Deep Neural Network for Drowsiness Detection from EEG

Chungho Lee; Rock Hyun Choi; Jinung An

doi:10.1109/BCI51272.2021.9385368

Deep Neural Network for Drowsiness Detection from EEG

Chungho Lee, Rock Hyun Choi, Jinung An

Division of Intelligent Robot

Daegu Gyeongbuk Institute of Science and Technology

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

2 Scopus citations

Abstract

This study aimed to detect drowsiness and find optimal electrode set by collecting and classifying the EEG dataset labeled with three classes: awakeness, drowsiness, and sleep. Blindfolded subjects were presented short audio stimulus in random duration and instructed to push button according to audio stimulus. For classification of 3 classes, EEG signal was segmented and labeled according to the sequence of button response. Then, segmented data were directly fed into classifier without further transformation. Training was accomplished by the proposed deep learning including four LSTM layers. The proposed drowsiness detection deep learning network resulted 82.8% accuracy with 18 channels, and 79.8% accuracy with 3 channels located at premotor area of right hemisphere.

Original language	English
Title of host publication	9th IEEE International Winter Conference on Brain-Computer Interface, BCI 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728184852
DOIs	https://doi.org/10.1109/BCI51272.2021.9385368
State	Published - 22 Feb 2021
Event	9th IEEE International Winter Conference on Brain-Computer Interface, BCI 2021 - Gangwon, Korea, Republic of Duration: 22 Feb 2021 → 24 Feb 2021

Publication series

Name	9th IEEE International Winter Conference on Brain-Computer Interface, BCI 2021

Conference

Conference	9th IEEE International Winter Conference on Brain-Computer Interface, BCI 2021
Country/Territory	Korea, Republic of
City	Gangwon
Period	22/02/21 → 24/02/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Keywords

LSTM
deep learning
drowsiness detection
multiclass classification

Access to Document

10.1109/BCI51272.2021.9385368

Cite this

Lee, C., Choi, R. H., & An, J. (2021). Deep Neural Network for Drowsiness Detection from EEG. In 9th IEEE International Winter Conference on Brain-Computer Interface, BCI 2021 Article 9385368 (9th IEEE International Winter Conference on Brain-Computer Interface, BCI 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BCI51272.2021.9385368

@inproceedings{61c8e48e81aa4a63a27bfbd1db70eeff,

title = "Deep Neural Network for Drowsiness Detection from EEG",

abstract = "This study aimed to detect drowsiness and find optimal electrode set by collecting and classifying the EEG dataset labeled with three classes: awakeness, drowsiness, and sleep. Blindfolded subjects were presented short audio stimulus in random duration and instructed to push button according to audio stimulus. For classification of 3 classes, EEG signal was segmented and labeled according to the sequence of button response. Then, segmented data were directly fed into classifier without further transformation. Training was accomplished by the proposed deep learning including four LSTM layers. The proposed drowsiness detection deep learning network resulted 82.8% accuracy with 18 channels, and 79.8% accuracy with 3 channels located at premotor area of right hemisphere.",

keywords = "LSTM, deep learning, drowsiness detection, multiclass classification",

author = "Chungho Lee and Choi, {Rock Hyun} and Jinung An",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 9th IEEE International Winter Conference on Brain-Computer Interface, BCI 2021 ; Conference date: 22-02-2021 Through 24-02-2021",

year = "2021",

month = feb,

day = "22",

doi = "10.1109/BCI51272.2021.9385368",

language = "English",

series = "9th IEEE International Winter Conference on Brain-Computer Interface, BCI 2021",

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

booktitle = "9th IEEE International Winter Conference on Brain-Computer Interface, BCI 2021",

}

Lee, C, Choi, RH & An, J 2021, Deep Neural Network for Drowsiness Detection from EEG. in 9th IEEE International Winter Conference on Brain-Computer Interface, BCI 2021., 9385368, 9th IEEE International Winter Conference on Brain-Computer Interface, BCI 2021, Institute of Electrical and Electronics Engineers Inc., 9th IEEE International Winter Conference on Brain-Computer Interface, BCI 2021, Gangwon, Korea, Republic of, 22/02/21. https://doi.org/10.1109/BCI51272.2021.9385368

Deep Neural Network for Drowsiness Detection from EEG. / Lee, Chungho; Choi, Rock Hyun; An, Jinung.
9th IEEE International Winter Conference on Brain-Computer Interface, BCI 2021. Institute of Electrical and Electronics Engineers Inc., 2021. 9385368 (9th IEEE International Winter Conference on Brain-Computer Interface, BCI 2021).

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

TY - GEN

T1 - Deep Neural Network for Drowsiness Detection from EEG

AU - Lee, Chungho

AU - Choi, Rock Hyun

AU - An, Jinung

PY - 2021/2/22

Y1 - 2021/2/22

N2 - This study aimed to detect drowsiness and find optimal electrode set by collecting and classifying the EEG dataset labeled with three classes: awakeness, drowsiness, and sleep. Blindfolded subjects were presented short audio stimulus in random duration and instructed to push button according to audio stimulus. For classification of 3 classes, EEG signal was segmented and labeled according to the sequence of button response. Then, segmented data were directly fed into classifier without further transformation. Training was accomplished by the proposed deep learning including four LSTM layers. The proposed drowsiness detection deep learning network resulted 82.8% accuracy with 18 channels, and 79.8% accuracy with 3 channels located at premotor area of right hemisphere.

AB - This study aimed to detect drowsiness and find optimal electrode set by collecting and classifying the EEG dataset labeled with three classes: awakeness, drowsiness, and sleep. Blindfolded subjects were presented short audio stimulus in random duration and instructed to push button according to audio stimulus. For classification of 3 classes, EEG signal was segmented and labeled according to the sequence of button response. Then, segmented data were directly fed into classifier without further transformation. Training was accomplished by the proposed deep learning including four LSTM layers. The proposed drowsiness detection deep learning network resulted 82.8% accuracy with 18 channels, and 79.8% accuracy with 3 channels located at premotor area of right hemisphere.

KW - LSTM

KW - deep learning

KW - drowsiness detection

KW - multiclass classification

UR - http://www.scopus.com/inward/record.url?scp=85104848995&partnerID=8YFLogxK

U2 - 10.1109/BCI51272.2021.9385368

DO - 10.1109/BCI51272.2021.9385368

M3 - Conference contribution

AN - SCOPUS:85104848995

T3 - 9th IEEE International Winter Conference on Brain-Computer Interface, BCI 2021

BT - 9th IEEE International Winter Conference on Brain-Computer Interface, BCI 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 9th IEEE International Winter Conference on Brain-Computer Interface, BCI 2021

Y2 - 22 February 2021 through 24 February 2021

ER -

Deep Neural Network for Drowsiness Detection from EEG

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this