The application of data mining techniques to model visual distraction of bicyclists
作者：
Highlights：
• A novel approach to modelling visual distraction of bicyclists is presented.
• A bicycle simulator for road traffic safety research is presented.
• We combine random forests for variable selection and support vector machine for modelling.
• A combination of qualitative and quantitative data provides the best results.
• The method may be used for automated vehicles to detect distracted bicyclists.
摘要
•A novel approach to modelling visual distraction of bicyclists is presented.•A bicycle simulator for road traffic safety research is presented.•We combine random forests for variable selection and support vector machine for modelling.•A combination of qualitative and quantitative data provides the best results.•The method may be used for automated vehicles to detect distracted bicyclists.
论文关键词：Bicycle simulator,Data mining,Bicyclist distraction,Random forest,Support vector machine,Automated driving systems
论文评审过程：Received 12 December 2014, Revised 4 January 2016, Accepted 5 January 2016, Available online 13 January 2016, Version of Record 17 February 2016.
论文官网地址：https://doi.org/10.1016/j.eswa.2016.01.006
