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:
ISSN:1046-2023, 1095-9130, 1095-9130
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract •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.
AbstractList 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.
•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.
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.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.
Author Li, Fan
Müller-Wittig, Wolfgang
Lan, Zirui
Liu, Yisi
Li, Ruilin
Sourina, Olga
Cui, Jian
Author_xml – sequence: 1
  givenname: Jian
  surname: Cui
  fullname: Cui, Jian
  email: cuijian@ntu.edu.sg
  organization: Fraunhofer Singapore, Nanyang Technological University, Singapore
– sequence: 2
  givenname: Zirui
  surname: Lan
  fullname: Lan, Zirui
  email: lan.zirui@fraunhofer.sg
  organization: Fraunhofer Singapore, Singapore
– sequence: 3
  givenname: Yisi
  surname: Liu
  fullname: Liu, Yisi
  email: liu.yisi@fraunhofer.sg
  organization: Fraunhofer Singapore, Singapore
– sequence: 4
  givenname: Ruilin
  surname: Li
  fullname: Li, Ruilin
  email: RUILIN001@e.ntu.edu.sg
  organization: Nanyang Technological University, Singapore
– sequence: 5
  givenname: Fan
  surname: Li
  fullname: Li, Fan
  email: lifan@ntu.edu.sg
  organization: Fraunhofer Singapore, Nanyang Technological University, Singapore
– sequence: 6
  givenname: Olga
  surname: Sourina
  fullname: Sourina, Olga
  email: EOSourina@ntu.edu.sg
  organization: Fraunhofer Singapore, Nanyang Technological University, Singapore
– sequence: 7
  givenname: Wolfgang
  surname: Müller-Wittig
  fullname: Müller-Wittig, Wolfgang
  email: Wolfgang.Mueller-wittig@fraunhofer.sg
  organization: Fraunhofer Singapore, Nanyang Technological University, Singapore
BackLink https://www.ncbi.nlm.nih.gov/pubmed/33901644$$D View this record in MEDLINE/PubMed
BookMark eNqNUbtuFDEUtVAQecAXICGXNDPxa3bGBUUULQEpEg3Ulse-Q7x47MX2bJQm3453N2lSRFTH8nno6pxzdBJiAIQ-UtJSQleXm_ZhhnLXMsJoS0RLaP8GnVEiu0ZSTk72b7FqKs1P0XnOG0IIZf3wDp1yLmuCEGfo8QqbOG-1KVgHi10okLYJih49VCbsol-Ki0F7HGBJByj3Mf3BU0zYpJhzk5dxAzXAJreDVCHeZxcgZ2yhVKLa8ZTijOvvbw-NudMhgMfr9c179HbSPsOHJ7xAv76uf15_a25_3Hy_vrptDJesNLqf6r2DZVJSLYdB6w4oAc4E0SPRQg7SMMkm0k-dnbph1VGxGoUFxoSmBvgF-nzM3ab4d4Fc1OyyAe91gLhkxbqOStrTnv-HlA5SCjbQKv30JF3GGazaJjfr9KCe660CeRQcikowKeOK3hdSknZeUaL2U6qNOkyp9lMqIlSdsnr5C-9z_OuuL0cX1DZ3DpLKxkEwYF2qUygb3av-fzEAupo
CitedBy_id crossref_primary_10_1109_ACCESS_2023_3293421
crossref_primary_10_1016_j_bspc_2024_107262
crossref_primary_10_3390_electronics14173469
crossref_primary_10_1007_s11042_023_16952_z
crossref_primary_10_3390_math10152819
crossref_primary_10_1109_JSEN_2024_3492176
crossref_primary_10_1088_1741_2552_ad6593
crossref_primary_10_1134_S1019331622040189
crossref_primary_10_1016_j_ijar_2025_109552
crossref_primary_10_3390_s25175530
crossref_primary_10_1007_s10548_023_01016_0
crossref_primary_10_1177_03611981221096118
crossref_primary_10_1109_TNSRE_2023_3336897
crossref_primary_10_1007_s11760_024_03613_3
crossref_primary_10_1080_10255842_2025_2456996
crossref_primary_10_1016_j_neucom_2023_126709
crossref_primary_10_1007_s12559_023_10233_5
crossref_primary_10_3389_fnhum_2022_866118
crossref_primary_10_1007_s11760_025_04102_x
crossref_primary_10_1016_j_engappai_2024_109825
crossref_primary_10_3390_aerospace12090786
crossref_primary_10_1016_j_bspc_2022_104237
crossref_primary_10_1016_j_engappai_2024_109153
crossref_primary_10_3390_electronics13071374
crossref_primary_10_1016_j_compbiomed_2023_107652
crossref_primary_10_1016_j_eswa_2023_120279
crossref_primary_10_1109_TITS_2023_3347075
crossref_primary_10_1016_j_measurement_2025_118644
crossref_primary_10_1016_j_aei_2025_103796
crossref_primary_10_1007_s11227_025_06947_y
crossref_primary_10_1109_TCDS_2025_3538947
crossref_primary_10_1109_TITS_2024_3442249
crossref_primary_10_1109_ACCESS_2023_3325283
crossref_primary_10_1016_j_aei_2024_102971
crossref_primary_10_1016_j_neucom_2024_128961
crossref_primary_10_3390_app14104124
crossref_primary_10_3390_app15169018
crossref_primary_10_1016_j_compbiolchem_2023_107863
crossref_primary_10_1080_10447318_2024_2446511
crossref_primary_10_1109_JBHI_2024_3377373
crossref_primary_10_1109_ACCESS_2025_3606900
crossref_primary_10_1080_10447318_2024_2306439
crossref_primary_10_1016_j_bspc_2024_106881
crossref_primary_10_1016_j_bspc_2025_108046
