The detection of drowsiness using a driver monitoring system

Abstract Objective: Drowsiness is a major cause of driver impairment leading to crashes and fatalities. Research has established the ability to detect drowsiness with various kinds of sensors. We studied drowsy driving in a high-fidelity driving simulator and evaluated the ability of an automotive production-ready driver monitoring system (DMS) to detect drowsy driving. Additionally, this feature was compared to and combined with signals from vehicle-based sensors. Methods: The National Advanced Driving Simulator was used to expose drivers to long, monotonous drives. Twenty participants drove for about 4 h in the simulator between 10 p.m. and 2 a.m. They were allowed to use cruise control and traffic was sparse and semirandom, with both slower- and faster-moving vehicles. Observational ratings of drowsiness (ORDs) were used as the ground truth for drowsiness, and several dependent measures were calculated from vehicle and DMS signals. Drowsiness classification models were created that used only vehicle signals, only driver monitoring signals, and a combination of the 2 sources. Results: The model that used DMS signals performed better than the one that used only vehicle signals; however, the combination of the two performed the best. The models were effective at discriminating low levels of drowsiness from moderate to severe drowsiness; however, they were not effective at telling the difference between moderate and severe levels. A binary model that lumped drowsiness into 2 classes had an area under the receiver operating characteristic (ROC) curve of 0.897. Conclusions: Blinks and saccades have been shown to be predictive of microsleeps; however, it may be that detection of microsleeps and lane departures occurs too late. Therefore, it is encouraging that the model was able to distinguish mild from moderate drowsy driving. The use of automation may make vehicle-based signals useless for characterizing driver states, providing further motivation for a DMS. Future improvements in impairment detection systems may be expected through a combination of improved hardware, physiological measures from unobtrusive sensors and wearables, and the intelligent integration of environmental variables like time of day and time on task.

[1]  Torsten Hothorn,et al.  Exploratory and Inferential Analysis of Benchmark Experiments , 2008 .

[2]  R. Schleicher,et al.  Blinks and saccades as indicators of fatigue in sleepiness warners: looking tired? , 2022 .

[3]  Anthony D. McDonald,et al.  Real-Time Detection of Drowsiness Related Lane Departures Using Steering Wheel Angle , 2012 .

[4]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[5]  D. Dinges,et al.  Psychomotor Vigilance Performance: Neurocognitive Assay Sensitive to Sleep Loss , 2004 .

[6]  David F. Dinges,et al.  Perclos: A valid psychophysiological measure of alertness as assessed by psychomotor vigilance , 1998 .

[7]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[8]  Tzyy-Ping Jung,et al.  Toward Drowsiness Detection Using Non-hair-Bearing EEG-Based Brain-Computer Interfaces , 2018, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[9]  Thomas G. Dietterich.  Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms , 1998, Neural Computation.

[10]  周健,et al.  Steering wheel. , 1972, British medical journal.

[11]  Toshihiro Hiraoka,et al.  Validation of HRV-based drowsy-driving detection method with EEG sleep stage classification , 2017 .

[12]  Michael G. Lenné,et al.  The relative importance of real-time in-cab and external feedback in managing fatigue in real-world commercial transport operations , 2017, Traffic injury prevention.

[13]  Sanjay Kumar Ghosh,et al.  Development of a Drowsy Driver Detection System Based on EEG and IR-based Eye Blink Detection Analysis , 2018 .

[14]  Kurt Hornik,et al.  The Design and Analysis of Benchmark Experiments , 2005 .

[15]  Shigeyuki Tateno,et al.  Development of Drowsiness Detection System Based on Respiration Changes Using Heart Rate Monitoring , 2018, 2018 57th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE).

[16]  W. Dement,et al.  Quantification of sleepiness: a new approach. , 1973, Psychophysiology.

[17]  Anthony D. McDonald,et al.  Steering in a Random Forest , 2014, Hum. Factors.

[18]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[19]  Max Kuhn,et al.  Building Predictive Models in R Using the caret Package , 2008 .

[20]  W W Wierwille,et al.  Evaluation of driver drowsiness by trained raters. , 1994, Accident; analysis and prevention.

[21]  Jarek Krajewski,et al.  Steering wheel behavior based estimation of fatigue , 2017 .

[22]  Thomas A. Dingus,et al.  Prevalence of Drowsy Driving Crashes: Estimates from a Large-Scale Naturalistic Driving Study , 2018 .

[23]  David J. Hand,et al.  A Simple Generalisation of the Area Under the ROC Curve for Multiple Class Classification Problems , 2001, Machine Learning.

[24]  William J. Horrey,et al.  The challenges and opportunities of technological approaches to fatigue management. , 2011, Accident; analysis and prevention.

[25]  Michael G. Lenné,et al.  Continuous monitoring of visual distraction and drowsiness in shift-workers during naturalistic driving , 2019, Safety Science.