EEG-based Classification of Microsleep by Means of Feature Selection: An Application in Aviation

Bijay Guragain; Ali Bahrami Rad; Chunwu Wang; Ajay K. Verma; Lewis Archer; Nicholas Wilson; Kouhyar Tavakolian

doi:10.1109/EMBC.2019.8856429

EEG-based Classification of Microsleep by Means of Feature Selection: An Application in Aviation

Bijay Guragain, Ali Bahrami Rad, Chunwu Wang, Ajay K. Verma, Lewis Archer, Nicholas Wilson, Kouhyar Tavakolian

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

10 Citations (Scopus)

Abstract

This paper presents a method for classification of microsleep (MS) from baseline utilizing linear and non-linear features derived from electroencephalography (EEG), which is recorded from five brain regions: frontal, central, parietal, occipital, and temporal. The EEG is acquired from sixteen commercially-rated pilots during the window of circadian low (2:00 am-6:00 am). MS events are annotated using the Driver Monitoring System and further verified using electrooculogram (EOG). A total of 55 features are extracted from EEG. A subset of these features is then selected using a wrapper-based method. The selected features are fed into a linear or quadratic discriminant analysis (LDA or QDA) classifier to automatically differentiate baseline from MS states. The overall classification performance of the best-proposed algorithm is 87.11% in terms of F1 score. This preliminary result highlights the potential of the proposed method towards automatic drowsiness detection which could assist mitigating aviation accidents in the future, pending hardware development to record such EEG signals from the confines of the aviation headset.

Original language	English
Title of host publication	Proceedings of the 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019
Publisher	IEEE
Pages	4060-4063
Number of pages	4
ISBN (Electronic)	9781538613115
DOIs	https://doi.org/10.1109/EMBC.2019.8856429
Publication status	Published - 1 Jul 2019
MoE publication type	A4 Conference publication
Event	Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Berlin, Germany Duration: 23 Jul 2019 → 27 Jul 2019 Conference number: 41

Conference

Conference	Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Abbreviated title	EMBC
Country/Territory	Germany
City	Berlin
Period	23/07/2019 → 27/07/2019

Keywords

Drowsiness
EEG
LDA
Microsleep
QDA

Access to Document

10.1109/EMBC.2019.8856429

Cite this

Guragain, B., Rad, A. B., Wang, C., Verma, A. K., Archer, L., Wilson, N., & Tavakolian, K. (2019). EEG-based Classification of Microsleep by Means of Feature Selection: An Application in Aviation. In Proceedings of the 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019 (pp. 4060-4063). Article 8856429 IEEE. https://doi.org/10.1109/EMBC.2019.8856429

@inproceedings{5f6bbf4af6e647429a61907c2237770b,

title = "EEG-based Classification of Microsleep by Means of Feature Selection: An Application in Aviation",

abstract = "This paper presents a method for classification of microsleep (MS) from baseline utilizing linear and non-linear features derived from electroencephalography (EEG), which is recorded from five brain regions: frontal, central, parietal, occipital, and temporal. The EEG is acquired from sixteen commercially-rated pilots during the window of circadian low (2:00 am-6:00 am). MS events are annotated using the Driver Monitoring System and further verified using electrooculogram (EOG). A total of 55 features are extracted from EEG. A subset of these features is then selected using a wrapper-based method. The selected features are fed into a linear or quadratic discriminant analysis (LDA or QDA) classifier to automatically differentiate baseline from MS states. The overall classification performance of the best-proposed algorithm is 87.11% in terms of F1 score. This preliminary result highlights the potential of the proposed method towards automatic drowsiness detection which could assist mitigating aviation accidents in the future, pending hardware development to record such EEG signals from the confines of the aviation headset.",

keywords = "Drowsiness, EEG, LDA, Microsleep, QDA",

author = "Bijay Guragain and Rad, {Ali Bahrami} and Chunwu Wang and Verma, {Ajay K.} and Lewis Archer and Nicholas Wilson and Kouhyar Tavakolian",

year = "2019",

month = jul,

day = "1",

doi = "10.1109/EMBC.2019.8856429",

language = "English",

pages = "4060--4063",

booktitle = "Proceedings of the 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019",

publisher = "IEEE",

address = "United States",

note = "Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC ; Conference date: 23-07-2019 Through 27-07-2019",

