• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

基于 Copula-Bayesian 网络的数据驱动特征学习方法及其在风险换道和跟驰行为比较研究中的应用。

A data-driven feature learning approach based on Copula-Bayesian Network and its application in comparative investigation on risky lane-changing and car-following maneuvers.

机构信息

School of Civil and Environmental Engineering, Nanyang Technological University, 639798, Singapore.

School of Civil and Environmental Engineering, Nanyang Technological University, 639798, Singapore; Institute for Infocomm Research, The Agency for Science, Technology and Research (A⁎STAR), Singapore.

出版信息

Accid Anal Prev. 2021 May;154:106061. doi: 10.1016/j.aap.2021.106061. Epub 2021 Mar 7.

DOI:10.1016/j.aap.2021.106061
PMID:33691229
Abstract

The era of 'Big Data' provides opportunities for researchers to have deep insights into traffic safety. By taking advantages of 'Big Data', this study proposes a data-driven method to develop a Copula-Bayesian Network (Copula-BN) using a large-scale naturalistic driving dataset with multiple features. The Copula-BN is able to explain the causality of a risky driving maneuver. As compared with conventional BNs, the Copula-BN developed in this study has the following advantages: the Copula-BN 1. Has a more rational and explainable structure; 2. Is less likely to be over-fitting and can attain more satisfactory prediction performance; and 3. Can handle not only discrete but also continuous features. In terms of technical innovations, Shapley Additive Explanation (SHAP) is used for feature selection, while Gaussian Copula function is employed to build the dependency structure of the Copula-BN. As for applications, the Copula-BNs are used to investigate the causality of risky lane-changing (LC) and car-following (CF) maneuvers, upon which the comparisons are made between the two essential but risky driving maneuvers. In this study, the Copula-BNs are developed based on the Second Highway Research Program (SHRP2) Naturalistic Driving Study (NDS) database. Upon network evaluation, the Copula-BNs for both risky LC and CF maneuvers demonstrate satisfactory structure performance and promising prediction performance. Feature inferences are conducted based on the Copula-BNs to respectively illustrate the causation of the two risky maneuvers. Several interesting findings related to features' contribution are discussed in this paper. To a certain extent, the Copula-BN developed using the data-driven method makes a trade-off between prediction and causality within the 'Big Data'. The comparison between risky LC and CF maneuvers also provides a valuable reference for crash risk evaluation, road safety policy-making, etc. In the future, the achievements of this study could be applied in Advanced Driver-Assistance System (ADAS) and accident diagnosis system to enhance road traffic safety.

摘要

“大数据”时代为研究人员深入洞察交通安全提供了机会。本研究利用“大数据”,提出了一种使用具有多种特征的大规模自然驾驶数据集开发 Copula-Bayesian 网络 (Copula-BN) 的数据驱动方法。Copula-BN 能够解释危险驾驶行为的因果关系。与传统的 BNs 相比,本研究中开发的 Copula-BN 具有以下优势:1. 具有更合理和可解释的结构;2. 不太可能过度拟合,并且可以获得更令人满意的预测性能;3. 不仅可以处理离散特征,还可以处理连续特征。在技术创新方面,Shapley Additive Explanation (SHAP) 用于特征选择,而高斯 Copula 函数用于构建 Copula-BN 的依赖结构。就应用而言,Copula-BNs 用于研究危险变道 (LC) 和跟车 (CF) 行为的因果关系,对这两种基本但危险的驾驶行为进行了比较。在本研究中,Copula-BNs 是基于第二高速公路研究计划 (SHRP2) 自然驾驶研究 (NDS) 数据库开发的。在网络评估中,危险 LC 和 CF 操作的 Copula-BNs 均表现出令人满意的结构性能和有前途的预测性能。根据 Copula-BNs 进行特征推理,分别说明两种危险行为的原因。本文讨论了与特征贡献相关的一些有趣发现。在一定程度上,使用数据驱动方法开发的 Copula-BN 在“大数据”中在预测和因果关系之间取得了平衡。危险 LC 和 CF 操作之间的比较也为碰撞风险评估、道路安全决策等提供了有价值的参考。在未来,本研究的成果可应用于先进驾驶辅助系统 (ADAS) 和事故诊断系统,以提高道路交通安全。

