GIB-UVa ERP-BCI dataset

Resum

This dataset contains EEG signals from 73 subjects (42 healthy; 31 disabled) using an ERP-based speller to control differentbrain-computer interface (BCI) applications. The dataset is divided in 3 sets (i.e., training set, validation set and test set) according to Santamaría-Vázquez et al., 2020 (link to article):Training set: contains data from 34 healthy subjectsValidation set: contains data from 8 healthy subjectsTest set: contains data from 31 motor disabled subjectsAdditionally, you will find the results of the original studybroken down by subject, the code to build the deep-learning models used inSantamaría-Vázquez et al., 2020 (i.e., EEG-Inception, EEGNet, DeepConvNet, CNN-BLSTM)and useful scripts to load the dataset or train EEG-Inception.