Accident; analysis and prevention最新文献_第10页

Safety analysis of motorcyclists’ overtaking maneuvers 摩托车手超车动作的安全分析

IF 5.7 1区工程技术 Q1 ERGONOMICS

Accident; analysis and prevention

Pub Date : 2024-10-11 DOI: 10.1016/j.aap.2024.107809

Francesco Bella , Federico Gulisano , Valerio Gagliardi

This paper aims to investigate the overtaking behavior of motorcyclists in a suburban environment. The goal is to model overtaking duration, identify the factors influencing it, and determine the likelihood of a rider overtaking a vehicle while maintaining critical lateral clearance. Riding data were collected using a passenger car equipped with cameras and a GPS device, which recorded videos of motorcyclists performing maneuvers to overtake it. This setup allowed for capturing natural motorcyclist behavior and avoided the potential limitations of instrumented motorcycle studies, such as bias due to participants being aware of their involvement in the experiment. A total of 119 overtaking maneuvers were recorded. A methodology combining digital image processing algorithms and GPS analysis was employed to characterize the recorded maneuvers. Survival and logistic analyses were then conducted to model the duration of overtaking and lateral clearance, respectively. The hazard-based duration model indicated that the duration of a motorcyclist’s overtaking maneuver is influenced by the final longitudinal distance between the motorcycle and the passed vehicle at the end of the maneuver. Other factors include the speed difference between the motorcycle and the front vehicle at the same instant, and the initial Time-To-Collision (TTC) between the motorcycle and the front vehicle at the beginning of the overtaking. The logistic regression analysis revealed that the probability of overtaking a vehicle with a lateral clearance below the critical threshold increases when the rider does not invade the opposite lane during the overtaking maneuver when a vehicle in the opposite lane induces the motorcyclist to return to the right lane, and as the duration of the overtaking maneuver increases. This research provides valuable contributions to understanding motorcyclist behavior during overtaking maneuvers, aiding in the development of more realistic microsimulation models that account for actual rider behavior. Additionally, the study contributes to the development of Advanced Rider Assistance Systems aimed at guiding motorcyclists to make safer overtaking decisions and reduce significant risk exposure from complex overtaking maneuvers.

本文旨在研究摩托车手在郊区环境中的超车行为。目的是建立超车持续时间模型，确定影响超车持续时间的因素，并确定骑手在保持临界横向间隙的情况下超车的可能性。骑行数据是通过一辆装有摄像头和 GPS 设备的客车收集的，该设备记录了摩托车手进行超车动作的视频。这种设置可以捕捉到摩托车手的自然行为，避免了带仪器的摩托车研究可能存在的局限性，例如由于参与者意识到自己参与了实验而产生的偏差。共记录了 119 次超车动作。实验采用了数字图像处理算法和 GPS 分析相结合的方法来描述所记录的动作。然后分别对超车和横向间隙的持续时间进行了生存分析和逻辑分析。基于危险的持续时间模型表明，摩托车手超车动作的持续时间受动作结束时摩托车与被超车辆之间的最终纵向距离的影响。其他因素包括摩托车与前车在同一时刻的速度差，以及超车开始时摩托车与前车的初始碰撞时间（TTC）。逻辑回归分析表明，当对向车道上的车辆诱使摩托车驾驶员返回右侧车道时，如果在超车过程中驾驶员没有侵入对向车道，那么在横向间隙低于临界阈值的情况下超车的概率就会增加，同时超车过程的持续时间也会增加。这项研究为了解摩托车手在超车过程中的行为做出了宝贵贡献，有助于开发更符合实际情况的微观模拟模型，以反映摩托车手的实际行为。此外，这项研究还有助于开发高级驾驶员辅助系统，以指导摩托车驾驶员做出更安全的超车决策，降低复杂超车动作带来的重大风险。

{"title":"Safety analysis of motorcyclists’ overtaking maneuvers","authors":"Francesco Bella , Federico Gulisano , Valerio Gagliardi","doi":"10.1016/j.aap.2024.107809","DOIUrl":"10.1016/j.aap.2024.107809","url":null,"abstract":"<div><div>This paper aims to investigate the overtaking behavior of motorcyclists in a suburban environment. The goal is to model overtaking duration, identify the factors influencing it, and determine the likelihood of a rider overtaking a vehicle while maintaining critical lateral clearance. Riding data were collected using a passenger car equipped with cameras and a GPS device, which recorded videos of motorcyclists performing maneuvers to overtake it. This setup allowed for capturing natural motorcyclist behavior and avoided the potential limitations of instrumented motorcycle studies, such as bias due to participants being aware of their involvement in the experiment. A total of 119 overtaking maneuvers were recorded. A methodology combining digital image processing algorithms and GPS analysis was employed to characterize the recorded maneuvers. Survival and logistic analyses were then conducted to model the duration of overtaking and lateral clearance, respectively. The hazard-based duration model indicated that the duration of a motorcyclist’s overtaking maneuver is influenced by the final longitudinal distance between the motorcycle and the passed vehicle at the end of the maneuver. Other factors include the speed difference between the motorcycle and the front vehicle at the same instant, and the initial Time-To-Collision (TTC) between the motorcycle and the front vehicle at the beginning of the overtaking. The logistic regression analysis revealed that the probability of overtaking a vehicle with a lateral clearance below the critical threshold increases when the rider does not invade the opposite lane during the overtaking maneuver when a vehicle in the opposite lane induces the motorcyclist to return to the right lane, and as the duration of the overtaking maneuver increases. This research provides valuable contributions to understanding motorcyclist behavior during overtaking maneuvers, aiding in the development of more realistic microsimulation models that account for actual rider behavior. Additionally, the study contributes to the development of Advanced Rider Assistance Systems aimed at guiding motorcyclists to make safer overtaking decisions and reduce significant risk exposure from complex overtaking maneuvers.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"208 ","pages":"Article 107809"},"PeriodicalIF":5.7,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142427778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Unraveling the determinants of traffic incident duration: A causal investigation using the framework of causal forests with debiased machine learning 揭示交通事故持续时间的决定因素：利用因果森林框架和去偏差机器学习进行因果调查。

