Datasets
Open Access
EEG dataset of 7-day Motor Imagery BCI
- Citation Author(s):
- Submitted by:
- Qing Zhou
- Last updated:
- Fri, 12/04/2020 - 01:55
- DOI:
- 10.21227/f1c7-7x89
- Data Format:
- License:
3114 Views- Categories:
- Keywords:
0 ratings - Please login to submit your rating.
Abstract
In this dataset, we performed a seven-day motor imagery (MI) based BCI experiment without feedback training on 20 healthy subjects. The MI tasks include left hand, right hand, feet and idle task.
Dataset Files
Subject A5 to A8 A5_A8.zip (2.16 GB)- Subject S1 and S2 S1_S2.zip (1.75 GB)
- Subject A1 to A4 A1_A4.zip (2.23 GB)
- Subject S3 and S4 S3_S4.zip (1.80 GB)
- Subject S5 and S6 S5_S6.zip (1.59 GB)
- Subject S7 and S8 S7_S8.zip (1.69 GB)
- Subject S9 and S10 S9_S10.zip (1.70 GB)
- Subject S11 S11.zip (1.02 GB)
- Subject S12 S12.zip (1.06 GB)
MI_dataset.py (12.24 kB)
Open Access dataset files are accessible to all logged in users. Don't have a login? Create a free IEEE account. IEEE Membership is not required.
Documentation
| Attachment | Size |
|---|---|
 readme_MIdataset.docx | 277.28 KB |
Comments
I'm a master student and my team is working on a small machine learning project for authentication using EEG. This dataset has a good amount of information over a span of different days and trials, it is suitable for the task.
I'm a research scholar working on EEG limb movement classification. I am searching for a multiclass EEG dataset for my research. This dataset which is collected at different time stamps would help me in doing my research.
I am a PhD student in artificial intelligence, and my research focuses on EEG classification and motor imagery for BCIs. I would be grateful if I could access the data set collected by you. In any case, I want to express my sincere gratitude to you and your colleagues for your efforts. ghezi661@gmail.com
This database is recommended.
So far, the study that achieved the highest accuracy rate using this data is:
https://doi.org/10.1080/10255842.2024.2355490
titled: "Authentication with a one-dimensional CNN model using EEG-based brain-computer interface"