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

英文中文

Vehicle detection in diverse traffic using an ensemble convolutional neural backbone via feature concatenation 基于特征拼接的集成卷积神经主干在不同交通条件下的车辆检测

IF 3.3 3区工程技术 Q2 TRANSPORTATION

Transportation Letters-The International Journal of Transportation Research

Pub Date : 2024-09-13 DOI: 10.1080/19427867.2023.2250622

Nowadays, deploying an intelligent vehicle detection system (IVDS) in diverse traffic is a work priority. It provides real-time traffic information with vehicle counts and types of vehicles. IVDS deployment in diverse traffic is challenging because different vehicle classes occlude each other on the road. In recent years, convolutional neural network (CNN) based deep learning (DL) methods have attained incredible progress in implementing IVDS. However, most CNN-based DL methods do not include diverse traffic conditions in Asian countries. Also, due to existing feature extraction backbones, they cannot accurately detect multi-scale vehicles. This work proposes an advanced visual computing deep learning (AVCDL) method with a vast labeled vehicle dataset to detect vehicles in diverse traffic. It includes an ensemble backbone and an improved multi-stage vehicle detection head (MSVDH). An ensemble CNN backbone extracts the vehicle features and combines them on a single channel via a feature concatenation. The final detection is carried out by an improved MSVDH that classifies the target vehicles. The proposed method is examined, tested, and evaluated using traffic statistics. It is contrasted with current cutting-edge vehicle detection techniques. It achieves 86.32% mean average precision (mAP) on self-collected diverse traffic labeled dataset (DTLD) and 86.17% mAP on KITTI. Moreover, the real-time performance is validated with NVIDIA Jetson Tx2 and Nano boards. It achieves 15 frames per second (FPS) on Jetson Tx2 and 7 FPS on Jetson Nano.

如今，在多样化交通中部署智能车辆检测系统（IVDS）已成为工作重点。它能提供实时交通信息，包括车辆数量和车辆类型。在多样化交通中部署智能车辆检测系统具有挑战性，因为不同类别的车辆在道路上相互遮挡。近年来，基于卷积神经网络（CNN）的深度学习（DL）方法在实施 IVDS 方面取得了令人难以置信的进展。然而，大多数基于卷积神经网络的深度学习方法并不包括亚洲国家的各种交通状况。此外，由于现有的特征提取骨干，它们无法准确检测多尺度车辆。本研究提出了一种先进的视觉计算深度学习（AVCDL）方法，该方法具有庞大的标注车辆数据集，可检测各种交通状况下的车辆。它包括一个集合骨干网和一个改进的多级车辆检测头（MSVDH）。集合 CNN 主干网提取车辆特征，并通过特征串联将其组合到一个通道上。最终的检测由改进的 MSVDH 完成，它能对目标车辆进行分类。我们利用交通统计数据对所提出的方法进行了检查、测试和评估。它与当前最先进的车辆检测技术进行了对比。该方法在自收集的多样化交通标注数据集（DTLD）上达到了 86.32% 的平均精度（mAP），在 KITTI 上达到了 86.17% 的平均精度（mAP）。此外，NVIDIA Jetson Tx2 和 Nano 板卡也验证了其实时性能。它在 Jetson Tx2 上达到每秒 15 帧 (FPS)，在 Jetson Nano 上达到每秒 7 帧 (FPS)。

