Road Safety Performance Function Analysis With Visual Feature Importance of Deep Neural Nets

• 作 者: Guangyuan Pan Liping Fu Qili C
• 机 构: DepartmentofCivilandEnvironmentalEngineering,FacultyofInformationTechnology,ElectronicEngineering
• 出 处: 自动化学报:英文版
• 发表日期: 2020年3期
• 关键词: DEEP learning DEEP NEURAL network(DNN) FEATURE IMPORTANCE road safety PERFORMANC
• 基金项目: supported by the National Science and Engineering Research Council of Canada(NSERC),Ontario Research Fund–Research Excellence(ORF-RE),the Ministry of Transportation Ontario(MTO)through Its Highway Inf

Road safety performance function(SPF) analysis using data-driven and nonparametric methods, especially recent developed deep learning approaches, has gained increasing achievements. However, due to the learning mechanisms are hidden in a"black box&qu