Modelling self-reported driver perspectives and fatigued driving via deep learning




driver fatigue, fatigue detection, multi-country survey, deep learning, binary logistic regression


Driving while fatigued is a considerably understudied risk factor contributing to car crashes every year. The first step in mitigating the respective crash risks is to attempt to infer fatigued driving from other parameters, in order to gauge its extend in road networks. The aim of this study is to investigate the extent to which declared fatigued driving behavior can be predicted based on overall driver opinions and perceptions on that issue. For that purpose, a broad cross-country questionnaire from the ESRA2 survey was used. The questionnaire is related to self-declared beliefs, perception, and attitudes towards a wide range of traffic safety topics. Initially, a binary logistic regression model was trained to provide causal insights on which variables affect the likelihood that a driver engaged in driving while fatigued. Drivers reporting driving under the influence of drugs, fatigue, or alcohol, as well as speeding, safety, and texting while driving or drivers who were more acceptable of fatigued driving were more likely to have recently driven while fatigued. In contrast, acceptability of other hazardous behaviors, namely mobile phone use and drunk driving, was negatively correlated with fatigued driving behavior, as were more responsible driver perspectives overall. To provide a more accurate detection mechanism, which would also incorporate non-linear effects, a Deep Neural Network (DNN) was subsequently trained on the data, slightly outperforming the binary logistic model. From the results of both models, it was concluded that declared fatigued driving behavior can be predicted from questionnaire data, providing new insights to fatigue detection.


Download data is not yet available.

Author Biographies

Alexandros Zoupos, The University of Edinburgh, United Kingdom

Alexandros Zoupos is currently studying Electronics and Electrical Engineering at The University of Edinburgh. He was a two-month intern at the National Technical University of Athens at the Department of Transportation Planning and Engineering at the School of Civil Engineering. His interests include Data Analysis research in R, as well as scientific programming in Python. Recently, he has engaged in machine learning programming.

Apostolos Ziakopoulos, National Technical University of Athens, Greece

Dr. Apostolos Ziakopoulos, PhD, MSc DIC, is a Research Associate at the Department of Transportation Planning and Engineering at the School of Civil Engineering of the National Technical University of Athens (NTUA). He holds a Civil Engineering Diploma from NTUA majoring in Transportation Engineering (2013). He holds a Master of Science – DIC in Transport from Imperial College London and University College London (2014). His Ph.D. dissertation was in spatial analysis of road safety and traffic behavior from NTUA (2020). His main research interests involve road crash analyses, statistical and spatial modelling and traffic engineering. He has participated in 8 research and engineering projects and has published 55 papers in scientific journals, textbooks and conferences.

George Yannis, National Technical University of Athens, Greece

Professor George Yannis is a Full Professor in Traffic Safety and Management with particular focus on data management and analysis at the Department of Transportation Planning and Engineering of the School of Civil Engineering of the National Technical University of Athens. He has contributed extensively in more than 245 research and engineering projects and studies and in several scientific committees of the European Commission and other International Organizations (UN/ECE, OECD, WHO, World Bank, EIB, CEDR, ERF, UITP, ETSC, ECTRI, WCTR, TRB). He has published more than 640 scientific papers (more than 200 in scientific journals) widely cited worldwide.


Aloi, A., Alonso, B., Benavente, J., Cordera, R., Echániz, E., González, F., ... & Sañudo, R. (2020) Effects of the COVID-19 lockdown on urban mobility: empirical evidence from the city of Santander (Spain). Sustainability, 12(9), p. 3870 DOI:

Arnold, T. B. (2017) kerasR: R interface to the keras deep learning library. Journal of Open Source Software, 2(14), 296 DOI:

Backer-Grøndahl, A., & Sagberg, F. (2011) Driving and telephoning: Relative accident risk when using hand-held and hands-free mobile phones. Safety Science, 49(2), pp. 324-330 DOI:

Bates, D., Maechler, M., Bolker, B., Walker, S., Christensen, R. H. B., Singmann, H., ... & Grothendieck, G. (2011) Package ‘lme4’. Linear mixed-effects models using S4 classes. R package version, 1(6)

