Journal of Safety Research最新文献_第2页

Risk of crashes among self-employed truck drivers: Prevalence evaluation using fatigue data and machine learning prediction models 自雇卡车司机发生车祸的风险：利用疲劳数据和机器学习预测模型评估普遍程度

IF 3.9 2区工程技术 Q1 ERGONOMICS

Journal of Safety Research

Pub Date : 2024-11-16 DOI: 10.1016/j.jsr.2024.11.002

Rodrigo Duarte Soliani , Alisson Vinicius Brito Lopes , Fábio Santiago , Luiz Bueno da Silva , Nwabueze Emekwuru , Ana Carolina Lorena

Introduction: Transportation companies have increasingly shifted their workforce from permanent to outsourced roles, a trend that has consequences for self-employed truck drivers. This transition leads to extended working hours, resulting in fatigue and an increased risk of crashes. The present study investigates the factors contributing to fatigue and impairment in truck driving performance while developing a machine learning-based model for predicting the risk of traffic crashes. Method: To achieve this, a comprehensive questionnaire was designed, covering various aspects of the participants’ sociodemographic characteristics, health, sleep, and working conditions. The questionnaire was administered to 363 self-employed truck drivers operating in the State of São Paulo, Brazil. Approximately 63% of the participants were smokers, while 17.56% reported drinking alcohol more than four times a week, and also admitted to being involved in at least one crash in the last three years. Fifty percent of the respondents reported consuming drugs (such as amphetamines, marijuana, or cocaine). Results: The surveyed individuals declared driving for approximately 14.62 h (SD = 1.97) before they felt fatigued, with an average of approximately 5.92 h of sleep in the last 24 h (SD = 0.96). Truck drivers unanimously agreed that waiting times for truck loading/unloading significantly impact the duration of their working day and rest time. The study employed eight machine learning algorithms to estimate the likelihood of truck drivers being involved in crashes, achieving accuracy rates ranging between 78% and 85%. Conclusions: These results validated the construction of accurate machine learning-derived models. Practical Applications: These findings can inform policies and practices aimed at enhancing the safety and well-being of self-employed truck drivers and the broader public.

导言：运输公司越来越多地将其劳动力从永久性岗位转为外包岗位，这一趋势对自雇卡车司机造成了影响。这种转变导致工作时间延长，从而导致疲劳和撞车风险增加。本研究调查了导致疲劳和卡车驾驶性能受损的因素，同时开发了一个基于机器学习的模型，用于预测交通事故风险。研究方法为此，我们设计了一份综合问卷，涵盖了参与者的社会人口特征、健康、睡眠和工作条件等各个方面。问卷调查对象为巴西圣保罗州的 363 名自营卡车司机。约 63% 的受访者吸烟，17.56% 的受访者称每周饮酒超过四次，并承认在过去三年中至少发生过一次车祸。50%的受访者表示曾吸食毒品（如苯丙胺、大麻或可卡因）。结果：受访者宣称驾驶约 14.62 小时（SD = 1.97）后才感到疲劳，过去 24 小时内平均睡眠时间约为 5.92 小时（SD = 0.96）。卡车司机一致认为，卡车装货/卸货的等待时间对其工作日的持续时间和休息时间有很大影响。研究采用了八种机器学习算法来估算卡车司机发生车祸的可能性，准确率在 78% 到 85% 之间。研究结论这些结果验证了准确的机器学习衍生模型的构建。实际应用：这些发现可以为旨在提高自雇卡车司机和广大公众的安全和福祉的政策和实践提供参考。

{"title":"Risk of crashes among self-employed truck drivers: Prevalence evaluation using fatigue data and machine learning prediction models","authors":"Rodrigo Duarte Soliani , Alisson Vinicius Brito Lopes , Fábio Santiago , Luiz Bueno da Silva , Nwabueze Emekwuru , Ana Carolina Lorena","doi":"10.1016/j.jsr.2024.11.002","DOIUrl":"10.1016/j.jsr.2024.11.002","url":null,"abstract":"<div><div><em>Introduction</em>: Transportation companies have increasingly shifted their workforce from permanent to outsourced roles, a trend that has consequences for self-employed truck drivers. This transition leads to extended working hours, resulting in fatigue and an increased risk of crashes. The present study investigates the factors contributing to fatigue and impairment in truck driving performance while developing a machine learning-based model for predicting the risk of traffic crashes. <em>Method:</em> To achieve this, a comprehensive questionnaire was designed, covering various aspects of the participants’ sociodemographic characteristics, health, sleep, and working conditions. The questionnaire was administered to 363 self-employed truck drivers operating in the State of São Paulo, Brazil. Approximately 63% of the participants were smokers, while 17.56% reported drinking alcohol more than four times a week, and also admitted to being involved in at least one crash in the last three years. Fifty percent of the respondents reported consuming drugs (such as amphetamines, marijuana, or cocaine). <em>Results:</em> The surveyed individuals declared driving for approximately 14.62 h (SD = 1.97) before they felt fatigued, with an average of approximately 5.92 h of sleep in the last 24 h (SD = 0.96). Truck drivers unanimously agreed that waiting times for truck loading/unloading significantly impact the duration of their working day and rest time. The study employed eight machine learning algorithms to estimate the likelihood of truck drivers being involved in crashes, achieving accuracy rates ranging between 78% and 85%. <em>Conclusions:</em> These results validated the construction of accurate machine learning-derived models. <em>Practical Applications</em>: These findings can inform policies and practices aimed at enhancing the safety and well-being of self-employed truck drivers and the broader public.</div></div>","PeriodicalId":48224,"journal":{"name":"Journal of Safety Research","volume":"92 ","pages":"Pages 68-80"},"PeriodicalIF":3.9,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Analyzing the time to death of pedestrian fatalities: A copula approach 分析行人死亡事故的死亡时间：共轭方法

IF 3.9 2区工程技术 Q1 ERGONOMICS

Journal of Safety Research

Pub Date : 2024-11-16 DOI: 10.1016/j.jsr.2024.11.007

Nafis Anwari , Tanmoy Bhowmik , Mohamed Abdel-Aty , Naveen Eluru , Juneyoung Park

