An EEG-based subject- and session-independent drowsiness detection

Chin Teng Lin, Nikhil R. Pal, Chien Yao Chuang, Tzyy Ping Jung, Li Wei Ko, Sheng Fu Liang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

17 Citations (Scopus)

Abstract

Monitoring and predicting human cognitive state and performance using physiological signals such as Electroencephalogram (EEG) have recently gained increasing attention in the fields of brain-computer interface and cognitive neuroscience. Most previous psychophysiological studies of cognitive changes have attempted to use the same model for all subjects. However, the relatively large individual variability in EEG dynamics relating to loss of alertness suggests that for many operators, group statistics cannot be used to accurately predict changes in cognitive states. Attempts have also been made to build a subject-dependent model for each individual based on his/her pilot data tb account for Individual variability. However, such methods assume the cross-session variability in EEG dynamics to be negligible, which could be problematic due to electrode displacements, environmental noises, and skin-electrode impedance. Here first we show that the EEG power in the alpha and theta bands are strongly correlated with changes in the subject's cognitive state reflected through his driving performance and hence his departure from alertness. Then under very mild and realistic assumptions we derive a model for the alert state of the person using EEG power in the alpha and theta bands. We demonstrate that deviations (computed by Mahalanobis distance) of the EEG power in the alpha and theta bands from the corresponding alert models are correlated to the changes in the driving performance. Finally, for detection of drowsiness we use a linear combination of deviations of the EEG power in the alpha band and theta band from the respective alert models that best correlates with subject's changing level of alertness, indexed by subject's behavioral response in the driving task. This approach could lead to a practical system for noninvasive monitoring of the cognitive state of human operators in attention-critical settings.

Original languageEnglish
Title of host publication2008 International Joint Conference on Neural Networks, IJCNN 2008
Pages3448-3454
Number of pages7
DOIs
Publication statusPublished - 2008 Nov 24
Event2008 International Joint Conference on Neural Networks, IJCNN 2008 - Hong Kong, China
Duration: 2008 Jun 12008 Jun 8

Publication series

NameProceedings of the International Joint Conference on Neural Networks

Other

Other2008 International Joint Conference on Neural Networks, IJCNN 2008
CountryChina
CityHong Kong
Period08-06-0108-06-08

Fingerprint

Electroencephalography
Electrodes
Brain computer interface
Monitoring
Mathematical operators
Skin
Statistics

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this

Lin, C. T., Pal, N. R., Chuang, C. Y., Jung, T. P., Ko, L. W., & Liang, S. F. (2008). An EEG-based subject- and session-independent drowsiness detection. In 2008 International Joint Conference on Neural Networks, IJCNN 2008 (pp. 3448-3454). [4634289] (Proceedings of the International Joint Conference on Neural Networks). https://doi.org/10.1109/IJCNN.2008.4634289
Lin, Chin Teng ; Pal, Nikhil R. ; Chuang, Chien Yao ; Jung, Tzyy Ping ; Ko, Li Wei ; Liang, Sheng Fu. / An EEG-based subject- and session-independent drowsiness detection. 2008 International Joint Conference on Neural Networks, IJCNN 2008. 2008. pp. 3448-3454 (Proceedings of the International Joint Conference on Neural Networks).
@inproceedings{523429cb6e73448db082706367c94e5e,
title = "An EEG-based subject- and session-independent drowsiness detection",
abstract = "Monitoring and predicting human cognitive state and performance using physiological signals such as Electroencephalogram (EEG) have recently gained increasing attention in the fields of brain-computer interface and cognitive neuroscience. Most previous psychophysiological studies of cognitive changes have attempted to use the same model for all subjects. However, the relatively large individual variability in EEG dynamics relating to loss of alertness suggests that for many operators, group statistics cannot be used to accurately predict changes in cognitive states. Attempts have also been made to build a subject-dependent model for each individual based on his/her pilot data tb account for Individual variability. However, such methods assume the cross-session variability in EEG dynamics to be negligible, which could be problematic due to electrode displacements, environmental noises, and skin-electrode impedance. Here first we show that the EEG power in the alpha and theta bands are strongly correlated with changes in the subject's cognitive state reflected through his driving performance and hence his departure from alertness. Then under very mild and realistic assumptions we derive a model for the alert state of the person using EEG power in the alpha and theta bands. We demonstrate that deviations (computed by Mahalanobis distance) of the EEG power in the alpha and theta bands from the corresponding alert models are correlated to the changes in the driving performance. Finally, for detection of drowsiness we use a linear combination of deviations of the EEG power in the alpha band and theta band from the respective alert models that best correlates with subject's changing level of alertness, indexed by subject's behavioral response in the driving task. This approach could lead to a practical system for noninvasive monitoring of the cognitive state of human operators in attention-critical settings.",
author = "Lin, {Chin Teng} and Pal, {Nikhil R.} and Chuang, {Chien Yao} and Jung, {Tzyy Ping} and Ko, {Li Wei} and Liang, {Sheng Fu}",
year = "2008",
month = "11",
day = "24",
doi = "10.1109/IJCNN.2008.4634289",
language = "English",
isbn = "9781424418213",
series = "Proceedings of the International Joint Conference on Neural Networks",
pages = "3448--3454",
booktitle = "2008 International Joint Conference on Neural Networks, IJCNN 2008",

