Prediction of drowsiness using multivariate analysis of biological information and driving performance

Atsuo Murata, Yutaka Ohkubo, Takehito Hayami, Makoto Moriwaka

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

The aim of this study was to predict drowsy states by applying multivariate analysis such as discrimination analysis and logistic regression model to biological information and establish a method to properly warn drivers of drowsy state. EEG, heart rate variability, EOG, and tracking error were used as evaluation measures of drowsiness. The drowsy states were predicted by applying discrimination analysis and logistic regression to these evaluation measures. The percentage correct prediction for discrimination analysis and logistic regression were 85% and 93%, respectively. The polynominal logistic regression model was found to lead to higher prediction accuracy. The biological data might be used for the long-term prediction of drowsiness, while the performance data such as tracking error can be used only for the short-term prediction.

Original languageEnglish
Title of host publicationAdvances in Physical Ergonomics and Safety
PublisherCRC Press
Pages423-432
Number of pages10
ISBN (Electronic)9781439870594
ISBN (Print)9781439870389
DOIs
Publication statusPublished - Jan 1 2012

Fingerprint

Logistics
Electroencephalography
Multivariate Analysis

Keywords

  • Biological information
  • Discrimination analysis
  • Drowsiness
  • Multivariate analysis
  • Polynominal logistic regression
  • Prediction technique

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Murata, A., Ohkubo, Y., Hayami, T., & Moriwaka, M. (2012). Prediction of drowsiness using multivariate analysis of biological information and driving performance. In Advances in Physical Ergonomics and Safety (pp. 423-432). CRC Press. https://doi.org/10.1201/b12323

Prediction of drowsiness using multivariate analysis of biological information and driving performance. / Murata, Atsuo; Ohkubo, Yutaka; Hayami, Takehito; Moriwaka, Makoto.

Advances in Physical Ergonomics and Safety. CRC Press, 2012. p. 423-432.

Research output: Chapter in Book/Report/Conference proceedingChapter

Murata, A, Ohkubo, Y, Hayami, T & Moriwaka, M 2012, Prediction of drowsiness using multivariate analysis of biological information and driving performance. in Advances in Physical Ergonomics and Safety. CRC Press, pp. 423-432. https://doi.org/10.1201/b12323
Murata A, Ohkubo Y, Hayami T, Moriwaka M. Prediction of drowsiness using multivariate analysis of biological information and driving performance. In Advances in Physical Ergonomics and Safety. CRC Press. 2012. p. 423-432 https://doi.org/10.1201/b12323
Murata, Atsuo ; Ohkubo, Yutaka ; Hayami, Takehito ; Moriwaka, Makoto. / Prediction of drowsiness using multivariate analysis of biological information and driving performance. Advances in Physical Ergonomics and Safety. CRC Press, 2012. pp. 423-432
@inbook{cb6cdf05febc4396b3efb9fad1ad93a3,
title = "Prediction of drowsiness using multivariate analysis of biological information and driving performance",
abstract = "The aim of this study was to predict drowsy states by applying multivariate analysis such as discrimination analysis and logistic regression model to biological information and establish a method to properly warn drivers of drowsy state. EEG, heart rate variability, EOG, and tracking error were used as evaluation measures of drowsiness. The drowsy states were predicted by applying discrimination analysis and logistic regression to these evaluation measures. The percentage correct prediction for discrimination analysis and logistic regression were 85{\%} and 93{\%}, respectively. The polynominal logistic regression model was found to lead to higher prediction accuracy. The biological data might be used for the long-term prediction of drowsiness, while the performance data such as tracking error can be used only for the short-term prediction.",
keywords = "Biological information, Discrimination analysis, Drowsiness, Multivariate analysis, Polynominal logistic regression, Prediction technique",
author = "Atsuo Murata and Yutaka Ohkubo and Takehito Hayami and Makoto Moriwaka",
year = "2012",
month = "1",
day = "1",
doi = "10.1201/b12323",
language = "English",
isbn = "9781439870389",
pages = "423--432",
booktitle = "Advances in Physical Ergonomics and Safety",
publisher = "CRC Press",

}

TY - CHAP

T1 - Prediction of drowsiness using multivariate analysis of biological information and driving performance

AU - Murata, Atsuo

AU - Ohkubo, Yutaka

AU - Hayami, Takehito

AU - Moriwaka, Makoto

PY - 2012/1/1

Y1 - 2012/1/1

N2 - The aim of this study was to predict drowsy states by applying multivariate analysis such as discrimination analysis and logistic regression model to biological information and establish a method to properly warn drivers of drowsy state. EEG, heart rate variability, EOG, and tracking error were used as evaluation measures of drowsiness. The drowsy states were predicted by applying discrimination analysis and logistic regression to these evaluation measures. The percentage correct prediction for discrimination analysis and logistic regression were 85% and 93%, respectively. The polynominal logistic regression model was found to lead to higher prediction accuracy. The biological data might be used for the long-term prediction of drowsiness, while the performance data such as tracking error can be used only for the short-term prediction.

AB - The aim of this study was to predict drowsy states by applying multivariate analysis such as discrimination analysis and logistic regression model to biological information and establish a method to properly warn drivers of drowsy state. EEG, heart rate variability, EOG, and tracking error were used as evaluation measures of drowsiness. The drowsy states were predicted by applying discrimination analysis and logistic regression to these evaluation measures. The percentage correct prediction for discrimination analysis and logistic regression were 85% and 93%, respectively. The polynominal logistic regression model was found to lead to higher prediction accuracy. The biological data might be used for the long-term prediction of drowsiness, while the performance data such as tracking error can be used only for the short-term prediction.

KW - Biological information

KW - Discrimination analysis

KW - Drowsiness

KW - Multivariate analysis

KW - Polynominal logistic regression

KW - Prediction technique

UR - http://www.scopus.com/inward/record.url?scp=85055493915&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055493915&partnerID=8YFLogxK

U2 - 10.1201/b12323

DO - 10.1201/b12323

M3 - Chapter

AN - SCOPUS:85055493915

SN - 9781439870389

SP - 423

EP - 432

BT - Advances in Physical Ergonomics and Safety

PB - CRC Press

ER -