计算机科学与探索 ›› 2021, Vol. 15 ›› Issue (9): 1694-1702.DOI: 10.3778/j.issn.1673-9418.2008093

• 人工智能 • 上一篇    下一篇

融合局部和全局时空特征的交通事故风险预测

王贝贝,万怀宇,郭晟楠,林友芳   

  1. 1. 北京交通大学 计算机与信息技术学院,北京 100044
    2. 北京交通大学 交通数据分析与挖掘北京市重点实验室,北京 100044
  • 出版日期:2021-09-01 发布日期:2021-09-06

Local and Global Spatial-Temporal Networks for Traffic Accident Risk Forecasting

WANG Beibei, WAN Huaiyu, GUO Shengnan, LIN Youfang   

  1. 1. School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China
    2. Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing 100044, China
  • Online:2021-09-01 Published:2021-09-06

摘要:

交通事故预测在城市公共安全、应急处置以及建设规划方面发挥着重要的作用。然而,在预测交通事故风险时仍然存在以下问题:首先交通事故的发生受到众多因素的影响,例如天气、道路状况等。其次交通事故的发生在空间范围内存在多尺度的时空依赖,主要包括局部区域的时空相关性和全局区域的时空相似性。同时,由于实际场景中交通事故发生次数相对较少,给预测带来了零膨胀问题。因此,对交通事故进行准确的预测具有很大的挑战,现有的预测方法无法综合考虑上述问题。提出了一种新颖的融合局部和全局时空特征的交通事故风险预测模型(ST-RiskNet),同时考虑时间、天气、交通流量等影响事故发生的多源因素,通过局部区域时空相关性模块和全局区域时空相似性模块同时建模多尺度的时空相关性和相似性,并设计样本加权损失函数,针对事故风险较大的样本设置较大的权重来解决零膨胀问题。在两个真实交通事故数据集的结果表明,ST-RiskNet的预测效果优于现有的预测方法。

关键词: 交通事故预测, 多源时空数据, 零膨胀, 图卷积(GCN)

Abstract:

Traffic accident forecasting is very important for urban public security, emergency treatment and construc-tion planning. However, the following problems still exist when forecasting traffic accident risk. Firstly, traffic accidents are affected by multiple factors, such as weather and road conditions. Besides, there are multi-scale correlations in the spatial dimension, i.e. local region spatial-temporal correlation and global region spatial-temporal similarity. Meanwhile, there is zero-inflated issue in the forecasting because of few traffic accidents in reality. Therefore, it is very challenging to forecast traffic accidents accurately, and existing traffic accident forecasting methods cannot take all the above problems into account. A novel model, named local and global spatial-temporal networks (ST-RiskNet), for traffic accident risk forecasting is proposed. The ST-RiskNet takes multi-source factors that affect traffic accidents into consideration, such as time, weather, traffic flow. It uses a local region spatial-temporal correlation module and a global region spatial-temporal similarity module to model the multi-scale spatial-temporal correlation and similarity simultaneously. Meanwhile, a sample weighted loss function is designed to solve the zero-inflated problem, which pays more weights to the higher risk samples. Extensive experiments on two real-world traffic accident datasets demonstrate the effectiveness of the ST-RiskNet against the state-of-the-art baseline methods.

Key words: traffic accident forecasting, multi-source spatial-temporal data, zero-inflated, graph convolutional network (GCN)