crossref_primary_10_3390_electronics14061069
crossref_primary_10_3389_fnins_2024_1508747
crossref_primary_10_1080_10255842_2022_2112574
crossref_primary_10_1016_j_bspc_2021_103070
crossref_primary_10_3389_fncom_2023_1232925
crossref_primary_10_3389_fphys_2023_1153268
crossref_primary_10_1016_j_bspc_2023_105892
crossref_primary_10_3390_s23052750
crossref_primary_10_3390_electronics13112084
crossref_primary_10_1109_TNNLS_2022_3147208
crossref_primary_10_1016_j_eswa_2024_125089
crossref_primary_10_1088_1741_2552_ad546d
crossref_primary_10_1109_ACCESS_2023_3288008
Cites_doi 10.1016/0013-4694(87)90096-4
10.1016/j.ssci.2008.01.007
10.1016/j.aei.2020.101047
10.1017/S0048577201393095
10.1016/j.bspc.2017.12.001
10.1007/s10618-019-00619-1
10.1016/j.neubiorev.2006.06.007
10.1007/s11571-018-9485-1
10.1088/1741-2552/aace8c
10.1016/j.clinph.2010.10.044
10.1109/TNSRE.2017.2721116
10.1016/j.bspc.2019.02.005
10.1109/TCDS.2018.2826840
10.3390/s18124477
10.1007/s00371-015-1183-y
10.1016/S0165-0173(98)00056-3
10.1109/TNSRE.2018.2872924
10.3389/fncom.2018.00085
10.1109/TCSI.2005.857555
10.1016/j.aei.2020.101157
10.1016/j.jneumeth.2019.108312
10.1109/SMC.2015.540
10.1038/s41597-019-0027-4
10.1088/1741-2552/ab260c
10.3389/fnins.2012.00039
10.1088/1741-2552/aaf3f6
10.1109/TBCAS.2010.2046415
10.1109/TNSRE.2018.2790359
10.1590/2446-4740.0693
10.1155/2008/519480
10.1016/j.micpro.2018.02.004
ContentType Journal Article
Copyright 2021 Elsevier Inc.
Copyright © 2021 Elsevier Inc. All rights reserved.
Copyright_xml – notice: 2021 Elsevier Inc.
– notice: Copyright © 2021 Elsevier Inc. All rights reserved.
DBID AAYXX
CITATION
NPM
7X8
7S9
L.6
DOI 10.1016/j.ymeth.2021.04.017
DatabaseName CrossRef
PubMed
MEDLINE - Academic
AGRICOLA
AGRICOLA - Academic
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
AGRICOLA
AGRICOLA - Academic
DatabaseTitleList PubMed
AGRICOLA

MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Anatomy & Physiology
Chemistry
EISSN 1095-9130
EndPage 184
ExternalDocumentID 33901644
10_1016_j_ymeth_2021_04_017
S1046202321001092
Genre Journal Article
GroupedDBID ---
--K
--M
-~X
.GJ
.~1
0R~
123
1B1
1RT
1~.
1~5
29M
4.4
457
4G.
53G
5VS
7-5
71M
8P~
9JM
AABNK
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXUO
ABEFU
ABFNM
ABFRF
ABGSF
ABJNI
ABMAC
ABUDA
ABXDB
ABYKQ
ACDAQ
ACGFO
ACGFS
ACRLP
ADBBV
ADEZE
ADFGL
ADMUD
ADUVX
AEBSH
AEFWE
AEHWI
AEKER
AENEX
AFKWA
AFTJW
AFXIZ
AGHFR
AGRDE
AGUBO
AGYEJ
AHHHB
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
ASPBG
AVWKF
AXJTR
AZFZN
BKOJK
BLXMC
CAG
COF
CS3
DM4
DOVZS
DU5
EBS
EFBJH
EFLBG
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
G-Q
GBLVA
HLW
HMG
HVGLF
HZ~
IHE
J1W
K-O
KOM
LG5
LX2
LZ5
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
ROL
RPZ
SBG
SCC
SDF
SDG
SDP
SES
SEW
SIN
SPCBC
SSU
SSZ
T5K
WUQ
XPP
Y6R
ZGI
ZMT
ZU3
~G-
9DU
AAHBH
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
AGCQF
AGRNS
BNPGV
NPM
SSH
7X8
7S9
L.6
ID FETCH-LOGICAL-c392t-a7f0168d2991a988aa5e10e3240ab0a4989c292f07f5df5865146b4de224a1ce3
ISICitedReferencesCount 75
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000804388400009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1046-2023
1095-9130
IngestDate Sun Sep 28 00:35:21 EDT 2025
Thu Sep 25 08:36:10 EDT 2025
Mon Jul 21 06:00:29 EDT 2025
Sat Nov 29 07:05:35 EST 2025
Tue Nov 18 22:29:50 EST 2025
Fri Feb 23 02:39:17 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Network visualization
Interpretable CNN
Single-channel EEG
Driver drowsiness detection
Convolutional neural network
Class activation mapping
Language English
License Copyright © 2021 Elsevier Inc. All rights reserved.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c392t-a7f0168d2991a988aa5e10e3240ab0a4989c292f07f5df5865146b4de224a1ce3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PMID 33901644
PQID 2518994281
PQPubID 23479
PageCount 12
ParticipantIDs proquest_miscellaneous_2551917173
proquest_miscellaneous_2518994281
pubmed_primary_33901644
crossref_citationtrail_10_1016_j_ymeth_2021_04_017
crossref_primary_10_1016_j_ymeth_2021_04_017
elsevier_sciencedirect_doi_10_1016_j_ymeth_2021_04_017
PublicationCentury 2000
PublicationDate June 2022
2022-06-00
2022-Jun
20220601
PublicationDateYYYYMMDD 2022-06-01
PublicationDate_xml – month: 06
  year: 2022
  text: June 2022
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Methods (San Diego, Calif.)