IF 5.7 1区工程技术 Q1 ERGONOMICS

Accident; analysis and prevention

Pub Date : 2024-10-07 DOI: 10.1016/j.aap.2024.107806

Yaming Guo , Meng Li , Keqiang Li , Huiping Li , Yunxuan Li

Predicting the duration of traffic incidents is challenging due to their stochastic nature. Accurate predictions can greatly benefit end-users by informing their route choices and safety warnings, while helping traffic operation managers more effectively manage non-recurrent traffic congestion and enhance road safety. This study conducts a comprehensive causal analysis of traffic incident duration using a data collected over a long time and including different types of roads across the city of Tianjin, China. Employing the innovative framework of causal forests with biased machine learning (CF-DML) techniques, this study advances beyond traditional methods by focusing on interpreting the causal relationships between various factors and incident duration, emphasizing the role of heterogeneity among these factors. The CF-DML framework enables the assessment of the average treatment effects (ATEs) of various factors on incident duration. Notably, the significant influence of road type and suburban setting on treatment effects is underscored, which is generally consistent with the results obtained through classical methods. Second, to look more closely at the important factors such as road and collision types, a conditional average treatment effects (CATE) analysis is conducted, explaining heterogeneity through a causal heterogeneity tree. Third, based on insights from causal analysis, policies related to lane configurations are explored, emphasizing the necessity of considering causal effects in traffic management decisions. The CF-DML framework enhances our understanding of traffic incident dynamics, contributing to improved road safety and traffic flow in diverse urban environments.

由于交通事故的随机性，预测交通事故的持续时间具有挑战性。准确的预测可以为最终用户提供路线选择和安全预警信息，同时帮助交通运营管理者更有效地管理非经常性交通拥堵并提高道路安全性，从而使最终用户受益匪浅。本研究利用长期收集的中国天津市不同类型道路的数据，对交通事故持续时间进行了全面的因果分析。本研究采用了创新性的因果森林与偏置机器学习（CF-DML）技术框架，超越了传统方法，重点解释了各种因素与事故持续时间之间的因果关系，强调了这些因素之间异质性的作用。CF-DML 框架可评估各种因素对事故持续时间的平均处理效应 (ATE)。值得注意的是，道路类型和郊区环境对治疗效果的重要影响得到了强调，这与经典方法得出的结果基本一致。其次，为了更仔细地研究道路和碰撞类型等重要因素，进行了条件平均处理效应（CATE）分析，通过因果异质性树来解释异质性。第三，基于因果分析的见解，探讨了与车道配置相关的政策，强调了在交通管理决策中考虑因果效应的必要性。CF-DML 框架增强了我们对交通事故动态的理解，有助于改善不同城市环境中的道路安全和交通流量。

{"title":"Unraveling the determinants of traffic incident duration: A causal investigation using the framework of causal forests with debiased machine learning","authors":"Yaming Guo , Meng Li , Keqiang Li , Huiping Li , Yunxuan Li","doi":"10.1016/j.aap.2024.107806","DOIUrl":"10.1016/j.aap.2024.107806","url":null,"abstract":"<div><div>Predicting the duration of traffic incidents is challenging due to their stochastic nature. Accurate predictions can greatly benefit end-users by informing their route choices and safety warnings, while helping traffic operation managers more effectively manage non-recurrent traffic congestion and enhance road safety. This study conducts a comprehensive causal analysis of traffic incident duration using a data collected over a long time and including different types of roads across the city of Tianjin, China. Employing the innovative framework of causal forests with biased machine learning (CF-DML) techniques, this study advances beyond traditional methods by focusing on interpreting the causal relationships between various factors and incident duration, emphasizing the role of heterogeneity among these factors. The CF-DML framework enables the assessment of the average treatment effects (ATEs) of various factors on incident duration. Notably, the significant influence of road type and suburban setting on treatment effects is underscored, which is generally consistent with the results obtained through classical methods. Second, to look more closely at the important factors such as road and collision types, a conditional average treatment effects (CATE) analysis is conducted, explaining heterogeneity through a causal heterogeneity tree. Third, based on insights from causal analysis, policies related to lane configurations are explored, emphasizing the necessity of considering causal effects in traffic management decisions. The CF-DML framework enhances our understanding of traffic incident dynamics, contributing to improved road safety and traffic flow in diverse urban environments.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"208 ","pages":"Article 107806"},"PeriodicalIF":5.7,"publicationDate":"2024-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142387210","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Investigating risk factors associated with injury severity in highway crashes: A hybrid approach integrating two-step cluster analysis and latent class ordered regression model with covariates 调查高速公路碰撞事故中与伤害严重程度相关的风险因素：将两步聚类分析与带有协变量的潜类有序回归模型相结合的混合方法。

IF 5.7 1区工程技术 Q1 ERGONOMICS

Accident; analysis and prevention

Pub Date : 2024-10-04 DOI: 10.1016/j.aap.2024.107805

Siliang Luan , Zhongtai Jiang , Dayi qu , Xiaoxia Yang , Fanyun Meng

Highway crashes are responsible for a significant number of severe and fatal injuries drawing considerable attention from transportation authorities and safety researchers. This paper aims to investigate the unobserved heterogeneous effects of various risk factors, such as pre-crash circumstances, environmental and road conditions, vehicle-involved information, and driver attributes on injury severities. Our methodology uses a hybrid approach that combines two-step cluster analysis and latent class ordered regression model with covariates. The proposed approach extends traditional latent class model by elucidating potential relationships among predictors, covariates, and outcomes. A cross-sectional crash data covering a period of over five years (2011–2016) was obtained via the Dutch crash registration database for modeling injury severity outcomes. The results reveal substantial and statistically significant differences in injury severity between two latent classes. Moreover, we identify road lighting, time of crash, road surface conditions, weather, and season as covariates influencing class membership prediction. Factors such as high speed, alcohol involvement, frontal collision points, and older driver demographics increase the probability of serious injury and facility across all cases analyzed. Additionally, we observe notable heterogeneity effects between the two classes regarding temporal characteristics, the number and type of vehicles involved, as well as driver gender. Our findings provide specific and valuable insights into injury severity outcomes, which can inform the formulation of targeted safety countermeasures and regulatory strategies for traffic policies and relevant agencies.

