TRB Pubsindex
Text Size:
x

« Prev Next »

Return to Results | New Search

Bookmark and Share

Title:

Non-Intrusive Assessment of Fatigue in Drivers Using Eye Tracking

Accession Number:

01660879

Record Type:

Component

Abstract:

Fatigue can negatively affect health, safety and performance in people and may have deadly consequences. In particular, drowsiness and fatigue are the cause of a substantial number of motor vehicle accidents. This paper investigates the use of eye tracking data as a non-intrusive measure of driver behavior for assessment of fatigue. A specific set of 34 features were extracted from eye tracking data collected in 25 subjects participating in a simulated driving experiment. The state of vigilance in these subjects was independently assessed by power spectral analysis of multichannel electroencephalogram (EEG) signals, recorded simultaneously, and binary labels of alert and drowsy (baseline) were generated for each epoch of the eye tracking data. A random forest (RF) classifier and a non-linear support vector machine (SVM) were employed for assessment of the state of vigilance. Evaluation results revealed a high accuracy of 88% for the RF classifier, which significantly outperformed the SVM with 81% accuracy (p < 0.001). Altogether, the results of this study showed a very high correspondence between the extracted eye tracking features and EEG as a physiological measure of vigilance and verified the potential of these features (employed along with a proper classification technique such as the RF) for non-intrusive long-term assessment of drowsiness in drivers. Ultimately, this research would lead to development of ubiquitous and real-time detection of the state of vigilance in drivers, as an imperative action towards improving road safety by managing fatigue in motorists.

Supplemental Notes:

This paper was sponsored by TRB committee AND10 Standing Committee on Vehicle User Characteristics.

Report/Paper Numbers:

18-03295

Language:

English

Authors:

Zandi, Ali Shahidi
Liang, Min
Quddus, Azhar
Prest, Laura
Comeau, Felix J E

Pagination:

8p

Publication Date:

2018

Conference:

Transportation Research Board 97th Annual Meeting

Location: Washington DC, United States
Date: 2018-1-7 to 2018-1-11
Sponsors: Transportation Research Board

Media Type:

Digital/other

Features:

Figures; References (35) ; Tables

Subject Areas:

Highways; Safety and Human Factors

Source Data:

Transportation Research Board Annual Meeting 2018 Paper #18-03295

Files:

TRIS, TRB, ATRI

Created Date:

Jan 8 2018 10:48AM