摘要
为了研究道路交通系统中"人-车-路"多因素对驾驶行为及车辆安全状态的影响,设计了多因素组合成6种场景的模拟驾驶对照试验。利用驾驶模拟器、生理仪、眼动仪分别采集驾驶行为相关的19项指标,选用方差分析比较各项驾驶行为指标差异情况。选用非线性支持向量机(Support VectorMachine,SVM)对样本数据进行分类及预测,建立了驾驶行为风险等级预测模型,并利用试验数据验证了模型的有效性。结果表明:模型的预测精度达到93.94%,建立的风险等级预测模型能够有效的判别驾驶员及车辆的状态。
In order to study the influence of multi-factors of human-vehicle-road on driving behavior and vehicle safety status in road traffic system, a simulated driving comparison test of six scenarios combined by multiple factors is designed. Driving simulator, physiography and eye tracker are used to collect 19 indicators related to driving behavior respectively. The differences of sample data are compared by variance analysis. The nonlinear SVM(support vector machine) is used to classify and predict the sample data. The driving behavior risk level prediction model is established, and the validity of the model is verified by the experimental data. The results show that the prediction accuracy of the model reaches 93.94%. The established risk level prediction model can effectively judge the status of the driver and the vehicle.
作者
安玉
焦朋朋
白紫秀
An Yu;Jiao Pengpeng;Bai Zixiu(Beijing Advanced Innovation Center for Future Urban Design,Beijing University of Civil Engineering and Architecture,Beijing 100044,China)
出处
《系统仿真学报》
CAS
CSCD
北大核心
2021年第1期118-126,共9页
Journal of System Simulation
基金
国家自然科学基金(51578040)
北京市属高校高水平教师队伍建设支持计划(CIT&TCD20180324)
北京市属高校基本科研业务费专项资金(X18081,X18094)。
关键词
风险预测
支持向量机
驾驶行为
交通安全
模拟驾驶
risk prediction
support vector machine
driving behavior
traffic safety
simulated driving
