The training set (train.mat) consists of the following variables:
signal_tr
: raw voltage readings at 2034.5 Hz. Each row is a new reading and each column is the reading from a particular electrode (32 in total). The voltage readings from the brain are collected via Electrocorticography (ECOG)
pos_x_tr
: x-component of the cursor's velocity vector at different time-steps (31,255 total time-steps). This one half the prediction label (the other is the y-component). These readings are at 25 Hz, so one of the things spectral estimation must do is down-sample the signal to 25 Hz as well (example.m does this already).
pos_y_tr
: y-component of the cursor's velocity vector at different time-steps. This is the same size as pos_x_tr and the second half of the label to be predicted.
timestamps_tr
: this gives the timestamps of the voltage samples (2034.5 Hz)
time_sample_tr
: the timestamps of the cursor at 25 Hz. Using this and the above data we can down-sample the signal to 25 Hz.
The testing set (test.mat) is very similar:
signal_te
: raw voltage readings that is a matrix of size (num. readings x electrodes).
timestamps_te
: the voltage timestamps
time_sample_te
: the cursor timestamps