Abstract

Driver drowsiness causes many road accidents, and preparing a risk map of these accidents with spatial criteria and data mining algorithms highlights accident points well. In this study, accidents risk caused by driver drowsiness in Qazvin province, Iran, was modelled using decision tree (DT), random forest (RF) and support-vector regression (SVR) algorithms in GIS environment. Seven spatial criteria including road segment length, road width, slope angle, speed limit, land use/cover, distance to service area and distance to speed camera were selected as effective criteria in modelling. The effect of criteria in modelling was applied using a fuzzy method, and three risk maps were prepared. Evaluation with ROC-AUC showed that the AUC for RF, SVR and DT models were 0.904, 0.863 and 0.805, respectively, and the RF model overall had the best performance. Examining the importance of criteria showed that the speed limit was the most important criterion for modelling.

摘要

驾驶员困倦导致许多道路事故，并且使用空间标准和数据挖掘算法准备这些事故的风险图可以很好地突出事故点。在这项研究中，在 GIS 环境中，使用决策树 (DT)、随机森林 (RF) 和支持向量回归 (SVR) 算法对伊朗加兹温省驾驶员嗜睡造成的事故风险进行了建模。选择路段长度、道路宽度、坡度、限速、土地利用/覆盖、到服务区的距离和到测速摄像头的距离等七个空间标准作为建模的有效标准。使用模糊方法应用标准在建模中的影响，并准备了三个风险图。ROC-AUC 评估表明 RF、SVR 和 DT 模型的 AUC 分别为 0.904、0.863 和 0.805，RF模型整体表现最好。检查标准的重要性表明，速度限制是建模的最重要标准。