A compact and interpretable convolutional neural network for cross-subject driver drowsiness detection from single-channel EEG

•An interpretable CNN model that can reveal important parts of input single-channel EEG signals for classification with the Class Activation Map (CAM) method.•The model can discover biologically explainable features from a diversity of EEG data of different subjects.•An average accuracy of 73.22% is...

Full description

Saved in:

Bibliographic Details
Published in:	Methods (San Diego, Calif.) Vol. 202; pp. 173 - 184
Main Authors:	Cui, Jian, Lan, Zirui, Liu, Yisi, Li, Ruilin, Li, Fan, Sourina, Olga, Müller-Wittig, Wolfgang
Format:	Journal Article
Language:	English
Published:	United States Elsevier Inc 01.06.2022
Subjects:	brain Class activation mapping Convolutional neural network Driver drowsiness detection electroencephalography Interpretable CNN muscles Network visualization neural networks neurophysiology Single-channel EEG transportation industry Network visualization Interpretable CNN Single-channel EEG Driver drowsiness detection Convolutional neural network Class activation mapping
ISSN:	1046-2023, 1095-9130, 1095-9130
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!