高速公路撞车事故造成了大量严重和致命伤害，引起了交通管理部门和安全研究人员的极大关注。本文旨在研究各种风险因素（如碰撞前情况、环境和道路条件、车辆信息和驾驶员属性）对伤害严重程度的非观测异质性影响。我们的方法采用了一种混合方法，结合了两步聚类分析和带有协变量的潜类有序回归模型。所提出的方法通过阐明预测因素、协变量和结果之间的潜在关系，扩展了传统的潜类模型。通过荷兰碰撞登记数据库获得了五年多（2011-2016 年）的横截面碰撞数据，用于建立伤害严重程度结果模型。结果显示，两个潜在类别之间的伤害严重程度存在实质性差异，且具有统计学意义。此外，我们还发现道路照明、撞车时间、路面状况、天气和季节是影响类别成员预测的协变量。在分析的所有案例中，高速行驶、酗酒、正面碰撞点和年长驾驶员等因素会增加重伤和设施的概率。此外，我们还观察到两个类别之间在时间特征、涉及车辆的数量和类型以及驾驶员性别方面存在明显的异质性效应。我们的研究结果对伤害严重性结果提供了具体而有价值的见解，可为交通政策和相关机构制定有针对性的安全对策和监管策略提供参考。

{"title":"Investigating risk factors associated with injury severity in highway crashes: A hybrid approach integrating two-step cluster analysis and latent class ordered regression model with covariates","authors":"Siliang Luan , Zhongtai Jiang , Dayi qu , Xiaoxia Yang , Fanyun Meng","doi":"10.1016/j.aap.2024.107805","DOIUrl":"10.1016/j.aap.2024.107805","url":null,"abstract":"<div><div>Highway crashes are responsible for a significant number of severe and fatal injuries drawing considerable attention from transportation authorities and safety researchers. This paper aims to investigate the unobserved heterogeneous effects of various risk factors, such as pre-crash circumstances, environmental and road conditions, vehicle-involved information, and driver attributes on injury severities. Our methodology uses a hybrid approach that combines two-step cluster analysis and latent class ordered regression model with covariates. The proposed approach extends traditional latent class model by elucidating potential relationships among predictors, covariates, and outcomes. A cross-sectional crash data covering a period of over five years (2011–2016) was obtained via the Dutch crash registration database for modeling injury severity outcomes. The results reveal substantial and statistically significant differences in injury severity between two latent classes. Moreover, we identify road lighting, time of crash, road surface conditions, weather, and season as covariates influencing class membership prediction. Factors such as high speed, alcohol involvement, frontal collision points, and older driver demographics increase the probability of serious injury and facility across all cases analyzed. Additionally, we observe notable heterogeneity effects between the two classes regarding temporal characteristics, the number and type of vehicles involved, as well as driver gender. Our findings provide specific and valuable insights into injury severity outcomes, which can inform the formulation of targeted safety countermeasures and regulatory strategies for traffic policies and relevant agencies.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"208 ","pages":"Article 107805"},"PeriodicalIF":5.7,"publicationDate":"2024-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142378965","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Predicting risky driving behaviours using the theory of planned behaviour: A meta-analysis 利用计划行为理论预测危险驾驶行为：荟萃分析。

IF 5.7 1区工程技术 Q1 ERGONOMICS

Accident; analysis and prevention

Pub Date : 2024-10-03 DOI: 10.1016/j.aap.2024.107797

Klaire Somoray , Katherine M. White , Barry Watson , Ioni Lewis

The current meta-analysis explored the efficacy of the theory of planned behaviour (TPB) in predicting high-risk driving behaviours. Specifically, we examined speeding (in relation to exceeding the limit as well as speed compliance), driving under the influence, distracted driving, and seat belt use. We searched four electronic databases (i.e., PubMed, Web of Science, Scopus, and ProQuest) and included original studies that quantitatively measured the relationships between the TPB variables (attitude, subjective norm, perceived behavioural control [PBC], intention, and prospective/objective behaviour). The study identified 80 records with 94 independent samples. Studies were assessed for risk of bias using the JBI checklist for cross-sectional studies and compliance with the TPB guidelines. Together, attitude, subjective norm and PBC explained between 30 % and 51 % of variance found in intention, with attitude showing as the strongest predictor for intention across the different driving behaviours. The findings also showed that the model explained 36 %–48 % variance found in predicting the observed and/or prospective behaviours for distracted driving, speed compliance and speeding. Understanding the varying strengths and thus relative importance of TPB constructs in predicting different risky driving behaviours is crucial for developing targeted road safety interventions.

当前的荟萃分析探讨了计划行为理论（TPB）在预测高风险驾驶行为方面的有效性。具体来说，我们研究了超速（与超限和遵守速度有关）、酒后驾驶、分心驾驶和安全带使用。我们搜索了四个电子数据库（即 PubMed、Web of Science、Scopus 和 ProQuest），收录了定量测量 TPB 变量（态度、主观规范、感知行为控制 [PBC]、意图和预期/目标行为）之间关系的原创研究。研究确定了 80 项记录和 94 个独立样本。研究使用横断面研究的 JBI 检查表对研究进行了偏倚风险评估，并对是否符合 TPB 准则进行了评估。态度、主观规范和 PBC 三者共同解释了 30% 到 51% 的意向变异，其中态度对不同驾驶行为的意向预测作用最强。研究结果还显示，在预测分心驾驶、遵守车速规定和超速行驶的观察和/或预期行为时，该模型可解释 36%-48% 的方差。了解 TPB 构建在预测不同危险驾驶行为方面的不同优势和相对重要性，对于制定有针对性的道路安全干预措施至关重要。

{"title":"Predicting risky driving behaviours using the theory of planned behaviour: A meta-analysis","authors":"Klaire Somoray , Katherine M. White , Barry Watson , Ioni Lewis","doi":"10.1016/j.aap.2024.107797","DOIUrl":"10.1016/j.aap.2024.107797","url":null,"abstract":"<div><div>The current <em>meta</em>-analysis explored the efficacy of the theory of planned behaviour (TPB) in predicting high-risk driving behaviours. Specifically, we examined speeding (in relation to exceeding the limit as well as speed compliance), driving under the influence, distracted driving, and seat belt use. We searched four electronic databases (i.e., PubMed, Web of Science, Scopus, and ProQuest) and included original studies that quantitatively measured the relationships between the TPB variables (attitude, subjective norm, perceived behavioural control [PBC], intention, and prospective/objective behaviour). The study identified 80 records with 94 independent samples. Studies were assessed for risk of bias using the JBI checklist for cross-sectional studies and compliance with the TPB guidelines. Together, attitude, subjective norm and PBC explained between 30 % and 51 % of variance found in intention, with attitude showing as the strongest predictor for intention across the different driving behaviours. The findings also showed that the model explained 36 %–48 % variance found in predicting the observed and/or prospective behaviours for distracted driving, speed compliance and speeding. Understanding the varying strengths and thus relative importance of TPB constructs in predicting different risky driving behaviours is crucial for developing targeted road safety interventions.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"208 ","pages":"Article 107797"},"PeriodicalIF":5.7,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142374953","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The effect of dual training on the hazard response and attention allocation of novice drivers when driving with advanced driver assistance system 双重训练对新手驾驶员使用高级驾驶辅助系统时危险反应和注意力分配的影响。

