IATSS Research最新文献_第5页

Analysing the effectiveness of unsignalized crossing infrastructure in improving pedestrian safety using multiple data-driven approaches 利用多种数据驱动方法分析无信号交叉口基础设施改善行人安全的有效性

IF 3.2 Q3 TRANSPORTATION

IATSS Research

Pub Date : 2025-07-01 Epub Date: 2025-06-23 DOI: 10.1016/j.iatssr.2025.06.002

Shengqi Liu, Harry Evdorides

This study investigates the effectiveness of unsignalized crossings to enhance pedestrian safety through a robust data-driven approach utilizing multiple machine learning models, including the statistical classifier Logistic Regression, Decision Tree, Random Forest, and Neural Network Multi-Layer Perceptron (MLP). While numerous studies have applied predictive models to traffic crash data, few have systematically analysed pedestrian crash severity at unsignalized crossings using multiple machine learning algorithms. By leveraging historical crash data from the UK's STATS19 database, key factors influencing pedestrian safety at unsignalized crossings were identified and analysed. The research highlights the superior predictive performance of Random Forest and MLP models, with accuracies of 84 % and 86 %, respectively, underscoring their capability to handle complex, nonlinear relationships in crash data. Feature importance analysis revealed critical determinants of crash severity. The findings emphasize the need for targeted interventions to mitigate crash severity of crash outcomes. Despite challenges like underreporting and data imputation biases, this study provides valuable insights into the role of infrastructure in pedestrian safety, offering a foundation for policy recommendations and future research on improving unsignalized crossing designs.

本研究利用多种机器学习模型，包括统计分类器逻辑回归、决策树、随机森林和神经网络多层感知器（MLP），通过稳健的数据驱动方法，研究了无信号交叉口提高行人安全的有效性。虽然许多研究已经将预测模型应用于交通事故数据，但很少有研究使用多种机器学习算法系统地分析无信号交叉路口的行人碰撞严重程度。通过利用英国STATS19数据库的历史碰撞数据，确定并分析了影响无信号交叉口行人安全的关键因素。研究强调了随机森林和MLP模型的卓越预测性能，准确率分别为84%和86%，强调了它们处理碰撞数据中复杂、非线性关系的能力。特征重要性分析揭示了碰撞严重程度的关键决定因素。研究结果强调了有针对性的干预措施的必要性，以减轻碰撞后果的严重程度。尽管存在低报和数据输入偏差等挑战，但本研究为基础设施在行人安全中的作用提供了有价值的见解，为改善无信号交叉口设计的政策建议和未来研究提供了基础。

{"title":"Analysing the effectiveness of unsignalized crossing infrastructure in improving pedestrian safety using multiple data-driven approaches","authors":"Shengqi Liu, Harry Evdorides","doi":"10.1016/j.iatssr.2025.06.002","DOIUrl":"10.1016/j.iatssr.2025.06.002","url":null,"abstract":"<div><div>This study investigates the effectiveness of unsignalized crossings to enhance pedestrian safety through a robust data-driven approach utilizing multiple machine learning models, including the statistical classifier Logistic Regression, Decision Tree, Random Forest, and Neural Network Multi-Layer Perceptron (MLP). While numerous studies have applied predictive models to traffic crash data, few have systematically analysed pedestrian crash severity at unsignalized crossings using multiple machine learning algorithms. By leveraging historical crash data from the UK's STATS19 database, key factors influencing pedestrian safety at unsignalized crossings were identified and analysed. The research highlights the superior predictive performance of Random Forest and MLP models, with accuracies of 84 % and 86 %, respectively, underscoring their capability to handle complex, nonlinear relationships in crash data. Feature importance analysis revealed critical determinants of crash severity. The findings emphasize the need for targeted interventions to mitigate crash severity of crash outcomes. Despite challenges like underreporting and data imputation biases, this study provides valuable insights into the role of infrastructure in pedestrian safety, offering a foundation for policy recommendations and future research on improving unsignalized crossing designs.</div></div>","PeriodicalId":47059,"journal":{"name":"IATSS Research","volume":"49 2","pages":"Pages 271-279"},"PeriodicalIF":3.2,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144338963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Understanding psychological factors behind motorcyclists crossing behavior on undivided roads in mixed traffic conditions: A case study of Hau Giang, Vietnam 了解混合交通条件下摩托车手在未分割道路上穿越行为背后的心理因素：以越南Hau Giang为例

IF 3.2 Q3 TRANSPORTATION

IATSS Research

Pub Date : 2025-07-01 Epub Date: 2025-03-22 DOI: 10.1016/j.iatssr.2025.02.003

Hai Ngoc Duong , Minh Cong Chu , Nathan Huynh

Motorcycle crashes are a common occurrence in developing countries with mixed traffic. A contributing factor to these crashes is the crossing maneuvers of motorcyclists on undivided roadways. This study applies the Theory of Planned Behavior to understand the intentions and behaviors of these motorcyclists when making such maneuvers. It utilizes data from two surveys conducted in Hau Giang, Vietnam in 2022. The first investigation surveyed 351 participants to elicit the motorcyclists' behavioral beliefs and control beliefs when making crossing maneuvers that complied with traffic rules (complying maneuvers, CM), and the second investigation interviewed 260 respondents to elicit motorcyclists' beliefs when making crossing maneuvers that violated traffic rules (illegal maneuvers, IM). By applying the Structural Equation Modeling approach, the results reveal that the intention of motorcyclists to perform crossing maneuvers (CMs) is influenced by facilitating circumstances, subjective norms, and descriptive norms. In contrast, the intention to perform improper maneuvers (IMs) is driven by advantage beliefs, descriptive norms, facilitating circumstances, subjective norms, and driving situation awareness. Additionally, risk perception directly affects motorcyclists' performance of CMs, while near-miss incidents related to IMs are directly influenced by facilitating circumstances and perceived risk. These findings suggest that reducing improper maneuvers and promoting safer road-crossing performance can be achieved through targeted safety intervention strategies. Such strategies could include addressing the consequences of advantage beliefs regarding IMs and enhancing riders' situation awareness and risk perception through driver education and training programs.

摩托车撞车事故在混合交通的发展中国家很常见。造成这些事故的一个因素是摩托车手在未分割的道路上的穿越动作。本研究运用计划行为理论来理解这些摩托车手在进行此类机动时的意图和行为。它利用了2022年在越南豪江进行的两次调查的数据。第一次调查通过对351名被试进行问卷调查，引出摩托车手在符合交通规则的情况下的行为信念和控制信念；第二次调查通过对260名被试进行问卷调查，引出摩托车手在违反交通规则的情况下的行为信念和控制信念。运用结构方程建模方法，研究结果表明：机动车驾驶员的穿越意愿受便利环境、主观规范和描述性规范的影响。相反，执行不当操作的意图是由优势信念、描述性规范、促进环境、主观规范和驱动情景意识驱动的。此外，风险感知直接影响摩托车手的医疗管理绩效，而与医疗管理相关的未遂事件直接受到便利环境和感知风险的影响。这些研究结果表明，通过有针对性的安全干预策略，可以减少不适当的操作，促进更安全的过马路行为。这些策略可以包括解决关于即时交通的优势信念的后果，并通过驾驶员教育和培训计划提高乘客的情况意识和风险感知。

{"title":"Understanding psychological factors behind motorcyclists crossing behavior on undivided roads in mixed traffic conditions: A case study of Hau Giang, Vietnam","authors":"Hai Ngoc Duong , Minh Cong Chu , Nathan Huynh","doi":"10.1016/j.iatssr.2025.02.003","DOIUrl":"10.1016/j.iatssr.2025.02.003","url":null,"abstract":"<div><div>Motorcycle crashes are a common occurrence in developing countries with mixed traffic. A contributing factor to these crashes is the crossing maneuvers of motorcyclists on undivided roadways. This study applies the Theory of Planned Behavior to understand the intentions and behaviors of these motorcyclists when making such maneuvers. It utilizes data from two surveys conducted in Hau Giang, Vietnam in 2022. The first investigation surveyed 351 participants to elicit the motorcyclists' behavioral beliefs and control beliefs when making crossing maneuvers that complied with traffic rules (complying maneuvers, CM), and the second investigation interviewed 260 respondents to elicit motorcyclists' beliefs when making crossing maneuvers that violated traffic rules (illegal maneuvers, IM). By applying the Structural Equation Modeling approach, the results reveal that the intention of motorcyclists to perform crossing maneuvers (CMs) is influenced by facilitating circumstances, subjective norms, and descriptive norms. In contrast, the intention to perform improper maneuvers (IMs) is driven by advantage beliefs, descriptive norms, facilitating circumstances, subjective norms, and driving situation awareness. Additionally, risk perception directly affects motorcyclists' performance of CMs, while near-miss incidents related to IMs are directly influenced by facilitating circumstances and perceived risk. These findings suggest that reducing improper maneuvers and promoting safer road-crossing performance can be achieved through targeted safety intervention strategies. Such strategies could include addressing the consequences of advantage beliefs regarding IMs and enhancing riders' situation awareness and risk perception through driver education and training programs.</div></div>","PeriodicalId":47059,"journal":{"name":"IATSS Research","volume":"49 2","pages":"Pages 114-126"},"PeriodicalIF":3.2,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143686355","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Perceptions of pedestrian safety in Delhi: A Rasch analysis approach 德里行人安全认知：一种Rasch分析方法

IF 3.2 Q3 TRANSPORTATION

IATSS Research

Pub Date : 2025-07-01 Epub Date: 2025-04-18 DOI: 10.1016/j.iatssr.2025.04.003

Neba C Tony , Geetam Tiwari , Taku Fujiyama , M. Manoj , Niladri Chatterjee

Safety perception about the built environment influences a pedestrian's walking and crossing decisions. Rasch analysis, a relatively underutilized psychometric technique in the road safety domain, can provide deep insights into pedestrian's perceptions and decision making process. This paper evaluates pedestrian safety perception based on built environment features in Delhi, India. Pedestrians' perceptions of built environment was collected and analyzed using the Rasch technique to simultaneously compute pedestrian performances and safety constructs. The analysis highlights key areas that need immediate interventions. Results revealed that most safety-related constructs are beyond the safety thresholds of even the most capable pedestrians, suggesting that the general pedestrian environment in Delhi is hostile to walking. This paper also discusses the implications of Rasch analysis for revising survey questions, providing valuable insights for early researchers about survey questionnaire design.

对建筑环境的安全感知影响着行人的行走和过马路决策。Rasch分析是一种在道路安全领域尚未得到充分利用的心理测量技术，它可以深入了解行人的感知和决策过程。本文基于印度德里的建筑环境特征对行人安全感知进行了评价。使用Rasch技术收集和分析行人对建筑环境的感知，同时计算行人性能和安全结构。分析强调了需要立即干预的关键领域。结果显示，即使是最有能力的行人，大多数与安全相关的结构也超过了安全阈值，这表明德里的一般行人环境对步行不利。本文还讨论了Rasch分析对问卷问题修改的启示，为早期研究者对问卷设计提供了有价值的见解。

引用次数: 0

Unpacking the relationship between task complexity and driving risk: Insights from a UK on-road trial 解开任务复杂性和驾驶风险之间的关系：来自英国道路试验的见解

IF 3.2 Q3 TRANSPORTATION

IATSS Research

Pub Date : 2025-07-01 Epub Date: 2025-03-28 DOI: 10.1016/j.iatssr.2025.03.003

Evita Papazikou , Rachel Talbot , Laurie Brown , Sally Maynard , Ashleigh Filtness

This study investigates the intricate relationship between task complexity and driving risk through a comprehensive four-phase on-road trial conducted in the UK. Employing Structural Equation Modelling (SEM), the research illuminates the factors influencing task complexity and its association with risk, treating both as latent concepts—unobservable variables in the study. The findings reveal a notable positive correlation between task complexity and risk, particularly concerning the headway indicator. In essence, the study demonstrates that an escalation in task complexity corresponds to an increased level of risk.

Throughout the four SEM analyses performed across two waves of on-road trials, the time spent in each safety tolerance zone level for headway measurements emerges as a key indicator of the latent construct of risk in all phases. Notably, the variables constituting the latent concept of task complexity—those proven statistically significant—show slight variations across phases. Variables consistently significant across all phases include the number of right Lane Departure Warnings (LDWs) per 30 s and the day of the week.

The models reveal the feasibility of quantifying the risk-task complexity relationship in real-world driving settings. This study provides insights to inform efforts to mitigate risk exposure through design and training interventions, targeting the most predictive factors linked to task complexity. Driver demographics did not emerge as statistically significant, emphasising the need for a holistic approach to improve road safety.

本研究通过在英国进行的一项全面的四阶段道路试验，调查了任务复杂性和驾驶风险之间的复杂关系。本研究采用结构方程模型（SEM），阐明了影响任务复杂性的因素及其与风险的关系，并将两者视为潜在概念-研究中的不可观察变量。研究结果显示，任务复杂性和风险之间存在显著的正相关关系，特别是在车头时距指标方面。从本质上讲，这项研究表明，任务复杂性的升级对应于风险水平的增加。在两波道路试验中进行的四次扫描电镜分析中，车头时距测量在每个安全容忍区水平上花费的时间成为所有阶段潜在风险构建的关键指标。值得注意的是，构成任务复杂性潜在概念的变量——那些被证明具有统计学意义的变量——在不同阶段表现出轻微的变化。在所有阶段中，重要的变量包括每30秒和一周中的哪一天发出的右车道偏离警告（ldw）的次数。这些模型揭示了在现实驾驶环境中量化风险-任务复杂性关系的可行性。这项研究为通过设计和培训干预措施来降低风险暴露的努力提供了见解，目标是与任务复杂性相关的最可预测因素。驾驶员的人口统计数据在统计上并不显著，这强调了需要采取整体方法来改善道路安全。

{"title":"Unpacking the relationship between task complexity and driving risk: Insights from a UK on-road trial","authors":"Evita Papazikou , Rachel Talbot , Laurie Brown , Sally Maynard , Ashleigh Filtness","doi":"10.1016/j.iatssr.2025.03.003","DOIUrl":"10.1016/j.iatssr.2025.03.003","url":null,"abstract":"<div><div>This study investigates the intricate relationship between task complexity and driving risk through a comprehensive four-phase on-road trial conducted in the UK. Employing Structural Equation Modelling (SEM), the research illuminates the factors influencing task complexity and its association with risk, treating both as latent concepts—unobservable variables in the study. The findings reveal a notable positive correlation between task complexity and risk, particularly concerning the headway indicator. In essence, the study demonstrates that an escalation in task complexity corresponds to an increased level of risk.</div><div>Throughout the four SEM analyses performed across two waves of on-road trials, the time spent in each safety tolerance zone level for headway measurements emerges as a key indicator of the latent construct of risk in all phases. Notably, the variables constituting the latent concept of task complexity—those proven statistically significant—show slight variations across phases. Variables consistently significant across all phases include the number of right Lane Departure Warnings (LDWs) per 30 s and the day of the week.</div><div>The models reveal the feasibility of quantifying the risk-task complexity relationship in real-world driving settings. This study provides insights to inform efforts to mitigate risk exposure through design and training interventions, targeting the most predictive factors linked to task complexity. Driver demographics did not emerge as statistically significant, emphasising the need for a holistic approach to improve road safety.</div></div>","PeriodicalId":47059,"journal":{"name":"IATSS Research","volume":"49 2","pages":"Pages 127-136"},"PeriodicalIF":3.2,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143714511","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

E-scooter riders: A cross-cultural analysis of traffic safety attitudes and behaviors 电动踏板车使用者：交通安全态度与行为的跨文化分析

IF 3.2 Q3 TRANSPORTATION

IATSS Research

Pub Date : 2025-07-01 Epub Date: 2025-06-09 DOI: 10.1016/j.iatssr.2025.05.002

Milad Delavary , Craig Lyon , Ward G.M. Vanlaar , Robyn D. Robertson , Dimitrios Nikolaou , George Yannis

The rapid adoption of electric scooters (e-scooters) has transformed urban mobility, offering a practical and flexible alternative to traditional transportation modes, particularly in areas with limited access to public transit. However, this rise in popularity has also brought about serious road safety concerns, particularly regarding risky behaviors such as riding under the influence of alcohol, carrying multiple passengers, and non-compliance with traffic regulations. While non-compliance with traffic regulations is not unique to e-scooter users, the combination of multiple risky behaviors observed among them may contribute to a higher likelihood of such violations. In addition, protective behaviors, such as helmet use, remain low among many riders, increasing injury risk in the event of a crash. This study aimed to analyze the prevalence of self-reported risky behaviors across various demographic groups and regions, and to assess factors contributing to the likelihood of unsafe e-scooter riding behavior. To achieve this, we used data from the third edition of the E-Survey of Road users' Attitudes (ESRA), focusing on responses from 39 countries worldwide. Descriptive analyses of self-reported data were conducted to examine e-scooter usage patterns and self-declared risky behaviors. Additionally, mixed-effects logistic regression models were employed to identify significant predictors of these behaviors, including gender, age, student status, crash history, and attitudes toward traffic laws. The results revealed that younger individuals and males are more likely to use e-scooters and engage in risky behaviors. Key factors influencing or associated with these behaviors included previous crash involvement, student status, and permissive attitudes toward safety regulations. The study highlights the need for targeted safety interventions that address infrastructural factors as well as behavioral factors, including demographic and attitudinal influences. This integrated approach can help policymakers develop more effective strategies to mitigate the risks associated with e-scooter use and enhance urban road safety.

电动滑板车（e-scooters）的迅速普及改变了城市交通，为传统交通方式提供了一种实用而灵活的替代方案，特别是在公共交通有限的地区。然而，这种受欢迎程度的上升也带来了严重的道路安全问题，特别是关于危险行为，如酒后骑行、携带多名乘客和不遵守交通规则。虽然不遵守交通法规并不是电动滑板车使用者所独有的，但在他们中间观察到的多种危险行为的结合可能会导致这种违规行为的可能性更高。此外，许多车手使用头盔等保护行为的比例仍然很低，这增加了发生碰撞时受伤的风险。本研究旨在分析不同人口群体和地区自我报告的危险行为的流行程度，并评估导致不安全电动滑板车骑行行为可能性的因素。为了实现这一目标，我们使用了第三版道路使用者态度电子调查（ESRA）的数据，重点关注了全球39个国家的反馈。对自我报告的数据进行描述性分析，以检查电动滑板车的使用模式和自我声明的危险行为。此外，采用混合效应逻辑回归模型来确定这些行为的重要预测因素，包括性别、年龄、学生身份、碰撞历史和对交通法规的态度。结果显示，年轻人和男性更有可能使用电动滑板车并从事危险行为。影响或相关这些行为的关键因素包括以前的碰撞参与，学生身份和对安全法规的宽容态度。该研究强调需要有针对性的安全干预措施，既要解决基础设施因素，也要解决行为因素，包括人口和态度的影响。这种综合方法可以帮助政策制定者制定更有效的战略，以减轻与电动滑板车使用相关的风险，并加强城市道路安全。

{"title":"E-scooter riders: A cross-cultural analysis of traffic safety attitudes and behaviors","authors":"Milad Delavary , Craig Lyon , Ward G.M. Vanlaar , Robyn D. Robertson , Dimitrios Nikolaou , George Yannis","doi":"10.1016/j.iatssr.2025.05.002","DOIUrl":"10.1016/j.iatssr.2025.05.002","url":null,"abstract":"<div><div>The rapid adoption of electric scooters (e-scooters) has transformed urban mobility, offering a practical and flexible alternative to traditional transportation modes, particularly in areas with limited access to public transit. However, this rise in popularity has also brought about serious road safety concerns, particularly regarding risky behaviors such as riding under the influence of alcohol, carrying multiple passengers, and non-compliance with traffic regulations. While non-compliance with traffic regulations is not unique to e-scooter users, the combination of multiple risky behaviors observed among them may contribute to a higher likelihood of such violations. In addition, protective behaviors, such as helmet use, remain low among many riders, increasing injury risk in the event of a crash. This study aimed to analyze the prevalence of self-reported risky behaviors across various demographic groups and regions, and to assess factors contributing to the likelihood of unsafe e-scooter riding behavior. To achieve this, we used data from the third edition of the <em>E</em>-Survey of Road users' Attitudes (ESRA), focusing on responses from 39 countries worldwide. Descriptive analyses of self-reported data were conducted to examine e-scooter usage patterns and self-declared risky behaviors. Additionally, mixed-effects logistic regression models were employed to identify significant predictors of these behaviors, including gender, age, student status, crash history, and attitudes toward traffic laws. The results revealed that younger individuals and males are more likely to use e-scooters and engage in risky behaviors. Key factors influencing or associated with these behaviors included previous crash involvement, student status, and permissive attitudes toward safety regulations. The study highlights the need for targeted safety interventions that address infrastructural factors as well as behavioral factors, including demographic and attitudinal influences. This integrated approach can help policymakers develop more effective strategies to mitigate the risks associated with e-scooter use and enhance urban road safety.</div></div>","PeriodicalId":47059,"journal":{"name":"IATSS Research","volume":"49 2","pages":"Pages 247-258"},"PeriodicalIF":3.2,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144242870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Exploring the factors affecting injury severity in highway and non-highway crashes in Bangladesh applying machine learning and SHAP 应用机器学习和SHAP探索影响孟加拉国公路和非公路碰撞伤害严重程度的因素

IF 3.2 Q3 TRANSPORTATION

IATSS Research

Pub Date : 2025-07-01 Epub Date: 2025-06-14 DOI: 10.1016/j.iatssr.2025.06.001

Nazmus Sakib , Tonmoy Paul , Subasish Das , Ahmed Hossain

To create effective preventive measures and targeted interventions, it is crucial to comprehend the contributing factors to the crash and quantify how they affect the injury, especially in least-developed countries. However, highway and non-highway crashes are linked to having distinguished characteristics, road-specific interventions, and data granularity. Combining all sorts of crashes into a single model may offer fewer insights than one would anticipate when building safety countermeasures. This research compares CART, RF, GBM, XGBoost, LightGBM, CatBoost, and AdaBoost and effectively simulates the complex relationship between collision injury severity and risk factors for both highway and non-highway crashes. Additionally, the Shapley Additive exPlanation (SHAP) framework is presented to explain the contribution of each risk factor from the output of the most appropriate classifier, thereby assisting in the construction of safety countermeasures and crash modification factors. GBM classifier was found to be the best classifier in terms of G-mean and AUC scores for both highway and non-highway models. Global SHAP values show that the type of collision, followed by the vehicle type, the vehicle involved, and road division, are the highest contributing factors for injury severity in highway crashes. For injury severity in non-highway crashes, the most important factors are the type of collision, followed by road division, vehicle type, and location type. Policy implications based on the study's findings have been suggested to develop successful preventive strategies and focused interventions. The study concludes by discussing the scope of future studies.

为了制定有效的预防措施和有针对性的干预措施，了解导致车祸的因素并量化它们如何影响伤害是至关重要的，特别是在最不发达国家。然而，公路和非公路碰撞与具有不同的特征、特定于道路的干预措施和数据粒度有关。在建立安全对策时，将各种各样的事故合并到一个模型中可能会提供比预期更少的见解。本研究对CART、RF、GBM、XGBoost、LightGBM、CatBoost和AdaBoost进行了比较，有效地模拟了公路和非公路碰撞中碰撞损伤严重程度与危险因素之间的复杂关系。此外，提出了Shapley加性解释（SHAP）框架，从最合适的分类器的输出中解释每个风险因素的贡献，从而帮助构建安全对策和碰撞修改因素。在高速公路和非高速公路模型的G-mean和AUC得分方面，GBM分类器都是最好的分类器。全球SHAP值表明，碰撞类型是影响公路碰撞伤害严重程度的最大因素，其次是车辆类型、涉及的车辆和道路划分。对于非公路碰撞的伤害严重程度，最重要的因素是碰撞类型，其次是道路划分、车辆类型和位置类型。根据研究结果提出的政策建议有助于制定成功的预防战略和有重点的干预措施。本研究最后讨论了未来研究的范围。

{"title":"Exploring the factors affecting injury severity in highway and non-highway crashes in Bangladesh applying machine learning and SHAP","authors":"Nazmus Sakib , Tonmoy Paul , Subasish Das , Ahmed Hossain","doi":"10.1016/j.iatssr.2025.06.001","DOIUrl":"10.1016/j.iatssr.2025.06.001","url":null,"abstract":"<div><div>To create effective preventive measures and targeted interventions, it is crucial to comprehend the contributing factors to the crash and quantify how they affect the injury, especially in least-developed countries. However, highway and non-highway crashes are linked to having distinguished characteristics, road-specific interventions, and data granularity. Combining all sorts of crashes into a single model may offer fewer insights than one would anticipate when building safety countermeasures. This research compares CART, RF, GBM, XGBoost, LightGBM, CatBoost, and AdaBoost and effectively simulates the complex relationship between collision injury severity and risk factors for both highway and non-highway crashes. Additionally, the Shapley Additive exPlanation (SHAP) framework is presented to explain the contribution of each risk factor from the output of the most appropriate classifier, thereby assisting in the construction of safety countermeasures and crash modification factors. GBM classifier was found to be the best classifier in terms of G-mean and AUC scores for both highway and non-highway models. Global SHAP values show that the type of collision, followed by the vehicle type, the vehicle involved, and road division, are the highest contributing factors for injury severity in highway crashes. For injury severity in non-highway crashes, the most important factors are the type of collision, followed by road division, vehicle type, and location type. Policy implications based on the study's findings have been suggested to develop successful preventive strategies and focused interventions. The study concludes by discussing the scope of future studies.</div></div>","PeriodicalId":47059,"journal":{"name":"IATSS Research","volume":"49 2","pages":"Pages 259-270"},"PeriodicalIF":3.2,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144280167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Study of psychological aspects of the safety culture of motorcyclists' behaviors in Indonesia's urban road traffic: Construction of road users' belief systems 印尼城市道路交通摩托车手行为安全文化的心理层面研究：道路使用者信念体系的建构

IF 3.2 Q3 TRANSPORTATION

IATSS Research

Pub Date : 2025-07-01 Epub Date: 2025-03-29 DOI: 10.1016/j.iatssr.2025.03.002

Andrijanto , Makoto Itoh , Sunardy , Michael Jonathan

The poor development of traffic safety culture by road traffic organizations in Indonesia has caused motorcyclists to behave irresponsibly while driving. Consequently, some behaviors may cause conflict with other road users, which may affect traffic safety. Therefore, studying the beliefs of road users regarding motorcyclists' behavior can describe the psychological aspects of the safety culture in urban road traffic. In this study, we used the reciprocal safety culture model as a framework, by applying a behavioral-based safety program to investigate motorcyclists' critical behaviors in urban areas in Indonesia. Adapting Ward's transformation model of belief systems to a behavior, we approach the psychological aspects of the traffic safety culture by observing the relationship between motorcyclists' critical behaviors and belief systems. We explore the belief system of Ward's model using a driving safety questionnaire (DSQ) and a cause-effect questionnaire. By applying multiple linear regression to the DSQ results, we revealed six motorcyclist behaviors critical to safety that affect car drivers and pedestrians. Furthermore, we constructed the belief systems of these behaviors by investigating behavioral beliefs, attitudes, normative beliefs, perceived norms, perceived control, and control beliefs to reveal “what road users think” about motorcyclits' behaviors related to traffic safety culture in the urban area.

印度尼西亚道路交通组织的交通安全文化发展不佳，导致摩托车手在驾驶时行为不负责任。因此，一些行为可能会引起与其他道路使用者的冲突，从而影响交通安全。因此，研究道路使用者对摩托车手行为的信念可以描述城市道路交通安全文化的心理层面。在本研究中，我们以互惠安全文化模型为框架，应用基于行为的安全计划来调查印度尼西亚城市地区摩托车手的关键行为。本文将Ward的信念系统转化模型应用于行为，通过观察摩托车手的批判行为与信念系统之间的关系，探讨了交通安全文化的心理层面。我们使用驾驶安全问卷（DSQ）和因果问卷来探讨Ward模型的信念系统。通过对DSQ结果进行多元线性回归，我们揭示了影响汽车驾驶员和行人的六种摩托车驾驶员对安全至关重要的行为。在此基础上，通过调查行为信念、态度信念、规范信念、感知规范信念、感知控制信念和控制信念，构建了这些行为的信念体系，以揭示道路使用者对城市地区摩托车驾驶员交通安全文化相关行为的“看法”。

{"title":"Study of psychological aspects of the safety culture of motorcyclists' behaviors in Indonesia's urban road traffic: Construction of road users' belief systems","authors":"Andrijanto , Makoto Itoh , Sunardy , Michael Jonathan","doi":"10.1016/j.iatssr.2025.03.002","DOIUrl":"10.1016/j.iatssr.2025.03.002","url":null,"abstract":"<div><div>The poor development of traffic safety culture by road traffic organizations in Indonesia has caused motorcyclists to behave irresponsibly while driving. Consequently, some behaviors may cause conflict with other road users, which may affect traffic safety. Therefore, studying the beliefs of road users regarding motorcyclists' behavior can describe the psychological aspects of the safety culture in urban road traffic. In this study, we used the reciprocal safety culture model as a framework, by applying a behavioral-based safety program to investigate motorcyclists' critical behaviors in urban areas in Indonesia. Adapting Ward's transformation model of belief systems to a behavior, we approach the psychological aspects of the traffic safety culture by observing the relationship between motorcyclists' critical behaviors and belief systems. We explore the belief system of Ward's model using a driving safety questionnaire (DSQ) and a cause-effect questionnaire. By applying multiple linear regression to the DSQ results, we revealed six motorcyclist behaviors critical to safety that affect car drivers and pedestrians. Furthermore, we constructed the belief systems of these behaviors by investigating behavioral beliefs, attitudes, normative beliefs, perceived norms, perceived control, and control beliefs to reveal “what road users think” about motorcyclits' behaviors related to traffic safety culture in the urban area.</div></div>","PeriodicalId":47059,"journal":{"name":"IATSS Research","volume":"49 2","pages":"Pages 137-154"},"PeriodicalIF":3.2,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143724118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Statistical analysis of motorcyclists' safety behavior and crash risks in Kuwait 科威特摩托车手安全行为与碰撞风险的统计分析

IF 3.2 Q3 TRANSPORTATION

IATSS Research

Pub Date : 2025-07-01 Epub Date: 2025-04-13 DOI: 10.1016/j.iatssr.2025.03.005

Sharaf AlKheder, Shaikha Al Mutairi, Dana Musaed, Dana Nayef

Road crashes represent a significant global safety crisis, with motorcyclists, cyclists, and pedestrians involved in over half of all traffic fatalities, motorcyclists being particularly vulnerable as both potential causes and victims of crashes. In Kuwait, the increasing use of motorcycles, particularly for delivery services, has raised crash risks, highlighting the need for updated safety measures. This study analyzes the driving behavior of motorcyclists and car drivers, focusing on road usage, traffic violations, and licensing while identifying key factors contributing to motorcycle crashes through surveys, interviews, and historical records. A busy area of the city was chosen as the research site due to its high concentration of restaurants and heavy traffic from delivery motorcyclists, customers, and other road users. Data was collected from interviews with 103 motorcyclists, an online survey of 300 car drivers, and publicly available open-source national data. Advanced statistical methods were used for analysis, including the Vector Autoregressive Model, Structural Equation Modeling, and Principal Component Analysis. The findings revealed that motorcycle-related road crashes are influenced by factors such as the motorcyclist's gender, spatial awareness, perceptual challenges, and familiarity with motorcycle positioning. Conversely, crash frequency is associated with the driver's experience, right-of-way violations by other road users, traffic violations by motorcyclists, and road conditions. To mitigate motorcycle-related road crashes, the study recommends the development of an Exclusive Motorcycle Lane with an optimal width of 1.855 m in the selected research site. This step has the potential to significantly improve road safety, reduce accidents, and save lives, contributing to safer urban mobility in Kuwait. Similar measures could also be implemented in countries with a high risk of motorcycle-related road crashes.

道路交通事故是一项重大的全球安全危机，半数以上的交通死亡事故涉及摩托车手、骑自行车者和行人，摩托车手作为事故的潜在原因和受害者尤其脆弱。在科威特，越来越多地使用摩托车，特别是用于送货服务，增加了撞车风险，突出表明需要更新安全措施。本研究分析了摩托车手和汽车司机的驾驶行为，重点关注道路使用、交通违规和许可，同时通过调查、访谈和历史记录确定导致摩托车撞车的关键因素。城市中一个繁忙的地区被选为研究地点，因为那里的餐馆高度集中，外卖摩托车手、顾客和其他道路使用者的交通繁忙。数据收集自对103名摩托车手的采访，对300名汽车司机的在线调查，以及公开的开源国家数据。采用先进的统计方法进行分析，包括向量自回归模型、结构方程模型和主成分分析。研究结果显示，摩托车相关道路交通事故受摩托车驾驶员性别、空间意识、感知挑战和对摩托车定位的熟悉程度等因素的影响。相反，碰撞频率与驾驶员的经验、其他道路使用者违反路权、摩托车手违反交通规则以及道路状况有关。为了减少与摩托车相关的道路交通事故，研究建议在选定的研究地点开发一条最佳宽度为1.855米的摩托车专用车道。这一步骤有可能显著改善道路安全，减少事故，挽救生命，为科威特更安全的城市交通做出贡献。在与摩托车有关的道路碰撞事故风险较高的国家也可采取类似措施。

{"title":"Statistical analysis of motorcyclists' safety behavior and crash risks in Kuwait","authors":"Sharaf AlKheder, Shaikha Al Mutairi, Dana Musaed, Dana Nayef","doi":"10.1016/j.iatssr.2025.03.005","DOIUrl":"10.1016/j.iatssr.2025.03.005","url":null,"abstract":"<div><div>Road crashes represent a significant global safety crisis, with motorcyclists, cyclists, and pedestrians involved in over half of all traffic fatalities, motorcyclists being particularly vulnerable as both potential causes and victims of crashes. In Kuwait, the increasing use of motorcycles, particularly for delivery services, has raised crash risks, highlighting the need for updated safety measures. This study analyzes the driving behavior of motorcyclists and car drivers, focusing on road usage, traffic violations, and licensing while identifying key factors contributing to motorcycle crashes through surveys, interviews, and historical records. A busy area of the city was chosen as the research site due to its high concentration of restaurants and heavy traffic from delivery motorcyclists, customers, and other road users. Data was collected from interviews with 103 motorcyclists, an online survey of 300 car drivers, and publicly available open-source national data. Advanced statistical methods were used for analysis, including the Vector Autoregressive Model, Structural Equation Modeling, and Principal Component Analysis. The findings revealed that motorcycle-related road crashes are influenced by factors such as the motorcyclist's gender, spatial awareness, perceptual challenges, and familiarity with motorcycle positioning. Conversely, crash frequency is associated with the driver's experience, right-of-way violations by other road users, traffic violations by motorcyclists, and road conditions. To mitigate motorcycle-related road crashes, the study recommends the development of an Exclusive Motorcycle Lane with an optimal width of 1.855 m in the selected research site. This step has the potential to significantly improve road safety, reduce accidents, and save lives, contributing to safer urban mobility in Kuwait. Similar measures could also be implemented in countries with a high risk of motorcycle-related road crashes.</div></div>","PeriodicalId":47059,"journal":{"name":"IATSS Research","volume":"49 2","pages":"Pages 169-179"},"PeriodicalIF":3.2,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143823578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Understanding the changes in long-distance travel behavior due to socio-economic and pandemic drivers 了解社会经济和流行病驱动因素导致的长途旅行行为的变化

IF 3.2 Q3 TRANSPORTATION

IATSS Research

Pub Date : 2025-07-01 Epub Date: 2025-06-27 DOI: 10.1016/j.iatssr.2025.06.003

Farzana Faiza Farha, Sadia Afroj, Md. Musleh Uddin Hasan, Effat Farzana

The unprecedented COVID-19 pandemic massively affected the long-distance trips all over the world. Like other countries worldwide, inter-regional mobility restrictions with the capital city were also imposed in Bangladesh to control the spread of coronavirus. Therefore, it is important to examine the changes in long-distance travel behavior to understand people's mobility needs and responses during travel restrictions, as well as the influences of individuals' socio-economic conditions and the country's COVID severity on their travel decisions. Data for this research were collected from 402 respondents in Dhaka using online questionnaires. Voluntary response and convenience sampling techniques were followed in this study. Moreover, district-wise COVID data was obtained from the dashboard of Directorate General of Health Services (DGHS). Descriptive statistics and spatial analyses were employed in this study. In addition, binary logistic regression model and mixed-effect logistic regression model were developed to understand the underlying factors behind the changes in long-distance travel behavior during the pandemic. The findings reveal that the majority of the respondents decreased their long-distance trips during the first pandemic wave. A notable percentage of trip makers' long-distance trip patterns and mode use remained the same as their pre-pandemic situation. Access to private cars was a positive determinant for long-distance trips during the pandemic; hence, the excess cost of private transportation compelled people to use risky public transportation. The presence of elderly individuals and children in households reduced the likelihood of traveling longer distances during the pandemic. Hygiene and safety from COVID-19 contamination were the main concerns for respondents while choosing long-distance travel modes. Individuals' high-risk perception regarding COVID-19 decreased the probability of traveling longer-distance during the pandemic. In general, travelers relatively less preferred COVID hotspots as their long-distance trip destinations during the first pandemic wave. This study's recommendations will assist planners and policymakers in designing a safe and affordable long-distance transport corridor during future pandemics.

前所未有的新冠肺炎大流行严重影响了世界各地的长途旅行。与世界其他国家一样，孟加拉国也实施了与首都的区域间流动限制，以控制冠状病毒的传播。因此，研究长途旅行行为的变化，以了解人们在旅行限制期间的出行需求和反应，以及个人的社会经济条件和国家的COVID严重程度对其旅行决策的影响，具有重要意义。这项研究的数据是通过在线问卷从达卡的402名受访者中收集的。本研究采用自愿回答和方便抽样的方法。此外，从卫生服务总局（DGHS）的仪表板获得了各地区的COVID数据。本研究采用描述性统计和空间分析。此外，还建立了二元logistic回归模型和混合效应logistic回归模型，以了解疫情期间长途旅行行为变化背后的潜在因素。调查结果显示，大多数答复者在第一波大流行期间减少了长途旅行。很大比例的旅行者的长途旅行模式和模式使用与大流行前的情况相同。在大流行期间，获得私家车是长途旅行的积极决定因素；因此，私人交通的超额成本迫使人们使用有风险的公共交通。在大流行期间，家庭中有老年人和儿童减少了长途旅行的可能性。受访者在选择长途旅行方式时主要考虑的是COVID-19污染的卫生和安全问题。个人对COVID-19的高风险认知降低了大流行期间长途旅行的可能性。一般来说，在第一波大流行期间，旅行者相对不太喜欢将COVID热点地区作为长途旅行目的地。这项研究的建议将有助于规划人员和决策者在未来大流行期间设计一条安全且负担得起的长途运输走廊。

{"title":"Understanding the changes in long-distance travel behavior due to socio-economic and pandemic drivers","authors":"Farzana Faiza Farha, Sadia Afroj, Md. Musleh Uddin Hasan, Effat Farzana","doi":"10.1016/j.iatssr.2025.06.003","DOIUrl":"10.1016/j.iatssr.2025.06.003","url":null,"abstract":"<div><div>The unprecedented COVID-19 pandemic massively affected the long-distance trips all over the world. Like other countries worldwide, inter-regional mobility restrictions with the capital city were also imposed in Bangladesh to control the spread of coronavirus. Therefore, it is important to examine the changes in long-distance travel behavior to understand people's mobility needs and responses during travel restrictions, as well as the influences of individuals' socio-economic conditions and the country's COVID severity on their travel decisions. Data for this research were collected from 402 respondents in Dhaka using online questionnaires. Voluntary response and convenience sampling techniques were followed in this study. Moreover, district-wise COVID data was obtained from the dashboard of Directorate General of Health Services (DGHS). Descriptive statistics and spatial analyses were employed in this study. In addition, binary logistic regression model and mixed-effect logistic regression model were developed to understand the underlying factors behind the changes in long-distance travel behavior during the pandemic. The findings reveal that the majority of the respondents decreased their long-distance trips during the first pandemic wave. A notable percentage of trip makers' long-distance trip patterns and mode use remained the same as their pre-pandemic situation. Access to private cars was a positive determinant for long-distance trips during the pandemic; hence, the excess cost of private transportation compelled people to use risky public transportation. The presence of elderly individuals and children in households reduced the likelihood of traveling longer distances during the pandemic. Hygiene and safety from COVID-19 contamination were the main concerns for respondents while choosing long-distance travel modes. Individuals' high-risk perception regarding COVID-19 decreased the probability of traveling longer-distance during the pandemic. In general, travelers relatively less preferred COVID hotspots as their long-distance trip destinations during the first pandemic wave. This study's recommendations will assist planners and policymakers in designing a safe and affordable long-distance transport corridor during future pandemics.</div></div>","PeriodicalId":47059,"journal":{"name":"IATSS Research","volume":"49 2","pages":"Pages 280-289"},"PeriodicalIF":3.2,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144491311","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Determinants of crash injury severity for delivery riders: Insights from an error components mixed logit model with heterogeneous means and variances 快递员碰撞伤害严重程度的决定因素：来自具有异构均值和方差的错误成分混合logit模型的见解

IF 3.2 Q3 TRANSPORTATION

IATSS Research

Pub Date : 2025-07-01 Epub Date: 2025-04-17 DOI: 10.1016/j.iatssr.2025.04.001

Thanapong Champahom , Chamroeun Se , Wimon Laphrom , Sajjakaj Jomnonkwao , Rattanaporn Kasemsri , Vatanavongs Ratanavaraha

The rapid growth of e-commerce and food delivery services has led to an increase in commercial motorcycle riders, raising concerns about their safety on the road. This study aims to identify and analyze the determinants of crash injury severity for delivery riders in Thailand. Questionairs data was collected from 2000 commercial motorcycle users across five regions of Thailand, incorporating a wide range of demographic, work-related, and environmental factors. The study employs a Heteroscedastic Error Components Mixed Logit with Heterogeneity in Means (HECMLHM) model to capture unobserved heterogeneity and complex interactions between variables. Key findings reveal that rider age, experience, education level, income, work frequency, and rest periods significantly influence crash injury severity, often with varying effects across the population. Counterintuitively, more experienced riders faced a higher risk of severe injuries. Based on these findings, policy recommendations include targeted safety education programs, experience-based training to mitigate overconfidence, work schedule management, and optimized rest period policies. This study contributes to the field by focusing exclusively on delivery riders, employing advanced modeling techniques, and providing a comprehensive analysis of factors influencing crash severity in an emerging market context. The findings offer valuable insights for developing targeted safety interventions and policies to reduce crash injury severity among this growing workforce.

电子商务和外卖服务的快速发展导致商业摩托车骑手的增加，引发了人们对他们在道路上安全的担忧。本研究旨在识别和分析泰国快递骑手碰撞伤害严重程度的决定因素。问卷数据收集自泰国5个地区的2000名商业摩托车使用者，包括广泛的人口统计、工作相关和环境因素。本研究采用异方差误差分量混合Logit均值异质性（HECMLHM）模型来捕捉未观察到的异质性和变量之间复杂的相互作用。主要研究结果表明，骑手的年龄、经验、教育水平、收入、工作频率和休息时间对碰撞损伤的严重程度有显著影响，而且对不同人群的影响各不相同。与直觉相反的是，经验丰富的骑手受到严重伤害的风险更高。基于这些发现，政策建议包括有针对性的安全教育计划、基于经验的培训以减轻过度自信、工作时间表管理和优化休息时间政策。这项研究通过专门关注快递员，采用先进的建模技术，并在新兴市场背景下对影响事故严重程度的因素进行全面分析，为该领域做出了贡献。研究结果为制定有针对性的安全干预措施和政策提供了有价值的见解，以降低这一不断增长的劳动力的碰撞伤害严重程度。

{"title":"Determinants of crash injury severity for delivery riders: Insights from an error components mixed logit model with heterogeneous means and variances","authors":"Thanapong Champahom , Chamroeun Se , Wimon Laphrom , Sajjakaj Jomnonkwao , Rattanaporn Kasemsri , Vatanavongs Ratanavaraha","doi":"10.1016/j.iatssr.2025.04.001","DOIUrl":"10.1016/j.iatssr.2025.04.001","url":null,"abstract":"<div><div>The rapid growth of e-commerce and food delivery services has led to an increase in commercial motorcycle riders, raising concerns about their safety on the road. This study aims to identify and analyze the determinants of crash injury severity for delivery riders in Thailand. Questionairs data was collected from 2000 commercial motorcycle users across five regions of Thailand, incorporating a wide range of demographic, work-related, and environmental factors. The study employs a Heteroscedastic Error Components Mixed Logit with Heterogeneity in Means (HECMLHM) model to capture unobserved heterogeneity and complex interactions between variables. Key findings reveal that rider age, experience, education level, income, work frequency, and rest periods significantly influence crash injury severity, often with varying effects across the population. Counterintuitively, more experienced riders faced a higher risk of severe injuries. Based on these findings, policy recommendations include targeted safety education programs, experience-based training to mitigate overconfidence, work schedule management, and optimized rest period policies. This study contributes to the field by focusing exclusively on delivery riders, employing advanced modeling techniques, and providing a comprehensive analysis of factors influencing crash severity in an emerging market context. The findings offer valuable insights for developing targeted safety interventions and policies to reduce crash injury severity among this growing workforce.</div></div>","PeriodicalId":47059,"journal":{"name":"IATSS Research","volume":"49 2","pages":"Pages 180-190"},"PeriodicalIF":3.2,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143838850","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0