采用特征变量选择和长短期记忆网络的高速公路交通事件检测研究  

Research on highway traffic accident detectionusing feature variable selection andlong and short-term memory network

作　　者：张兵[1] 张校梁 屈永强[2] 上官小荣 邹少权 ZHANG Bing;ZHANG Xiaoliang;QU Yongqiang;SHANGGUAN Xiaorong;ZOU Shaoquan(School of Transportation Engineering,East China Jiaotong University,Nanchang 330013,China;Jiangxi V&T College of Communications,Nanchang 330013,China;Jiangxi Institute of Traffic Planning,Reconnaissance and Design,Nanchang 330013,China)

机构地区：[1]华东交通大学交通运输工程学院,南昌330013 [2]江西交通职业技术学院,南昌330013 [3]江西省交通规划勘察设计院,南昌330013

出　　处：《重庆理工大学学报（自然科学）》2023年第4期157-165,共9页Journal of Chongqing University of Technology：Natural Science

基　　金：江西省教育厅一般课题(GJJ190331);国家自然科学基金项目(52162042);江西省交通运输厅一般课题(2020H0053)。

摘　　要：为提升高速公路交通事件检测效果,依据交通事件发生时上、下游交通流参数的变化特性,构建一组相对全面的交通事件检测初始特征变量集,使用随机森林-交叉验证递归特征消除(RF-RFECV)算法筛选出重要特征变量。利用重要特征变量作为输入训练长短期记忆网络(LSTM),通过贝叶斯优化算法(BOA)优化LSTM网络的超参数。使用真实高速公路数据进行验证和对比分析,采用Borderline-SMOTE解决交通数据集的不平衡问题。实验结果表明:筛选出对交通事件检测更为敏感的重要特征变量,可以提高检测精度,LSTM的检测效果也明显优于随机森林(RF)和支持向量机(SVM)。In order to improve the effectiveness of highway traffic accident detection,according to the changing characteristics of upstream and downstream traffic flow parameters at the occurrence of traffic accidents,this paper constructs a relatively comprehensive set of initial feature variables for traffic accident detection,and filters out important feature variables by using the Random Forest-Recursive Feature Elimination with Cross Validation(RF-RFECV)algorithm.The long and short-term memory(LSTM)network is trained by using significant feature variables as the input,and the hyperparameters of the LSTM network are optimized by a Bayesian optimization algorithm(BOA).Finally,real highway data are used for validation and comparative analysis,and Borderline-SMOTE is used to solve the imbalance of the traffic dataset.The experimental results show that selecting the important feature variables that are more sensitive to traffic accident detection can improve the detection accuracy,and the detection effect of LSTM is significantly better than that of random forest(RF)and support vector machine(SVM).

关 键 词：交通事件检测 特征变量选择 贝叶斯优化 长短期记忆网络 

分 类 号：U491[交通运输工程—交通运输规划与管理]