基于LightGBM的驾驶人风险感知能力判别方法

A Method for Identifying Drivers’Risk Perception Based on LightGBM

碰撞风险与风险感知能力有关,为准确评估驾驶人风险感知能力,设计考虑危险源个数与类型的驾驶模拟试验,采集危险场景下的驾驶人驾驶行为与眼动特征等数据。利用Mantel-Haenszel检验分析危险源因素、驾驶人个人特性在不同风险感知水平人群下的差异性,借助Spearman相关性分析探索驾驶行为、眼动特征与风险感知能力之间的关系。结果表明:危险源个数、类型与风险感知能力负相关。驾龄、车速、纵向加速度、刹车深度、制动反应时间及位置等与风险感知能力显著相关。风险感知能力迟钝的驾驶人车速偏高且加速度更大,刹车深度更深,从发现危险事件到采取行动需要更多的反应时间。构建综合风险感知能力评价指标集,借助Random Forest算法对特征进行重要性排序,在此基础上利用LightGBM算法建立驾驶人风险感知能力判别模型,分析不同特征个数输入对模型性能的影响。结果表明:与SVM和AdaBoost等算法相比,基于LightGBM算法的模型F1值达到86.07%,精度为86.14%,可以有效地对不同风险感知等级的驾驶人进行分类。

Accident risk is related to risk perception,and a driving simulation is designed to evaluate the ability of drivers’risk perception considering hazard target’type(explicit/implicit)and amount(single/double).Data of driving behaviors and eye movement characteristics is collected under different risk scenarios.Mantel-Haenszel test is used to analyze differences of hazard target’factors and drivers’characteristics under different risk perception levels.The Spearman correlation test is used to study relationships among driving behaviors,eye movement characteristics,and risk perception ability.The results show that hazard target’factors are negatively correlated with risk perception.Driving age,vehicle speed,longitudinal acceleration,braking depth,braking response time,and response position are significantly related to risk perception.Drivers with poor risk perception would drive at higher speeds with faster acceleration and deeper brake.They need more time to react to emergencies.The evaluation set of risk perception ability is constructed,and the importance of features is ranked using the Random Forest algorithm.The model of risk perception is built based on LightGBM with the effects of different features analyzed.The results show that the identification effect of the model is the best based on LightGBM compared with SVM and AdaBoost.The F1 value reaches 86.07%with an accuracy of 86.14%,which can classify drivers with different risk perception levels.