}

Lin, CT, Pal, NR, Chuang, CY, Jung, TP, Ko, LW & Liang, SF 2008, An EEG-based subject- and session-independent drowsiness detection. in 2008 International Joint Conference on Neural Networks, IJCNN 2008., 4634289, Proceedings of the International Joint Conference on Neural Networks, pp. 3448-3454, 2008 International Joint Conference on Neural Networks, IJCNN 2008, Hong Kong, China, 08-06-01. https://doi.org/10.1109/IJCNN.2008.4634289

An EEG-based subject- and session-independent drowsiness detection. / Lin, Chin Teng; Pal, Nikhil R.; Chuang, Chien Yao; Jung, Tzyy Ping; Ko, Li Wei; Liang, Sheng Fu.

2008 International Joint Conference on Neural Networks, IJCNN 2008. 2008. p. 3448-3454 4634289 (Proceedings of the International Joint Conference on Neural Networks).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - An EEG-based subject- and session-independent drowsiness detection

AU - Lin, Chin Teng

AU - Pal, Nikhil R.

AU - Chuang, Chien Yao

AU - Jung, Tzyy Ping

AU - Ko, Li Wei

AU - Liang, Sheng Fu

PY - 2008/11/24

Y1 - 2008/11/24

N2 - Monitoring and predicting human cognitive state and performance using physiological signals such as Electroencephalogram (EEG) have recently gained increasing attention in the fields of brain-computer interface and cognitive neuroscience. Most previous psychophysiological studies of cognitive changes have attempted to use the same model for all subjects. However, the relatively large individual variability in EEG dynamics relating to loss of alertness suggests that for many operators, group statistics cannot be used to accurately predict changes in cognitive states. Attempts have also been made to build a subject-dependent model for each individual based on his/her pilot data tb account for Individual variability. However, such methods assume the cross-session variability in EEG dynamics to be negligible, which could be problematic due to electrode displacements, environmental noises, and skin-electrode impedance. Here first we show that the EEG power in the alpha and theta bands are strongly correlated with changes in the subject's cognitive state reflected through his driving performance and hence his departure from alertness. Then under very mild and realistic assumptions we derive a model for the alert state of the person using EEG power in the alpha and theta bands. We demonstrate that deviations (computed by Mahalanobis distance) of the EEG power in the alpha and theta bands from the corresponding alert models are correlated to the changes in the driving performance. Finally, for detection of drowsiness we use a linear combination of deviations of the EEG power in the alpha band and theta band from the respective alert models that best correlates with subject's changing level of alertness, indexed by subject's behavioral response in the driving task. This approach could lead to a practical system for noninvasive monitoring of the cognitive state of human operators in attention-critical settings.

AB - Monitoring and predicting human cognitive state and performance using physiological signals such as Electroencephalogram (EEG) have recently gained increasing attention in the fields of brain-computer interface and cognitive neuroscience. Most previous psychophysiological studies of cognitive changes have attempted to use the same model for all subjects. However, the relatively large individual variability in EEG dynamics relating to loss of alertness suggests that for many operators, group statistics cannot be used to accurately predict changes in cognitive states. Attempts have also been made to build a subject-dependent model for each individual based on his/her pilot data tb account for Individual variability. However, such methods assume the cross-session variability in EEG dynamics to be negligible, which could be problematic due to electrode displacements, environmental noises, and skin-electrode impedance. Here first we show that the EEG power in the alpha and theta bands are strongly correlated with changes in the subject's cognitive state reflected through his driving performance and hence his departure from alertness. Then under very mild and realistic assumptions we derive a model for the alert state of the person using EEG power in the alpha and theta bands. We demonstrate that deviations (computed by Mahalanobis distance) of the EEG power in the alpha and theta bands from the corresponding alert models are correlated to the changes in the driving performance. Finally, for detection of drowsiness we use a linear combination of deviations of the EEG power in the alpha band and theta band from the respective alert models that best correlates with subject's changing level of alertness, indexed by subject's behavioral response in the driving task. This approach could lead to a practical system for noninvasive monitoring of the cognitive state of human operators in attention-critical settings.

UR - http://www.scopus.com/inward/record.url?scp=56349098254&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=56349098254&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2008.4634289

DO - 10.1109/IJCNN.2008.4634289

M3 - Conference contribution

AN - SCOPUS:56349098254

SN - 9781424418213

T3 - Proceedings of the International Joint Conference on Neural Networks

SP - 3448

EP - 3454

BT - 2008 International Joint Conference on Neural Networks, IJCNN 2008

ER -

Lin CT, Pal NR, Chuang CY, Jung TP, Ko LW, Liang SF. An EEG-based subject- and session-independent drowsiness detection. In 2008 International Joint Conference on Neural Networks, IJCNN 2008. 2008. p. 3448-3454. 4634289. (Proceedings of the International Joint Conference on Neural Networks). https://doi.org/10.1109/IJCNN.2008.4634289