VIGNet: A Deep Convolutional Neural Network for EEG-based Driver Vigilance Estimation

Wonjun Ko; Kwanseok Oh; Eunjin Jeon; Heung Il Suk

doi:10.1109/BCI48061.2020.9061668

VIGNet: A Deep Convolutional Neural Network for EEG-based Driver Vigilance Estimation

Wonjun Ko, Kwanseok Oh, Eunjin Jeon, Heung Il Suk

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

39 Citations (Scopus)

Abstract

Estimating driver fatigue is an important issue for traffic safety and user-centered brain-computer interface. In this paper, based on differential entropy (DE) extracted from electroencephalography (EEG) signals, we develop a novel deep convolutional neural network to detect driver drowsiness. By exploiting DE of EEG samples, the proposed network effectively extracts class-discriminative deep and hierarchical features. Then, a densely-connected layer is used for the final decision making to identify driver condition. To demonstrate the validity of our proposed method, we conduct classification and regression experiments using publicly available SEED-VIG dataset. Further, we also compare the proposed network to other competitive state-of-the-art methods with an appropriate statistical analysis. Furthermore, we inspect the real-world usability of our method by visualizing a change in the probability of driver status and confusion matrices.

Original language	English
Title of host publication	8th International Winter Conference on Brain-Computer Interface, BCI 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728147079
DOIs	https://doi.org/10.1109/BCI48061.2020.9061668
Publication status	Published - 2020 Feb
Event	8th International Winter Conference on Brain-Computer Interface, BCI 2020 - Gangwon, Korea, Republic of Duration: 2020 Feb 26 → 2020 Feb 28

Publication series

Name	8th International Winter Conference on Brain-Computer Interface, BCI 2020

Conference

Conference	8th International Winter Conference on Brain-Computer Interface, BCI 2020
Country/Territory	Korea, Republic of
City	Gangwon
Period	20/2/26 → 20/2/28

Bibliographical note

Funding Information:
ACKNOWLEDGMENT This work was supported by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (No. 2017-0-00451; Development of BCI based Brain and Cognitive Computing Technology for Recognizing User’s Intentions using Deep Learning).

Publisher Copyright:
© 2020 IEEE.

Keywords

Brain-Computer Interface
Convolutional Neural Network
Deep Learning
Drowsiness Detection
Electroencephalogram

ASJC Scopus subject areas

Behavioral Neuroscience
Cognitive Neuroscience
Artificial Intelligence
Human-Computer Interaction

Access to Document

10.1109/BCI48061.2020.9061668

Cite this

Ko, W., Oh, K., Jeon, E., & Suk, H. I. (2020). VIGNet: A Deep Convolutional Neural Network for EEG-based Driver Vigilance Estimation. In 8th International Winter Conference on Brain-Computer Interface, BCI 2020 Article 9061668 (8th International Winter Conference on Brain-Computer Interface, BCI 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BCI48061.2020.9061668

VIGNet: A Deep Convolutional Neural Network for EEG-based Driver Vigilance Estimation. / Ko, Wonjun; Oh, Kwanseok; Jeon, Eunjin et al.
8th International Winter Conference on Brain-Computer Interface, BCI 2020. Institute of Electrical and Electronics Engineers Inc., 2020. 9061668 (8th International Winter Conference on Brain-Computer Interface, BCI 2020).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Ko, W, Oh, K, Jeon, E & Suk, HI 2020, VIGNet: A Deep Convolutional Neural Network for EEG-based Driver Vigilance Estimation. in 8th International Winter Conference on Brain-Computer Interface, BCI 2020., 9061668, 8th International Winter Conference on Brain-Computer Interface, BCI 2020, Institute of Electrical and Electronics Engineers Inc., 8th International Winter Conference on Brain-Computer Interface, BCI 2020, Gangwon, Korea, Republic of, 20/2/26. https://doi.org/10.1109/BCI48061.2020.9061668

Ko W, Oh K, Jeon E, Suk HI. VIGNet: A Deep Convolutional Neural Network for EEG-based Driver Vigilance Estimation. In 8th International Winter Conference on Brain-Computer Interface, BCI 2020. Institute of Electrical and Electronics Engineers Inc. 2020. 9061668. (8th International Winter Conference on Brain-Computer Interface, BCI 2020). doi: 10.1109/BCI48061.2020.9061668