PublicationTitleAlternate Methods
PublicationYear 2022
Publisher Elsevier Inc
Publisher_xml – name: Elsevier Inc
References Yeo (b0020) 2009; 47
Luo (b0030) 2019; 51
Schirrmeister (b0230) 2017
Lawhern (b0140) 2018; 15
Torsvall, åAkerstedt (b0010) 1987; 66
Simon (b0235) 2011; 122
Administration, N.H.T.S., 2018 Fatal Motor Vehicle Crashes: Overview. 2019.
Delta wave. Available from: https://en.wikipedia.org/wiki/Delta_wave.
Bashivan, P., et al., Learning representations from EEG with deep recurrent-convolutional neural networks. arXiv preprint arXiv:1511.06448, 2015.
Sors (b0160) 2018; 42
Belakhdar (b0130) 2018; 58
Clevert, D.-A., T. Unterthiner, and S. Hochreiter, Fast and accurate deep network learning by exponential linear units (elus). arXiv preprint arXiv:1511.07289, 2015.
Längkvist, Karlsson, Loutfi (b0145) 2012; 2012
Hu, Min (b0025) 2018; 12
Lan (b0075) 2016; 32
Yıldırım, Baloglu, Acharya (b0165) 2018
Wei (b0205) 2018; 26
Scikit-learn Machine Learning in Python. Available from
Fawaz (b0045) 2019; 33
vlawhern, Army Research Laboratory (ARL) EEGModels Project: A Collection of Convolutional Neural Network (CNN) models for EEG signal classification, using Keras and Tensorflow.
.
Ioffe, S. and C. Szegedy, Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167, 2015.
Shaw, J.C., The brain’s alpha rhythms and the mind. BV Elsevier Science, 2003.
Hou, X., et al. EEG based stress monitoring. in 2015 IEEE International Conference on Systems, Man, and Cybernetics. 2015. IEEE.
Chinara (b0135) 2020; 347
Kingma, D.P. and J. Ba, Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
Lan (b0080) 2014
Lin, M., Q. Chen, and S. Yan, Network in network. arXiv preprint arXiv:1312.4400, 2013.
Srivastava (b0220) 2014; 15
Simonyan, K. and A. Zisserman, Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.
Onton (b0105) 2006; 30
Supratak (b0155) 2017; 25
Ang (b0240) 2012; 6
Ogino, Mitsukura (b0115) 2018; 18
Silveira, T.d., A.d.J. Kozakevicius, and C.R. Rodrigues, Drowsiness detection for single channel EEG by DWT best m-term approximation. Research on Biomedical Engineering, 2015. 31(2): p. 107-115.
Lan (b0065) 2020; 44
Lin (b0120) 2010; 4
Fahimi (b0170) 2019; 16
Cao (b0190) 2019; 6
Krizhevsky, A., I. Sutskever, and G.E. Hinton. Imagenet classification with deep convolutional neural networks. in Advances in neural information processing systems. 2012.
Britton, J.W., et al., Electroencephalography (EEG): An introductory text and atlas of normal and abnormal findings in adults, children, and infants. 2016.
Lal, Craig (b0015) 2002; 39
Klimesch (b0110) 1999; 29
Zhou (b0060) 2016
Bresch, Großekathöfer, Garcia-Molina (b0175) 2018; 12
Liu (b0095) 2019
Mousavi (b0180) 2019; 324
Selvaraju (b0275) 2017
Lin (b0210) 2005; 52
Roy (b0050) 2019; 16
Lim, Sourina, Wang (b0085) 2018; 26
Ding (b0185) 2019
(bib276) 2021
Lin, Z.C.M.C.J.T.K.C.-T. Multi-channel EEG recordings during a sustained-attention driving task (pre-processed dataset). 2019; Available from: https://figshare.com/articles/Multi-channel_EEG_recordings_during_a_sustained-attention_driving_task_preprocessed_dataset_/7666055.
Lan (b0070) 2018; 11
Pal (b0200) 2008; 2008
Liu (b0100) 2020; 46
Zhou (10.1016/j.ymeth.2021.04.017_b0060) 2016
Selvaraju (10.1016/j.ymeth.2021.04.017_b0275) 2017
Yeo (10.1016/j.ymeth.2021.04.017_b0020) 2009; 47
10.1016/j.ymeth.2021.04.017_b0005
Lan (10.1016/j.ymeth.2021.04.017_b0065) 2020; 44
Längkvist (10.1016/j.ymeth.2021.04.017_b0145) 2012; 2012
Ang (10.1016/j.ymeth.2021.04.017_b0240) 2012; 6
10.1016/j.ymeth.2021.04.017_b0125
10.1016/j.ymeth.2021.04.017_b0245
10.1016/j.ymeth.2021.04.017_b0040
10.1016/j.ymeth.2021.04.017_b0090
Lan (10.1016/j.ymeth.2021.04.017_b0070) 2018; 11
Hu (10.1016/j.ymeth.2021.04.017_b0025) 2018; 12
Lin (10.1016/j.ymeth.2021.04.017_b0120) 2010; 4
Schirrmeister (10.1016/j.ymeth.2021.04.017_b0230) 2017
10.1016/j.ymeth.2021.04.017_b0215
Torsvall (10.1016/j.ymeth.2021.04.017_b0010) 1987; 66
Ding (10.1016/j.ymeth.2021.04.017_b0185) 2019
Lan (10.1016/j.ymeth.2021.04.017_b0080) 2014
10.1016/j.ymeth.2021.04.017_b0255
Lin (10.1016/j.ymeth.2021.04.017_b0210) 2005; 52
10.1016/j.ymeth.2021.04.017_b0250
Luo (10.1016/j.ymeth.2021.04.017_b0030) 2019; 51
10.1016/j.ymeth.2021.04.017_b0055
Srivastava (10.1016/j.ymeth.2021.04.017_b0220) 2014; 15
Supratak (10.1016/j.ymeth.2021.04.017_b0155) 2017; 25
Belakhdar (10.1016/j.ymeth.2021.04.017_b0130) 2018; 58
Roy (10.1016/j.ymeth.2021.04.017_b0050) 2019; 16
