安全与环境工程2024，Vol.31Issue(6)：91-99,9.DOI:10.13578/j.cnki.issn.1671-1556.20240624
基于改进深度森林算法的高速公路交通事故风险预测
Highway traffic accident risk prediction based on improved deep forest algorithm
摘要
Abstract
Highway traffic accident risk prediction is very important for dynamic traffic safety management.In order to explore the main factors affecting the highway traffic accident risk and accurately predict the highway traffic accident risk,a highway traffic accident risk prediction model based on improved deep forest algorithm is proposed.Firstly,based on expressway traffic accident data,traffic flow data,weather data,road conditions and special time period data,the characteristic variables that can represent highway traffic accident risk were selected.The random forest algorithm was used to calculate the importance of the characteristic variables,and screen out the important characteristic variables that have a greater impact on the highway traffic accident risk,and solve the dimensional disaster problem in the following calculation process.Then the cascade forest structure of the deep forest model was improved by using LightGBM and XGBoost algorithms based on decision tree.Finally,the improved deep forest algorithm was applied to highway accident risk prediction.The results show that compared with the existing SVM,random forest and deep forest algorithms,the improved deep forest algorithm has better prediction performance,and the accuracy rate reaches 88.84%.The prediction results can provide decision support for the highway traffic management department to make more effective safety control measures.关键词
高速公路交通事故/风险预测/改进深度森林算法/深度学习Key words
highway traffic accident/risk prediction/improving the deep forest algorithm/deep learning分类
资源环境引用本文复制引用
张浩..基于改进深度森林算法的高速公路交通事故风险预测[J].安全与环境工程,2024,31(6):91-99,9.基金项目
湖北省安全生产专项资金科技项目(SJZX20230904) （SJZX20230904）