Beck, K.H., Lee, C.J. and Weiner, T. (2018) Motivational factors associated with drowsy driving behavior: a qualitative investigation of college students. Sleep Health, 4(1), pp.116-121 DOI:

Dawson, C. W., & Wilby, R. (1998) An artificial neural network approach to rainfall-runoff modelling. Hydrological Sciences Journal, 43(1), pp. 47-66. DOI:

Feldhütter, A., Gold, C., Schneider, S., & Bengler, K. (2016) How the Duration of Automated Driving Influences Take-Over Performance and Gaze Behavior. Advances in Ergonomic Design of Systems, Products and Processes, pp. 309–318 DOI:

Feng, R., Zhang, G., & Cheng, B. (2009) An on-board system for detecting driver drowsiness based on multi-sensor data fusion using Dempster-Shafer theory. In 2009 International Conference on Networking, Sensing and Control (pp. 897-902). IEEE. DOI:

Goldenbeld, C., Torfs, K., Vlakveld, W., & Houwing, S. (2020) Impaired driving due to alcohol or drugs: International differences and determinants based on E-Survey of Road Users' Attitudes first-wave results in 32 countries. IATSS Research, 44(3), pp. 188–196 DOI:

Gonçalves, J., Happee, R., & Bengler, K. (2016) Drowsiness in conditional automation: proneness, diagnosis and driving performance effects. In 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC) (pp. 873-878). IEEE. DOI:

Grossman, E.S., & Rosenbloom, T. (2016) Perceived level of performance impairment caused by alcohol and restricted sleep. Transportation Research Part F, 41: pp. 113–123 DOI:

Gulli, A., & Pal, S. (2017) Deep learning with Keras. Packt Publishing Ltd. ISBN: 978-1-78712-842-2.

Hara, K., Saito, D., & Shouno, H. (2015) Analysis of function of rectified linear unit used in deep learning. In 2015 IEEE International Joint Conference on Neural Networks (IJCNN) (pp. 1-8). DOI:

Harrell, F. E. (2015) Binary logistic regression. In Harrell, F. E. Regression modeling strategies (pp. 219-274). Springer, Cham. ISBN: 978-3-319-19425-7. DOI:

Hosmer DW, Lemeshow S. (1989) Applied logistic regression. New York: John Wiley & Son. ISBN: 9781118548387. DOI:

Jackson, P., Hilditch, C., Holmes, A., Reed, N., Merat, N. and Smith, L., (2011) Fatigue and road safety: a critical analysis of recent evidence. UK Department for Transport, Road Safety Web Publication, 21. ISBN: 978-1-84864-110-5.

Khan M.I., Mansoor A.B. (2008) Real Time Eyes Tracking and Classification for Driver Fatigue Detection. In: Campilho A., Kamel M. (eds) Image Analysis and Recognition. ICIAR 2008. Lecture Notes in Computer Science, vol 5112. Springer, Berlin, Heidelberg. DOI:

Kong, W., Zhou, L., Wang, Y., Zhang, J., Liu, J. and Gao, S., (2015) A system of driving fatigue detection based on machine vision and its application on smart device. Journal of Sensors, 2015. DOI:

Li, R., Chen, Y. V., & Zhang, L. (2021) A method for fatigue detection based on Driver's steering wheel grip. International Journal of Industrial Ergonomics, 82, 103083. DOI:

Li, K., Gong, Y., & Ren, Z. (2020) A fatigue driving detection algorithm based on facial multi-feature fusion. IEEE Access, 8, pp. 101244-101259 DOI:

Li, Z., Chen, L., Peng, J., & Wu, Y. (2017) Automatic Detection of Driver Fatigue Using Driving Operation Information for Transportation Safety. Sensors, 17(6), p. 1212 DOI:

Meesmann, U., Torfs, K., Wardenier, N. & Van den Berghe, W. (2021) ESRA2 methodology. ESRA2 report Nr. 1 (updated version). ESRA project (E-Survey of Road users’ Attitudes). Brussels, Belgium: Vias institute. Available:

Miyata, S., Noda, A., Ozaki, N., Hara, Y., Minoshima, M., Iwamoto, K., Takahashi, M., Iidaka, T., & Koike, Y. (2010) Insufficient sleep impairs driving performance and cognitive function. Neuroscience letters, 469(2), pp. 229–233 DOI:

Nordbakke, S., & Sagberg, F. (2007) Sleepy at the wheel: Knowledge, symptoms and behaviour among car drivers. Transportation Research Part F: Traffic Psychology and Behaviour, 10(1), pp. 1–10 DOI:

Parsa, M.J., Javadi, M. and Mazinan, A.H. (2021) Fatigue level detection using multivariate autoregressive exogenous nonlinear modeling based on driver body pressure distribution. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, p. 09544070211014290 DOI:

Pires, C., Torfs, K., Areal, A., Goldenbeld, C., Vanlaar, W., Granie, M.A., Stürmer, Y.A., Usami, D.S., Kaiser, S., Jankowska-Karpa, D. and Nikolaou, D. (2020) Car drivers' road safety performance: A benchmark across 32 countries. IATSS research, 44(3), pp.166-179 DOI:

R Core Team (2019) R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. URL:

Radun, I., Radun, J., Wahde, M., Watling, C.N. and Kecklund, G. (2015) Self-reported circumstances and consequences of driving while sleepy. Transportation Research Part F: Traffic Psychology And Behaviour, 32, pp. 91-100 DOI:

Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) "Why should I trust you?" Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp. 1135-1144 DOI:

Samarasinghe, S. (2006) Neural Networks For Applied Sciences And Engineering: From Fundamentals To Complex Pattern Recognition. CRC Press. ISBN 9780849333750

Sayed, R., & Eskandarian, A. (2001) Unobtrusive drowsiness detection by neural network learning of driver steering. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, 215(9), pp. 969–975 DOI:

Schmidhuber, J. (2015) Deep learning in neural networks: An overview. Neural networks, 61, pp. 85-117 DOI:

Sikander, G., & Anwar, S. (2018) Driver fatigue detection systems: A review. IEEE Transactions on Intelligent Transportation Systems, 20(6), pp. 2339-2352 DOI:

Singh, S. (2018) Critical reasons for crashes investigated in the National Motor Vehicle Crash Causation Survey. (Traffic Safety Facts Crash Stats. Report No. DOT HS 812 506). Washington, DC: U.S. National Highway Traffic Safety Administration.

Singh, S. (2015) Critical reasons for crashes investigated in the National Motor Vehicle Crash Causation Survey. NHTSA Report (No. DOT HS 812 115).

Smolensky, M. H., Di Milia, L., Ohayon, M. M., & Philip, P. (2011) Sleep disorders, medical conditions, and road accident risk. Accident Analysis and Prevention, 43(2), pp. 533–548 DOI:

Talbot, R., Filtness. A. (2017) Fatigue – Not Enough Sleep/Driving While Tired, European Road Safety Decision Support System, developed by the H2020 project SafetyCube. Retrieved from on 11 June 2021

Tefft, B.C. (2010) Asleep at the wheel: The prevalence and impact of drowsy driving. AAA Foundation for Traffic Safety. Available: content/uploads/2018/02/2010DrowsyDrivingReport.pdf

Torfs, K., Meesmann, U., Van den Berghe, W., & Trotta, M. (2016) ESRA 2015 – The results. Synthesis of the main findings from the ESRA survey in 17 countries. ESRA project (European Survey of Road users’ safety Attitudes). Brussels, Belgium. Available:

Tranmer, M., & Elliot, M. (2008) Binary logistic regression. Cathie Marsh for census and survey research, paper, 20. Available:

United States National Sleep Foundation (2013) 2013 International Bedroom Poll: (Accessed 11 June 2021)

United States Federal Motor Carrier Safety Administration (FMCSA) (2011) Hours of service of drivers. U.S. Federal Register, vol. 76(248)

United States National Center for Statistics and Analysis (NCSA). (2020) Overview of motor vehicle crashes in 2019. (Traffic Safety Facts Research Note. Report No. DOT HS 813 060). National Highway Traffic Safety Administration (NHTSA).