Introduction: The study aims to investigate the instant fatality likelihood and time to death (lag time) of pedestrian fatalities using a copula-based joint modeling framework. The upper level model investigates whether or not the pedestrian died instantly, while the lower level model investigates time to death for pedestrians who did not die instantly. Method: The joint model was run on a dataset of 33,615 observations obtained from the Fatality Accident Reporting System for the 2015–2019 period. The effect of roadway and traffic characteristics were investigated on time to death using six copula structures along with their parameterized versions. Results: Gaussian parameterized copula was found to have the best fit. Weather, Driver age groups, Drunk/ distracted/ drowsy drivers, Hit and Run, Involvement of Large Truck, VRU age group, VRU Gender, Presence of Sidewalk, Presence of Intersection, Light Condition, and Speeding were significant common factors for both sub-models. The factors found to be significant exclusively to one of the sub-models include: Area type for the Binary Logit model, and Presence of Crosswalk and Fire station nearby for the Ordered Logit model. Conclusions: Instant fatality likelihood increased and lag time for non-instant fatalities decreased for 16–24 year old drivers, drunk drivers, during hit and run situations, when large trucks were involved, for the elderly pedestrians, for female pedestrians, during dark conditions, and when vehicles were speeding. On the other hand, instant fatality likelihood decreased and lag time for non-instant fatalities increased in adverse weather conditions, for elderly drivers, on sidewalks, at intersections, and during daylight hours. Practical applications: Results can be useful to transportation policymakers and practitioners in implementing countermeasures to improve road safety. These include placing sidewalks, various types of crosswalks, traffic calming measures, and adequate artificial lighting in areas frequented by pedestrians. Alcohol and drug testing need to be enforced.

简介本研究旨在利用基于 copula 的联合建模框架，研究行人死亡事故的当场死亡可能性和死亡时间（滞后时间）。上层模型研究行人是否当场死亡，下层模型研究未当场死亡的行人的死亡时间。方法：联合模型在 2015-2019 年期间从死亡事故报告系统中获得的 33615 个观测数据集上运行。使用六种 copula 结构及其参数化版本研究了道路和交通特征对死亡时间的影响。研究结果发现高斯参数化 copula 的拟合效果最好。天气、驾驶员年龄组、醉酒/分心/瞌睡驾驶员、肇事逃逸、涉及大型卡车、自愿驾驶员年龄组、自愿驾驶员性别、有无人行道、有无交叉路口、灯光条件和超速是两个子模型的显著共同因素。仅对其中一个子模型有显著影响的因素包括二元 Logit 模型中的地区类型，以及有序 Logit 模型中的人行横道和附近消防站的存在。结论对于 16-24 岁的司机、醉酒司机、肇事逃逸情况下、涉及大型卡车时、老年行人、女性行人、黑暗条件下以及车辆超速行驶时，即刻死亡的可能性增加，而非即刻死亡的滞后时间减少。另一方面，在恶劣天气条件下、老年驾驶员、人行道上、十字路口和白天，当场死亡的可能性降低，非当场死亡的滞后时间增加。实际应用：研究结果可帮助交通决策者和从业人员实施改善道路安全的对策。这些措施包括在行人经常出入的区域设置人行道、各种类型的人行横道、交通疏导措施和充足的人工照明。需要实施酒精和药物测试。

{"title":"Analyzing the time to death of pedestrian fatalities: A copula approach","authors":"Nafis Anwari , Tanmoy Bhowmik , Mohamed Abdel-Aty , Naveen Eluru , Juneyoung Park","doi":"10.1016/j.jsr.2024.11.007","DOIUrl":"10.1016/j.jsr.2024.11.007","url":null,"abstract":"<div><div><em>Introduction:</em> The study aims to investigate the instant fatality likelihood and time to death (lag time) of pedestrian fatalities using a copula-based joint modeling framework. The upper level model investigates whether or not the pedestrian died instantly, while the lower level model investigates time to death for pedestrians who did not die instantly. <em>Method:</em> The joint model was run on a dataset of 33,615 observations obtained from the Fatality Accident Reporting System for the 2015–2019 period. The effect of roadway and traffic characteristics were investigated on time to death using six copula structures along with their parameterized versions. <em>Results:</em> Gaussian parameterized copula was found to have the best fit. Weather, Driver age groups, Drunk/ distracted/ drowsy drivers, Hit and Run, Involvement of Large Truck, VRU age group, VRU Gender, Presence of Sidewalk, Presence of Intersection, Light Condition, and Speeding were significant common factors for both sub-models. The factors found to be significant exclusively to one of the sub-models include: Area type for the Binary Logit model, and Presence of Crosswalk and Fire station nearby for the Ordered Logit model. <em>Conclusions:</em> Instant fatality likelihood increased and lag time for non-instant fatalities decreased for 16–24 year old drivers, drunk drivers, during hit and run situations, when large trucks were involved, for the elderly pedestrians, for female pedestrians, during dark conditions, and when vehicles were speeding. On the other hand, instant fatality likelihood decreased and lag time for non-instant fatalities increased in adverse weather conditions, for elderly drivers, on sidewalks, at intersections, and during daylight hours. <em>Practical applications:</em> Results can be useful to transportation policymakers and practitioners in implementing countermeasures to improve road safety. These include placing sidewalks, various types of crosswalks, traffic calming measures, and adequate artificial lighting in areas frequented by pedestrians. Alcohol and drug testing need to be enforced.</div></div>","PeriodicalId":48224,"journal":{"name":"Journal of Safety Research","volume":"92 ","pages":"Pages 55-67"},"PeriodicalIF":3.9,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662463","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Latent class analysis of autonomous vehicle crashes 自动驾驶汽车碰撞事故的潜在类别分析

IF 3.9 2区工程技术 Q1 ERGONOMICS

Journal of Safety Research

Pub Date : 2024-11-16 DOI: 10.1016/j.jsr.2024.11.014

Jianfeng Qiao, Yanan Wang, Zixiu Zhao, Dawei Chen, Yanping Fu, Jie Hou

Introduction: Since September 2014, the California Department of Motor Vehicles has requested autonomous vehicle (AV) manufacturers to report their accidents if they take field tests on public roadways in California. These collision reports are heterogeneous containing a variety of accident factors. Method: To describe the accident more elaborately, we add three new category variables: ‘traffic control and status,’ ‘speed/speed change,’ and ‘type of accident location,’ extracted from crash narratives. Combining with the existing variables as model inputs, we use Latent Class Analysis (LCA) to investigate the mixture types of traffic accidents. After using ‘Mplus’ (LCA tool), the data set with 308 cases has been segmented into three clusters, including ‘rear-end collisions after the speed change of AV,’ ‘sideswipe collisions at parking places,’ and ‘hit-object collisions in normal traffic road.’ Results: These three clusters are not highlighted in previous literature and Cluster 1 shows AV should not be designed too ethically. To follow the driving habits of traditional drivers, AVs should accelerate vehicles quickly when they start to move and delay stopping in front of stop lines, traffic lights, and yielding. The cluster-based analyses show that applying LCA as a preliminary analysis can reveal the interesting hierarchical patterns hidden in the dataset and help traffic safety researchers improve AV safety performances.