{"title":"Vehicle detection in diverse traffic using an ensemble convolutional neural backbone via feature concatenation","authors":"","doi":"10.1080/19427867.2023.2250622","DOIUrl":"10.1080/19427867.2023.2250622","url":null,"abstract":"<div><div>Nowadays, deploying an intelligent vehicle detection system (IVDS) in diverse traffic is a work priority. It provides real-time traffic information with vehicle counts and types of vehicles. IVDS deployment in diverse traffic is challenging because different vehicle classes occlude each other on the road. In recent years, convolutional neural network (CNN) based deep learning (DL) methods have attained incredible progress in implementing IVDS. However, most CNN-based DL methods do not include diverse traffic conditions in Asian countries. Also, due to existing feature extraction backbones, they cannot accurately detect multi-scale vehicles. This work proposes an advanced visual computing deep learning (AVCDL) method with a vast labeled vehicle dataset to detect vehicles in diverse traffic. It includes an ensemble backbone and an improved multi-stage vehicle detection head (MSVDH). An ensemble CNN backbone extracts the vehicle features and combines them on a single channel via a feature concatenation. The final detection is carried out by an improved MSVDH that classifies the target vehicles. The proposed method is examined, tested, and evaluated using traffic statistics. It is contrasted with current cutting-edge vehicle detection techniques. It achieves 86.32% mean average precision (mAP) on self-collected diverse traffic labeled dataset (DTLD) and 86.17% mAP on KITTI. Moreover, the real-time performance is validated with NVIDIA Jetson Tx2 and Nano boards. It achieves 15 frames per second (FPS) on Jetson Tx2 and 7 FPS on Jetson Nano.</div></div>","PeriodicalId":48974,"journal":{"name":"Transportation Letters-The International Journal of Transportation Research","volume":"16 8","pages":"Pages 838-856"},"PeriodicalIF":3.3,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45326643","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

Simulation and optimization of dynamic-hybrid parking reservation strategies for one-way vehicle-sharing systems 单向车辆共享系统动态混合停车预约策略的仿真与优化

IF 3.3 3区工程技术 Q2 TRANSPORTATION

Transportation Letters-The International Journal of Transportation Research

Pub Date : 2024-09-13 DOI: 10.1080/19427867.2023.2254527

In this paper, we explore the regulation of one-way station-based vehicle-sharing system (OSVS) through dynamic-hybrid parking reservation policies. We first propose a dynamic-hybrid parking reservation policy. This policy only requires trips with expected travel distances shorter than a specific threshold to make a parking reservation. The distance threshold varies with time. We develop a discrete event simulation model based on the O2DES (object-oriented discrete event simulation) framework to compare the dynamic-hybrid parking reservation (DHPR) strategy with the no-reservation (NR), static-hybrid parking reservation (SHPR) and complete parking reservation (CPR) strategies. Furthermore, we propose a simulation-optimization model and an Elitism-based Genetic algorithm with the optimal computation budget allocation to determine the fleet size, station capacity, and dynamic reservation distance threshold. The analysis of case studies of a real-world system indicates that DHPR is always superior to NR, SHPR and CPR.

在本文中，我们探讨了通过动态混合停车位预订政策对基于单向车站的车辆共享系统（OSVS）进行调节的问题。我们首先提出了一种动态混合停车预约政策。该政策只要求预期出行距离小于特定阈值的出行进行停车预约。距离阈值随时间变化。我们基于 O2DES（面向对象离散事件仿真）框架开发了一个离散事件仿真模型，将动态混合停车位预订（DHPR）策略与无预订（NR）、静态混合停车位预订（SHPR）和完全停车位预订（CPR）策略进行比较。此外，我们还提出了一个仿真优化模型和一种基于litism的遗传算法，通过优化计算预算分配来确定车队规模、站点容量和动态预约距离阈值。对实际系统的案例分析表明，DHPR 始终优于 NR、SHPR 和 CPR。

引用次数: 0

Determination of the optimal connected and automated vehicles platoon size based on the merging success rate 基于归并成功率的网联与自动驾驶车辆最优队列大小确定

