Correlative exploration of EEG signals for direct brain-computer communication

In this study we present a method for classifying EEG signals based on the information content of their correlative time-frequency-space representation (CTFSR). A support vector machine (SVM) kernel is proposed that can be calculated in the time domain while it computes a similarity measure in the CTFSR space. This classification method is used in a brain-computer interface (BCI) application. The use of the SVM approach allows us to propose a simple strategy for adapting the BCI to possible long term variations in the brain activity.