A novel real-time driving fatigue detection system based on wireless dry EEG

Hongtao Wang, Andrei Dragomir, Nida Itrat Abbasi, Junhua Li, Nitish V Thakor, Anastasios Bezerianos

Research output: Contribution to journalArticle

Abstract

Development of techniques for detection of mental fatigue has varied applications in areas where sustaining attention is of critical importance like security and transportation. The objective of this study is to develop a novel real-time driving fatigue detection methodology based on dry Electroencephalographic (EEG) signals. The study has employed two methods in the online detection of mental fatigue: power spectrum density (PSD) and sample entropy (SE). The wavelet packets transform (WPT) method was utilized to obtain the (Formula presented.) (4–7 Hz), (Formula presented.) (8–12 Hz) and (Formula presented.) (13–30 Hz) bands frequency components for calculating corresponding PSD of the selected channels. In order to improve the fatigue detection performance, the system was individually calibrated for each subject in terms of fatigue-sensitive channels selection. Two fatigue-related indexes: ((Formula presented.))/(Formula presented.) and (Formula presented.)/(Formula presented.) were computed and then fused into an integrated metric to predict the degree of driving fatigue. In the case of SE extraction, the mean of SE averaged across two EEG channels (‘O1h’ and ‘O2h’) was used for fatigue detection. Ten healthy subjects participated in our study and each of them performed two sessions of simulated driving. In each session, subjects were required to drive simulated car for 90 min without any break. The results demonstrate that our proposed methods are effective for fatigue detection. The prediction of fatigue is consistent with the observation of reaction time that was recorded during simulated driving, which is considered as an objective behavioral measure.

Original languageEnglish (US)
Pages (from-to)1-12
Number of pages12
JournalCognitive Neurodynamics
DOIs
StateAccepted/In press - Feb 21 2018
Externally publishedYes

Fingerprint

Fatigue
Entropy
Mental Fatigue
Wavelet Analysis
Reaction Time
Healthy Volunteers
Observation

Keywords

  • Channel selection
  • Driving fatigue
  • Dry electrodes
  • Electroencephalogram
  • PSD and entropy

ASJC Scopus subject areas

  • Cognitive Neuroscience

Cite this

A novel real-time driving fatigue detection system based on wireless dry EEG. / Wang, Hongtao; Dragomir, Andrei; Abbasi, Nida Itrat; Li, Junhua; Thakor, Nitish V; Bezerianos, Anastasios.

In: Cognitive Neurodynamics, 21.02.2018, p. 1-12.

Research output: Contribution to journalArticle

Wang, Hongtao ; Dragomir, Andrei ; Abbasi, Nida Itrat ; Li, Junhua ; Thakor, Nitish V ; Bezerianos, Anastasios. / A novel real-time driving fatigue detection system based on wireless dry EEG. In: Cognitive Neurodynamics. 2018 ; pp. 1-12.
@article{2d877b7f7e804e4eaac1845305b24222,
title = "A novel real-time driving fatigue detection system based on wireless dry EEG",
abstract = "Development of techniques for detection of mental fatigue has varied applications in areas where sustaining attention is of critical importance like security and transportation. The objective of this study is to develop a novel real-time driving fatigue detection methodology based on dry Electroencephalographic (EEG) signals. The study has employed two methods in the online detection of mental fatigue: power spectrum density (PSD) and sample entropy (SE). The wavelet packets transform (WPT) method was utilized to obtain the (Formula presented.) (4–7 Hz), (Formula presented.) (8–12 Hz) and (Formula presented.) (13–30 Hz) bands frequency components for calculating corresponding PSD of the selected channels. In order to improve the fatigue detection performance, the system was individually calibrated for each subject in terms of fatigue-sensitive channels selection. Two fatigue-related indexes: ((Formula presented.))/(Formula presented.) and (Formula presented.)/(Formula presented.) were computed and then fused into an integrated metric to predict the degree of driving fatigue. In the case of SE extraction, the mean of SE averaged across two EEG channels (‘O1h’ and ‘O2h’) was used for fatigue detection. Ten healthy subjects participated in our study and each of them performed two sessions of simulated driving. In each session, subjects were required to drive simulated car for 90 min without any break. The results demonstrate that our proposed methods are effective for fatigue detection. The prediction of fatigue is consistent with the observation of reaction time that was recorded during simulated driving, which is considered as an objective behavioral measure.",
keywords = "Channel selection, Driving fatigue, Dry electrodes, Electroencephalogram, PSD and entropy",
author = "Hongtao Wang and Andrei Dragomir and Abbasi, {Nida Itrat} and Junhua Li and Thakor, {Nitish V} and Anastasios Bezerianos",
year = "2018",
month = "2",
day = "21",
doi = "10.1007/s11571-018-9481-5",
language = "English (US)",
pages = "1--12",
journal = "Cognitive Neurodynamics",
issn = "1871-4080",
publisher = "Springer Netherlands",