IF 3.3 3区工程技术 Q2 TRANSPORTATION

Transportation Letters-The International Journal of Transportation Research

Pub Date : 2024-09-13 DOI: 10.1080/19427867.2023.2252220

The platoon size is a critical parameter in connected and automated vehicle (CAV) platoon configuration. However, the optimal platoon size configuration for the mixed human-driven vehicles (HVs) and CAVs traffic has not been well-studied, especially in merging areas. This paper aims to determine the optimal platoon size in the merge area through numerical analysis. Specifically, the existing merge probability calculation model is improved considering the impact of mainline random platoon size on on-ramp vehicles. In the improved model, the CAV platoon is treated as a vehicle with different lengths, and the headway between the platoon and single vehicle and the headway between the platoons are related to the maximum platoon size and CAV penetration rate. Three key parameters, namely the CAV penetration rate, acceleration lane length, and mainline traffic volume, were combined at various values. Based on this input, the relationship between the success rate and the platoon size was analyzed. The numerical analysis results indicate that: (1) when the CAV penetration rate is 10% ~30%, the merge success rate increases and stabilizes as the platoon size increases, and the optimal platoon size is 4 ~ 6. (2) When the CAV penetration rate is 40% ~70%, the trend of merge success rate varies with increasing platoon size under different mainline traffic volumes and acceleration lane lengths. Under the situation with lower traffic and longer acceleration length, the merge success rate tends to decline easier with larger platoon sizes, with 3 ~ 8 being the optimal platoon size. (3) When the CAV penetration rate is 80% ~90%, as the platoon size increases, the merging success rate tends to increase to the highest point and decrease. The optimal platoon size is 3 ~ 5. Finally, the validity of the theoretical model is confirmed through simulation experiments, and its limitations are discussed.

排规模是互联和自动驾驶车辆（CAV）排配置中的一个关键参数。然而，人类驾驶车辆（HVs）和 CAVs 混合交通的最佳排规模配置尚未得到充分研究，尤其是在并线区域。本文旨在通过数值分析确定并线区域的最佳排规模。具体来说，考虑到主线随机排数对匝道车辆的影响，对现有的并线概率计算模型进行了改进。在改进后的模型中，CAV 排被视为不同长度的车辆，排与单车之间的车头间距和排与排之间的车头间距与最大排规模和 CAV 渗透率相关。三个关键参数，即 CAV 渗透率、加速车道长度和主线交通量，以不同的值进行组合。在此基础上，分析了成功率与排规模之间的关系。数值分析结果表明(1）当 CAV 渗透率为 10% ~30% 时，并线成功率随着排数的增加而增加并趋于稳定，最佳排数为 4 ~ 6。(2) 当 CAV 渗透率为 40% ~70% 时，在不同的主线交通流量和加速车道长度下，并线成功率的变化趋势随排数的增加而变化。在交通流量较小、加速车道长度较长的情况下，并线成功率随排数增加而下降，3 ~ 8 排为最佳排数；在交通流量较小、加速车道长度较长的情况下，并线成功率随排数增加而下降，3 ~ 8 排为最佳排数。(3）当 CAV 渗透率为 80% ~ 90% 时，随着排数的增加，并线成功率趋于上升到最高点后下降。最佳排数为 3 ~ 5。最后，通过仿真实验证实了理论模型的正确性，并讨论了其局限性。

{"title":"Determination of the optimal connected and automated vehicles platoon size based on the merging success rate","authors":"","doi":"10.1080/19427867.2023.2252220","DOIUrl":"10.1080/19427867.2023.2252220","url":null,"abstract":"<div><div>The platoon size is a critical parameter in connected and automated vehicle (CAV) platoon configuration. However, the optimal platoon size configuration for the mixed human-driven vehicles (HVs) and CAVs traffic has not been well-studied, especially in merging areas. This paper aims to determine the optimal platoon size in the merge area through numerical analysis. Specifically, the existing merge probability calculation model is improved considering the impact of mainline random platoon size on on-ramp vehicles. In the improved model, the CAV platoon is treated as a vehicle with different lengths, and the headway between the platoon and single vehicle and the headway between the platoons are related to the maximum platoon size and CAV penetration rate. Three key parameters, namely the CAV penetration rate, acceleration lane length, and mainline traffic volume, were combined at various values. Based on this input, the relationship between the success rate and the platoon size was analyzed. The numerical analysis results indicate that: (1) when the CAV penetration rate is 10% ~30%, the merge success rate increases and stabilizes as the platoon size increases, and the optimal platoon size is 4 ~ 6. (2) When the CAV penetration rate is 40% ~70%, the trend of merge success rate varies with increasing platoon size under different mainline traffic volumes and acceleration lane lengths. Under the situation with lower traffic and longer acceleration length, the merge success rate tends to decline easier with larger platoon sizes, with 3 ~ 8 being the optimal platoon size. (3) When the CAV penetration rate is 80% ~90%, as the platoon size increases, the merging success rate tends to increase to the highest point and decrease. The optimal platoon size is 3 ~ 5. Finally, the validity of the theoretical model is confirmed through simulation experiments, and its limitations are discussed.</div></div>","PeriodicalId":48974,"journal":{"name":"Transportation Letters-The International Journal of Transportation Research","volume":"16 8","pages":"Pages 857-871"},"PeriodicalIF":3.3,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42014197","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