IF 5.7 1区工程技术 Q1 ERGONOMICS

Accident; analysis and prevention

Pub Date : 2024-10-02 DOI: 10.1016/j.aap.2024.107802

Chunxi Huang , Zuyuan Wang , Dengbo He

To ensure traffic safety when driving with an advanced driving assistance system (ADAS), drivers are still required to take over control of the vehicle in case of emergency. Drivers’ takeover performance jointly relies on their capability to anticipate the potential hazards in traffic scenarios and an appropriate understanding of ADAS capabilities. However, previous research mostly focused on strengthening drivers’ understanding of ADAS capabilities but ignored drivers’ hazard perception capabilities when using ADAS – the latter is especially weak among novice drivers. This study proposed and evaluated three training methods for novice drivers, i.e., ADAS training only (AD training), hazard perception training only (HP training), and AD+HP training. Their effectiveness on drivers’ attention allocation strategies and responses to hazardous scenarios when handling hazardous scenarios with different levels of complexity were evaluated among 32 novice drivers in a driving simulator study. Results show that the proposed AD+HP training outperformed AD training and HP training in terms of attention allocation strategies (i.e., wider distribution of attention) and responses in hazardous scenarios (i.e., quicker and more attention to cues of importance and larger minimum time gap). However, the effectiveness of all kinds of training was weakened in more complex scenarios. Findings from this study provide insights into driver training in the context of driving automation.

在使用高级驾驶辅助系统（ADAS）进行驾驶时，为确保交通安全，驾驶员仍需在紧急情况下接管对车辆的控制。驾驶员的接管能力取决于他们对交通场景中潜在危险的预测能力以及对 ADAS 功能的适当理解。然而，以往的研究大多侧重于加强驾驶员对 ADAS 功能的理解，却忽视了驾驶员在使用 ADAS 时的危险感知能力，而后者在新手驾驶员中尤为薄弱。本研究提出并评估了针对新手驾驶员的三种培训方法，即仅ADAS培训（AD培训）、仅危险感知培训（HP培训）和AD+HP培训。在驾驶模拟器研究中，对 32 名新手驾驶员在处理不同复杂程度的危险场景时注意力分配策略和对危险场景反应的有效性进行了评估。结果表明，在注意力分配策略（即更广泛的注意力分配）和危险场景反应（即更快、更多地注意重要线索和更大的最小时间间隙）方面，拟议的 AD+HP 训练优于 AD 训练和 HP 训练。然而，在更为复杂的场景中，各种训练的效果都有所减弱。本研究的结果为自动驾驶背景下的驾驶员培训提供了启示。

{"title":"The effect of dual training on the hazard response and attention allocation of novice drivers when driving with advanced driver assistance system","authors":"Chunxi Huang , Zuyuan Wang , Dengbo He","doi":"10.1016/j.aap.2024.107802","DOIUrl":"10.1016/j.aap.2024.107802","url":null,"abstract":"<div><div>To ensure traffic safety when driving with an advanced driving assistance system (ADAS), drivers are still required to take over control of the vehicle in case of emergency. Drivers’ takeover performance jointly relies on their capability to anticipate the potential hazards in traffic scenarios and an appropriate understanding of ADAS capabilities. However, previous research mostly focused on strengthening drivers’ understanding of ADAS capabilities but ignored drivers’ hazard perception capabilities when using ADAS – the latter is especially weak among novice drivers. This study proposed and evaluated three training methods for novice drivers, i.e., ADAS training only (AD training), hazard perception training only (HP training), and AD+HP training. Their effectiveness on drivers’ attention allocation strategies and responses to hazardous scenarios when handling hazardous scenarios with different levels of complexity were evaluated among 32 novice drivers in a driving simulator study. Results show that the proposed AD+HP training outperformed AD training and HP training in terms of attention allocation strategies (i.e., wider distribution of attention) and responses in hazardous scenarios (i.e., quicker and more attention to cues of importance and larger minimum time gap). However, the effectiveness of all kinds of training was weakened in more complex scenarios. Findings from this study provide insights into driver training in the context of driving automation.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"208 ","pages":"Article 107802"},"PeriodicalIF":5.7,"publicationDate":"2024-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142370699","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Uncertainty-aware probabilistic graph neural networks for road-level traffic crash prediction 用于道路级别交通事故预测的不确定性感知概率图神经网络。

IF 5.7 1区工程技术 Q1 ERGONOMICS

Accident; analysis and prevention

Pub Date : 2024-10-02 DOI: 10.1016/j.aap.2024.107801

Xiaowei Gao , Xinke Jiang , James Haworth , Dingyi Zhuang , Shenhao Wang , Huanfa Chen , Stephen Law

Traffic crashes present substantial challenges to human safety and socio-economic development in urban areas. Developing a reliable and responsible traffic crash prediction model is crucial to address growing public safety concerns and improve the safety of urban mobility systems. Traditional methods face limitations at fine spatiotemporal scales due to the sporadic nature of high-risk crashes and the predominance of non-crash characteristics. Furthermore, while most current models show promising occurrence prediction, they overlook the uncertainties arising from the inherent nature of crashes, and then fail to adequately map the hierarchical ranking of crash risk values for more precise insights. To address these issues, we introduce the Spatiotemporal Zero-Inflated Tweedie Graph Neural Networks (STZITD-GNN), the first uncertainty-aware probabilistic graph deep learning model in road-level daily-basis traffic crash prediction for multi-steps. Our model combines the interpretability of the statistical Tweedie family with the predictive power of graph neural networks, excelling in predicting a comprehensive range of crash risks. The decoder employs a compound Tweedie model, handling the non-Gaussian distribution inherent in crash data, with a zero-inflated component for accurately identifying non-crash cases and low-risk roads. The model accurately predicts and differentiates between high-risk, low-risk, and no-risk scenarios, providing a holistic view of road safety that accounts for the full spectrum of probability and severity of crashes. Empirical tests using real-world traffic data from London, UK, demonstrate that the STZITD-GNN surpasses other baseline models across multiple benchmarks, including a reduction in regression error of up to 34.60% in point estimation metrics and an improvement of above 47% in interval-based uncertainty metrics.