Sors (10.1016/j.ymeth.2021.04.017_b0160) 2018; 42
Yıldırım (10.1016/j.ymeth.2021.04.017_b0165) 2018
Simon (10.1016/j.ymeth.2021.04.017_b0235) 2011; 122
Chinara (10.1016/j.ymeth.2021.04.017_b0135) 2020; 347
10.1016/j.ymeth.2021.04.017_b0225
10.1016/j.ymeth.2021.04.017_b0265
Ogino (10.1016/j.ymeth.2021.04.017_b0115) 2018; 18
Pal (10.1016/j.ymeth.2021.04.017_b0200) 2008; 2008
Lan (10.1016/j.ymeth.2021.04.017_b0075) 2016; 32
10.1016/j.ymeth.2021.04.017_b0260
Liu (10.1016/j.ymeth.2021.04.017_b0100) 2020; 46
Klimesch (10.1016/j.ymeth.2021.04.017_b0110) 1999; 29
Onton (10.1016/j.ymeth.2021.04.017_b0105) 2006; 30
Bresch (10.1016/j.ymeth.2021.04.017_b0175) 2018; 12
Fahimi (10.1016/j.ymeth.2021.04.017_b0170) 2019; 16
Mousavi (10.1016/j.ymeth.2021.04.017_b0180) 2019; 324
Cao (10.1016/j.ymeth.2021.04.017_b0190) 2019; 6
Fawaz (10.1016/j.ymeth.2021.04.017_b0045) 2019; 33
Liu (10.1016/j.ymeth.2021.04.017_b0095) 2019
10.1016/j.ymeth.2021.04.017_b0035
Lim (10.1016/j.ymeth.2021.04.017_b0085) 2018; 26
Lal (10.1016/j.ymeth.2021.04.017_b0015) 2002; 39
Lawhern (10.1016/j.ymeth.2021.04.017_b0140) 2018; 15
10.1016/j.ymeth.2021.04.017_b0195
10.1016/j.ymeth.2021.04.017_b0150
Wei (10.1016/j.ymeth.2021.04.017_b0205) 2018; 26
10.1016/j.ymeth.2021.04.017_b0270
References_xml – volume: 2008
  year: 2008
  ident: b0200
  article-title: EEG-based subject-and session-independent drowsiness detection: an unsupervised approach
  publication-title: EURASIP J. Adv. Signal Process.
– volume: 39
  start-page: 313
  year: 2002
  end-page: 321
  ident: b0015
  article-title: Driver fatigue: electroencephalography and psychological assessment
  publication-title: Psychophysiology
– year: 2019
  ident: b0185
  article-title: Cascaded Convolutional Neural Network with Attention Mechanism for Mobile EEG-based Driver Drowsiness Detection System
– volume: 33
  start-page: 917
  year: 2019
  end-page: 963
  ident: b0045
  article-title: Deep learning for time series classification: a review
  publication-title: Data Min. Knowl. Disc.
– year: 2021
  ident: bib276
– reference: Ioffe, S. and C. Szegedy, Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167, 2015.
– volume: 58
  start-page: 13
  year: 2018
  end-page: 23
  ident: b0130
  article-title: Single-channel-based automatic drowsiness detection architecture with a reduced number of EEG features
  publication-title: Microprocess. Microsyst.
– volume: 16
  year: 2019
  ident: b0170
  article-title: Inter-subject transfer learning with an end-to-end deep convolutional neural network for EEG-based BCI
  publication-title: J. Neural Eng.
– volume: 4
  start-page: 214
  year: 2010
  end-page: 222
  ident: b0120
  article-title: A real-time wireless brain–computer interface system for drowsiness detection
  publication-title: IEEE Trans. Biomed. Circuits Syst.
– reference: Britton, J.W., et al., Electroencephalography (EEG): An introductory text and atlas of normal and abnormal findings in adults, children, and infants. 2016.
– volume: 26
  start-page: 2106
  year: 2018
  end-page: 2114
  ident: b0085
  article-title: STEW: Simultaneous task EEG workload data set
  publication-title: IEEE Trans. Neural Syst. Rehabil. Eng.
– volume: 30
  start-page: 808
  year: 2006
  end-page: 822
  ident: b0105
  article-title: Imaging human EEG dynamics using independent component analysis
  publication-title: Neurosci. Biobehav. Rev.
– reference: Lin, M., Q. Chen, and S. Yan, Network in network. arXiv preprint arXiv:1312.4400, 2013.
– volume: 16
  year: 2019
  ident: b0050
  article-title: Deep learning-based electroencephalography analysis: A systematic review
  publication-title: J. Neural Eng.
– volume: 12
  start-page: 431
  year: 2018
  end-page: 440
  ident: b0025
  article-title: Automated detection of driver fatigue based on EEG signals using gradient boosting decision tree model
  publication-title: Cognitive Neurodynamics
– year: 2016
  ident: b0060
  article-title: Learning deep features for discriminative localization
  publication-title: in
– volume: 18
  start-page: 4477
  year: 2018
  ident: b0115
  article-title: Portable drowsiness detection through use of a prefrontal single-channel electroencephalogram
  publication-title: Sensors
– volume: 2012
  year: 2012
  ident: b0145
  article-title: Sleep stage classification using unsupervised feature learning
  publication-title: Adv. Artificial Neural Syst.