Crossing conflict models for urban un-signalized T-intersections in India 印度城市无信号t型交叉口的交叉冲突模型

IF 3.3 3区工程技术 Q2 TRANSPORTATION

Transportation Letters-The International Journal of Transportation Research

Pub Date : 2024-09-13 DOI: 10.1080/19427867.2023.2250161

Traffic conflict is frequently utilized as a stand-in for crashes for analyzing traffic safety from a broader perspective for varying roadways and traffic conditions. In Indian heterogeneous traffic conditions, vehicles with various static and dynamic properties interact simultaneously in longitudinal and lateral directions, forming traffic conflicts. To this end, the present study develops crossing conflict-based safety performance functions (C-SPFs) for eight urban un-signalized T-intersections. The video-graphic survey approach was used to gather the necessary traffic data with different intersection and traffic flow characteristics. After that, from the recorded video, traffic conflicts were identified using the Post encroachment time (PET) for the selected eight study intersections. Based on the PET values, crossing conflicts were initially divided into critical conflicts (CC) and non-critical conflicts (NCC). Then, using the Poisson-Tweedie regression technique, crossing conflicts were modeled as a function of traffic flow and intersection-related parameters. The findings showed that the most important factors defining the number of CC and NCC are intersection geometry (with or without Central Island), time of day, traffic volume, and composition (offending and conflicting approach). Based on the study’s findings, city planners and traffic engineers estimate the number of CC and NCC; as a result, they may project the necessary laws, rules, and regulations to enhance traffic safety operations.

交通冲突经常被用来代替碰撞事故，以便从更广阔的角度分析不同道路和交通状况下的交通安全。在印度的异构交通条件下，具有各种静态和动态特性的车辆在纵向和横向同时发生相互作用，形成交通冲突。为此，本研究为八个城市非信号灯 T 型交叉路口开发了基于交叉冲突的安全性能函数（C-SPF）。本研究采用视频图形调查方法，收集不同交叉口和交通流特征的必要交通数据。然后，根据录制的视频，使用后侵占时间（PET）对选定的八个研究交叉口的交通冲突进行识别。根据 PET 值，交叉口冲突被初步分为关键冲突（CC）和非关键冲突（NCC）。然后，利用泊松-特威迪回归技术，将交叉口冲突模拟为交通流量和交叉口相关参数的函数。研究结果表明，决定交叉口冲突和非关键冲突数量的最重要因素是交叉口的几何形状（有无中央岛）、一天中的时间、交通流量和组成（违规和冲突方向）。根据研究结果，城市规划者和交通工程师可估算出 CC 和 NCC 的数量，并据此制定必要的法律、规则和法规，以加强交通安全运行。