交通事故给城市地区的人类安全和社会经济发展带来了巨大挑战。开发可靠、负责任的交通事故预测模型对于解决日益增长的公共安全问题和提高城市交通系统的安全性至关重要。由于高风险碰撞事故的偶发性和非碰撞特征的主导性，传统方法在精细时空尺度上面临着局限性。此外，虽然目前的大多数模型对事故发生率的预测很有希望，但它们忽视了碰撞事故固有性质所带来的不确定性，因此无法充分映射碰撞事故风险值的分级排序，以获得更精确的见解。为了解决这些问题，我们引入了时空零膨胀特威迪图神经网络（STZITD-GNN），这是首个用于多步骤道路级日基准交通事故预测的不确定性感知概率图深度学习模型。我们的模型结合了统计特威迪家族的可解释性和图神经网络的预测能力，在预测各种碰撞风险方面表现出色。解码器采用复合特威迪模型，可处理碰撞数据中固有的非高斯分布，其零膨胀成分可准确识别非碰撞案例和低风险道路。该模型能准确预测和区分高风险、低风险和无风险情况，提供了一个全面的道路安全视角，考虑到了碰撞事故的所有概率和严重程度。使用英国伦敦的真实交通数据进行的实证测试表明，STZITD-GNN 在多个基准方面超越了其他基线模型，包括在点估计指标方面减少了高达 34.60% 的回归误差，在基于区间的不确定性指标方面提高了 47% 以上。

{"title":"Uncertainty-aware probabilistic graph neural networks for road-level traffic crash prediction","authors":"Xiaowei Gao , Xinke Jiang , James Haworth , Dingyi Zhuang , Shenhao Wang , Huanfa Chen , Stephen Law","doi":"10.1016/j.aap.2024.107801","DOIUrl":"10.1016/j.aap.2024.107801","url":null,"abstract":"<div><div>Traffic crashes present substantial challenges to human safety and socio-economic development in urban areas. Developing a reliable and responsible traffic crash prediction model is crucial to address growing public safety concerns and improve the safety of urban mobility systems. Traditional methods face limitations at fine spatiotemporal scales due to the sporadic nature of high-risk crashes and the predominance of non-crash characteristics. Furthermore, while most current models show promising occurrence prediction, they overlook the uncertainties arising from the inherent nature of crashes, and then fail to adequately map the hierarchical ranking of crash risk values for more precise insights. To address these issues, we introduce the <strong><u>S</u></strong>patio<strong><u>t</u></strong>emporal <strong><u>Z</u></strong>ero-<strong><u>I</u></strong>nflated <strong><u>T</u></strong>wee<strong><u>d</u></strong>ie <strong><u>G</u></strong>raph <strong><u>N</u></strong>eural <strong><u>N</u></strong>etworks (STZITD-GNN), the first uncertainty-aware probabilistic graph deep learning model in road-level daily-basis traffic crash prediction for multi-steps. Our model combines the interpretability of the statistical Tweedie family with the predictive power of graph neural networks, excelling in predicting a comprehensive range of crash risks. The decoder employs a compound Tweedie model, handling the non-Gaussian distribution inherent in crash data, with a zero-inflated component for accurately identifying non-crash cases and low-risk roads. The model accurately predicts and differentiates between high-risk, low-risk, and no-risk scenarios, providing a holistic view of road safety that accounts for the full spectrum of probability and severity of crashes. Empirical tests using real-world traffic data from London, UK, demonstrate that the STZITD-GNN surpasses other baseline models across multiple benchmarks, including a reduction in regression error of up to 34.60% in point estimation metrics and an improvement of above 47% in interval-based uncertainty metrics.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"208 ","pages":"Article 107801"},"PeriodicalIF":5.7,"publicationDate":"2024-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142370700","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Anticipated buffer time – An evasive surrogate safety indicator for risk assessment of unsignalized intersections under heterogeneous traffic and aggressive driving conditions 预计缓冲时间--在异质交通和激烈驾驶条件下，用于无信号交叉口风险评估的避让替代安全指标。

IF 5.7 1区工程技术 Q1 ERGONOMICS

Accident; analysis and prevention

Pub Date : 2024-10-02 DOI: 10.1016/j.aap.2024.107796

Manish Dutta , Suprava Jena , Bansil Korat , Sarthak Bhandari , George Kennedy Lyngdoh

Risk assessment of unsignalized intersections is particularly challenging when confronted with a combination of factors such as heavy traffic, diverse vehicle types, lane indiscipline, aggressive driving, and evasive manoeuvres. Understanding how people drive in these situations is crucial for accurately assessing the risks at unsignalized intersections. This study introduces a novel surrogate safety indicator, i.e. Anticipated Buffer Time (ABT), designed to account for these various factors. Additionally, three new indicators derived from ABT are introduced, namely ABT Negation Ratio, ABT Extremity Ratio, and ABT Progression Ratio. A risk assessment measure, denoted as UnSigRisk Score, is formulated using these three indicators for unsignalized intersections. Three intersections in Ahmedabad, India, were selected for the study due to their manifestation of these challenging conditions. Spearman Rank Correlation Coefficient was estimated to find out how well can UnSigRisk Score measure is able to quantify evasive behaviour. The results indicate that this score proficiently measures evasive behaviour, exhibiting coefficients exceeding 0.6 in all cases—significantly outperforming the current evasive indicators, Yaw Rate Ratio and Jerk. The proposed risk assessment score could serve as a practical tool for transportation authorities, enabling them to identify the most vulnerable intersections and allocate resources for targeted safety interventions wisely. The study unequivocally demonstrates that the use of ABT paves the way for a thorough examination of safety at unsignalized intersections, regardless of driving behaviour and traffic conditions.