@inproceedings{45ef4a11119f4854a3fb53b81d9f9bd2,

title = "VIGNet: A Deep Convolutional Neural Network for EEG-based Driver Vigilance Estimation",

abstract = "Estimating driver fatigue is an important issue for traffic safety and user-centered brain-computer interface. In this paper, based on differential entropy (DE) extracted from electroencephalography (EEG) signals, we develop a novel deep convolutional neural network to detect driver drowsiness. By exploiting DE of EEG samples, the proposed network effectively extracts class-discriminative deep and hierarchical features. Then, a densely-connected layer is used for the final decision making to identify driver condition. To demonstrate the validity of our proposed method, we conduct classification and regression experiments using publicly available SEED-VIG dataset. Further, we also compare the proposed network to other competitive state-of-the-art methods with an appropriate statistical analysis. Furthermore, we inspect the real-world usability of our method by visualizing a change in the probability of driver status and confusion matrices.",

keywords = "Brain-Computer Interface, Convolutional Neural Network, Deep Learning, Drowsiness Detection, Electroencephalogram",

author = "Wonjun Ko and Kwanseok Oh and Eunjin Jeon and Suk, {Heung Il}",

note = "Funding Information: ACKNOWLEDGMENT This work was supported by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (No. 2017-0-00451; Development of BCI based Brain and Cognitive Computing Technology for Recognizing User{\textquoteright}s Intentions using Deep Learning). Publisher Copyright: {\textcopyright} 2020 IEEE.; 8th International Winter Conference on Brain-Computer Interface, BCI 2020 ; Conference date: 26-02-2020 Through 28-02-2020",

year = "2020",

month = feb,

doi = "10.1109/BCI48061.2020.9061668",

language = "English",

series = "8th International Winter Conference on Brain-Computer Interface, BCI 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "8th International Winter Conference on Brain-Computer Interface, BCI 2020",

}

TY - GEN

T1 - VIGNet

T2 - 8th International Winter Conference on Brain-Computer Interface, BCI 2020

AU - Ko, Wonjun

AU - Oh, Kwanseok

AU - Jeon, Eunjin

AU - Suk, Heung Il

N1 - Funding Information: ACKNOWLEDGMENT This work was supported by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (No. 2017-0-00451; Development of BCI based Brain and Cognitive Computing Technology for Recognizing User’s Intentions using Deep Learning). Publisher Copyright: © 2020 IEEE.

PY - 2020/2

Y1 - 2020/2

N2 - Estimating driver fatigue is an important issue for traffic safety and user-centered brain-computer interface. In this paper, based on differential entropy (DE) extracted from electroencephalography (EEG) signals, we develop a novel deep convolutional neural network to detect driver drowsiness. By exploiting DE of EEG samples, the proposed network effectively extracts class-discriminative deep and hierarchical features. Then, a densely-connected layer is used for the final decision making to identify driver condition. To demonstrate the validity of our proposed method, we conduct classification and regression experiments using publicly available SEED-VIG dataset. Further, we also compare the proposed network to other competitive state-of-the-art methods with an appropriate statistical analysis. Furthermore, we inspect the real-world usability of our method by visualizing a change in the probability of driver status and confusion matrices.

AB - Estimating driver fatigue is an important issue for traffic safety and user-centered brain-computer interface. In this paper, based on differential entropy (DE) extracted from electroencephalography (EEG) signals, we develop a novel deep convolutional neural network to detect driver drowsiness. By exploiting DE of EEG samples, the proposed network effectively extracts class-discriminative deep and hierarchical features. Then, a densely-connected layer is used for the final decision making to identify driver condition. To demonstrate the validity of our proposed method, we conduct classification and regression experiments using publicly available SEED-VIG dataset. Further, we also compare the proposed network to other competitive state-of-the-art methods with an appropriate statistical analysis. Furthermore, we inspect the real-world usability of our method by visualizing a change in the probability of driver status and confusion matrices.

KW - Brain-Computer Interface

KW - Convolutional Neural Network

KW - Deep Learning

KW - Drowsiness Detection

KW - Electroencephalogram

UR - http://www.scopus.com/inward/record.url?scp=85084085676&partnerID=8YFLogxK

U2 - 10.1109/BCI48061.2020.9061668

DO - 10.1109/BCI48061.2020.9061668

M3 - Conference contribution

AN - SCOPUS:85084085676

T3 - 8th International Winter Conference on Brain-Computer Interface, BCI 2020

BT - 8th International Winter Conference on Brain-Computer Interface, BCI 2020

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 26 February 2020 through 28 February 2020

ER -

VIGNet: A Deep Convolutional Neural Network for EEG-based Driver Vigilance Estimation

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this