– volume: 6
  start-page: 1
  year: 2019
  end-page: 8
  ident: b0190
  article-title: Multi-channel EEG recordings during a sustained-attention driving task
  publication-title: Sci. Data
– volume: 52
  start-page: 2726
  year: 2005
  end-page: 2738
  ident: b0210
  article-title: EEG-based drowsiness estimation for safety driving using independent component analysis
  publication-title: IEEE Trans. Circuits Syst. I Regul. Pap.
– volume: 42
  start-page: 107
  year: 2018
  end-page: 114
  ident: b0160
  article-title: A convolutional neural network for sleep stage scoring from raw single-channel EEG
  publication-title: Biomed. Signal Process. Control
– reference: Bashivan, P., et al., Learning representations from EEG with deep recurrent-convolutional neural networks. arXiv preprint arXiv:1511.06448, 2015.
– reference: Simonyan, K. and A. Zisserman, Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.
– volume: 347
  year: 2020
  ident: b0135
  article-title: Automatic classification methods for detecting drowsiness using wavelet packet transform extracted time-domain features from single-channel EEG signal
  publication-title: J. Neurosci. Methods
– reference: Hou, X., et al. EEG based stress monitoring. in 2015 IEEE International Conference on Systems, Man, and Cybernetics. 2015. IEEE.
– reference: Krizhevsky, A., I. Sutskever, and G.E. Hinton. Imagenet classification with deep convolutional neural networks. in Advances in neural information processing systems. 2012.
– volume: 29
  start-page: 169
  year: 1999
  end-page: 195
  ident: b0110
  article-title: EEG alpha and theta oscillations reflect cognitive and memory performance: a review and analysis
  publication-title: Brain Res. Rev.
– year: 2017
  ident: b0230
  article-title: Deep learning with convolutional neural networks for brain mapping and decoding of movement-related information from the human EEG
  publication-title: arXiv
– volume: 44
  year: 2020
  ident: b0065
  article-title: SAFE: An EEG dataset for stable affective feature selection
  publication-title: Adv. Eng. Inf.
– volume: 11
  start-page: 85
  year: 2018
  end-page: 94
  ident: b0070
  article-title: Domain adaptation techniques for EEG-based emotion recognition: a comparative study on two public datasets
  publication-title: IEEE Trans. Cognit. Development. Syst.
– volume: 12
  start-page: 85
  year: 2018
  ident: b0175
  article-title: Recurrent deep neural networks for real-time sleep stage classification from single channel EEG
  publication-title: Front. Comput. Neurosci.
– volume: 66
  start-page: 502
  year: 1987
  end-page: 511
  ident: b0010
  article-title: Sleepiness on the job: Continuously measured EEG changes in train drivers
  publication-title: Electroencephalography Clin. Neurophysiol.
– volume: 32
  start-page: 347
  year: 2016
  end-page: 358
  ident: b0075
  article-title: Real-time EEG-based emotion monitoring using stable features
  publication-title: Visual Comput.
– reference: Delta wave. Available from: https://en.wikipedia.org/wiki/Delta_wave.
– volume: 47
  start-page: 115
  year: 2009
  end-page: 124
  ident: b0020
  article-title: Can SVM be used for automatic EEG detection of drowsiness during car driving?
  publication-title: Saf. Sci.
– start-page: 1
  year: 2018
  end-page: 12
  ident: b0165
  article-title: A deep convolutional neural network model for automated identification of abnormal EEG signals
  publication-title: Neural Comput. Appl.
– reference: Silveira, T.d., A.d.J. Kozakevicius, and C.R. Rodrigues, Drowsiness detection for single channel EEG by DWT best m-term approximation. Research on Biomedical Engineering, 2015. 31(2): p. 107-115.
– volume: 15
  year: 2018
  ident: b0140
  article-title: EEGNet: A compact convolutional neural network for EEG-based brain–computer interfaces
  publication-title: J. Neural Eng.
– volume: 25
  start-page: 1998
  year: 2017
  end-page: 2008
  ident: b0155
  article-title: DeepSleepNet: a model for automatic sleep stage scoring based on raw single-channel EEG
  publication-title: IEEE Trans. Neural Syst. Rehabil. Eng.
– reference: Lin, Z.C.M.C.J.T.K.C.-T. Multi-channel EEG recordings during a sustained-attention driving task (pre-processed dataset). 2019; Available from: https://figshare.com/articles/Multi-channel_EEG_recordings_during_a_sustained-attention_driving_task_preprocessed_dataset_/7666055.
– reference: Shaw, J.C., The brain’s alpha rhythms and the mind. BV Elsevier Science, 2003.
– volume: 46
  year: 2020
  ident: b0100
  article-title: Inter-subject transfer learning for EEG-based mental fatigue recognition
  publication-title: Adv. Eng. Inf.
– reference: Kingma, D.P. and J. Ba, Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
– reference: Clevert, D.-A., T. Unterthiner, and S. Hochreiter, Fast and accurate deep network learning by exponential linear units (elus). arXiv preprint arXiv:1511.07289, 2015.
– volume: 51
  start-page: 50
  year: 2019
  end-page: 58
  ident: b0030
  article-title: Research on fatigue driving detection using forehead EEG based on adaptive multi-scale entropy
  publication-title: Biomed. Signal Process. Control
– year: 2014
  ident: b0080
  article-title: Stability of features in real-time EEG-based emotion recognition algorithm
– reference: vlawhern, Army Research Laboratory (ARL) EEGModels Project: A Collection of Convolutional Neural Network (CNN) models for EEG signal classification, using Keras and Tensorflow.
– year: 2019
  ident: b0095
  article-title: EEG-Based Cross-Subject Mental Fatigue Recognition
– reference: .
– volume: 26
  start-page: 400
  year: 2018
  end-page: 406
  ident: b0205
  article-title: Toward drowsiness detection using non-hair-bearing EEG-based brain-computer interfaces
  publication-title: IEEE Trans. Neural Syst. Rehabil. Eng.
