重庆理工大学学报(自然科学) ›› 2023, Vol. 37 ›› Issue (4): 157-165.

• 智能技术 • 上一篇    下一篇

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

张 兵,张校梁,屈永强   

  1. 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)
  • 出版日期:2023-05-06 发布日期:2023-05-06
  • 作者简介:张兵,男,博士,副教授,主要从事交通安全及交通事件智能检测研究,Email:zhangbing@ecjtu.edu.cn

Research on highway traffic accident detection using feature variable selection and long and short-term memory network

  • Online:2023-05-06 Published:2023-05-06

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)。

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

Abstract: 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).

中图分类号: 

  • U491