基于集成模型的交通事故严重程度预测  

Prediction of Traffic Accident Severity Based on Integrated Models

作　　者：杨翰琨 鲁帅 秦文杰 张彦敏[2] YANG Han-kun;LU Shuai;QIN Wen-jie;ZHANG Yan-min(Harbin Engineering University,Yantai Graduate School,Yantai 265500,China;Hubei Key Laboratory of Marine Electromagnetic Detection and Control,Wuhan Second Ship Design and Research Institute,Wuhan 430064,China)

机构地区：[1]哈尔滨工程大学烟台研究生院,烟台265500 [2]武汉第二船舶设计研究所海洋电磁探测与控制湖北省重点实验室,武汉430064

出　　处：《科学技术与工程》2025年第10期4355-4360,共6页Science Technology and Engineering

基　　金：国家自然科学基金(52101383)。

摘　　要：交通事故对公共安全构成重大风险,是交通运输系统中的重要问题。准确预测事故严重程度对于采取有效的预防和干预措施至关重要。提出了一种基于集成学习的方法,将XGBoost和MLP两种先进算法相结合,以更精准地预测交通事故的严重程度。建立了一个堆叠分类器,并详细评估了其在交通事故预测中的性能。实验结果表明,该集成模型相较于传统XGBoost模型,在预测准确性上有明显提升,在宏平均F_1分数上显著提高了20.41%。展示了模型优势与创新性,包括模型集成与网络改造。此外,还分析了影响预测结果的关键特征,并探讨了模型在实际应用中的潜在价值。该研究为交通安全管理提供了更科学、更高效的决策支持,有望在交通管理、智能驾驶等领域发挥重要作用。Traffic accidents pose significant risks to public safety and represent a critical issue in transportation systems.The accurate prediction of accident severity is essential for implementing effective prevention and intervention measures.An ensemble learning approach,combining the advanced algorithms XGBoost and MLP,was proposed to enhance the accuracy of traffic accident severity predictions.A stacked classifier was established and its performance in traffic accident prediction was thoroughly evaluated.The experimental results demonstrate that the integrated model significantly improves prediction accuracy compared to the traditional XGBoost model,with a notable 20.41%increase in the macro-average F 1 score.The advantages and innovations of the model,including model integration and network transformation,were highlighted.Additionally,the key features affecting the prediction results were analyzed,and the model's potential value in practical applications was explored.This study provides more scientific and efficient decision support for traffic safety management and is expected to play a crucial role in fields such as traffic management and intelligent driving.

关 键 词：交通事故 严重程度预测 XGBoost MLP 特征分析 集成学习 深度学习 

分 类 号：U491.3[交通运输工程—交通运输规划与管理]