无信号交叉路口的风险评估尤其具有挑战性，因为会面临交通繁忙、车辆类型多样、车道不规范、激进驾驶和回避动作等综合因素。要准确评估无信号交叉路口的风险，了解人们在这些情况下的驾驶方式至关重要。本研究引入了一个新的替代安全指标，即预期缓冲时间（ABT），旨在考虑这些不同的因素。此外，还引入了从 ABT 派生的三个新指标，即 ABT 否定比、ABT 极端比和 ABT 进展比。利用这三个指标为无信号交叉路口制定了一个风险评估指标，称为 UnSigRisk Score。研究选择了印度艾哈迈达巴德的三个交叉路口，因为这些交叉路口都具有这些挑战性条件。对 Spearman Rank Correlation Coefficient 进行了估算，以了解 UnSigRisk Score 测量方法对规避行为的量化程度。结果表明，该评分能有效衡量规避行为，在所有情况下系数均超过 0.6，明显优于当前的规避指标--偏航率比和抖动。建议的风险评估分数可作为交通管理部门的实用工具，使其能够识别最脆弱的交叉路口，并为有针对性的安全干预措施合理分配资源。这项研究明确表明，无论驾驶行为和交通状况如何，ABT 的使用都为彻底检查无信号交叉口的安全铺平了道路。

{"title":"Anticipated buffer time – An evasive surrogate safety indicator for risk assessment of unsignalized intersections under heterogeneous traffic and aggressive driving conditions","authors":"Manish Dutta , Suprava Jena , Bansil Korat , Sarthak Bhandari , George Kennedy Lyngdoh","doi":"10.1016/j.aap.2024.107796","DOIUrl":"10.1016/j.aap.2024.107796","url":null,"abstract":"<div><div>Risk assessment of unsignalized intersections is particularly challenging when confronted with a combination of factors such as heavy traffic, diverse vehicle types, lane indiscipline, aggressive driving, and evasive manoeuvres. Understanding how people drive in these situations is crucial for accurately assessing the risks at unsignalized intersections. This study introduces a novel surrogate safety indicator, i.e. Anticipated Buffer Time (ABT), designed to account for these various factors. Additionally, three new indicators derived from ABT are introduced, namely ABT Negation Ratio, ABT Extremity Ratio, and ABT Progression Ratio. A risk assessment measure, denoted as UnSigRisk Score, is formulated using these three indicators for unsignalized intersections. Three intersections in Ahmedabad, India, were selected for the study due to their manifestation of these challenging conditions. Spearman Rank Correlation Coefficient was estimated to find out how well can UnSigRisk Score measure is able to quantify evasive behaviour. The results indicate that this score proficiently measures evasive behaviour, exhibiting coefficients exceeding 0.6 in all cases—significantly outperforming the current evasive indicators, Yaw Rate Ratio and Jerk. The proposed risk assessment score could serve as a practical tool for transportation authorities, enabling them to identify the most vulnerable intersections and allocate resources for targeted safety interventions wisely. The study unequivocally demonstrates that the use of ABT paves the way for a thorough examination of safety at unsignalized intersections, regardless of driving behaviour and traffic conditions.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"208 ","pages":"Article 107796"},"PeriodicalIF":5.7,"publicationDate":"2024-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142370698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Effects of helmet usage on moped riders’ injury severity in moped-vehicle crashes: Insights from partially temporal constrained random parameters bivariate probit models 头盔的使用对轻便摩托车与车辆碰撞事故中轻便摩托车骑行者受伤严重程度的影响：部分时间约束随机参数双变量概率模型的启示。

IF 5.7 1区工程技术 Q1 ERGONOMICS

Accident; analysis and prevention

Pub Date : 2024-10-01 DOI: 10.1016/j.aap.2024.107800

Chenzhu Wang , Mohamed Abdel-Aty , Pengfei Cui , Lei Han

Mopeds are small and move unpredictably, making them difficult for other drivers to perceive. This lack of visibility, coupled with the minimal protection that mopeds provide, can lead to serious crashes, particularly when the rider is not wearing a helmet. This paper explores the association between helmet usage and injury severity among moped riders involved in collisions with other vehicles. A series of joint bivariate probit models are employed, with injury severity and helmet usage serving as dependent variables. Data on two-vehicle moped crashes in Florida from 2019 to 2021 are collected and categorized into three periods: before, during, and after the COVID-19 pandemic. Crash involvement ratios are calculated to examine the safety risk elements of moped riders in various categories, while significant temporal shifts are also explored. The correlated joint random parameters bivariate probit models with heterogeneity in means demonstrate their superiority in capturing interactive unobserved heterogeneity, revealing how various variables significantly affect injury outcomes and helmet usage. Temporal instability related to the COVID-19 pandemic is validated through likelihood ratio tests, out-of-sample predictions, and calculations of marginal effects. Additionally, several parameters are noted to remain temporally stable across multiple periods, prompting the development of a partially temporally constrained modeling approach to provide insights from a long-term perspective. Specifically, it is found that male moped riders are less likely to wear helmets and are negatively associated with injury/fatality rates. Moped riders on two-lane roads are also less likely to wear helmets. Furthermore, moped riders face a lower risk of injury or fatality during daylight conditions, while angle crashes consistently lead to a higher risk of injuries and fatalities across the three periods. These findings provide valuable insights into helmet usage and injury severity among moped riders and offer guidance for developing countermeasures to protect them.

轻便摩托车体积小，行驶速度难以预测，因此其他司机很难察觉。这种缺乏可见度的情况，再加上轻便摩托车提供的保护极少，可能会导致严重的撞车事故，尤其是在骑手没有佩戴头盔的情况下。本文探讨了与其他车辆发生碰撞的轻便摩托车驾驶者头盔使用情况与受伤严重程度之间的关系。本文采用了一系列联合双变量 probit 模型，将受伤严重程度和头盔使用情况作为因变量。收集了 2019 年至 2021 年佛罗里达州两车轻便摩托车碰撞事故的数据，并将其分为三个时期：COVID-19 大流行之前、期间和之后。通过计算碰撞参与比来研究各类轻便摩托车驾驶者的安全风险要素，同时还探讨了重大的时间变化。具有均值异质性的相关联合随机参数双变量 probit 模型在捕捉交互式非观察异质性方面显示出其优越性，揭示了各种变量如何显著影响伤害结果和头盔的使用。通过似然比检验、样本外预测和边际效应计算，验证了与 COVID-19 大流行相关的时间不稳定性。此外，研究还注意到一些参数在多个时期内保持时间稳定性，这促使我们开发了一种部分时间限制的建模方法，以便从长期角度提供见解。具体而言，研究发现男性轻便摩托车驾驶者戴头盔的可能性较低，并且与受伤/死亡率呈负相关。在双车道道路上骑轻便摩托车的人也不太可能戴头盔。此外，轻便摩托车驾驶者在白天的受伤或死亡风险较低，而在这三个时间段内，角度碰撞始终导致较高的受伤和死亡风险。这些发现为了解轻便摩托车驾驶者的头盔使用情况和受伤严重程度提供了宝贵的信息，并为制定保护他们的对策提供了指导。