}

TY - JOUR

T1 - A novel real-time driving fatigue detection system based on wireless dry EEG

AU - Wang, Hongtao

AU - Dragomir, Andrei

AU - Abbasi, Nida Itrat

AU - Li, Junhua

AU - Thakor, Nitish V

AU - Bezerianos, Anastasios

PY - 2018/2/21

Y1 - 2018/2/21

N2 - Development of techniques for detection of mental fatigue has varied applications in areas where sustaining attention is of critical importance like security and transportation. The objective of this study is to develop a novel real-time driving fatigue detection methodology based on dry Electroencephalographic (EEG) signals. The study has employed two methods in the online detection of mental fatigue: power spectrum density (PSD) and sample entropy (SE). The wavelet packets transform (WPT) method was utilized to obtain the (Formula presented.) (4–7 Hz), (Formula presented.) (8–12 Hz) and (Formula presented.) (13–30 Hz) bands frequency components for calculating corresponding PSD of the selected channels. In order to improve the fatigue detection performance, the system was individually calibrated for each subject in terms of fatigue-sensitive channels selection. Two fatigue-related indexes: ((Formula presented.))/(Formula presented.) and (Formula presented.)/(Formula presented.) were computed and then fused into an integrated metric to predict the degree of driving fatigue. In the case of SE extraction, the mean of SE averaged across two EEG channels (‘O1h’ and ‘O2h’) was used for fatigue detection. Ten healthy subjects participated in our study and each of them performed two sessions of simulated driving. In each session, subjects were required to drive simulated car for 90 min without any break. The results demonstrate that our proposed methods are effective for fatigue detection. The prediction of fatigue is consistent with the observation of reaction time that was recorded during simulated driving, which is considered as an objective behavioral measure.

AB - Development of techniques for detection of mental fatigue has varied applications in areas where sustaining attention is of critical importance like security and transportation. The objective of this study is to develop a novel real-time driving fatigue detection methodology based on dry Electroencephalographic (EEG) signals. The study has employed two methods in the online detection of mental fatigue: power spectrum density (PSD) and sample entropy (SE). The wavelet packets transform (WPT) method was utilized to obtain the (Formula presented.) (4–7 Hz), (Formula presented.) (8–12 Hz) and (Formula presented.) (13–30 Hz) bands frequency components for calculating corresponding PSD of the selected channels. In order to improve the fatigue detection performance, the system was individually calibrated for each subject in terms of fatigue-sensitive channels selection. Two fatigue-related indexes: ((Formula presented.))/(Formula presented.) and (Formula presented.)/(Formula presented.) were computed and then fused into an integrated metric to predict the degree of driving fatigue. In the case of SE extraction, the mean of SE averaged across two EEG channels (‘O1h’ and ‘O2h’) was used for fatigue detection. Ten healthy subjects participated in our study and each of them performed two sessions of simulated driving. In each session, subjects were required to drive simulated car for 90 min without any break. The results demonstrate that our proposed methods are effective for fatigue detection. The prediction of fatigue is consistent with the observation of reaction time that was recorded during simulated driving, which is considered as an objective behavioral measure.

KW - Channel selection

KW - Driving fatigue

KW - Dry electrodes

KW - Electroencephalogram

KW - PSD and entropy

UR - http://www.scopus.com/inward/record.url?scp=85042210596&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042210596&partnerID=8YFLogxK

U2 - 10.1007/s11571-018-9481-5

DO - 10.1007/s11571-018-9481-5

M3 - Article

C2 - 30137873

AN - SCOPUS:85042210596

SP - 1

EP - 12

JO - Cognitive Neurodynamics

JF - Cognitive Neurodynamics

SN - 1871-4080

ER -