– volume: 15
  start-page: 1929
  year: 2014
  end-page: 1958
  ident: b0220
  article-title: Dropout: A simple way to prevent neural networks from overfitting
  publication-title: J. Mach. Learn. Res.
– volume: 6
  start-page: 39
  year: 2012
  ident: b0240
  article-title: Filter bank common spatial pattern algorithm on BCI competition IV datasets 2a and 2b
  publication-title: Front. Neurosci.
– volume: 324
  year: 2019
  ident: b0180
  article-title: Deep convolutional neural network for classification of sleep stages from single-channel EEG signals
  publication-title: J. Neurosci. Methods
– reference: Scikit-learn Machine Learning in Python. Available from:
– volume: 122
  start-page: 1168
  year: 2011
  end-page: 1178
  ident: b0235
  article-title: EEG alpha spindle measures as indicators of driver fatigue under real traffic conditions
  publication-title: Clin. Neurophysiol.
– year: 2017
  ident: b0275
  article-title: Grad-cam: Visual explanations from deep networks via gradient-based localization
  publication-title: in
– reference: Administration, N.H.T.S., 2018 Fatal Motor Vehicle Crashes: Overview. 2019.
– volume: 66
  start-page: 502
  issue: 6
  year: 1987
  ident: 10.1016/j.ymeth.2021.04.017_b0010
  article-title: Sleepiness on the job: Continuously measured EEG changes in train drivers
  publication-title: Electroencephalography Clin. Neurophysiol.
  doi: 10.1016/0013-4694(87)90096-4
– volume: 47
  start-page: 115
  issue: 1
  year: 2009
  ident: 10.1016/j.ymeth.2021.04.017_b0020
  article-title: Can SVM be used for automatic EEG detection of drowsiness during car driving?
  publication-title: Saf. Sci.
  doi: 10.1016/j.ssci.2008.01.007
– ident: 10.1016/j.ymeth.2021.04.017_b0255
– year: 2019
  ident: 10.1016/j.ymeth.2021.04.017_b0185
– volume: 44
  year: 2020
  ident: 10.1016/j.ymeth.2021.04.017_b0065
  article-title: SAFE: An EEG dataset for stable affective feature selection
  publication-title: Adv. Eng. Inf.
  doi: 10.1016/j.aei.2020.101047
– volume: 39
  start-page: 313
  issue: 3
  year: 2002
  ident: 10.1016/j.ymeth.2021.04.017_b0015
  article-title: Driver fatigue: electroencephalography and psychological assessment
  publication-title: Psychophysiology
  doi: 10.1017/S0048577201393095
– volume: 42
  start-page: 107
  year: 2018
  ident: 10.1016/j.ymeth.2021.04.017_b0160
  article-title: A convolutional neural network for sleep stage scoring from raw single-channel EEG
  publication-title: Biomed. Signal Process. Control
  doi: 10.1016/j.bspc.2017.12.001
– volume: 33
  start-page: 917
  issue: 4
  year: 2019
  ident: 10.1016/j.ymeth.2021.04.017_b0045
  article-title: Deep learning for time series classification: a review
  publication-title: Data Min. Knowl. Disc.
  doi: 10.1007/s10618-019-00619-1
– volume: 347
  year: 2020
  ident: 10.1016/j.ymeth.2021.04.017_b0135
  article-title: Automatic classification methods for detecting drowsiness using wavelet packet transform extracted time-domain features from single-channel EEG signal
  publication-title: J. Neurosci. Methods
– volume: 30
  start-page: 808
  issue: 6
  year: 2006
  ident: 10.1016/j.ymeth.2021.04.017_b0105
  article-title: Imaging human EEG dynamics using independent component analysis
  publication-title: Neurosci. Biobehav. Rev.
  doi: 10.1016/j.neubiorev.2006.06.007
– volume: 15
  start-page: 1929
  issue: 1
  year: 2014
  ident: 10.1016/j.ymeth.2021.04.017_b0220
  article-title: Dropout: A simple way to prevent neural networks from overfitting
  publication-title: J. Mach. Learn. Res.
– volume: 12
  start-page: 431
  issue: 4
  year: 2018
  ident: 10.1016/j.ymeth.2021.04.017_b0025
  article-title: Automated detection of driver fatigue based on EEG signals using gradient boosting decision tree model
  publication-title: Cognitive Neurodynamics
  doi: 10.1007/s11571-018-9485-1
– ident: 10.1016/j.ymeth.2021.04.017_b0245
– volume: 15
  issue: 5
  year: 2018
  ident: 10.1016/j.ymeth.2021.04.017_b0140
  article-title: EEGNet: A compact convolutional neural network for EEG-based brain–computer interfaces
  publication-title: J. Neural Eng.
  doi: 10.1088/1741-2552/aace8c
– volume: 122
  start-page: 1168
  issue: 6
  year: 2011
  ident: 10.1016/j.ymeth.2021.04.017_b0235
  article-title: EEG alpha spindle measures as indicators of driver fatigue under real traffic conditions
  publication-title: Clin. Neurophysiol.
  doi: 10.1016/j.clinph.2010.10.044
– volume: 25
  start-page: 1998
  issue: 11
  year: 2017
  ident: 10.1016/j.ymeth.2021.04.017_b0155
  article-title: DeepSleepNet: a model for automatic sleep stage scoring based on raw single-channel EEG
  publication-title: IEEE Trans. Neural Syst. Rehabil. Eng.