}

Guragain, B, Rad, AB, Wang, C, Verma, AK, Archer, L, Wilson, N & Tavakolian, K 2019, EEG-based Classification of Microsleep by Means of Feature Selection: An Application in Aviation. in Proceedings of the 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019., 8856429, IEEE, pp. 4060-4063, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Berlin, Germany, 23/07/2019. https://doi.org/10.1109/EMBC.2019.8856429

EEG-based Classification of Microsleep by Means of Feature Selection: An Application in Aviation. / Guragain, Bijay; Rad, Ali Bahrami; Wang, Chunwu et al.
Proceedings of the 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019. IEEE, 2019. p. 4060-4063 8856429.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - EEG-based Classification of Microsleep by Means of Feature Selection

T2 - Annual International Conference of the IEEE Engineering in Medicine and Biology Society

AU - Guragain, Bijay

AU - Rad, Ali Bahrami

AU - Wang, Chunwu

AU - Verma, Ajay K.

AU - Archer, Lewis

AU - Wilson, Nicholas

AU - Tavakolian, Kouhyar

N1 - Conference code: 41

PY - 2019/7/1

Y1 - 2019/7/1

N2 - This paper presents a method for classification of microsleep (MS) from baseline utilizing linear and non-linear features derived from electroencephalography (EEG), which is recorded from five brain regions: frontal, central, parietal, occipital, and temporal. The EEG is acquired from sixteen commercially-rated pilots during the window of circadian low (2:00 am-6:00 am). MS events are annotated using the Driver Monitoring System and further verified using electrooculogram (EOG). A total of 55 features are extracted from EEG. A subset of these features is then selected using a wrapper-based method. The selected features are fed into a linear or quadratic discriminant analysis (LDA or QDA) classifier to automatically differentiate baseline from MS states. The overall classification performance of the best-proposed algorithm is 87.11% in terms of F1 score. This preliminary result highlights the potential of the proposed method towards automatic drowsiness detection which could assist mitigating aviation accidents in the future, pending hardware development to record such EEG signals from the confines of the aviation headset.

AB - This paper presents a method for classification of microsleep (MS) from baseline utilizing linear and non-linear features derived from electroencephalography (EEG), which is recorded from five brain regions: frontal, central, parietal, occipital, and temporal. The EEG is acquired from sixteen commercially-rated pilots during the window of circadian low (2:00 am-6:00 am). MS events are annotated using the Driver Monitoring System and further verified using electrooculogram (EOG). A total of 55 features are extracted from EEG. A subset of these features is then selected using a wrapper-based method. The selected features are fed into a linear or quadratic discriminant analysis (LDA or QDA) classifier to automatically differentiate baseline from MS states. The overall classification performance of the best-proposed algorithm is 87.11% in terms of F1 score. This preliminary result highlights the potential of the proposed method towards automatic drowsiness detection which could assist mitigating aviation accidents in the future, pending hardware development to record such EEG signals from the confines of the aviation headset.

KW - Drowsiness

KW - EEG

KW - LDA

KW - Microsleep

KW - QDA

UR - http://www.scopus.com/inward/record.url?scp=85077882719&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2019.8856429

DO - 10.1109/EMBC.2019.8856429

M3 - Conference article in proceedings

C2 - 31946764

AN - SCOPUS:85077882719

SP - 4060

EP - 4063

BT - Proceedings of the 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019

PB - IEEE

Y2 - 23 July 2019 through 27 July 2019

ER -

EEG-based Classification of Microsleep by Means of Feature Selection: An Application in Aviation

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this