Sensor-based risk perception ability network design for drivers in snow and ice environmental freeway: a deep learning and rough sets approach
- 176 Downloads
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.
KeywordsFreeway curves Fuzzy sets DBN Deep learning Risk perception ability
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.
- 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
- 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
- Highway Traffic Safety Administration, N., and U. Department of Transportation. (2013). Research Note: 2013 Motor Vehicle Crashes: OverviewGoogle Scholar
- Highway Traffic Safety Administration N, U Department of Transportation (2012) Research Note: 2012 motor vehicle crashes: overviewGoogle Scholar
- 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
- 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
- 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