Development of a method to predict crash risk using trend analysis of driver behavior changes over time

Atsuo Murata, Kohei Fukuda

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

ABSTRACT: Objective: This study aimed at identifying and predicting in advance the point in time with a high risk of a virtual accident before a virtual accident actually occurs using the change of behavioral measures and subjective rating on drowsiness over time and the trend analysis of each behavioral measure. Methods: Behavioral measures such as neck bending angle and tracking error in steering maneuvering during the simulated driving task were recorded under the low arousal condition of all participants who stayed up all night without sleeping. The trend analysis of each evaluation measure was conducted using a single regression model where time and each measure of drowsiness corresponded to an independent variable and a dependent variable, respectively. Applying the trend analysis technique to the experimental data, we proposed a method to predict in advance the point in time with a high risk of a virtual accident (in a real-world driving environment, this corresponds to a crash) before the point in time when the participant would have encountered a crucial accident if he or she continued driving a vehicle (we call this the point in time of a virtual accident). Results: On the basis of applying the proposed trend analysis method to behavioral measures, we found that the proposed approach could predict in advance the point in time with a high risk of a virtual accident before the point in time of a virtual accident. Conclusion: The proposed method is a promising technique for predicting in advance the time zone with potentially high risk (probability) of being involved in an accident due to drowsy driving and for warning drivers of such a drowsy and risky state.

Original languageEnglish
Pages (from-to)114-121
Number of pages8
JournalTraffic Injury Prevention
Volume17
Issue number2
DOIs
Publication statusPublished - Feb 17 2016

Fingerprint

Accidents
driver
accident
trend
Sleep Stages
time
Arousal
Neck
rating
regression
evaluation

Keywords

  • behavioral measure
  • drowsiness
  • identification of point in time with a high risk of crash
  • point in time of a virtual accident
  • trend analysis

ASJC Scopus subject areas

  • Public Health, Environmental and Occupational Health
  • Safety Research

Cite this

Development of a method to predict crash risk using trend analysis of driver behavior changes over time. / Murata, Atsuo; Fukuda, Kohei.

In: Traffic Injury Prevention, Vol. 17, No. 2, 17.02.2016, p. 114-121.

Research output: Contribution to journalArticle

@article{3a9e6aff1a4c4b5093418c14d75616ef,
title = "Development of a method to predict crash risk using trend analysis of driver behavior changes over time",
abstract = "ABSTRACT: Objective: This study aimed at identifying and predicting in advance the point in time with a high risk of a virtual accident before a virtual accident actually occurs using the change of behavioral measures and subjective rating on drowsiness over time and the trend analysis of each behavioral measure. Methods: Behavioral measures such as neck bending angle and tracking error in steering maneuvering during the simulated driving task were recorded under the low arousal condition of all participants who stayed up all night without sleeping. The trend analysis of each evaluation measure was conducted using a single regression model where time and each measure of drowsiness corresponded to an independent variable and a dependent variable, respectively. Applying the trend analysis technique to the experimental data, we proposed a method to predict in advance the point in time with a high risk of a virtual accident (in a real-world driving environment, this corresponds to a crash) before the point in time when the participant would have encountered a crucial accident if he or she continued driving a vehicle (we call this the point in time of a virtual accident). Results: On the basis of applying the proposed trend analysis method to behavioral measures, we found that the proposed approach could predict in advance the point in time with a high risk of a virtual accident before the point in time of a virtual accident. Conclusion: The proposed method is a promising technique for predicting in advance the time zone with potentially high risk (probability) of being involved in an accident due to drowsy driving and for warning drivers of such a drowsy and risky state.",
keywords = "behavioral measure, drowsiness, identification of point in time with a high risk of crash, point in time of a virtual accident, trend analysis",
author = "Atsuo Murata and Kohei Fukuda",
year = "2016",
month = "2",
day = "17",
doi = "10.1080/15389588.2015.1050720",
language = "English",
volume = "17",
pages = "114--121",
journal = "Traffic Injury Prevention",
issn = "1538-9588",
publisher = "Taylor and Francis Ltd.",
number = "2",

}

TY - JOUR

T1 - Development of a method to predict crash risk using trend analysis of driver behavior changes over time

AU - Murata, Atsuo

AU - Fukuda, Kohei

PY - 2016/2/17

Y1 - 2016/2/17

N2 - ABSTRACT: Objective: This study aimed at identifying and predicting in advance the point in time with a high risk of a virtual accident before a virtual accident actually occurs using the change of behavioral measures and subjective rating on drowsiness over time and the trend analysis of each behavioral measure. Methods: Behavioral measures such as neck bending angle and tracking error in steering maneuvering during the simulated driving task were recorded under the low arousal condition of all participants who stayed up all night without sleeping. The trend analysis of each evaluation measure was conducted using a single regression model where time and each measure of drowsiness corresponded to an independent variable and a dependent variable, respectively. Applying the trend analysis technique to the experimental data, we proposed a method to predict in advance the point in time with a high risk of a virtual accident (in a real-world driving environment, this corresponds to a crash) before the point in time when the participant would have encountered a crucial accident if he or she continued driving a vehicle (we call this the point in time of a virtual accident). Results: On the basis of applying the proposed trend analysis method to behavioral measures, we found that the proposed approach could predict in advance the point in time with a high risk of a virtual accident before the point in time of a virtual accident. Conclusion: The proposed method is a promising technique for predicting in advance the time zone with potentially high risk (probability) of being involved in an accident due to drowsy driving and for warning drivers of such a drowsy and risky state.

AB - ABSTRACT: Objective: This study aimed at identifying and predicting in advance the point in time with a high risk of a virtual accident before a virtual accident actually occurs using the change of behavioral measures and subjective rating on drowsiness over time and the trend analysis of each behavioral measure. Methods: Behavioral measures such as neck bending angle and tracking error in steering maneuvering during the simulated driving task were recorded under the low arousal condition of all participants who stayed up all night without sleeping. The trend analysis of each evaluation measure was conducted using a single regression model where time and each measure of drowsiness corresponded to an independent variable and a dependent variable, respectively. Applying the trend analysis technique to the experimental data, we proposed a method to predict in advance the point in time with a high risk of a virtual accident (in a real-world driving environment, this corresponds to a crash) before the point in time when the participant would have encountered a crucial accident if he or she continued driving a vehicle (we call this the point in time of a virtual accident). Results: On the basis of applying the proposed trend analysis method to behavioral measures, we found that the proposed approach could predict in advance the point in time with a high risk of a virtual accident before the point in time of a virtual accident. Conclusion: The proposed method is a promising technique for predicting in advance the time zone with potentially high risk (probability) of being involved in an accident due to drowsy driving and for warning drivers of such a drowsy and risky state.

KW - behavioral measure

KW - drowsiness

KW - identification of point in time with a high risk of crash

KW - point in time of a virtual accident

KW - trend analysis

UR - http://www.scopus.com/inward/record.url?scp=84957427873&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84957427873&partnerID=8YFLogxK

U2 - 10.1080/15389588.2015.1050720

DO - 10.1080/15389588.2015.1050720

M3 - Article

C2 - 26044083

AN - SCOPUS:84957427873

VL - 17

SP - 114

EP - 121

JO - Traffic Injury Prevention

JF - Traffic Injury Prevention

SN - 1538-9588

IS - 2

ER -