Adaptive on-line classification for EEG-based Brain Computer Interfaces with ARR parameters and band power estimates

We present the result of on-line feedback Brain Computer Interface experiments using adaptive and non-adaptive feature extraction methods with an on-line adaptive classifier based on Quadratic Discriminant Analysis. Experiments were performed with 12 naïve subjects, feedback was provided from the first moment and no training sessions were needed. Experiments run in three different days with each subject. Six of them received feedback with Adaptive Autoregressive parameters and the rest with logarithmic Band Power estimates. The study was done using single trial analysis of each of the sessions and the value of the Error Rate and the Mutual Information of the classification were used to discuss the results. Finally, it was shown that even subjects starting with a low performance were able to control the system in a few hours: and contrary to previous results no differences between AAR and BP estimates were found.