Multinomial Logistic Regression Model for Predicting Driver's Drowsiness Using Behavioral Measures

Atsuo Murata, Yoshito Fujii, Kensuke Naitoh

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

The aim of this study was to explore the effectiveness of behavioral evaluation measures for predicting drivers’ subjective drowsiness. Behavioral measures included neck vending angle (horizontal and vertical), back pressure, foot pressure, COP (Center of Pressure) movement on sitting surface, and tracking error in driving simulator task. Drowsy states were predicted by means of the multinomial logistic regression model where physiological and behavioral measures and subjective evaluation of drowsiness corresponded to independent variables and a dependent variable, respectively. First, we compared the effectiveness of two methods (correlation coefficient-based method and odds ratio-based method) for determining the order of entering behavioral measures into the prediction model. It was found that the prediction accuracy did not differ between both methods. Second, the prediction accuracy was compared among the numbers of behavioral measures. The prediction accuracy did not differ among four, five, and six behavioral measures, and it was concluded that entering at least four behavioral measures into the prediction model is enough to achieve higher prediction accuracy. Third, the prediction accuracy was compared between the strongly drowsy and the weakly drowsy group. The prediction accuracy differed between the two groups, and the proposed method was effective (the prediction accuracy was significantly higher) especially under the condition where drowsiness was induced to a larger extent.

Original languageEnglish
Pages (from-to)2426-2433
Number of pages8
JournalProcedia Manufacturing
Volume3
DOIs
Publication statusPublished - 2015

Fingerprint

Logistics
Physiological models
Correlation methods
Simulators

Keywords

  • Behavioral measures
  • Drowsy driving
  • Multinomial logistic regression
  • Physiological measures
  • Prediction accuracy
  • Subjective drowsiness
  • Traffic accident

ASJC Scopus subject areas

  • Artificial Intelligence
  • Industrial and Manufacturing Engineering

Cite this

Multinomial Logistic Regression Model for Predicting Driver's Drowsiness Using Behavioral Measures. / Murata, Atsuo; Fujii, Yoshito; Naitoh, Kensuke.

In: Procedia Manufacturing, Vol. 3, 2015, p. 2426-2433.

Research output: Contribution to journalArticle

@article{88984139a46f452ea18d4d66c95fb7bc,
title = "Multinomial Logistic Regression Model for Predicting Driver's Drowsiness Using Behavioral Measures",
abstract = "The aim of this study was to explore the effectiveness of behavioral evaluation measures for predicting drivers’ subjective drowsiness. Behavioral measures included neck vending angle (horizontal and vertical), back pressure, foot pressure, COP (Center of Pressure) movement on sitting surface, and tracking error in driving simulator task. Drowsy states were predicted by means of the multinomial logistic regression model where physiological and behavioral measures and subjective evaluation of drowsiness corresponded to independent variables and a dependent variable, respectively. First, we compared the effectiveness of two methods (correlation coefficient-based method and odds ratio-based method) for determining the order of entering behavioral measures into the prediction model. It was found that the prediction accuracy did not differ between both methods. Second, the prediction accuracy was compared among the numbers of behavioral measures. The prediction accuracy did not differ among four, five, and six behavioral measures, and it was concluded that entering at least four behavioral measures into the prediction model is enough to achieve higher prediction accuracy. Third, the prediction accuracy was compared between the strongly drowsy and the weakly drowsy group. The prediction accuracy differed between the two groups, and the proposed method was effective (the prediction accuracy was significantly higher) especially under the condition where drowsiness was induced to a larger extent.",
keywords = "Behavioral measures, Drowsy driving, Multinomial logistic regression, Physiological measures, Prediction accuracy, Subjective drowsiness, Traffic accident",
author = "Atsuo Murata and Yoshito Fujii and Kensuke Naitoh",
year = "2015",
doi = "10.1016/j.promfg.2015.07.502",
language = "English",
volume = "3",
pages = "2426--2433",
journal = "Procedia Manufacturing",
issn = "2351-9789",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - Multinomial Logistic Regression Model for Predicting Driver's Drowsiness Using Behavioral Measures

AU - Murata, Atsuo

AU - Fujii, Yoshito

AU - Naitoh, Kensuke

PY - 2015

Y1 - 2015

N2 - The aim of this study was to explore the effectiveness of behavioral evaluation measures for predicting drivers’ subjective drowsiness. Behavioral measures included neck vending angle (horizontal and vertical), back pressure, foot pressure, COP (Center of Pressure) movement on sitting surface, and tracking error in driving simulator task. Drowsy states were predicted by means of the multinomial logistic regression model where physiological and behavioral measures and subjective evaluation of drowsiness corresponded to independent variables and a dependent variable, respectively. First, we compared the effectiveness of two methods (correlation coefficient-based method and odds ratio-based method) for determining the order of entering behavioral measures into the prediction model. It was found that the prediction accuracy did not differ between both methods. Second, the prediction accuracy was compared among the numbers of behavioral measures. The prediction accuracy did not differ among four, five, and six behavioral measures, and it was concluded that entering at least four behavioral measures into the prediction model is enough to achieve higher prediction accuracy. Third, the prediction accuracy was compared between the strongly drowsy and the weakly drowsy group. The prediction accuracy differed between the two groups, and the proposed method was effective (the prediction accuracy was significantly higher) especially under the condition where drowsiness was induced to a larger extent.

AB - The aim of this study was to explore the effectiveness of behavioral evaluation measures for predicting drivers’ subjective drowsiness. Behavioral measures included neck vending angle (horizontal and vertical), back pressure, foot pressure, COP (Center of Pressure) movement on sitting surface, and tracking error in driving simulator task. Drowsy states were predicted by means of the multinomial logistic regression model where physiological and behavioral measures and subjective evaluation of drowsiness corresponded to independent variables and a dependent variable, respectively. First, we compared the effectiveness of two methods (correlation coefficient-based method and odds ratio-based method) for determining the order of entering behavioral measures into the prediction model. It was found that the prediction accuracy did not differ between both methods. Second, the prediction accuracy was compared among the numbers of behavioral measures. The prediction accuracy did not differ among four, five, and six behavioral measures, and it was concluded that entering at least four behavioral measures into the prediction model is enough to achieve higher prediction accuracy. Third, the prediction accuracy was compared between the strongly drowsy and the weakly drowsy group. The prediction accuracy differed between the two groups, and the proposed method was effective (the prediction accuracy was significantly higher) especially under the condition where drowsiness was induced to a larger extent.

KW - Behavioral measures

KW - Drowsy driving

KW - Multinomial logistic regression

KW - Physiological measures

KW - Prediction accuracy

KW - Subjective drowsiness

KW - Traffic accident

UR - http://www.scopus.com/inward/record.url?scp=85009953644&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009953644&partnerID=8YFLogxK

U2 - 10.1016/j.promfg.2015.07.502

DO - 10.1016/j.promfg.2015.07.502

M3 - Article

AN - SCOPUS:85009953644

VL - 3

SP - 2426

EP - 2433

JO - Procedia Manufacturing

JF - Procedia Manufacturing

SN - 2351-9789

ER -