Multinomial logistic regression model by stepwise method for predicting subjective drowsiness using performance and behavioral measures

Atsuo Murata, Yukio Ohta, Makoto Moriwaka

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

1 Citation (Scopus)

Abstract

The aim of this study was to explore the effectiveness of physiological and behavioral evaluation measures for predicting a drivers’ subjective drowsiness based on a multinomial logistic regression model. The participants were required to steer a steering wheel and keep their vehicle to the centerline as much as they could, and to maintain the distance between their own car and a preceding car properly as much as possible using a brake or an accelerator. A number of measures were recorded during a simulated driving task, and the participants were required to report subjective drowsiness once every minute. EEG (electroencephalography), heart rate variability (RRV3), and blink frequency were the physiological measures recorded. Meanwhile, behavioral measures included neck bending angle (horizontal and vertical), back pressure, foot pressure, and tracking error in a driving simulator task. Drowsy states were predicted via a multinomial logistic regression model. Physiological and behavioral measures were independent variables in the regression model and equated to the dependent variable: subjective evaluation of drowsiness. The stepwise method was adopted for the estimation of parameters of multinomial logistic regression model. The interval used for attaining the highest prediction accuracy was a 100 s interval between 20 and 120 s before the prediction. This approach clarified that the parameters finally appeared in the multinomial logistic regression model were different among participants, which indicated that the optimal structure of the model for predicting subjective drowsiness should be different among participants.

Original languageEnglish
Title of host publicationAdvances in Physical Ergonomics and Human Factors - Proceedings of the AHFE 2016 International Conference on Physical Ergonomics and Human Factors
PublisherSpringer Verlag
Pages665-674
Number of pages10
Volume489
ISBN (Print)9783319416939
DOIs
Publication statusPublished - 2016
EventInternational Conference on Physical Ergonomics and Human Factors, AHFE 2016 - Walt Disney World, United States
Duration: Jul 27 2016Jul 31 2016

Publication series

NameAdvances in Intelligent Systems and Computing
Volume489
ISSN (Print)21945357

Other

OtherInternational Conference on Physical Ergonomics and Human Factors, AHFE 2016
CountryUnited States
CityWalt Disney World
Period7/27/167/31/16

Fingerprint

Logistics
Railroad cars
Electroencephalography
Brakes
Particle accelerators
Wheels
Simulators

Keywords

  • Behavioral measure
  • Drowsiness
  • Multinomial regression model
  • Physiological measure
  • Stepwise method

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science(all)

Cite this

Murata, A., Ohta, Y., & Moriwaka, M. (2016). Multinomial logistic regression model by stepwise method for predicting subjective drowsiness using performance and behavioral measures. In Advances in Physical Ergonomics and Human Factors - Proceedings of the AHFE 2016 International Conference on Physical Ergonomics and Human Factors (Vol. 489, pp. 665-674). (Advances in Intelligent Systems and Computing; Vol. 489). Springer Verlag. https://doi.org/10.1007/978-3-319-41694-6_64

Multinomial logistic regression model by stepwise method for predicting subjective drowsiness using performance and behavioral measures. / Murata, Atsuo; Ohta, Yukio; Moriwaka, Makoto.

Advances in Physical Ergonomics and Human Factors - Proceedings of the AHFE 2016 International Conference on Physical Ergonomics and Human Factors. Vol. 489 Springer Verlag, 2016. p. 665-674 (Advances in Intelligent Systems and Computing; Vol. 489).

