Non-invasive Handwriting Imagery EEG

Citation Author(s):
Guang
Ouyang
Submitted by:
Guang Ouyang
Last updated:
Thu, 10/31/2024 - 05:34
DOI:
10.21227/5x8q-de66
License:
13 Views
Categories:
Keywords:
0
0 ratings - Please login to submit your rating.

Abstract 

The dataset consists of EEG recorded non-invasively from five participants while they are performing a handwriting imagery task, in which each participant was instructed to imagine the process of handwriting the 26 English letters. Major preprocessing steps have been conducted, including large-amplitude artifact removal using Independent Component Analysis and bandpass filtering between 0.1-45 Hz.

Instructions: 

The dataset consists of five MATLAB .mat file, each generated by one participant. Each participant generated 7,800 samples (300 samples for each English letter). Each data sample is a 2d matrix of size 24*801, where 24 is the number of EEG electrodes and 801 is the number of time points. All the data samples from one participant were put into a 3d array of size 24*801*7800, which is named as "data". The array named "label" stores integers 1 to 26, indicating theĀ corresponding letter of each sample. The array "time_points" stores the sampling times, which start at -200 and end at 3000 in ms (sampling frequency 250 Hz; sampling period 4 ms), and the "channel_label" stores the names of the 24 EEG electrodes.