{"title":"Effects of helmet usage on moped riders’ injury severity in moped-vehicle crashes: Insights from partially temporal constrained random parameters bivariate probit models","authors":"Chenzhu Wang , Mohamed Abdel-Aty , Pengfei Cui , Lei Han","doi":"10.1016/j.aap.2024.107800","DOIUrl":"10.1016/j.aap.2024.107800","url":null,"abstract":"<div><div>Mopeds are small and move unpredictably, making them difficult for other drivers to perceive. This lack of visibility, coupled with the minimal protection that mopeds provide, can lead to serious crashes, particularly when the rider is not wearing a helmet. This paper explores the association between helmet usage and injury severity among moped riders involved in collisions with other vehicles. A series of joint bivariate probit models are employed, with injury severity and helmet usage serving as dependent variables. Data on two-vehicle moped crashes in Florida from 2019 to 2021 are collected and categorized into three periods: before, during, and after the COVID-19 pandemic. Crash involvement ratios are calculated to examine the safety risk elements of moped riders in various categories, while significant temporal shifts are also explored. The correlated joint random parameters bivariate probit models with heterogeneity in means demonstrate their superiority in capturing interactive unobserved heterogeneity, revealing how various variables significantly affect injury outcomes and helmet usage. Temporal instability related to the COVID-19 pandemic is validated through likelihood ratio tests, out-of-sample predictions, and calculations of marginal effects. Additionally, several parameters are noted to remain temporally stable across multiple periods, prompting the development of a partially temporally constrained modeling approach to provide insights from a long-term perspective. Specifically, it is found that male moped riders are less likely to wear helmets and are negatively associated with injury/fatality rates. Moped riders on two-lane roads are also less likely to wear helmets. Furthermore, moped riders face a lower risk of injury or fatality during daylight conditions, while angle crashes consistently lead to a higher risk of injuries and fatalities across the three periods. These findings provide valuable insights into helmet usage and injury severity among moped riders and offer guidance for developing countermeasures to protect them.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"208 ","pages":"Article 107800"},"PeriodicalIF":5.7,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142363846","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Endogeneity of pedestrian survival time and emergency medical service response time: Variations across disadvantaged and non-disadvantaged communities 行人存活时间和紧急医疗服务响应时间的内生性：弱势社区与非弱势社区之间的差异。

IF 5.7 1区工程技术 Q1 ERGONOMICS

Accident; analysis and prevention

Pub Date : 2024-10-01 DOI: 10.1016/j.aap.2024.107799

A. Latif Patwary , Asad J. Khattak

The Vision Zero-Safe Systems Approach prioritizes fast access to Emergency Medical Services (EMS) to improve the survivability of road users in transportation crashes, especially concerning the recent increase in pedestrian-involved crashes. Pedestrian crashes resulting in immediate or early death are considerably more severe than those taking longer. The time gap between injury and fatality is known as survival time, and it heavily relies on EMS response time. The characteristics of the crash location may be associated with EMS response and survival time. A US Department of Transportation initiative identifies communities often facing challenges. Six disadvantaged community (DAC) indicators, including economy, environment, equity, health, resilience, and transportation access, enable an analysis of how survival and EMS response times vary across DACs and non-DACs. To this end, this study created a unique and comprehensive database by linking DACs data with 2017–2021 pedestrian-involved fatal crashes. This study utilizes two-stage residual inclusion models with segmentation for DACs and non-DACs accounting for the endogenous relationship between EMS response and pedestrian survival time. The results indicate that EMS response time is higher and pedestrian survival time is lower in DACs than in non-DACs. A delayed EMS response time is associated with a greater reduction in survival time in DACs compared to non-DACs. Factors, e.g., nighttime and interstate crashes, contribute to higher EMS response time, while pedestrian drugs, driver speeding, and hit-and-run behaviors are associated with a greater reduction in survival time in DACs than non-DACs. The implications of the findings are discussed in the paper.

零伤亡愿景-安全系统方法优先考虑快速获得紧急医疗服务（EMS），以提高交通事故中道路使用者的存活率，尤其是最近涉及行人的交通事故的增加。与时间较长的交通事故相比，导致行人立即或提前死亡的交通事故要严重得多。受伤与死亡之间的时间差被称为存活时间，它在很大程度上取决于急救服务的响应时间。撞车地点的特征可能与急救响应和存活时间有关。美国交通部的一项倡议确定了经常面临挑战的社区。六项弱势社区 (DAC) 指标（包括经济、环境、公平、健康、复原力和交通便利性）有助于分析 DAC 和非 DAC 社区的存活率和急救响应时间有何不同。为此，本研究通过将 DACs 数据与 2017-2021 年涉及行人的致命车祸联系起来，创建了一个独特而全面的数据库。本研究采用两阶段残差包含模型，对 DAC 和非 DAC 进行细分，以考虑 EMS 响应与行人存活时间之间的内生关系。结果表明，与非危险货物运输中心相比，危险货物运输中心的急救响应时间更长，行人存活时间更短。与非危险区域相比，紧急医疗服务响应时间的延迟与危险区域行人存活时间的缩短有更大的关联。夜间和州际碰撞等因素会导致更长的急救响应时间，而行人吸毒、驾驶员超速和肇事逃逸行为则会导致危险驾驶区域的存活时间比非危险驾驶区域缩短更多。本文讨论了这些发现的意义。

