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!
Description
Summary:•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 achieved by the model on 11 subjects for 2-class cross-subject EEG signal classification.•We use the model to discover interesting features from EEG signals that can be indicators of alert or drowsy states. Driver drowsiness is one of the main factors leading to road fatalities and hazards in the transportation industry. Electroencephalography (EEG) has been considered as one of the best physiological signals to detect drivers’ drowsy states, since it directly measures neurophysiological activities in the brain. However, designing a calibration-free system for driver drowsiness detection with EEG is still a challenging task, as EEG suffers from serious mental and physical drifts across different subjects. In this paper, we propose a compact and interpretable Convolutional Neural Network (CNN) to discover shared EEG features across different subjects for driver drowsiness detection. We incorporate the Global Average Pooling (GAP) layer in the model structure, allowing the Class Activation Map (CAM) method to be used for localizing regions of the input signal that contribute most for classification. Results show that the proposed model can achieve an average accuracy of 73.22% on 11 subjects for 2-class cross-subject EEG signal classification, which is higher than conventional machine learning methods and other state-of-art deep learning methods. It is revealed by the visualization technique that the model has learned biologically explainable features, e.g., Alpha spindles and Theta burst, as evidence for the drowsy state. It is also interesting to see that the model uses artifacts that usually dominate the wakeful EEG, e.g., muscle artifacts and sensor drifts, to recognize the alert state. The proposed model illustrates a potential direction to use CNN models as a powerful tool to discover shared features related to different mental states across different subjects from EEG signals.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1046-2023
1095-9130
1095-9130
DOI:10.1016/j.ymeth.2021.04.017