基于图注意力与图卷积网络的交通事故预测方法  

Traffic Accident Prediction Method Based on Graph Attention and Graph Convolutional Network

作　　者：张金松 袁一博 马玉鑫 ZHANG Jinsong;YUAN Yibo;MA Yuxin(School of Maritime Economics and Management,Dalian Maritime University,Dalian 116026,China)

机构地区：[1]大连海事大学航运经济与管理学院,辽宁大连116026

出　　处：《计算机与现代化》2025年第4期12-18,共7页Computer and Modernization

基　　金：中央高校基本科研业务费项目(3132024302);教育部人文社会科学研究项目(21YJC630066)。

摘　　要：交通事故的发生会给人员、社会带来巨大损失,为了提高交通事故预测准确率,提出一种基于图注意力与图卷积网络的交通事故预测方法(GAGC)。该方法首先通过边特征提取模块,提取路网中复杂的边特征信息;然后引入图注意力层使网络快速关注事故频发的节点,利用叠加的图注意力层来减少特征信息在传递过程中的信息丢失;通过Dropout和批处理归一化(BN)来平衡特征重要性,提升模型的泛化性和鲁棒性。实验使用现有文献公开的基于图的交通事故预测数据存储库TAP进行验证,结果表明,GAGC取得了较好的效果,在F1指数、AUC和MAP方面均优于5个基线模型。最后,通过消融实验进一步验证了本文设计的GAGC模型的有效性和可靠性。Traffic accidents result in significant losses to individuals and society.To enhance the accuracy of traffic accident prediction,a traffic accident prediction method based on graph attention and graph convolutional networks(GAGC)is proposed.Firstly,the method extracts complex edge feature information in the road network through an edge feature extraction module.Then,it introduces a graph attention layer to enable the network quickly focusing on nodes with frequent accidents,and uses overlapping graph attention layers to reduce information loss during feature information transmission.It also employs Dropout and Batch Normalization(BN)to balance feature importance and improve the generalization and robustness of the model.Experimental results show that GAGC achieves good results,and the model can fully consider the geospatial features in complex road networks,with better performance than five baseline models in terms of F1 index,AUC,and MAP.The ablation experiment further verifies the effectiveness and reliability of the GAGC model designed in this study.

关 键 词：图卷积网络 图注意力 道路交通 交通事故预测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]