Vanlaar, W., Simpson, H., Mayhew, D., & Robertson, R. (2008) Fatigued and drowsy driving: A survey of attitudes, opinions and behaviors. Journal of Safety Research, 39(3), pp. 303-309 DOI:

Wang, M. S., Jeong, N. T., Kim, K. S., Choi, S. B., Yang, S. M., You, S. H., ... & Suh, M. W. (2016) Drowsy behavior detection based on driving information. International Journal of Automotive Technology, 17(1), pp. 165-173. DOI:

Wang, S.C. (2003) Artificial Neural Network in Wang, S.C., Interdisciplinary Computing in Java Programming, 81–100. ISBN: 978-1-4615-0377-4. DOI:

Washington, S., Karlaftis, M. G., Mannering, F., & Anastasopoulos, P. (2020) Statistical and Econometric Methods for Transportation Data Analysis. CRC Press. ISBN: 9780429244018. DOI:

Watling, C.N., Armstrong, K.A., Obst, P.L. and Smith, S.S., (2014) Continuing to drive while sleepy: The influence of sleepiness countermeasures, motivation for driving sleepy, and risk perception. Accident Analysis & Prevention, 73, pp.262-268 DOI:

Watling, C.N. (2014) Sleepy driving and pulling over for a rest: Investigating individual factors that contribute to these driving behaviours. Personality and Individual Differences, 56, pp. 105-110 DOI:

Wilson, R.J., Fang, M., Cooper, P.J. and Beirness, D.J. (2006) Sleepiness among night-time drivers: relationship to blood alcohol concentration and other factors. Traffic Injury Prevention, 7(1), pp. 15-22 DOI:

World Health Organization – WHO. (2018) Global status report on road safety 2018. ISBN: 9789241565684. Available:

Yannis, G., Nikolaou, D., Laiou, A., Stürmer, Y. A., Buttler, I., & Jankowska-Karpa, D. (2020) Vulnerable road users: Cross-cultural perspectives on performance and attitudes. IATSS Research, 44(3), pp. 220–229 DOI:

Zhang, C., Wang, H., & Fu, R. (2014) Automated Detection of Driver Fatigue Based on Entropy and Complexity Measures. IEEE Transactions on Intelligent Transportation Systems, 15(1), pp. 168–177 DOI:

Zhang, G., Yau, K. K., Zhang, X., & Li, Y. (2016) Traffic accidents involving fatigue driving and their extent of casualties. Accident Analysis & Prevention, 87, pp. 34-42 DOI:

Zhou, F., Alsaid, A., Blommer, M., Curry, R., Swaminathan, R., Kochhar, D., Talamonti, W., Tijerina, L., & Lei, B. (2020) Driver fatigue transition prediction in highly automated driving using physiological features. Expert Systems with Applications, 147, p. 113204 DOI:

Zou, X., Yue, W. L., & Le Vu, H. (2018) Visualization and analysis of mapping knowledge domain of road safety studies. Accident Analysis & Prevention, 118, pp. 131-145 DOI:

Ziakopoulos, A., Theofilatos, A., Laiou, A., Michelaraki, E., Yannis, G., & Rosenbloom, T. (2021a) Examining the relationship between impaired driving and past crash involvement in Europe: Insights from the ESRA study. International Journal of Injury Control and Safety Promotion, pp. 1–11 DOI:

Ziakopoulos, A., Nikolaou, D., & Yannis, G. (2021b) Correlations of multiple rider behaviors with self-reported attitudes, perspectives on traffic rule strictness and social desirability. Transportation Research Part F: Traffic Psychology and Behaviour, 80, pp. 313–327 DOI:




How to Cite

Zoupos, A., Ziakopoulos, A., & Yannis, G. (2021). Modelling self-reported driver perspectives and fatigued driving via deep learning. Traffic Safety Research, 1, 000003.



Research articles