导言：自 2014 年 9 月起，加利福尼亚州机动车辆管理局要求自动驾驶汽车（AV）制造商报告其在加利福尼亚州公共道路上进行实地测试时发生的事故。这些碰撞报告包含多种事故因素。方法：为了更详细地描述事故，我们添加了三个新的类别变量："交通管制和状态"、"速度/速度变化 "和 "事故地点类型"，这些变量都是从碰撞事故叙述中提取的。结合现有变量作为模型输入，我们使用潜类分析（LCA）来研究交通事故的混合类型。在使用 "Mplus"（LCA 工具）后，308 个案例的数据集被划分为三个群组，包括 "AV 车变速后的追尾碰撞"、"停车处的侧擦碰撞 "和 "正常交通道路上的撞击物体碰撞"。结果：这三个群组在以往的文献中并不突出，群组 1 表明 AV 的设计不应过于道德。为了遵循传统驾驶员的驾驶习惯，AV 应在车辆开始行驶时迅速加速，并在停车线、红绿灯和让行前延迟停车。基于聚类的分析表明，应用生命周期分析作为初步分析，可以揭示隐藏在数据集中的有趣的层次模式，帮助交通安全研究人员提高 AV 的安全性能。

{"title":"Latent class analysis of autonomous vehicle crashes","authors":"Jianfeng Qiao, Yanan Wang, Zixiu Zhao, Dawei Chen, Yanping Fu, Jie Hou","doi":"10.1016/j.jsr.2024.11.014","DOIUrl":"10.1016/j.jsr.2024.11.014","url":null,"abstract":"<div><div><em>Introduction:</em> Since September 2014, the California Department of Motor Vehicles has requested autonomous vehicle (AV) manufacturers to report their accidents if they take field tests on public roadways in California. These collision reports are heterogeneous containing a variety of accident factors. <em>Method:</em> To describe the accident more elaborately, we add three new category variables: ‘traffic control and status,’ ‘speed/speed change,’ and ‘type of accident location,’ extracted from crash narratives. Combining with the existing variables as model inputs, we use Latent Class Analysis (LCA) to investigate the mixture types of traffic accidents. After using ‘Mplus’ (LCA tool), the data set with 308 cases has been segmented into three clusters, including ‘rear-end collisions after the speed change of AV,’ ‘sideswipe collisions at parking places,’ and ‘hit-object collisions in normal traffic road.’ <em>Results:</em> These three clusters are not highlighted in previous literature and Cluster 1 shows AV should not be designed too ethically. To follow the driving habits of traditional drivers, AVs should accelerate vehicles quickly when they start to move and delay stopping in front of stop lines, traffic lights, and yielding. The cluster-based analyses show that applying LCA as a preliminary analysis can reveal the interesting hierarchical patterns hidden in the dataset and help traffic safety researchers improve AV safety performances.</div></div>","PeriodicalId":48224,"journal":{"name":"Journal of Safety Research","volume":"92 ","pages":"Pages 81-90"},"PeriodicalIF":3.9,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662501","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Predictors of driving errors contributing to crashes in older adults across age groups, 2010 to 2020 2010 年至 2020 年各年龄组老年人驾驶失误导致撞车事故的预测因素

IF 3.9 2区工程技术 Q1 ERGONOMICS

Journal of Safety Research

Pub Date : 2024-11-15 DOI: 10.1016/j.jsr.2024.11.010

Gilsu Pae , Jonathan Davis , Joseph Cavanaugh , Motao Zhu , Cara Hamann

Introduction: Given the largely autocentric nature of the United States, drivers continue to operate vehicles with varying levels of driving ability and self-restriction as they advance into older age. This study explores the associations of vehicle actions and traffic control devices with older drivers’ driving errors contributing to crashes, incorporating age group as effect modifiers of these relationships. Method: This study includes crashes reported to the Iowa Department of Transportation from 2010 to 2020. Analysis was completed for drivers involved in a crash who were aged 45 years and older (n = 254,912). Driving errors were identified based on driver contributing factors reported in the Iowa crash data. A multivariable logistic regression model was built to model predictors of driving errors, focusing on crash-related vehicle actions and traffic control devices. Additionally, interaction terms were incorporated to examine the moderating effect of age groups (45–64; 65–74; 75–84; 85+). Results: Driving errors increased with age, especially in the middle-old age group (75–84). A higher probability of driving errors was observed in changing lanes, merging, and turning, with right turns showing the most substantive increase in the middle-old age group compared to the other age groups. Stop and yield signs were associated with a higher probability of driving errors, increasing monotonically with age. The middle-old age group exhibited a notable increase in driving errors at uncontrolled or traffic signaled locations compared to the other age groups. Conclusions: The significant increase in driving errors at and beyond the middle-old age group may demonstrate higher age-related declines in safe driving compared to younger age groups. Practical Applications: Careful evaluations for older drivers’ fitness to drive during license renewal periods are needed once drivers reach the middle-old age. Additionally, effective combinations of advanced technologies, traffic systems, and policies are necessary to reduce the burdens associated with aging.

导言：由于美国基本上是以汽车为中心的国家，随着年龄的增长，驾驶员的驾驶能力和自我约束能力也在不断提高。本研究探讨了车辆操作和交通控制设备与老年驾驶员驾驶失误导致撞车事故之间的关系，并将年龄组作为这些关系的效应调节因子。研究方法：本研究包括 2010 年至 2020 年向爱荷华州交通局报告的撞车事故。分析对象为年龄在 45 岁及以上的车祸驾驶员（n = 254,912 人）。根据爱荷华州车祸数据中报告的驾驶员诱因确定了驾驶错误。我们建立了一个多变量逻辑回归模型来模拟驾驶失误的预测因素，重点关注与车祸相关的车辆行为和交通控制设备。此外，还加入了交互项，以检验年龄组（45-64 岁；65-74 岁；75-84 岁；85 岁以上）的调节作用。研究结果驾驶错误随着年龄的增长而增加，尤其是在中老年组（75-84 岁）。与其他年龄组相比，中老年组在变更车道、并线和转弯时出现驾驶错误的概率较高，其中右转弯的错误率增幅最大。停车和让行标志与较高的驾驶失误概率有关，随着年龄的增长而单调增加。与其他年龄组相比，中年组在不受控制或有交通信号的地点出现驾驶错误的概率明显增加。结论与年轻人相比，中年及中年以上年龄组的驾驶失误率明显增加，这可能表明与年龄相关的安全驾驶下降率更高。实际应用：一旦驾驶员达到中年年龄，就需要在驾驶执照更新期间对老年驾驶员的驾驶能力进行仔细评估。此外，有必要将先进技术、交通系统和政策有效结合起来，以减轻老龄化带来的负担。

{"title":"Predictors of driving errors contributing to crashes in older adults across age groups, 2010 to 2020","authors":"Gilsu Pae , Jonathan Davis , Joseph Cavanaugh , Motao Zhu , Cara Hamann","doi":"10.1016/j.jsr.2024.11.010","DOIUrl":"10.1016/j.jsr.2024.11.010","url":null,"abstract":"<div><div><em>Introduction:</em> Given the largely autocentric nature of the United States, drivers continue to operate vehicles with varying levels of driving ability and self-restriction as they advance into older age. This study explores the associations of vehicle actions and traffic control devices with older drivers’ driving errors contributing to crashes, incorporating age group as effect modifiers of these relationships. <em>Method:</em> This study includes crashes reported to the Iowa Department of Transportation from 2010 to 2020. Analysis was completed for drivers involved in a crash who were aged 45 years and older (n = 254,912). Driving errors were identified based on driver contributing factors reported in the Iowa crash data. A multivariable logistic regression model was built to model predictors of driving errors, focusing on crash-related vehicle actions and traffic control devices. Additionally, interaction terms were incorporated to examine the moderating effect of age groups (45–64; 65–74; 75–84; 85+). <em>Results:</em> Driving errors increased with age, especially in the middle-old age group (75–84). A higher probability of driving errors was observed in changing lanes, merging, and turning, with right turns showing the most substantive increase in the middle-old age group compared to the other age groups. Stop and yield signs were associated with a higher probability of driving errors, increasing monotonically with age. The middle-old age group exhibited a notable increase in driving errors at uncontrolled or traffic signaled locations compared to the other age groups. <em>Conclusions:</em> The significant increase in driving errors at and beyond the middle-old age group may demonstrate higher age-related declines in safe driving compared to younger age groups. <em>Practical Applications:</em> Careful evaluations for older drivers’ fitness to drive during license renewal periods are needed once drivers reach the middle-old age. Additionally, effective combinations of advanced technologies, traffic systems, and policies are necessary to reduce the burdens associated with aging.</div></div>","PeriodicalId":48224,"journal":{"name":"Journal of Safety Research","volume":"92 ","pages":"Pages 40-47"},"PeriodicalIF":3.9,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

A machine learning approach to understanding the road and traffic environments of crashes involving driver distraction and inattention (DDI) on rural multilane highways 采用机器学习方法了解农村多车道高速公路上涉及驾驶员分心和注意力不集中（DDI）的碰撞事故的道路和交通环境

IF 3.9 2区工程技术 Q1 ERGONOMICS

Journal of Safety Research

Pub Date : 2024-11-14 DOI: 10.1016/j.jsr.2024.11.011

Chenxuan Yang , Jun Liu , Zihe Zhang , Emmanuel Kofi Adanu , Praveena Penmetsa , Steven Jones

Introduction: Driver distraction and inattention (DDI) are major causes of road crashes, especially on rural highways. However, not all instances of distracted or inattentive driving lead to crashes. Previous studies indicate that DDI-related driving behavior is closely associated with low-traffic and less complex driving environments. Nevertheless, it is unclear if these traffic or road environments also increase the likelihood of crashes involving DDI. Method: This study employed machine learning algorithms to identify the factors contributing to DDI-involved crashes on rural highways. This study applied multiple machine learning models including the Light Gradient Boosting Model (LGBM), Random Forest (RF), and Neural Network (NN) to quantify the correlations of DDI-involved crashes related to road and traffic environments. The study leveraged a statewide crash database with unique roadway data that contains variables for median type (e.g., 4-ft flush medians) and roadside access point density. To deal with the extreme imbalance of data, two sampling methods (over and under-sampling) were used to balance the data for machine learning. Results: Modeling results indicated that the road and traffic environments that are strongly linked to DDI-involved crashes in general overlap with the environments that lead to DDI-related driving behavior, except for the truck volumes in traffic. Crashes that involved DDI were more likely to occur in environments with non-traversable medians (compared to 4-ft flush medians), lower-volume traffic, and greater access spacing on roadsides. With regard to truck volumes, a non-linear relationship with the occurrence of DDI-involved crashes was uncovered. Traffic with about 8 to 10% of trucks is associated with the highest likelihood of DDI-involved crashes. Practical Applications: This study provides valuable information for drivers who need to be careful while driving in certain environments with a risk of DDI-involved crashes and for agencies who need to take actions to address the issue of DDI under such environments.

简介驾驶员分心和注意力不集中（DDI）是造成道路交通事故的主要原因，尤其是在农村公路上。然而，并非所有分心或注意力不集中的驾驶行为都会导致车祸。以往的研究表明，与分心和注意力不集中相关的驾驶行为与低交通流量和不太复杂的驾驶环境密切相关。然而，目前还不清楚这些交通或道路环境是否也会增加涉及分心驾驶的撞车事故的可能性。方法：本研究采用机器学习算法来确定导致农村公路上发生涉及 DDI 的碰撞事故的因素。本研究采用了多种机器学习模型，包括轻梯度提升模型（LGBM）、随机森林（RF）和神经网络（NN），以量化与道路和交通环境相关的涉及 DDI 的碰撞事故的相关性。该研究利用了全州范围内的碰撞数据库，其中包含独特的道路数据，这些数据包含中间分隔带类型（如 4 英尺齐平中间分隔带）和路边出入口密度等变量。为了解决数据极度不平衡的问题，采用了两种采样方法（过度采样和不足采样）来平衡机器学习的数据。结果建模结果表明，与涉及 DDI 的交通事故密切相关的道路和交通环境总体上与导致 DDI 相关驾驶行为的环境重叠，但卡车交通量除外。在不可穿透的中间分隔带（与 4 英尺平齐中间分隔带相比）、车流量较小以及路边通道间距较大的环境中，更有可能发生涉及 DDI 的碰撞事故。在卡车交通量方面，发现 DDI 引发的碰撞事故与卡车交通量之间存在非线性关系。约 8%至 10%的卡车流量与发生涉及危险驾驶数据交换的碰撞事故的可能性最大。实际应用：这项研究为驾驶员提供了有价值的信息，他们在某些环境中驾驶时需要小心谨慎，因为这些环境有可能发生涉及 DDI 的碰撞事故，同时也为机构提供了有价值的信息，这些机构需要采取行动来解决此类环境下的 DDI 问题。

{"title":"A machine learning approach to understanding the road and traffic environments of crashes involving driver distraction and inattention (DDI) on rural multilane highways","authors":"Chenxuan Yang , Jun Liu , Zihe Zhang , Emmanuel Kofi Adanu , Praveena Penmetsa , Steven Jones","doi":"10.1016/j.jsr.2024.11.011","DOIUrl":"10.1016/j.jsr.2024.11.011","url":null,"abstract":"<div><div><em>Introduction</em>: Driver distraction and inattention (DDI) are major causes of road crashes, especially on rural highways. However, not all instances of distracted or inattentive driving lead to crashes. Previous studies indicate that DDI-related driving behavior is closely associated with low-traffic and less complex driving environments. Nevertheless, it is unclear if these traffic or road environments also increase the likelihood of crashes involving DDI. <em>Method</em>: This study employed machine learning algorithms to identify the factors contributing to DDI-involved crashes on rural highways. This study applied multiple machine learning models including the Light Gradient Boosting Model (LGBM), Random Forest (RF), and Neural Network (NN) to quantify the correlations of DDI-involved crashes related to road and traffic environments. The study leveraged a statewide crash database with unique roadway data that contains variables for median type (e.g., 4-ft flush medians) and roadside access point density. To deal with the extreme imbalance of data, two sampling methods (over and under-sampling) were used to balance the data for machine learning<em>. Results</em>: Modeling results indicated that the road and traffic environments that are strongly linked to DDI-involved crashes in general overlap with the environments that lead to DDI-related driving behavior, except for the truck volumes in traffic. Crashes that involved DDI were more likely to occur in environments with non-traversable medians (compared to 4-ft flush medians), lower-volume traffic, and greater access spacing on roadsides. With regard to truck volumes, a non-linear relationship with the occurrence of DDI-involved crashes was uncovered. Traffic with about 8 to 10% of trucks is associated with the highest likelihood of DDI-involved crashes. <em>Practical Applications:</em> This study provides valuable information for drivers who need to be careful while driving in certain environments with a risk of DDI-involved crashes and for agencies who need to take actions to address the issue of DDI under such environments.</div></div>","PeriodicalId":48224,"journal":{"name":"Journal of Safety Research","volume":"92 ","pages":"Pages 14-26"},"PeriodicalIF":3.9,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662459","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Safety assurance for automated systems in transport: A collective case study of real-world fatal crashes 交通自动化系统的安全保障：真实世界致命碰撞事故的集体案例研究

IF 3.9 2区工程技术 Q1 ERGONOMICS

Journal of Safety Research

Pub Date : 2024-11-14 DOI: 10.1016/j.jsr.2024.11.008

Stuart Ballingall, Majid Sarvi, Peter Sweatman

Introduction: Traditional vehicle safety assurance frameworks are challenged by Automated Driving Systems (ADSs) that enable dynamic driving tasks to be performed without active involvement of a human driver. Further, an ADS’s driving functionality can be changed during in-service operation, using software updates developed using Machine Learning (ML). Learnings from real-world cases will be a key input to reforming current regulatory frameworks to assure ADS safety. However, ADSs are yet to be deployed in mass volumes, and limited data are available regarding their in-service safety performance. Method: To overcome these limitations, a collective case study was undertaken, drawing upon three relevant real-world cases involving automated control systems that were a causative factor in major transport safety incidents. Results: A range of findings were identified, which informed recommendations for reform. The study found some assurance processes, decisions and oversight were not commensurate with risk or safety integrity levels, including a lack of independence with reviews and approvals for safety–critical system components. Two cases were also impacted by conflict or bias with regulatory approvals. Other commonalities included a lack of safeguards to ensure systems were not operated outside their design domain, and a lack of system redundancy to ensure safe operation if a system component fails. Further, the identification and validation of system responses to scenarios that could be encountered within design domain boundaries was lacking. For the two cases in which safety–critical functionality was developed using ML, it’s concerning no regulator reports provided detailed findings regarding the role of ML models, algorithms, or training data.

导言：自动驾驶系统（ADS）无需人类驾驶员的主动参与即可执行动态驾驶任务，这对传统的车辆安全保障框架提出了挑战。此外，自动驾驶系统的驾驶功能可在使用过程中通过使用机器学习（ML）开发的软件更新进行更改。从实际案例中汲取的经验将成为改革当前监管框架以确保自动驾驶辅助系统安全的关键投入。然而，自动驾驶辅助系统尚未大规模部署，有关其在役安全性能的数据也很有限。方法：为了克服这些局限性，我们进行了一项集体案例研究，借鉴了三个相关的真实案例，这些案例涉及自动控制系统，它们是重大运输安全事故的诱因。研究结果研究发现了一系列问题，并提出了改革建议。研究发现，一些保证流程、决策和监督与风险或安全完整性水平不相称，包括对安全关键系统组件的审查和批准缺乏独立性。两个案例还受到监管审批冲突或偏见的影响。其他共性还包括缺乏保障措施以确保系统不在设计范围之外运行，以及缺乏系统冗余以确保系统组件发生故障时的安全运行。此外，还缺乏对设计域范围内可能遇到的情况的系统响应的识别和验证。在使用 ML 开发安全关键功能的两个案例中，令人担忧的是，监管机构的报告没有提供有关 ML 模型、算法或训练数据作用的详细调查结果。

{"title":"Safety assurance for automated systems in transport: A collective case study of real-world fatal crashes","authors":"Stuart Ballingall, Majid Sarvi, Peter Sweatman","doi":"10.1016/j.jsr.2024.11.008","DOIUrl":"10.1016/j.jsr.2024.11.008","url":null,"abstract":"<div><div><em>Introduction</em>: Traditional vehicle safety assurance frameworks are challenged by Automated Driving Systems (ADSs) that enable dynamic driving tasks to be performed without active involvement of a human driver. Further, an ADS’s driving functionality can be changed during in-service operation, using software updates developed using Machine Learning (ML). Learnings from real-world cases will be a key input to reforming current regulatory frameworks to assure ADS safety. However, ADSs are yet to be deployed in mass volumes, and limited data are available regarding their in-service safety performance. <em>Method:</em> To overcome these limitations, a collective case study was undertaken, drawing upon three relevant real-world cases involving automated control systems that were a causative factor in major transport safety incidents. <em>Results:</em> A range of findings were identified, which informed recommendations for reform. The study found some assurance processes, decisions and oversight were not commensurate with risk or safety integrity levels, including a lack of independence with reviews and approvals for safety–critical system components. Two cases were also impacted by conflict or bias with regulatory approvals. Other commonalities included a lack of safeguards to ensure systems were not operated outside their design domain, and a lack of system redundancy to ensure safe operation if a system component fails. Further, the identification and validation of system responses to scenarios that could be encountered within design domain boundaries was lacking. For the two cases in which safety–critical functionality was developed using ML, it’s concerning no regulator reports provided detailed findings regarding the role of ML models, algorithms, or training data.</div></div>","PeriodicalId":48224,"journal":{"name":"Journal of Safety Research","volume":"92 ","pages":"Pages 27-39"},"PeriodicalIF":3.9,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662460","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Experimental and finite element analysis of rear impacts on bicycles with child seats 带儿童座椅自行车后部撞击的实验和有限元分析

IF 3.9 2区工程技术 Q1 ERGONOMICS

Journal of Safety Research

Pub Date : 2024-11-14 DOI: 10.1016/j.jsr.2024.10.008

Takaaki Terashima , Ryuga Miyata , Koji Mizuno

Introduction: In Japan, bicycles equipped with child seats have become popular in urban areas as a convenient means of transportation for preschool children. As such, it is necessary to conduct more studies and evaluations to prevent crashes and/or mitigate injuries of children in child-carrying bicycles. This study primarily aims to comprehend the kinematic behavior and injury risks to a child seated in a child seat attached to a bicycle when it is struck from the rear by a car. Method: First, collision tests were conducted to investigate the effects of bicycle tire sizes where a car collides against a bicycle with a rear-mounted child seat. The Hybrid III 3-year-old was seated in the child seat behind the Hybrid III 5F, representing a bicycle rider. Second, a finite element (FE) analysis was conducted for the same collision configurations as the tests. The FE analysis using Hybrid III dummy and THUMS models was employed, and the time frame was calculated from the moment the car began making contact with the bicycle to when the child collided with the adult. Results: The 26-inch tire bicycle lifted its front wheel upward, while the 20-inch tire bicycle pushed forward without lifting. The risk of injury to the child’s head was in the order of ground impact, adult rider impact, and vehicle hood impact. The FE analysis confirmed that both the child passenger and an adult rider could sustain injuries when contacting with each other. Conclusions: Our current study has demonstrated that the kinematic behavior of the bicycle and potential injuries to the child passenger and adult rider differed between bicycles with 26 and 20-inch tire sizes. Practical Applications: The findings are useful in the selection of bicycles suitable for child seats and in the design of child seats tailored to bicycles with different tire sizes.

导言在日本，装有儿童座椅的自行车作为学龄前儿童的便捷交通工具在城市地区很受欢迎。因此，有必要进行更多的研究和评估，以防止碰撞事故和/或减轻儿童在携带儿童的自行车上受到的伤害。本研究的主要目的是了解坐在自行车儿童座椅上的儿童被汽车从后方撞击时的运动行为和受伤风险。研究方法：首先，我们进行了碰撞测试，以研究汽车与装有后置儿童座椅的自行车相撞时，自行车轮胎尺寸的影响。Hybrid III 3 岁儿童坐在 Hybrid III 5F 后面的儿童座椅上，代表自行车骑行者。其次，对与测试相同的碰撞配置进行了有限元（FE）分析。使用 Hybrid III 假人和 THUMS 模型进行有限元分析，并计算了从汽车开始接触自行车到儿童与成人相撞的时间范围。结果：26 英寸轮胎的自行车前轮向上抬起，而 20 英寸轮胎的自行车则向前推，没有抬起。儿童头部受伤的风险依次为地面撞击、成人骑手撞击和汽车引擎盖撞击。有限元分析证实，儿童乘客和成人骑手在相互接触时都可能受伤。结论：我们目前的研究表明，26 英寸和 20 英寸轮胎规格的自行车的运动行为以及对儿童乘客和成人骑手可能造成的伤害是不同的。实际应用：研究结果有助于选择适合安装儿童座椅的自行车，也有助于设计适合不同轮胎尺寸自行车的儿童座椅。

{"title":"Experimental and finite element analysis of rear impacts on bicycles with child seats","authors":"Takaaki Terashima , Ryuga Miyata , Koji Mizuno","doi":"10.1016/j.jsr.2024.10.008","DOIUrl":"10.1016/j.jsr.2024.10.008","url":null,"abstract":"<div><div><em>Introduction:</em> In Japan, bicycles equipped with child seats have become popular in urban areas as a convenient means of transportation for preschool children. As such, it is necessary to conduct more studies and evaluations to prevent crashes and/or mitigate injuries of children in child-carrying bicycles. This study primarily aims to comprehend the kinematic behavior and injury risks to a child seated in a child seat attached to a bicycle when it is struck from the rear by a car. <em>Method:</em> First, collision tests were conducted to investigate the effects of bicycle tire sizes where a car collides against a bicycle with a rear-mounted child seat. The Hybrid III 3-year-old was seated in the child seat behind the Hybrid III 5F, representing a bicycle rider. Second, a finite element (FE) analysis was conducted for the same collision configurations as the tests. The FE analysis using Hybrid III dummy and THUMS models was employed, and the time frame was calculated from the moment the car began making contact with the bicycle to when the child collided with the adult. <em>Results:</em> The 26-inch tire bicycle lifted its front wheel upward, while the 20-inch tire bicycle pushed forward without lifting. The risk of injury to the child’s head was in the order of ground impact, adult rider impact, and vehicle hood impact. The FE analysis confirmed that both the child passenger and an adult rider could sustain injuries when contacting with each other. <em>Conclusions:</em> Our current study has demonstrated that the kinematic behavior of the bicycle and potential injuries to the child passenger and adult rider differed between bicycles with 26 and 20-inch tire sizes. <em>Practical Applications:</em> The findings are useful in the selection of bicycles suitable for child seats and in the design of child seats tailored to bicycles with different tire sizes.</div></div>","PeriodicalId":48224,"journal":{"name":"Journal of Safety Research","volume":"91 ","pages":"Pages 437-446"},"PeriodicalIF":3.9,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142653095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

A large language model framework to uncover underreporting in traffic crashes 发现交通事故漏报的大型语言模型框架

IF 3.9 2区工程技术 Q1 ERGONOMICS

Journal of Safety Research

Pub Date : 2024-11-13 DOI: 10.1016/j.jsr.2024.11.009

Cristian Arteaga, JeeWoong Park

Introduction: Crash reports support the development of traffic safety countermeasures, but these reports often suffer from underreporting of crucial crash factors due to miscoded entries during data collection. To rectify these issues, the current practice relies on manual information rectification, which is time consuming and error prone, especially with large data volumes. To address these hurdles, we develop a framework to analyze traffic crash narratives and uncover underreported crash factors by capitalizing on the capabilities of Large Language Models (LLM). Method: The framework integrates procedures for prompt definition, selection of LLM generation parameters, output parsing, and underreporting determination. For evaluation, we present a case study on identification of underreported alcohol involvement in traffic crashes. We investigate the framework’s identification accuracy in relation to different underlying LLMs (i.e., ChatGPT, Flan-UL2, and Llama-2), prompt framings (i.e., explicit vs. implicit matching), and generation parameters (i.e., sampling temperature and nucleus probability). Our validation dataset consists of 500 crash reports from the State of Massachusetts. Results: Analysis results demonstrate that the developed framework achieves a recall and precision of up to 1.0 and 0.93, respectively, indicating a successful retrieval of underreported instances. These findings indicate that the developed framework addresses a critical gap in the existing traffic safety analysis workflow by enabling safety analysts to uncover underreporting in crash data efficiently and accurately, without the need for extensive expertise in natural language processing. Practical Applications: Thus, the developed approach offers unprecedented opportunities to maximize the quality and comprehensiveness of traffic crash records, paving the way for more effective countermeasure development.

导言：碰撞事故报告为交通安全对策的制定提供了支持，但由于数据收集过程中的误码输入，这些报告经常会出现关键碰撞因素报告不足的问题。为了纠正这些问题，目前的做法是依靠人工纠正信息，这既耗时又容易出错，尤其是在数据量较大的情况下。为了解决这些问题，我们开发了一个框架，利用大型语言模型 (LLM) 的功能来分析交通事故叙述，并揭示未充分报告的事故因素。方法：该框架整合了提示定义、LLM 生成参数选择、输出解析和漏报确定等程序。为了进行评估，我们提出了一个案例研究，用于识别交通事故中少报的酒精参与情况。我们根据不同的底层 LLM（即 ChatGPT、Flan-UL2 和 Llama-2）、提示框架（即显式匹配与隐式匹配）和生成参数（即采样温度和核概率）来研究该框架的识别准确性。我们的验证数据集包括来自马萨诸塞州的 500 份碰撞报告。分析结果分析结果表明，所开发框架的召回率和精确率分别高达 1.0 和 0.93，表明成功检索了未充分报告的实例。这些结果表明，所开发的框架解决了现有交通安全分析工作流程中的一个关键缺口，使安全分析人员能够高效、准确地发现碰撞数据中的漏报情况，而无需具备丰富的自然语言处理专业知识。实际应用：因此，所开发的方法为最大限度地提高交通事故记录的质量和全面性提供了前所未有的机会，为更有效地制定对策铺平了道路。

{"title":"A large language model framework to uncover underreporting in traffic crashes","authors":"Cristian Arteaga, JeeWoong Park","doi":"10.1016/j.jsr.2024.11.009","DOIUrl":"10.1016/j.jsr.2024.11.009","url":null,"abstract":"<div><div><em>Introduction:</em> Crash reports support the development of traffic safety countermeasures, but these reports often suffer from underreporting of crucial crash factors due to miscoded entries during data collection. To rectify these issues, the current practice relies on manual information rectification, which is time consuming and error prone, especially with large data volumes. To address these hurdles, we develop a framework to analyze traffic crash narratives and uncover underreported crash factors by capitalizing on the capabilities of Large Language Models (LLM). <em>Method:</em> The framework integrates procedures for prompt definition, selection of LLM generation parameters, output parsing, and underreporting determination. For evaluation, we present a case study on identification of underreported alcohol involvement in traffic crashes. We investigate the framework’s identification accuracy in relation to different underlying LLMs (i.e., ChatGPT, Flan-UL2, and Llama-2), prompt framings (i.e., explicit vs. implicit matching), and generation parameters (i.e., sampling temperature and nucleus probability). Our validation dataset consists of 500 crash reports from the State of Massachusetts. <em>Results:</em> Analysis results demonstrate that the developed framework achieves a recall and precision of up to 1.0 and 0.93, respectively, indicating a successful retrieval of underreported instances. These findings indicate that the developed framework addresses a critical gap in the existing traffic safety analysis workflow by enabling safety analysts to uncover underreporting in crash data efficiently and accurately, without the need for extensive expertise in natural language processing. <em>Practical Applications:</em> Thus, the developed approach offers unprecedented opportunities to maximize the quality and comprehensiveness of traffic crash records, paving the way for more effective countermeasure development.</div></div>","PeriodicalId":48224,"journal":{"name":"Journal of Safety Research","volume":"92 ","pages":"Pages 1-13"},"PeriodicalIF":3.9,"publicationDate":"2024-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662539","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Drivers’ long-term crash risks associated with being ticketed for speeding 驾驶员因超速被开罚单而面临的长期撞车风险

IF 3.9 2区工程技术 Q1 ERGONOMICS

Journal of Safety Research

Pub Date : 2024-11-07 DOI: 10.1016/j.jsr.2024.10.009

Darren Walton , Ross Hendy

Introduction: This research analyzes the relationship between police-issued tickets for speeding and the crash risk of those drivers, in New Zealand, between 2015–2019. Method: The main data are constructed through data-matching license details of crash outcomes with all officer-issued tickets for speeding between 2015–2016 (N = 534,935). The sub-group of drivers that accumulate tickets is compared to a coarsened exact matched set of drivers of the same age. Results: There is a strong relationship between the number of tickets a person has in a two-year period (2015–16) and the likelihood of a crash outcome (2017–2019). However, the accumulation of tickets is not the best predictor of crash likelihood. A combination of the excess in speed and the accumulation of tickets increases the relative odds of a subsequent crash. These results are discussed considering the threshold at which New Zealand criminalizes alcohol-relating offending (notionally 4.2 times the base rate crash risk). The same rate of elevated crash risk exists when a driver has one ticket for being 10 km/h over the speed limit and has another speeding ticket within two years.

导言：本研究分析了 2015-2019 年间新西兰警方开出的超速罚单与这些司机的撞车风险之间的关系。研究方法：主要数据是通过将碰撞结果的驾驶执照详细信息与 2015-2016 年间所有警官开出的超速罚单（N = 534,935 ）进行数据匹配而构建的。累积罚单的驾驶员子群与经过粗略精确匹配的同龄驾驶员子群进行比较。结果显示一个人在两年内（2015-2016 年）的罚单数量与发生碰撞结果的可能性（2017-2019 年）之间存在密切关系。然而，罚单的累积并不是预测车祸可能性的最佳指标。超速和罚单累积的结合会增加随后发生碰撞的相对几率。在讨论这些结果时，我们考虑了新西兰将与酒精有关的违法行为定为刑事犯罪的临界值（名义上是基准碰撞风险的 4.2 倍）。当一名驾驶员因超速 10 公里/小时而被开罚单，并在两年内再次被开超速罚单时，发生车祸的风险率也会升高。

{"title":"Drivers’ long-term crash risks associated with being ticketed for speeding","authors":"Darren Walton , Ross Hendy","doi":"10.1016/j.jsr.2024.10.009","DOIUrl":"10.1016/j.jsr.2024.10.009","url":null,"abstract":"<div><div><em>Introduction</em>: This research analyzes the relationship between police-issued tickets for speeding and the crash risk of those drivers, in New Zealand, between 2015–2019. <em>Method</em>: The main data are constructed through data-matching license details of crash outcomes with all officer-issued tickets for speeding between 2015–2016 (N = 534,935). The sub-group of drivers that accumulate tickets is compared to a coarsened exact matched set of drivers of the same age. <em>Results:</em> There is a strong relationship between the number of tickets a person has in a two-year period (2015–16) and the likelihood of a crash outcome (2017–2019). However, the accumulation of tickets is not the best predictor of crash likelihood. A combination of the excess in speed <em>and</em> the accumulation of tickets increases the relative odds of a subsequent crash. These results are discussed considering the threshold at which New Zealand criminalizes alcohol-relating offending (notionally 4.2 times the base rate crash risk). The same rate of elevated crash risk exists when a driver has one ticket for being 10 km/h over the speed limit and has another speeding ticket within two years.</div></div>","PeriodicalId":48224,"journal":{"name":"Journal of Safety Research","volume":"91 ","pages":"Pages 431-436"},"PeriodicalIF":3.9,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142653096","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Factors influencing behavioral intentions to use conditionally automated vehicles 影响使用有条件自动驾驶汽车行为意向的因素

IF 3.9 2区工程技术 Q1 ERGONOMICS

Journal of Safety Research

Pub Date : 2024-10-28 DOI: 10.1016/j.jsr.2024.10.006

Sjaan Koppel , David B. Logan , Xin Zou , Fareed Kaviani , Hayley McDonald , Joseph F. Hair Jr , Renée M. St. Louis , Lisa J. Molnar , Judith L. Charlton

Background: This study explored factors influencing the acceptance of conditionally automated vehicles among Australian drivers by extending the Technology Acceptance Model with the Technology Readiness Index. Method: Data from an online survey of 844 participants were analyzed using partial least squares structural equation modeling (PLS-SEM). Results: Perceived usefulness had the strongest direct effect on behavioral intention (0.469, p < 0.001), followed by attitude (0.318, p < 0.001). Innovativeness positively influenced behavioral intention (0.183, p < 0.001), while insecurity had a negative impact (−0.071, p < 0.01). Optimism and discomfort were not significant. Perceived usefulness also had significant indirect effects through attitude (0.156, p < 0.001) and trust (0.072, p < 0.001). Perceived ease of use indirectly influenced behavioral intention through perceived usefulness (0.306, p < 0.001), attitude (0.102, p < 0.001), trust (0.047, p < 0.001), and their combinations. Trust indirectly affected behavioral intention via attitude (0.130, p < 0.001). Perceived security and privacy risks had indirect negative effects through trust and attitude (−0.035, p < 0.001; −0.005, p < 0.05). Conclusion: These results suggest that fostering acceptance among less tech-savvy individuals may help promote positive attitudes, increase conditionally automated vehicle adoption, and potentially enhance road safety. Practical implications: These findings suggest a need for targeted programs to enhance perceived usefulness and trust while addressing security and privacy concerns, ultimately contributing to safer road systems through the adoption of conditionally automated vehicles.

研究背景本研究通过扩展技术接受模型与技术准备指数，探讨影响澳大利亚驾驶员接受有条件自动驾驶汽车的因素。研究方法采用偏最小二乘法结构方程模型（PLS-SEM）对 844 名参与者的在线调查数据进行分析。结果显示感知有用性对行为意向的直接影响最大（0.469，p <0.001），其次是态度（0.318，p <0.001）。创新性对行为意向有积极影响（0.183，p <0.001），而不安全感则有消极影响（-0.071，p <0.01）。乐观和不适感没有显著影响。感知有用性还通过态度（0.156，p < 0.001）和信任（0.072，p < 0.001）产生了显著的间接影响。感知易用性通过感知有用性（0.306，p < 0.001）、态度（0.102，p < 0.001）、信任（0.047，p < 0.001）及其组合间接影响行为意向。信任通过态度间接影响行为意向（0.130，p < 0.001）。感知到的安全和隐私风险通过信任和态度间接产生负面影响（-0.035，p < 0.001；-0.005，p < 0.05）。结论这些结果表明，促进对技术不太了解的人接受自动驾驶汽车可能有助于促进积极的态度，提高有条件自动驾驶汽车的采用率，并有可能加强道路安全。实际意义：这些研究结果表明，在解决安全和隐私问题的同时，有必要制定有针对性的计划来提高人们的实用性和信任度，最终通过有条件自动驾驶汽车的采用来提高道路系统的安全性。

{"title":"Factors influencing behavioral intentions to use conditionally automated vehicles","authors":"Sjaan Koppel , David B. Logan , Xin Zou , Fareed Kaviani , Hayley McDonald , Joseph F. Hair Jr , Renée M. St. Louis , Lisa J. Molnar , Judith L. Charlton","doi":"10.1016/j.jsr.2024.10.006","DOIUrl":"10.1016/j.jsr.2024.10.006","url":null,"abstract":"<div><div><em>Background:</em> This study explored factors influencing the acceptance of conditionally automated vehicles among Australian drivers by extending the Technology Acceptance Model with the Technology Readiness Index. <em>Method:</em> Data from an online survey of 844 participants were analyzed using partial least squares structural equation modeling (PLS-SEM). <em>Results:</em> Perceived usefulness had the strongest direct effect on behavioral intention (0.469, p < 0.001), followed by attitude (0.318, p < 0.001). Innovativeness positively influenced behavioral intention (0.183, p < 0.001), while insecurity had a negative impact (−0.071, p < 0.01). Optimism and discomfort were not significant. Perceived usefulness also had significant indirect effects through attitude (0.156, p < 0.001) and trust (0.072, p < 0.001). Perceived ease of use indirectly influenced behavioral intention through perceived usefulness (0.306, p < 0.001), attitude (0.102, p < 0.001), trust (0.047, p < 0.001), and their combinations. Trust indirectly affected behavioral intention via attitude (0.130, p < 0.001). Perceived security and privacy risks had indirect negative effects through trust and attitude (−0.035, p < 0.001; −0.005, p < 0.05). <em>Conclusion:</em> These results suggest that fostering acceptance among less tech-savvy individuals may help promote positive attitudes, increase conditionally automated vehicle adoption, and potentially enhance road safety. <em>Practical implications:</em> These findings suggest a need for targeted programs to enhance perceived usefulness and trust while addressing security and privacy concerns, ultimately contributing to safer road systems through the adoption of conditionally automated vehicles.</div></div>","PeriodicalId":48224,"journal":{"name":"Journal of Safety Research","volume":"91 ","pages":"Pages 423-430"},"PeriodicalIF":3.9,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142532197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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