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

Murata, A, Ohta, Y & Moriwaka, M 2016, Multinomial logistic regression model by stepwise method for predicting subjective drowsiness using performance and behavioral measures. in Advances in Physical Ergonomics and Human Factors - Proceedings of the AHFE 2016 International Conference on Physical Ergonomics and Human Factors. vol. 489, Advances in Intelligent Systems and Computing, vol. 489, Springer Verlag, pp. 665-674, International Conference on Physical Ergonomics and Human Factors, AHFE 2016, Walt Disney World, United States, 7/27/16. https://doi.org/10.1007/978-3-319-41694-6_64
Murata A, Ohta Y, Moriwaka M. Multinomial logistic regression model by stepwise method for predicting subjective drowsiness using performance and behavioral measures. In Advances in Physical Ergonomics and Human Factors - Proceedings of the AHFE 2016 International Conference on Physical Ergonomics and Human Factors. Vol. 489. Springer Verlag. 2016. p. 665-674. (Advances in Intelligent Systems and Computing). https://doi.org/10.1007/978-3-319-41694-6_64
Murata, Atsuo ; Ohta, Yukio ; Moriwaka, Makoto. / Multinomial logistic regression model by stepwise method for predicting subjective drowsiness using performance and behavioral measures. Advances in Physical Ergonomics and Human Factors - Proceedings of the AHFE 2016 International Conference on Physical Ergonomics and Human Factors. Vol. 489 Springer Verlag, 2016. pp. 665-674 (Advances in Intelligent Systems and Computing).
@inproceedings{46527d5e822941a59c1c1b1f0e379fdf,
title = "Multinomial logistic regression model by stepwise method for predicting subjective drowsiness using performance and behavioral measures",
abstract = "The aim of this study was to explore the effectiveness of physiological and behavioral evaluation measures for predicting a drivers’ subjective drowsiness based on a multinomial logistic regression model. The participants were required to steer a steering wheel and keep their vehicle to the centerline as much as they could, and to maintain the distance between their own car and a preceding car properly as much as possible using a brake or an accelerator. A number of measures were recorded during a simulated driving task, and the participants were required to report subjective drowsiness once every minute. EEG (electroencephalography), heart rate variability (RRV3), and blink frequency were the physiological measures recorded. Meanwhile, behavioral measures included neck bending angle (horizontal and vertical), back pressure, foot pressure, and tracking error in a driving simulator task. Drowsy states were predicted via a multinomial logistic regression model. Physiological and behavioral measures were independent variables in the regression model and equated to the dependent variable: subjective evaluation of drowsiness. The stepwise method was adopted for the estimation of parameters of multinomial logistic regression model. The interval used for attaining the highest prediction accuracy was a 100 s interval between 20 and 120 s before the prediction. This approach clarified that the parameters finally appeared in the multinomial logistic regression model were different among participants, which indicated that the optimal structure of the model for predicting subjective drowsiness should be different among participants.",
keywords = "Behavioral measure, Drowsiness, Multinomial regression model, Physiological measure, Stepwise method",
author = "Atsuo Murata and Yukio Ohta and Makoto Moriwaka",
year = "2016",
doi = "10.1007/978-3-319-41694-6_64",
language = "English",
isbn = "9783319416939",
volume = "489",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer Verlag",
pages = "665--674",
booktitle = "Advances in Physical Ergonomics and Human Factors - Proceedings of the AHFE 2016 International Conference on Physical Ergonomics and Human Factors",

}

TY - GEN

T1 - Multinomial logistic regression model by stepwise method for predicting subjective drowsiness using performance and behavioral measures

AU - Murata, Atsuo

AU - Ohta, Yukio

AU - Moriwaka, Makoto

PY - 2016

Y1 - 2016

N2 - The aim of this study was to explore the effectiveness of physiological and behavioral evaluation measures for predicting a drivers’ subjective drowsiness based on a multinomial logistic regression model. The participants were required to steer a steering wheel and keep their vehicle to the centerline as much as they could, and to maintain the distance between their own car and a preceding car properly as much as possible using a brake or an accelerator. A number of measures were recorded during a simulated driving task, and the participants were required to report subjective drowsiness once every minute. EEG (electroencephalography), heart rate variability (RRV3), and blink frequency were the physiological measures recorded. Meanwhile, behavioral measures included neck bending angle (horizontal and vertical), back pressure, foot pressure, and tracking error in a driving simulator task. Drowsy states were predicted via a multinomial logistic regression model. Physiological and behavioral measures were independent variables in the regression model and equated to the dependent variable: subjective evaluation of drowsiness. The stepwise method was adopted for the estimation of parameters of multinomial logistic regression model. The interval used for attaining the highest prediction accuracy was a 100 s interval between 20 and 120 s before the prediction. This approach clarified that the parameters finally appeared in the multinomial logistic regression model were different among participants, which indicated that the optimal structure of the model for predicting subjective drowsiness should be different among participants.

AB - The aim of this study was to explore the effectiveness of physiological and behavioral evaluation measures for predicting a drivers’ subjective drowsiness based on a multinomial logistic regression model. The participants were required to steer a steering wheel and keep their vehicle to the centerline as much as they could, and to maintain the distance between their own car and a preceding car properly as much as possible using a brake or an accelerator. A number of measures were recorded during a simulated driving task, and the participants were required to report subjective drowsiness once every minute. EEG (electroencephalography), heart rate variability (RRV3), and blink frequency were the physiological measures recorded. Meanwhile, behavioral measures included neck bending angle (horizontal and vertical), back pressure, foot pressure, and tracking error in a driving simulator task. Drowsy states were predicted via a multinomial logistic regression model. Physiological and behavioral measures were independent variables in the regression model and equated to the dependent variable: subjective evaluation of drowsiness. The stepwise method was adopted for the estimation of parameters of multinomial logistic regression model. The interval used for attaining the highest prediction accuracy was a 100 s interval between 20 and 120 s before the prediction. This approach clarified that the parameters finally appeared in the multinomial logistic regression model were different among participants, which indicated that the optimal structure of the model for predicting subjective drowsiness should be different among participants.

KW - Behavioral measure

KW - Drowsiness

KW - Multinomial regression model

KW - Physiological measure

KW - Stepwise method

UR - http://www.scopus.com/inward/record.url?scp=84992695503&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84992695503&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-41694-6_64

DO - 10.1007/978-3-319-41694-6_64

M3 - Conference contribution

SN - 9783319416939

VL - 489

T3 - Advances in Intelligent Systems and Computing

SP - 665

EP - 674

BT - Advances in Physical Ergonomics and Human Factors - Proceedings of the AHFE 2016 International Conference on Physical Ergonomics and Human Factors

PB - Springer Verlag

ER -