  doi: 10.1109/TNSRE.2017.2721116
– ident: 10.1016/j.ymeth.2021.04.017_b0040
– ident: 10.1016/j.ymeth.2021.04.017_b0195
– volume: 51
  start-page: 50
  year: 2019
  ident: 10.1016/j.ymeth.2021.04.017_b0030
  article-title: Research on fatigue driving detection using forehead EEG based on adaptive multi-scale entropy
  publication-title: Biomed. Signal Process. Control
  doi: 10.1016/j.bspc.2019.02.005
– volume: 11
  start-page: 85
  issue: 1
  year: 2018
  ident: 10.1016/j.ymeth.2021.04.017_b0070
  article-title: Domain adaptation techniques for EEG-based emotion recognition: a comparative study on two public datasets
  publication-title: IEEE Trans. Cognit. Development. Syst.
  doi: 10.1109/TCDS.2018.2826840
– volume: 18
  start-page: 4477
  issue: 12
  year: 2018
  ident: 10.1016/j.ymeth.2021.04.017_b0115
  article-title: Portable drowsiness detection through use of a prefrontal single-channel electroencephalogram
  publication-title: Sensors
  doi: 10.3390/s18124477
– volume: 32
  start-page: 347
  issue: 3
  year: 2016
  ident: 10.1016/j.ymeth.2021.04.017_b0075
  article-title: Real-time EEG-based emotion monitoring using stable features
  publication-title: Visual Comput.
  doi: 10.1007/s00371-015-1183-y
– year: 2019
  ident: 10.1016/j.ymeth.2021.04.017_b0095
– year: 2017
  ident: 10.1016/j.ymeth.2021.04.017_b0230
  article-title: Deep learning with convolutional neural networks for brain mapping and decoding of movement-related information from the human EEG
  publication-title: arXiv
– volume: 29
  start-page: 169
  issue: 2–3
  year: 1999
  ident: 10.1016/j.ymeth.2021.04.017_b0110
  article-title: EEG alpha and theta oscillations reflect cognitive and memory performance: a review and analysis
  publication-title: Brain Res. Rev.
  doi: 10.1016/S0165-0173(98)00056-3
– ident: 10.1016/j.ymeth.2021.04.017_b0005
– ident: 10.1016/j.ymeth.2021.04.017_b0265
– volume: 2012
  year: 2012
  ident: 10.1016/j.ymeth.2021.04.017_b0145
  article-title: Sleep stage classification using unsupervised feature learning
  publication-title: Adv. Artificial Neural Syst.
– start-page: 1
  year: 2018
  ident: 10.1016/j.ymeth.2021.04.017_b0165
  article-title: A deep convolutional neural network model for automated identification of abnormal EEG signals
  publication-title: Neural Comput. Appl.
– year: 2014
  ident: 10.1016/j.ymeth.2021.04.017_b0080
– volume: 26
  start-page: 2106
  issue: 11
  year: 2018
  ident: 10.1016/j.ymeth.2021.04.017_b0085
  article-title: STEW: Simultaneous task EEG workload data set
  publication-title: IEEE Trans. Neural Syst. Rehabil. Eng.
  doi: 10.1109/TNSRE.2018.2872924
– volume: 12
  start-page: 85
  year: 2018
  ident: 10.1016/j.ymeth.2021.04.017_b0175
  article-title: Recurrent deep neural networks for real-time sleep stage classification from single channel EEG
  publication-title: Front. Comput. Neurosci.
  doi: 10.3389/fncom.2018.00085
– ident: 10.1016/j.ymeth.2021.04.017_b0150
– volume: 52
  start-page: 2726
  issue: 12
  year: 2005
  ident: 10.1016/j.ymeth.2021.04.017_b0210
  article-title: EEG-based drowsiness estimation for safety driving using independent component analysis
  publication-title: IEEE Trans. Circuits Syst. I Regul. Pap.
  doi: 10.1109/TCSI.2005.857555
– ident: 10.1016/j.ymeth.2021.04.017_b0035
– volume: 46
  year: 2020
  ident: 10.1016/j.ymeth.2021.04.017_b0100
  article-title: Inter-subject transfer learning for EEG-based mental fatigue recognition
  publication-title: Adv. Eng. Inf.
  doi: 10.1016/j.aei.2020.101157
– volume: 324
  year: 2019
  ident: 10.1016/j.ymeth.2021.04.017_b0180
  article-title: Deep convolutional neural network for classification of sleep stages from single-channel EEG signals
  publication-title: J. Neurosci. Methods
  doi: 10.1016/j.jneumeth.2019.108312
– year: 2017
  ident: 10.1016/j.ymeth.2021.04.017_b0275
  article-title: Grad-cam: Visual explanations from deep networks via gradient-based localization
– ident: 10.1016/j.ymeth.2021.04.017_b0090
  doi: 10.1109/SMC.2015.540
– ident: 10.1016/j.ymeth.2021.04.017_b0250
– volume: 6
  start-page: 1
  issue: 1
  year: 2019
  ident: 10.1016/j.ymeth.2021.04.017_b0190
  article-title: Multi-channel EEG recordings during a sustained-attention driving task
  publication-title: Sci. Data
  doi: 10.1038/s41597-019-0027-4
– year: 2016
  ident: 10.1016/j.ymeth.2021.04.017_b0060
  article-title: Learning deep features for discriminative localization
– volume: 16
  issue: 5
  year: 2019
  ident: 10.1016/j.ymeth.2021.04.017_b0050
  article-title: Deep learning-based electroencephalography analysis: A systematic review
  publication-title: J. Neural Eng.
  doi: 10.1088/1741-2552/ab260c
– ident: 10.1016/j.ymeth.2021.04.017_b0260
– ident: 10.1016/j.ymeth.2021.04.017_b0225
– volume: 6
  start-page: 39
  year: 2012
  ident: 10.1016/j.ymeth.2021.04.017_b0240
  article-title: Filter bank common spatial pattern algorithm on BCI competition IV datasets 2a and 2b
  publication-title: Front. Neurosci.
