Datasets
Standard Dataset
Non-invasive Handwriting Imagery EEG
- Citation Author(s):
- Submitted by:
- Guang Ouyang
- Last updated:
- Thu, 10/31/2024 - 05:34
- DOI:
- 10.21227/5x8q-de66
- License:
- Categories:
- Keywords:
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.
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.
Dataset Files
- data_EEG_AI_sub1.mat (837.70 MB)
- data_EEG_AI_sub2.mat (851.66 MB)
- data_EEG_AI_sub4.mat (861.15 MB)
- data_EEG_AI_sub5.mat (858.83 MB)
- data_EEG_AI_sub6.mat (856.03 MB)