this problem will be discussed. This is joint work with Claudia Sannelli, Benjamin Blankertz and Klaus-Robert Müller.