  doi: 10.3389/fnins.2012.00039
– ident: 10.1016/j.ymeth.2021.04.017_b0055
– volume: 16
  issue: 2
  year: 2019
  ident: 10.1016/j.ymeth.2021.04.017_b0170
  article-title: Inter-subject transfer learning with an end-to-end deep convolutional neural network for EEG-based BCI
  publication-title: J. Neural Eng.
  doi: 10.1088/1741-2552/aaf3f6
– volume: 4
  start-page: 214
  issue: 4
  year: 2010
  ident: 10.1016/j.ymeth.2021.04.017_b0120
  article-title: A real-time wireless brain–computer interface system for drowsiness detection
  publication-title: IEEE Trans. Biomed. Circuits Syst.
  doi: 10.1109/TBCAS.2010.2046415
– volume: 26
  start-page: 400
  issue: 2
  year: 2018
  ident: 10.1016/j.ymeth.2021.04.017_b0205
  article-title: Toward drowsiness detection using non-hair-bearing EEG-based brain-computer interfaces
  publication-title: IEEE Trans. Neural Syst. Rehabil. Eng.
  doi: 10.1109/TNSRE.2018.2790359
– ident: 10.1016/j.ymeth.2021.04.017_b0125
  doi: 10.1590/2446-4740.0693
– volume: 2008
  issue: 1
  year: 2008
  ident: 10.1016/j.ymeth.2021.04.017_b0200
  article-title: EEG-based subject-and session-independent drowsiness detection: an unsupervised approach
  publication-title: EURASIP J. Adv. Signal Process.
  doi: 10.1155/2008/519480
– ident: 10.1016/j.ymeth.2021.04.017_b0270
– volume: 58
  start-page: 13
  year: 2018
  ident: 10.1016/j.ymeth.2021.04.017_b0130
  article-title: Single-channel-based automatic drowsiness detection architecture with a reduced number of EEG features
  publication-title: Microprocess. Microsyst.
  doi: 10.1016/j.micpro.2018.02.004
– ident: 10.1016/j.ymeth.2021.04.017_b0215
SSID ssj0001278
Score 2.6320162
Snippet •An interpretable CNN model that can reveal important parts of input single-channel EEG signals for classification with the Class Activation Map (CAM)...
Driver drowsiness is one of the main factors leading to road fatalities and hazards in the transportation industry. Electroencephalography (EEG) has been...
SourceID proquest
pubmed
crossref
elsevier
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 173
SubjectTerms brain
Class activation mapping
Convolutional neural network
Driver drowsiness detection
electroencephalography
Interpretable CNN
muscles
Network visualization
neural networks
neurophysiology
Single-channel EEG
transportation industry
Title A compact and interpretable convolutional neural network for cross-subject driver drowsiness detection from single-channel EEG
URI https://dx.doi.org/10.1016/j.ymeth.2021.04.017
https://www.ncbi.nlm.nih.gov/pubmed/33901644
https://www.proquest.com/docview/2518994281
https://www.proquest.com/docview/2551917173
Volume 202
WOSCitedRecordID wos000804388400009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1095-9130
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001278
  issn: 1046-2023
  databaseCode: AIEXJ
  dateStart: 19950201
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bb9MwFLa6DgleEGwwymUyEtpLSRXnUsePVemAaRQkOqniJXJiF2UqaWmTsb3wO_i5HF-SpZpWjQdeksaNkyjfl-Pj43NB6E3gCxFy4TpCEOEElIMcDH0OwtBLU8aoy1yhi03Q8TiaTtmXVutPFQtzMad5Hl1esuV_hRraAGwVOvsPcNcXhQb4DaDDFmCH7Z2AHxi_8rSwiZUqp0IVIqV8zO3NARqVy1LvtCe4djjUg6azLhNlnumKlfLagN3il3WPF7KQpri4jktRhoa5dFT0cC7n3dHofVPZ_aSrU2uz7lcQI-8y-d0YZlU8WK9hgxiW2qfgpEHVU2OY_Zatyqxuy0o9YmTrRpPmSJnNbQZxa8CAuW_taGVlLkzRHVXFvSmU4bi77BHqOyQKGgKWmMIndqy2_90YBoxF4rx3pcpw9-BaROezNVGim0m3x5_j47PT03gymk6Olj8dVY9Mrdvb4iw7aNejIYvaaHfwcTQ9qUd54lETZmkfvspopX0Hb9z3Nq3ntlmN1m4mj9BDOy3BA0Onx6gl8z20P8h5sfhxhY-wdhTWKzB76P6wKhK4j34PsGUbBrbhDbbhDbZhwzZs2YaBbXiDbdiwDV-zDddsw4pteJNtGNj2BJ0djybDD44t6eGkoIgXDqczeEORACWIcBZFnIeSuFJlheSJywMWsdRj3syls1DMwqgP-nw_CYQETZOTVPpPUTtf5PIZwl4iA0mET13JYRRKeECSPhUsVBmPaEI7yKteeZzafPeq7Mo8rhwbz2ONU6xwit0gBpw66G3daWnSvWw_vV9hGVuN1WiiMTBxe8fXFfIxIKYW6XguF-U6hvlGxFjgRWTbOaEys8C30EEHhjb10_rKiAmTnOd36P0CPbj-IF-idrEq5St0L70osvXqEO3QaXRoef8XkQPZzQ
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+compact+and+interpretable+convolutional+neural+network+for+cross-subject+driver+drowsiness+detection+from+single-channel+EEG&rft.jtitle=Methods+%28San+Diego%2C+Calif.%29&rft.au=Cui%2C+Jian&rft.au=Lan%2C+Zirui&rft.au=Liu%2C+Yisi&rft.au=Li%2C+Ruilin&rft.date=2022-06-01&rft.issn=1046-2023&rft.volume=202+p.173-184&rft.spage=173&rft.epage=184&rft_id=info:doi/10.1016%2Fj.ymeth.2021.04.017&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1046-2023&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1046-2023&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1046-2023&client=summon