Instant classification for the spatially-coded BCI

The archive contains EEG data from a newly developed brain-computer interface paradigm. The method is described in [1], and the dataset has been recorded for the application described in [2]. Each file in the archive contains data from the online session of the respective participant. The Matlab data structure contains the following fields: data. fsample: sampling rate (512 Hz)<br> data.trial: EEG signals for each trial<br> data.time: sampling time points<br> data.classified: classifier output for each step<br> data.class: true class<br> data.accuracy: classification accuracy<br> data.probability: posterior class probabilities [1] Maye A, Zhang D, Engel AK (2017) "Utilizing Retinotopic Mapping for a Multi-Target SSVEP BCI With a Single Flicker Frequency", IEEE Transactions on Neural Systems and Rehabilitation Engineering, in press. [2] Maÿe A. Rauterberg R, Engel AK (2021) "Instant classification for the spatially-coded BCI", PLoS ONE, iunder review.