Skip to content

The code implements the EON model for cross-dataset driver drowsiness recognition with EEG. The proposed method is tested on the domain adaptation task with two public datasets and achieves 2-class recognition accuracies of 89.2% and 77.6%,

Notifications You must be signed in to change notification settings

cuijiancorbin/EEG-based-Cross-dataset-Driver-Drowsiness-Recognition-with-an-Entropy-Optimization-Network

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 

Repository files navigation

EEG-based-Cross-dataset-Driver-Drowsiness-Recognition-with-an-Entropy-Optimization-Network

Pytorch implementation of the model "EON" proposed in the paper "EEG-based-Cross-dataset-Driver-Drowsiness-Recognition-with-an-Entropy-Optimization-Network".

If you find the codes useful, pls cite the paper:

L. Yuan, S. Zhang, R. Li, Z. Zheng, J. Cui and M. Y. Siyal, "EEG-based Cross-dataset Driver Drowsiness Recognition with an Entropy Optimization Network," in IEEE Journal of Biomedical and Health Informatics, doi: 10.1109/JBHI.2024.3519730.

Paper link: https://ieeexplore.ieee.org/document/9714736

figure

The processed SADT dataset can be downloaded here: https://figshare.com/articles/dataset/EEG_driver_drowsiness_dataset/14273687

The processed SEED-VIG dataset can be downloaded here: https://figshare.com/articles/dataset/Extracted_SEED-VIG_dataset_for_cross-dataset_driver_drowsiness_recognition/26104987

Description on the backbone ICNN model can be found from:

Cui J, Lan Z, Sourina O, et al. EEG-based cross-subject driver drowsiness recognition with an interpretable convolutional neural network[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 34(10): 7921-7933. DOI: 10.1109/TNNLS.2022.3147208

About

The code implements the EON model for cross-dataset driver drowsiness recognition with EEG. The proposed method is tested on the domain adaptation task with two public datasets and achieves 2-class recognition accuracies of 89.2% and 77.6%,

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages