Transportation Letters-The International Journal of Transportation Research最新文献

英文中文

Mobility experiment twin for analyzing travel behavior decisions employing shared electric autonomous vehicles 用于分析使用共享电动自动驾驶汽车的出行行为决策的移动性实验双胞胎

IF 3.3 3区工程技术 Q2 TRANSPORTATION

Transportation Letters-The International Journal of Transportation Research

Pub Date : 2026-01-02 DOI: 10.1080/19427867.2025.2525290

Son Van Pham , Akimasa Fujiwara , Makoto Chikaraishi , Anh Son Le , Nang Ho Xuan

The introduction of new mobility services (NMS) strongly depends on the public acceptance. Acceptance is evaluated by allowing users to experience these solutions before their widespread implementation. However, there is limited research on establishing robust frameworks for analyzing travel behavior decisions across the stages and environmental contexts of implementation. This study proposes the mobility experiment twin (MEXT) framework, which integrates cyber and physical experiments using a five-step approach. We introduced shared autonomous electric vehicles (SAEVs) as first-last-mile (FLM) urban mobility vehicles in Hanoi. Utilizing randomized controlled trials with cyber and physical groups to estimate the impact of MEXT. The users preferred SAEVs, willingly accepting longer travel times and higher costs, while young people were more inclined to adopt SAEVs with economic costs. Future works must consider more representative experimental locations and develop a theoretical model that better reflects the current SAEV situation in developing societies.

新的移动服务（NMS）的引入很大程度上取决于公众的接受程度。通过允许用户在广泛实现之前体验这些解决方案来评估接受度。然而，关于建立跨阶段和环境背景的旅行行为决策分析框架的研究有限。本研究提出了移动实验孪生（MEXT）框架，该框架采用五步方法整合了网络和物理实验。我们在河内推出了共享自动驾驶电动汽车（saev）作为第一最后一英里（FLM）城市交通工具。利用网络和物理组的随机对照试验来估计next的影响。用户更喜欢自驾汽车，愿意接受更长的出行时间和更高的成本，而年轻人更倾向于采用经济成本的自驾汽车。未来的工作必须考虑更具代表性的实验地点，并建立一个更好地反映发展中社会当前SAEV情况的理论模型。

{"title":"Mobility experiment twin for analyzing travel behavior decisions employing shared electric autonomous vehicles","authors":"Son Van Pham , Akimasa Fujiwara , Makoto Chikaraishi , Anh Son Le , Nang Ho Xuan","doi":"10.1080/19427867.2025.2525290","DOIUrl":"10.1080/19427867.2025.2525290","url":null,"abstract":"<div><div>The introduction of new mobility services (NMS) strongly depends on the public acceptance. Acceptance is evaluated by allowing users to experience these solutions before their widespread implementation. However, there is limited research on establishing robust frameworks for analyzing travel behavior decisions across the stages and environmental contexts of implementation. This study proposes the mobility experiment twin (MEXT) framework, which integrates cyber and physical experiments using a five-step approach. We introduced shared autonomous electric vehicles (SAEVs) as first-last-mile (FLM) urban mobility vehicles in Hanoi. Utilizing randomized controlled trials with cyber and physical groups to estimate the impact of MEXT. The users preferred SAEVs, willingly accepting longer travel times and higher costs, while young people were more inclined to adopt SAEVs with economic costs. Future works must consider more representative experimental locations and develop a theoretical model that better reflects the current SAEV situation in developing societies.</div></div>","PeriodicalId":48974,"journal":{"name":"Transportation Letters-The International Journal of Transportation Research","volume":"18 1","pages":"Pages 23-38"},"PeriodicalIF":3.3,"publicationDate":"2026-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146098760","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

“Car sharers are not bigger tree-huggers than others: at least not in the Swedish forest” “汽车共享者并不比其他人更热爱环保：至少在瑞典的森林里不是这样。”

IF 3.3 3区工程技术 Q2 TRANSPORTATION

Transportation Letters-The International Journal of Transportation Research

Pub Date : 2026-01-02 DOI: 10.1080/19427867.2025.2537175

John Magnus Roos

Car sharing is often promoted as a sustainable mobility solution and a hallmark of the sharing economy. It is commonly assumed that environmental concerns are a key motivation for consumers who use car sharing services. However, previous studies offer mixed findings regarding the link between car sharing and environmental attitudes. Drawing on nationally representative survey data from 2019 to 2024 (N = 10,170), this study examines the relationship between consumers’ environmental attitudes and car sharing use. Results show that environmental attitudes have only limited influence. Most attitudinal measures, including general environmental concern and support for reducing car use, did not significantly differ (p < .05) between car sharers and non-car sharers. These findings challenge the notion that environmental motivations are central to car sharing adoption. Instead, they suggest that practical considerations, such as cost and convenience, may be more influential. In the context of Mobility as a Service (MaaS), this underscores the need to prioritize everyday mobility needs over assumed ecological values.

汽车共享通常被宣传为一种可持续的出行解决方案和共享经济的标志。人们普遍认为，环境问题是消费者使用汽车共享服务的主要动机。然而，之前的研究提供了关于汽车共享和环境态度之间联系的复杂结果。本研究利用2019年至2024年具有全国代表性的调查数据（N = 10,170），研究了消费者的环境态度与汽车共享使用之间的关系。结果表明，环境态度的影响有限。大多数态度措施，包括一般的环境关注和减少汽车使用的支持，在汽车共享者和非汽车共享者之间没有显著差异（p < 0.05）。这些发现挑战了环保动机是汽车共享采用的核心的观念。相反，他们认为实际的考虑，如成本和便利性，可能更有影响力。在出行即服务（MaaS）的背景下，这强调了将日常出行需求置于假定的生态价值之上的必要性。

{"title":"“Car sharers are not bigger tree-huggers than others: at least not in the Swedish forest”","authors":"John Magnus Roos","doi":"10.1080/19427867.2025.2537175","DOIUrl":"10.1080/19427867.2025.2537175","url":null,"abstract":"<div><div>Car sharing is often promoted as a sustainable mobility solution and a hallmark of the sharing economy. It is commonly assumed that environmental concerns are a key motivation for consumers who use car sharing services. However, previous studies offer mixed findings regarding the link between car sharing and environmental attitudes. Drawing on nationally representative survey data from 2019 to 2024 (<em>N</em> = 10,170), this study examines the relationship between consumers’ environmental attitudes and car sharing use. Results show that environmental attitudes have only limited influence. Most attitudinal measures, including general environmental concern and support for reducing car use, did not significantly differ (<em>p</em> < .05) between car sharers and non-car sharers. These findings challenge the notion that environmental motivations are central to car sharing adoption. Instead, they suggest that practical considerations, such as cost and convenience, may be more influential. In the context of Mobility as a Service (MaaS), this underscores the need to prioritize everyday mobility needs over assumed ecological values.</div></div>","PeriodicalId":48974,"journal":{"name":"Transportation Letters-The International Journal of Transportation Research","volume":"18 1","pages":"Pages 179-193"},"PeriodicalIF":3.3,"publicationDate":"2026-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146098797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Traffic signal coordinated control model for long arterial based on traffic flow spatiotemporal characteristics 基于交通流时空特征的长干线交通信号协调控制模型

IF 3.3 3区工程技术 Q2 TRANSPORTATION

Transportation Letters-The International Journal of Transportation Research

Pub Date : 2025-11-26 DOI: 10.1080/19427867.2025.2488971

Qile Li , Zhizhen Liu , Lan Yao , Hangze Li , Guanzhi Xiong , Yuxuan Zhang

Traditional signal coordination methods face challenges in ensuring efficient traffic flow on long arterials due to urban expansion and complex spatiotemporal variations. However, existing methods struggle to achieve effective signal coordination under complex spatiotemporal variations, and lack methodological framework for universally applicable green wave coordination. To address this, a spatiotemporal partitioning-based green wave trajectory feature coordination optimization model is proposed. First, temporal partitioning is performed using an improved Fisher optimal segmentation method, while spatial subarea division is achieved via an enhanced K-Medoids algorithm. For each subarea, an arterial traffic signal control model is established based on green wave trajectory characteristics. Phase difference coordination equations are then applied to synchronize adjacent subareas. The model is validated on Foshan’s Lvjing Road, with evening peak performance compared against a classical green wave trajectory approach. Results indicate that the proposed model reduces vehicle average delay by 13.18% and the number of stops by 18.05%.

由于城市扩张和复杂的时空变化，传统的信号协调方法在保证长主干道上的高效交通流方面面临挑战。然而，现有方法难以实现复杂时空变化下的有效信号协调，缺乏普遍适用的绿波协调方法框架。针对这一问题，提出了一种基于时空分区的绿波轨迹特征协调优化模型。首先，采用改进的Fisher最优分割方法进行时间分区，通过增强的K-Medoids算法进行空间子区域划分。针对每个分区，建立了基于绿波轨迹特征的主干道交通信号控制模型。然后应用相位差协调方程同步相邻子区域。该模型在佛山绿景路进行了验证，并将其与经典的绿波轨迹方法进行了对比。结果表明，该模型可使车辆平均延误时间减少13.18%，停车次数减少18.05%。

{"title":"Traffic signal coordinated control model for long arterial based on traffic flow spatiotemporal characteristics","authors":"Qile Li , Zhizhen Liu , Lan Yao , Hangze Li , Guanzhi Xiong , Yuxuan Zhang","doi":"10.1080/19427867.2025.2488971","DOIUrl":"10.1080/19427867.2025.2488971","url":null,"abstract":"<div><div>Traditional signal coordination methods face challenges in ensuring efficient traffic flow on long arterials due to urban expansion and complex spatiotemporal variations. However, existing methods struggle to achieve effective signal coordination under complex spatiotemporal variations, and lack methodological framework for universally applicable green wave coordination. To address this, a spatiotemporal partitioning-based green wave trajectory feature coordination optimization model is proposed. First, temporal partitioning is performed using an improved Fisher optimal segmentation method, while spatial subarea division is achieved via an enhanced K-Medoids algorithm. For each subarea, an arterial traffic signal control model is established based on green wave trajectory characteristics. Phase difference coordination equations are then applied to synchronize adjacent subareas. The model is validated on Foshan’s Lvjing Road, with evening peak performance compared against a classical green wave trajectory approach. Results indicate that the proposed model reduces vehicle average delay by 13.18% and the number of stops by 18.05%.</div></div>","PeriodicalId":48974,"journal":{"name":"Transportation Letters-The International Journal of Transportation Research","volume":"17 10","pages":"Pages 1739-1754"},"PeriodicalIF":3.3,"publicationDate":"2025-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145665514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

An optimization method of high-speed train rescheduling based on PER-D3QN 基于PER-D3QN的高速列车调度优化方法

IF 3.3 3区工程技术 Q2 TRANSPORTATION

Transportation Letters-The International Journal of Transportation Research

Pub Date : 2025-11-26 DOI: 10.1080/19427867.2025.2496860

Junting Lin , Maolin Li , Ning Qin , Mingjun Ni , Xiaohui Qiu

This paper addresses delay problems from moderate and slight disturbances in high-speed train operation by constructing an optimization model that minimizes total train delay time, solved using reinforcement learning. The research introduces a linear programming method to balance rescheduling frequency and total delay time, proposing a dynamic adjustment method of state transfer step size based on reinforcement learning’s greedy strategy and train operation constraints. This approach shortens calculation time and improves solution quality. The simulation environment is on a single direction of the double-track railway from Beijing South Station to Jinan West Station, and three experimental scenarios are designed. The experimental results show that dynamic adjustment of state transfer step size reduces average algorithm computation time by 30.5% and average total train delay by 8.2%. Compared to the CPLEX solver-based strategy, the approach decreases average timetable generation time by 7.4%.

本文通过构建一个优化模型来解决高速列车运行中由中度和轻微干扰引起的延误问题，该模型采用强化学习方法求解，使列车总延误时间最小化。研究引入线性规划方法平衡重调度频率和总延迟时间，提出了一种基于强化学习贪婪策略和列车运行约束的状态转移步长动态调整方法。该方法缩短了计算时间，提高了求解质量。仿真环境为北京南站至济南西站单线双轨铁路，设计了三种实验场景。实验结果表明，动态调整状态转移步长可使算法平均计算时间减少30.5%，列车平均总延误减少8.2%。与基于CPLEX求解器的策略相比，该方法平均时间表生成时间缩短了7.4%。

引用次数: 0

Analyzing severity of vehicle–bicycle crashes: an explainable boosting machine strategy 分析汽车-自行车碰撞的严重程度：一种可解释的助推机器策略

IF 3.3 3区工程技术 Q2 TRANSPORTATION

Transportation Letters-The International Journal of Transportation Research

Pub Date : 2025-11-26 DOI: 10.1080/19427867.2025.2500817

Sheng Dong , Afaq Khattak , Feng Chen , Jibiao Zhou , Feifei Xu

Vehicular crashes involving bicycles result in substantial annual fatalities, raising serious concerns for traffic safety authorities. Understanding the factors influencing crash severity is vital for designing effective countermeasures. However, the limited interpretability of many machine learning models complicates traffic safety assessments. This study introduces the Explainable Boosting Machine (EBM), a transparent glass-box model developed to predict the severity of vehicle–bicycle crashes and identify influential factors. A dataset of 5,341 crashes from the Ningbo Public Security Bureau (2020–2021) was analyzed. To address class imbalance, multiple data augmentation techniques were employed, and Bayesian optimization was used for hyperparameter tuning. EBM performance was benchmarked against black-box models, including LightGBM and XGBoost, using holdout evaluation. The EBM combined with borderline-SMOTE achieved a G-mean of 0.816 and an imbalanced accuracy of 0.651. Key predictors included weather and seasonal effects, with season–location interactions significantly influencing crash severity. This framework provides interpretable insights for data-driven traffic safety interventions and future research.

涉及自行车的交通事故每年造成大量死亡，引起了交通安全部门的严重关注。了解影响碰撞严重程度的因素对于设计有效的对策至关重要。然而，许多机器学习模型的有限可解释性使交通安全评估变得复杂。本研究引入可解释促进机（EBM），这是一个透明的玻璃盒模型，用于预测汽车-自行车碰撞的严重程度并识别影响因素。选取宁波市公安局2020-2021年5341起交通事故数据集进行分析。为了解决类不平衡问题，采用了多种数据增强技术，并使用贝叶斯优化进行超参数调优。EBM的性能以黑盒模型（包括LightGBM和XGBoost）为基准，使用holdout评估。EBM结合borderline-SMOTE的g均值为0.816，不平衡精度为0.651。关键的预测因素包括天气和季节影响，季节和地点的相互作用显著影响坠机的严重程度。该框架为数据驱动的交通安全干预和未来研究提供了可解释的见解。

{"title":"Analyzing severity of vehicle–bicycle crashes: an explainable boosting machine strategy","authors":"Sheng Dong , Afaq Khattak , Feng Chen , Jibiao Zhou , Feifei Xu","doi":"10.1080/19427867.2025.2500817","DOIUrl":"10.1080/19427867.2025.2500817","url":null,"abstract":"<div><div>Vehicular crashes involving bicycles result in substantial annual fatalities, raising serious concerns for traffic safety authorities. Understanding the factors influencing crash severity is vital for designing effective countermeasures. However, the limited interpretability of many machine learning models complicates traffic safety assessments. This study introduces the Explainable Boosting Machine (EBM), a transparent glass-box model developed to predict the severity of vehicle–bicycle crashes and identify influential factors. A dataset of 5,341 crashes from the Ningbo Public Security Bureau (2020–2021) was analyzed. To address class imbalance, multiple data augmentation techniques were employed, and Bayesian optimization was used for hyperparameter tuning. EBM performance was benchmarked against black-box models, including LightGBM and XGBoost, using holdout evaluation. The EBM combined with borderline-SMOTE achieved a G-mean of 0.816 and an imbalanced accuracy of 0.651. Key predictors included weather and seasonal effects, with season–location interactions significantly influencing crash severity. This framework provides interpretable insights for data-driven traffic safety interventions and future research.</div></div>","PeriodicalId":48974,"journal":{"name":"Transportation Letters-The International Journal of Transportation Research","volume":"17 10","pages":"Pages 1856-1869"},"PeriodicalIF":3.3,"publicationDate":"2025-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145665518","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Discrepancies in Pedestrian Crossing of Static vs. Dynamic Crowds: An Experimental Study 静态与动态人群行人过街差异的实验研究

IF 3.3 3区工程技术 Q2 TRANSPORTATION

Transportation Letters-The International Journal of Transportation Research

Pub Date : 2025-11-26 DOI: 10.1080/19427867.2025.2522592

Jinghui Wang , Yajuan Jiang , Xiaoying Zhang , Fangwei Deng , Wei Lv

In this paper, we investigate disparities in pedestrian crossing behaviors within static and dynamic crowds through experimental analysis. First, qualitative trajectory observations revealed significant behavioral differences. To quantitatively assess these discrepancies, we introduced a metric termed the swarm factor. In static contexts, limited variations in speed and swarm factor were observed, which may contribute to the formation of cross-channels, a phenomenon of pedestrian self-organization (tactical level). In contrast, speed and swarm factor exhibited inverse synchronization in dynamic contexts, indicating density-dependent behavioral adaptation (operational level). Finally, orthogonal velocity analysis demonstrated a fundamental pattern in crossing motions: as global density increased, both instantaneous velocity and crossing velocity decreased, while transverse velocity remained stable.

本文通过实验分析研究了静态人群和动态人群中行人过马路行为的差异。首先，定性轨迹观察揭示了显著的行为差异。为了定量地评估这些差异，我们引入了一个称为群体因子的度量。在静态环境下，观察到速度和群体因子的有限变化，这可能有助于交叉通道的形成，这是一种行人自组织现象（战术层面）。相反，在动态环境中，速度和群体因子表现出反向同步，表明密度依赖的行为适应（操作层面）。最后，正交速度分析揭示了穿越运动的基本规律：随着整体密度的增加，瞬时速度和穿越速度均减小，而横向速度保持稳定。

引用次数: 0

Robustness assessment of a multilayer composite network with a two-stage fusion community detection algorithm 基于两阶段融合社区检测算法的多层复合网络鲁棒性评估

IF 3.3 3区工程技术 Q2 TRANSPORTATION

Transportation Letters-The International Journal of Transportation Research

Pub Date : 2025-11-26 DOI: 10.1080/19427867.2025.2496805

Nengye Mu , Yunjin Han , Huimei Fan , Peiling Tian , Yuanshun Wang , Dudu Guo

Multimodal transportation, including aviation, high-speed rail, and waterways, is crucial for urban freight in China. To evaluate the robustness of urban freight networks, this study constructs a multilayer composite network model for aviation, high-speed rail, and waterways based on complex network theory. A two-stage fusion community detection algorithm (TFCA) is proposed for community partitioning. The study simulates network attack risks under deliberate attack strategies, based on network characteristics and community division results. Results show that nodes with high equilibrium centrality, mainly in East and Central China, require early intervention to enhance network robustness; the network is resilient against random risks but more vulnerable to attacks targeting high equilibrium centrality nodes; Adjusting capacity coefficients φ, τ, and ε can strengthen network robustness, with τ and ε having a more significant impact. These findings provide a scientific basis for optimizing urban freight networks and improving their overall risk resistance.

包括航空、高铁和水路在内的多式联运对中国的城市货运至关重要。为了评估城市货运网络的鲁棒性，本文基于复杂网络理论构建了航空、高铁和水路的多层复合网络模型。提出了一种用于社团划分的两阶段融合社团检测算法（TFCA）。基于网络特征和社区划分结果，模拟了故意攻击策略下的网络攻击风险。结果表明，均衡中心性较高的节点（主要集中在华东和华中地区）需要早期干预以增强网络的鲁棒性；网络对随机风险具有弹性，但更容易受到针对高平衡中心性节点的攻击；调节容量系数φ、τ和ε可以增强网络的鲁棒性，其中τ和ε的影响更为显著。研究结果为优化城市货运网络，提高城市货运网络的整体抗风险能力提供了科学依据。

{"title":"Robustness assessment of a multilayer composite network with a two-stage fusion community detection algorithm","authors":"Nengye Mu , Yunjin Han , Huimei Fan , Peiling Tian , Yuanshun Wang , Dudu Guo","doi":"10.1080/19427867.2025.2496805","DOIUrl":"10.1080/19427867.2025.2496805","url":null,"abstract":"<div><div>Multimodal transportation, including aviation, high-speed rail, and waterways, is crucial for urban freight in China. To evaluate the robustness of urban freight networks, this study constructs a multilayer composite network model for aviation, high-speed rail, and waterways based on complex network theory. A two-stage fusion community detection algorithm (TFCA) is proposed for community partitioning. The study simulates network attack risks under deliberate attack strategies, based on network characteristics and community division results. Results show that nodes with high equilibrium centrality, mainly in East and Central China, require early intervention to enhance network robustness; the network is resilient against random risks but more vulnerable to attacks targeting high equilibrium centrality nodes; Adjusting capacity coefficients <em>φ</em>, <em>τ</em>, and <em>ε</em> can strengthen network robustness, with <em>τ</em> and <em>ε</em> having a more significant impact. These findings provide a scientific basis for optimizing urban freight networks and improving their overall risk resistance.</div></div>","PeriodicalId":48974,"journal":{"name":"Transportation Letters-The International Journal of Transportation Research","volume":"17 10","pages":"Pages 1819-1838"},"PeriodicalIF":3.3,"publicationDate":"2025-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145665513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Evaluation of conflict classification methods in pedestrian safety analyses: a comparative study with practical guidance 行人安全分析中冲突分类方法的评价：具有实践指导意义的比较研究

IF 3.3 3区工程技术 Q2 TRANSPORTATION

Transportation Letters-The International Journal of Transportation Research

Pub Date : 2025-11-26 DOI: 10.1080/19427867.2025.2514986

Ziqian Zhang , Haojie Li , Wenzhang Yang , Gang Ren

This study compares different conflict classification methods based on three surrogate safety indicators (PET, TTC, DST). Single-indicator measures (PET-based, TTC-based, DST-based thresholds) and mixed-indicator measures (Accumulative-percentile, Clustering, Manual-review) are evaluated. Results show PET-based thresholds method detects more serious conflicts, while TTC-based thresholds method identifies more minor conflicts. Among mixed methods, the classification results of Accumulative-percentile method largely depend on the selection of dividing percentiles, while Clustering method and Manual-review method differ mainly in ‘normal passage’ and ‘minor conflict’ proportions. For single-indicator measures, PET-based thresholds method covers the widest range of influencing factors, whereas TTC-based and DST-based methods focus more on ‘evasive action’ factors. Mixed-indicator measures generally identify more variables than single-indicator measures. We further provide practical guidance to help with the selection of conflict classification methods.

本研究比较了基于PET、TTC、DST三个替代安全指标的不同冲突分类方法。评估单指标测量（基于pet，基于ttc，基于dst的阈值）和混合指标测量（累积百分位数，聚类，手动审查）。结果表明，基于pet的阈值方法检测到的冲突更严重，而基于ttc的阈值方法检测到的冲突更轻微。在混合方法中，累积百分位数法的分类结果在很大程度上取决于划分百分位数的选择，而聚类法和Manual-review法的区别主要在于“正常通过”和“小冲突”的比例。对于单指标测量，基于pet的阈值方法涵盖了最广泛的影响因素，而基于ttc和基于dst的方法更侧重于“规避行为”因素。混合指标度量通常比单一指标度量识别更多的变量。我们进一步提供了实用的指导，以帮助选择冲突分类方法。

{"title":"Evaluation of conflict classification methods in pedestrian safety analyses: a comparative study with practical guidance","authors":"Ziqian Zhang , Haojie Li , Wenzhang Yang , Gang Ren","doi":"10.1080/19427867.2025.2514986","DOIUrl":"10.1080/19427867.2025.2514986","url":null,"abstract":"<div><div>This study compares different conflict classification methods based on three surrogate safety indicators (PET, TTC, DST). Single-indicator measures (PET-based, TTC-based, DST-based thresholds) and mixed-indicator measures (Accumulative-percentile, Clustering, Manual-review) are evaluated. Results show PET-based thresholds method detects more serious conflicts, while TTC-based thresholds method identifies more minor conflicts. Among mixed methods, the classification results of Accumulative-percentile method largely depend on the selection of dividing percentiles, while Clustering method and Manual-review method differ mainly in ‘normal passage’ and ‘minor conflict’ proportions. For single-indicator measures, PET-based thresholds method covers the widest range of influencing factors, whereas TTC-based and DST-based methods focus more on ‘evasive action’ factors. Mixed-indicator measures generally identify more variables than single-indicator measures. We further provide practical guidance to help with the selection of conflict classification methods.</div></div>","PeriodicalId":48974,"journal":{"name":"Transportation Letters-The International Journal of Transportation Research","volume":"17 10","pages":"Pages 1870-1887"},"PeriodicalIF":3.3,"publicationDate":"2025-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145665522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Optimal location planning for battery exchange and charging stations for electric scooters in leisure areas considering stochastic user dwell times 考虑随机用户停留时间的休闲区域电动滑板车电池交换和充电站的最优位置规划

IF 3.3 3区工程技术 Q2 TRANSPORTATION

Transportation Letters-The International Journal of Transportation Research

Pub Date : 2025-11-26 DOI: 10.1080/19427867.2025.2521080

Chih-Kang Lin , Shangyao Yan , Guan-Ting Ou

Stochastic factors significantly affect the optimal planning for locating electric scooter charging stations and scheduling battery exchanges in real operations. A plan that does not account for stochastic factors might turn out to be overly optimistic when implemented in real-world operations, where such stochastic disturbances are common. In this study, we apply mathematical programming and network flow techniques to develop a model for determining the optimal locations of battery exchange and charging stations for electric scooters, while accounting for stochastic user dwell times in leisure areas. The proposed stochastic model, designed to address a location-scheduling problem, is formulated as a mixed-integer network flow problem with side constraints. We develop a simulation-based evaluation method and conduct computational tests to assess the model’s performance. Computational tests using real data from a city in Taiwan show that the stochastic model outperforms the deterministic model and has significant potential for practical applications.

在实际运行中，随机因素对电动滑板车充电站选址和换电池调度的最优规划有显著影响。一个不考虑随机因素的计划在实际操作中实施时可能会过于乐观，因为这种随机干扰很常见。在这项研究中，我们应用数学规划和网络流技术来开发一个模型，用于确定电动滑板车电池交换和充电站的最佳位置，同时考虑到用户在休闲区域的随机停留时间。所提出的随机模型，旨在解决的位置调度问题，是一个混合整数网络流问题的边约束。我们开发了一种基于仿真的评估方法，并进行了计算测试来评估模型的性能。利用台湾某城市的实际数据进行的计算测试表明，随机模型优于确定性模型，具有很大的实际应用潜力。

{"title":"Optimal location planning for battery exchange and charging stations for electric scooters in leisure areas considering stochastic user dwell times","authors":"Chih-Kang Lin , Shangyao Yan , Guan-Ting Ou","doi":"10.1080/19427867.2025.2521080","DOIUrl":"10.1080/19427867.2025.2521080","url":null,"abstract":"<div><div>Stochastic factors significantly affect the optimal planning for locating electric scooter charging stations and scheduling battery exchanges in real operations. A plan that does not account for stochastic factors might turn out to be overly optimistic when implemented in real-world operations, where such stochastic disturbances are common. In this study, we apply mathematical programming and network flow techniques to develop a model for determining the optimal locations of battery exchange and charging stations for electric scooters, while accounting for stochastic user dwell times in leisure areas. The proposed stochastic model, designed to address a location-scheduling problem, is formulated as a mixed-integer network flow problem with side constraints. We develop a simulation-based evaluation method and conduct computational tests to assess the model’s performance. Computational tests using real data from a city in Taiwan show that the stochastic model outperforms the deterministic model and has significant potential for practical applications.</div></div>","PeriodicalId":48974,"journal":{"name":"Transportation Letters-The International Journal of Transportation Research","volume":"17 10","pages":"Pages 1888-1903"},"PeriodicalIF":3.3,"publicationDate":"2025-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145665516","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

Investigation of hit-and-run crash severity through explainable machine learning 通过可解释的机器学习来调查肇事逃逸事故的严重程度

IF 3.3 3区工程技术 Q2 TRANSPORTATION

Transportation Letters-The International Journal of Transportation Research

Pub Date : 2025-11-26 DOI: 10.1080/19427867.2025.2488976

Stella Roussou , Apostolos Ziakopoulos , George Yannis

This study investigates factors influencing the severity of hit-and-run crashes using explainable machine learning techniques. A 5-year dataset from Victoria, Australia, was analyzed with CatBoost algorithms and SHAP values to highlight key severity factors. The presence of police at the crash scene emerges as the most critical determinant, underscoring the importance of law enforcement in mitigating severe crash outcomes. Crashes involving passenger vehicles and those on weekends were also linked to higher severity. The number of vehicles and total persons involved showed non-linear effects, with both low and high values associated with lower severity. Alcohol-related crashes and speed limit zones, while moderately important, revealed complex roles in severity prediction. These novel findings offer valuable insights for targeted interventions and policy-making to mitigate the impact of severe hit-and-run crashes and enhance road safety. In this way, policymakers can develop more effective strategies to reduce the impact of these phenomena.

本研究使用可解释的机器学习技术调查影响肇事逃逸事故严重程度的因素。来自澳大利亚维多利亚州的5年数据集使用CatBoost算法和SHAP值进行分析，以突出关键的严重因素。警察在事故现场的存在是最关键的决定因素，强调了执法在减轻严重事故后果方面的重要性。涉及乘用车和周末的撞车事故也与更高的严重程度有关。车辆数量和涉及的总人数呈非线性影响，低值和高值与较低的严重程度相关。与酒精有关的撞车事故和限速区虽然中等重要，但在严重程度预测中却发挥了复杂的作用。这些新发现为有针对性的干预措施和政策制定提供了宝贵的见解，以减轻严重肇事逃逸事故的影响并加强道路安全。通过这种方式，决策者可以制定更有效的战略来减少这些现象的影响。

{"title":"Investigation of hit-and-run crash severity through explainable machine learning","authors":"Stella Roussou , Apostolos Ziakopoulos , George Yannis","doi":"10.1080/19427867.2025.2488976","DOIUrl":"10.1080/19427867.2025.2488976","url":null,"abstract":"<div><div>This study investigates factors influencing the severity of hit-and-run crashes using explainable machine learning techniques. A 5-year dataset from Victoria, Australia, was analyzed with CatBoost algorithms and SHAP values to highlight key severity factors. The presence of police at the crash scene emerges as the most critical determinant, underscoring the importance of law enforcement in mitigating severe crash outcomes. Crashes involving passenger vehicles and those on weekends were also linked to higher severity. The number of vehicles and total persons involved showed non-linear effects, with both low and high values associated with lower severity. Alcohol-related crashes and speed limit zones, while moderately important, revealed complex roles in severity prediction. These novel findings offer valuable insights for targeted interventions and policy-making to mitigate the impact of severe hit-and-run crashes and enhance road safety. In this way, policymakers can develop more effective strategies to reduce the impact of these phenomena.</div></div>","PeriodicalId":48974,"journal":{"name":"Transportation Letters-The International Journal of Transportation Research","volume":"17 10","pages":"Pages 1755-1770"},"PeriodicalIF":3.3,"publicationDate":"2025-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145665519","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

Transportation Letters-The International Journal of Transportation Research

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