相似文献

1
A data-driven feature learning approach based on Copula-Bayesian Network and its application in comparative investigation on risky lane-changing and car-following maneuvers.基于 Copula-Bayesian 网络的数据驱动特征学习方法及其在风险换道和跟驰行为比较研究中的应用。
Accid Anal Prev. 2021 May;154:106061. doi: 10.1016/j.aap.2021.106061. Epub 2021 Mar 7.
2
Key feature selection and risk prediction for lane-changing behaviors based on vehicles' trajectory data.基于车辆轨迹数据的变道行为关键特征选择与风险预测。
Accid Anal Prev. 2019 Aug;129:156-169. doi: 10.1016/j.aap.2019.05.017. Epub 2019 May 28.
3
When driving becomes risky: Micro-scale variants of the lane-changing maneuver in highway traffic.当驾驶变得危险时:高速公路交通中的变道微尺度变体。
Traffic Inj Prev. 2023;24(7):583-591. doi: 10.1080/15389588.2023.2242993. Epub 2023 Aug 11.
4
Detecting lane change maneuvers using SHRP2 naturalistic driving data: A comparative study machine learning techniques.利用 SHRP2 自然驾驶数据检测变道行为:机器学习技术的比较研究。
Accid Anal Prev. 2020 Jul;142:105578. doi: 10.1016/j.aap.2020.105578. Epub 2020 May 11.
5
Near crash characteristics among risky drivers using the SHRP2 naturalistic driving study.高危驾驶员在 SHRP2 自然驾驶研究中的事故临近特征。
J Safety Res. 2020 Jun;73:263-269. doi: 10.1016/j.jsr.2020.03.012. Epub 2020 Apr 2.
6
How do drivers overtake pedestrians? Evidence from field test and naturalistic driving data.驾驶员如何超越行人?来自现场测试和自然驾驶数据的证据。
Accid Anal Prev. 2020 May;139:105494. doi: 10.1016/j.aap.2020.105494. Epub 2020 Mar 20.
7
An integrated framework for driving risk evaluation that combines lane-changing detection and an attention-based prediction model.一种结合变道检测和基于注意力的预测模型的用于驾驶风险评估的集成框架。
Traffic Inj Prev. 2025;26(2):198-206. doi: 10.1080/15389588.2024.2399301. Epub 2024 Oct 2.
8
Key Factors Analysis of Severity of Automobile to Two-Wheeler Traffic Accidents Based on Bayesian Network.基于贝叶斯网络的汽车与两轮车交通事故严重程度关键因素分析
Int J Environ Res Public Health. 2022 May 15;19(10):6013. doi: 10.3390/ijerph19106013.
9
Prediction and analysis of likelihood of freeway crash occurrence considering risky driving behavior.考虑危险驾驶行为的高速公路事故发生可能性预测与分析。
Accid Anal Prev. 2023 Nov;192:107244. doi: 10.1016/j.aap.2023.107244. Epub 2023 Aug 11.
10
Driver Behavior During Overtaking Maneuvers from the 100-Car Naturalistic Driving Study.来自100辆汽车自然驾驶研究的超车操作过程中的驾驶员行为。
Traffic Inj Prev. 2015;16 Suppl 2:S176-81. doi: 10.1080/15389588.2015.1057281.

引用本文的文献

1
Comparing Resampling Algorithms and Classifiers for Modeling Traffic Risk Prediction.比较用于建模交通风险预测的重采样算法和分类器。
Int J Environ Res Public Health. 2022 Oct 21;19(20):13693. doi: 10.3390/ijerph192013693.
2
Key Factors Analysis of Severity of Automobile to Two-Wheeler Traffic Accidents Based on Bayesian Network.基于贝叶斯网络的汽车与两轮车交通事故严重程度关键因素分析
Int J Environ Res Public Health. 2022 May 15;19(10):6013. doi: 10.3390/ijerph19106013.