A Generalizable BCI using Machine Learning for Feature Discovery
datasetposted on 15.06.2015 by EWAN NURSE, Pip Karoly
Datasets usually provide raw data for analysis. This raw data often comes in spreadsheet form, but can be any collection of data, on which analysis can be performed.
The first variable is data_key_'participant letter', which takes the value 1,2 or 3, depending on if they didn't squeeze their hand, squeezed right or squeezed left during that epoch.
The second is data_epochs_'participant letter'. This is the EEG data corresponding to the data key. The first dimension is all the channels (62 channels for the first two sets) concatenated into a single row, so there's 100 data points for each channel for each epoch.