Soft Computing

, Volume 22, Issue 5, pp 1457–1466 | Cite as

Sensor-based risk perception ability network design for drivers in snow and ice environmental freeway: a deep learning and rough sets approach

  • Wei Zhao
  • Liangjie Xu
  • Jing Bai
  • Menglu Ji
  • Troy Runge
Focus
  • 176 Downloads

Abstract

Due to factors such as snow and ice impeding drivers’ vision, the number of automobile crashes significantly rises during winter months. This study sets forth an automatic evaluation network of the risk perceived ability for motorists driving on the freeway in snow and ice environments, using a deep learning approach and the rough sets technique. First, a naturalistic driving experiment involving thirteen licensed drivers was conducted on a freeway in Jilin, China, with a crash hot spot set prior to the start of the experiment. Then multi-sensor (eye-trackers, mini-cameras, and speed detectors) apparatuses, collecting both images and numerical data, were utilized. Afterward, restricted Boltzmann machine was used to develop a deep belief network (DBN) along with training procedures. Rough sets technique was added as judgment in output layer of the DBN. Finally, fixation duration, pupil size, changes in speed, etc., were used as input impact factors and the perception conditions were used as output variables to train the network. Furthermore, after comparing the DBN-based risk perception ability network with Naïve Bayes and BP-ANN (artificial neural networks with back propagations), the results indicate that the DBN-FS not only outperforms both Naïve Bayes and BP-ANN, but also improves the accuracy of perceiving risky conditions. This approach can provide reference for the design of hazard detection systems of partially automated vehicles.

Keywords

Freeway curves Fuzzy sets DBN Deep learning Risk perception ability 

Notes

Acknowledgements

I have disclosed those interests fully to Research Projects of Social Science and Humanity on Young Fund of the Ministry of Education of China (16YJCZH157), while this work also supported by Social science planning project of Inner Mongolia (2015JDA008) and National Natural Science Foundation of China (71764020).

Compliance with ethical standards

Conflict of interest

No potential conflict of interest was reported by the authors.

References

  1. Assum T (1997) Attitudes and road accident risk. Accid Anal Prev 29(2):153–159CrossRefGoogle Scholar
  2. Bamberg J, Cairns G, Kilminster D (2003) The crystallographic restriction, permutations, and Goldbach’s conjecture. Ame Math Mon 110(3):202–209MathSciNetCrossRefMATHGoogle Scholar
  3. Button K, Taylor S (2000) International air transportation and economic development. J Air Transp Manag 6(4):209–222CrossRefGoogle Scholar
  4. Charlton SG (2007) The role of attention in horizontal curves: a comparison of advance warning, delineation, and road marking treatments. Accid Anal Prev 39(5):873–885CrossRefGoogle Scholar
  5. Chen J, Huang H, Tian S, Qu Y (2009) Feature selection for text classification with Naïve Bayes. Expert Syst Appl 36(3):5432–5435CrossRefGoogle Scholar
  6. Dahl GE, Yu D, Deng L, Acero A (2012) Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Trans Audio Speech Lang Process 20(1):30–42CrossRefGoogle Scholar
  7. Dong D, McAvoy TJ (1995). Multi-stage batch process monitoring. In: Proceedings of the 1995 American control conference. IEEE, vol 3, pp 1857–1861Google Scholar
  8. Faber MH, Stewart MG (2003) Risk assessment for civil engineering facilities: critical overview and discussion. Reliab Eng Syst Saf 80(2):173–184CrossRefGoogle Scholar
  9. Fischer A, Igel C (2014) Training restricted Boltzmann machines: an introduction. Pattern Recognit 47(1):25–39CrossRefMATHGoogle Scholar
  10. Francis CM, Saurola P (2004) Estimating components of variance in demographic parameters of Tawny Owls, Strix aluco. Anim Biodivers Conserv 27(1):489–502Google Scholar
  11. Herrera-Viedma E, Cabrerizo FJ, Kacprzyk J, Pedrycz W (2014) A review of soft consensus models in a fuzzy environment. Inf Fusion 17:4–13CrossRefGoogle Scholar
  12. Highway Traffic Safety Administration, N., and U. Department of Transportation. (2013). Research Note: 2013 Motor Vehicle Crashes: OverviewGoogle Scholar
  13. Highway Traffic Safety Administration N, U Department of Transportation (2012) Research Note: 2012 motor vehicle crashes: overviewGoogle Scholar
  14. Khanzode VV, Maiti J, Ray PK (2012) Occupational injury and accident research: a comprehensive review. Saf Sci 50(5):1355–1367CrossRefGoogle Scholar
  15. Kollar T, Tellex S, Roy D, Roy N (2010). Toward understanding natural language directions. In 2010 5th ACM/IEEE international conference on human–robot interaction (HRI). IEEE, pp 259–266Google Scholar
  16. Li-sheng J, Wen-ping F, Ying-nan Z, Shuang-bin Y, Hai-jing H (2009). Research on safety lane change model of driver assistant system on highway. In: Intelligent vehicles symposium, 2009 IEEE. IEEE, pp 1051—1056Google Scholar
  17. Liu YC, Wu TJ (2009) Fatigued driver’s driving behavior and cognitive task performance: effects of road environments and road environment changes. Saf Sci 47(8):1083–1089CrossRefGoogle Scholar
  18. Pasetto M, Barbati SD (2012) When the road layout becomes persuasive for the road users: a functional study on safety and driver behaviour. Proc Soc Behav Sci 48:3274–3283CrossRefGoogle Scholar
  19. Rodríguez RM, Martínez L, Torra V, Xu ZS, Herrera F (2014) Hesitant fuzzy sets: state of the art and future directions. Int J Intell Syst 29(6):495–524CrossRefGoogle Scholar
  20. Salakhutdinov R, Murray I (2008). On the quantitative analysis of deep belief networks. In: Proceedings of the 25th international conference on machine learning. ACM, pp 872–879Google Scholar
  21. Saravanan N, Ramachandran KI (2010) Incipient gear box fault diagnosis using discrete wavelet transform (DWT) for feature extraction and classification using artificial neural network (ANN). Expert Syst Appl 37(6):4168–4181CrossRefGoogle Scholar
  22. Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 61:85–117CrossRefGoogle Scholar
  23. Wang XT, Chang CC, Lin CC, Li MC (2012) A novel multi-group exploiting modification direction method based on switch map. Signal Process 92(6):1525–1535CrossRefGoogle Scholar
  24. Yin J, Zhao W (2016) Fault diagnosis network design for vehicle on-board equipments of high-speed railway: a deep learning approach. Eng Appl Artif Intell 56:250–259CrossRefGoogle Scholar
  25. Yu R, Abdel-Aty M (2013) Utilizing support vector machine in real-time crash risk evaluation. Accid Anal Prev 51:252–259CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany 2017

Authors and Affiliations

  1. 1.School of TransportationWuhan University of TechnologyWuhanChina
  2. 2.School of Economics and ManagementInner Mongolia University of Science and TechnologyBaotouChina
  3. 3.Key Laboratory of Intelligent Perception and Image Understanding of Ministry of EducationXidian UniversityXi’anChina
  4. 4.College of Agricultural and Life SciencesUniversity of Wisconsin-MadisonMadisonUSA

Personalised recommendations