{"title":"Endogeneity of pedestrian survival time and emergency medical service response time: Variations across disadvantaged and non-disadvantaged communities","authors":"A. Latif Patwary , Asad J. Khattak","doi":"10.1016/j.aap.2024.107799","DOIUrl":"10.1016/j.aap.2024.107799","url":null,"abstract":"<div><div>The Vision Zero-Safe Systems Approach prioritizes fast access to Emergency Medical Services (EMS) to improve the survivability of road users in transportation crashes, especially concerning the recent increase in pedestrian-involved crashes. Pedestrian crashes resulting in immediate or early death are considerably more severe than those taking longer. The time gap between injury and fatality is known as survival time, and it heavily relies on EMS response time. The characteristics of the crash location may be associated with EMS response and survival time. A US Department of Transportation initiative identifies communities often facing challenges. Six disadvantaged community (DAC) indicators, including economy, environment, equity, health, resilience, and transportation access, enable an analysis of how survival and EMS response times vary across DACs and non-DACs. To this end, this study created a unique and comprehensive database by linking DACs data with 2017–2021 pedestrian-involved fatal crashes. This study utilizes two-stage residual inclusion models with segmentation for DACs and non-DACs accounting for the endogenous relationship between EMS response and pedestrian survival time. The results indicate that EMS response time is higher and pedestrian survival time is lower in DACs than in non-DACs. A delayed EMS response time is associated with a greater reduction in survival time in DACs compared to non-DACs. Factors, e.g., nighttime and interstate crashes, contribute to higher EMS response time, while pedestrian drugs, driver speeding, and hit-and-run behaviors are associated with a greater reduction in survival time in DACs than non-DACs. The implications of the findings are discussed in the paper.</div></div>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"208 ","pages":"Article 107799"},"PeriodicalIF":5.7,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142363847","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Driving risk identification of urban arterial and collector roads based on multi-scale data. 基于多尺度数据的城市干道和集散路驾驶风险识别。

IF 5.7 1区工程技术 Q1 ERGONOMICS

Accident; analysis and prevention

Pub Date : 2024-10-01 Epub Date: 2024-07-15 DOI: 10.1016/j.aap.2024.107712

Xintong Yan, Jie He, Guanhe Wu, Shuang Sun, Chenwei Wang, Zhiming Fang, Changjian Zhang

Urban arterial and collector roads, while interconnected within the urban transportation network, serve distinct purposes, leading to different driving risk profiles. Investigating these differences using advanced methods is of paramount significance. This study aims to achieve this by primarily collecting and processing relevant vehicle trajectory data alongside driver-vehicle-road-environment data. A comprehensive risk assessment matrix is constructed to assess driving risks, incorporating multiple conflict and traffic flow indicators with statistically temporal stability. The Entropy weight-TOPSIS method and the K-means algorithm are employed to determine the risk scores and levels of the target arterial and collector roads. Using risk levels as the outcome variables and multi-scale features as the explanatory variables, random parameters models with heterogeneity in means and variances are developed to identify the determinants of driving risks at different levels. Likelihood ratio tests and comparisons of out-of-sample and within-sample prediction are conducted. Results reveal significant statistical differences in the risk profiles between arterial and collector roads. The marginal effects of significant parameters are then calculated separately for arterial and collector roads, indicating that several factors have different impacts on the probability of risk levels for arterial and collector roads, such as the number of movable elements in road landscape pictures, the standard deviation of the vehicle's lateral acceleration, the average standard deviation of speed for all vehicles on the road segment, and the number of one-way lanes on the road segment. Some practical implications are provided based on the findings. Future research can be implemented by expanding the collected data to different regions and cities over longer periods.

城市主干道和集散路虽然在城市交通网中相互连接，但却有着不同的用途，从而导致不同的驾驶风险。使用先进的方法调查这些差异具有重要意义。本研究旨在通过主要收集和处理相关车辆轨迹数据以及驾驶员-车辆-道路-环境数据来实现这一目标。本研究构建了一个综合风险评估矩阵来评估驾驶风险，该矩阵包含多个冲突和交通流量指标，并具有统计上的时间稳定性。采用熵权-TOPSIS 方法和 K-means 算法来确定目标干道和集散道路的风险分数和等级。以风险等级为结果变量，以多尺度特征为解释变量，建立均值和方差异质性随机参数模型，以确定不同等级驾驶风险的决定因素。对样本外预测和样本内预测进行了似然比检验和比较。结果显示，主干道和集散道路之间的风险概况存在明显的统计差异。然后分别计算了主干道和集散道路重要参数的边际效应，结果表明有几个因素对主干道和集散道路的风险等级概率有不同的影响，如道路景观图片中可移动元素的数量、车辆横向加速度的标准偏差、路段上所有车辆速度的平均标准偏差以及路段上单向车道的数量。研究结果提供了一些实际意义。未来的研究可以将收集到的数据扩展到不同地区和城市，并进行更长时间的研究。

{"title":"Driving risk identification of urban arterial and collector roads based on multi-scale data.","authors":"Xintong Yan, Jie He, Guanhe Wu, Shuang Sun, Chenwei Wang, Zhiming Fang, Changjian Zhang","doi":"10.1016/j.aap.2024.107712","DOIUrl":"10.1016/j.aap.2024.107712","url":null,"abstract":"<p><p>Urban arterial and collector roads, while interconnected within the urban transportation network, serve distinct purposes, leading to different driving risk profiles. Investigating these differences using advanced methods is of paramount significance. This study aims to achieve this by primarily collecting and processing relevant vehicle trajectory data alongside driver-vehicle-road-environment data. A comprehensive risk assessment matrix is constructed to assess driving risks, incorporating multiple conflict and traffic flow indicators with statistically temporal stability. The Entropy weight-TOPSIS method and the K-means algorithm are employed to determine the risk scores and levels of the target arterial and collector roads. Using risk levels as the outcome variables and multi-scale features as the explanatory variables, random parameters models with heterogeneity in means and variances are developed to identify the determinants of driving risks at different levels. Likelihood ratio tests and comparisons of out-of-sample and within-sample prediction are conducted. Results reveal significant statistical differences in the risk profiles between arterial and collector roads. The marginal effects of significant parameters are then calculated separately for arterial and collector roads, indicating that several factors have different impacts on the probability of risk levels for arterial and collector roads, such as the number of movable elements in road landscape pictures, the standard deviation of the vehicle's lateral acceleration, the average standard deviation of speed for all vehicles on the road segment, and the number of one-way lanes on the road segment. Some practical implications are provided based on the findings. Future research can be implemented by expanding the collected data to different regions and cities over longer periods.</p>","PeriodicalId":6926,"journal":{"name":"Accident; analysis and prevention","volume":"206 ","pages":"107712"},"PeriodicalIF":5.7,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141603109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0