{"title":"Crossing conflict models for urban un-signalized T-intersections in India","authors":"","doi":"10.1080/19427867.2023.2250161","DOIUrl":"10.1080/19427867.2023.2250161","url":null,"abstract":"<div><div>Traffic conflict is frequently utilized as a stand-in for crashes for analyzing traffic safety from a broader perspective for varying roadways and traffic conditions. In Indian heterogeneous traffic conditions, vehicles with various static and dynamic properties interact simultaneously in longitudinal and lateral directions, forming traffic conflicts. To this end, the present study develops crossing conflict-based safety performance functions (C-SPFs) for eight urban un-signalized T-intersections. The video-graphic survey approach was used to gather the necessary traffic data with different intersection and traffic flow characteristics. After that, from the recorded video, traffic conflicts were identified using the Post encroachment time (PET) for the selected eight study intersections. Based on the PET values, crossing conflicts were initially divided into critical conflicts (CC) and non-critical conflicts (NCC). Then, using the Poisson-Tweedie regression technique, crossing conflicts were modeled as a function of traffic flow and intersection-related parameters. The findings showed that the most important factors defining the number of CC and NCC are intersection geometry (with or without Central Island), time of day, traffic volume, and composition (offending and conflicting approach). Based on the study’s findings, city planners and traffic engineers estimate the number of CC and NCC; as a result, they may project the necessary laws, rules, and regulations to enhance traffic safety operations.</div></div>","PeriodicalId":48974,"journal":{"name":"Transportation Letters-The International Journal of Transportation Research","volume":"16 8","pages":"Pages 829-837"},"PeriodicalIF":3.3,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42586026","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

Performance-based transit subsidy allocation scheme to fulfill multiple policy criteria 基于绩效的公交补贴分配方案，以满足多个政策标准

IF 3.3 3区工程技术 Q2 TRANSPORTATION

Transportation Letters-The International Journal of Transportation Research

Pub Date : 2024-09-13 DOI: 10.1080/19427867.2023.2247895

Performance-based subsidy allocation schemes are typically intended to satisfy a single policy goal (e.g. social welfare maximization) and often do not include objective approaches to quantifying bus service efficiency. This paper proposes a framework for network data envelopment analysis and introduces an innovative transit subsidy allocation scheme with a fixed budget that fulfills multiple policy criteria. The proposed basic scheme minimizes the maximum deviation from efficient allocation in proportion to the operating scales across all routes in a two-stage production system. Multiple policy criteria are then added to the basic scheme as additional goal components. The proposed scheme is evaluated by using an empirical dataset of 344 subsidized intercity bus routes collected from 20 Taiwanese bus operators. The results demonstrate that the subsidies allocated on the basis of the proposed scheme can satisfy the policy criteria incorporated into the scheme. The proposed modeling framework is flexible, and therefore, local governments can easily incorporate policy criteria into the scheme according to their own interests and needs.

基于绩效的补贴分配方案通常旨在满足单一政策目标（如社会福利最大化），通常不包括量化公交服务效率的客观方法。本文提出了一个网络数据包络分析框架，并介绍了一种创新的公交补贴分配方案，该方案预算固定，可满足多种政策标准。所提出的基本方案最大限度地减小了与两阶段生产系统中所有线路的运营规模成比例的有效分配的最大偏差。然后在基本方案中加入多个政策标准，作为额外的目标组成部分。通过使用从 20 家台湾巴士运营商处收集的 344 条受补贴城际巴士线路的经验数据集，对所提出的方案进行了评估。结果表明，根据建议方案分配的补贴能够满足方案中的政策标准。建议的建模框架非常灵活，因此地方政府可以根据自己的利益和需要轻松地将政策标准纳入该方案。

{"title":"Performance-based transit subsidy allocation scheme to fulfill multiple policy criteria","authors":"","doi":"10.1080/19427867.2023.2247895","DOIUrl":"10.1080/19427867.2023.2247895","url":null,"abstract":"<div><div>Performance-based subsidy allocation schemes are typically intended to satisfy a single policy goal (e.g. social welfare maximization) and often do not include objective approaches to quantifying bus service efficiency. This paper proposes a framework for network data envelopment analysis and introduces an innovative transit subsidy allocation scheme with a fixed budget that fulfills multiple policy criteria. The proposed basic scheme minimizes the maximum deviation from efficient allocation in proportion to the operating scales across all routes in a two-stage production system. Multiple policy criteria are then added to the basic scheme as additional goal components. The proposed scheme is evaluated by using an empirical dataset of 344 subsidized intercity bus routes collected from 20 Taiwanese bus operators. The results demonstrate that the subsidies allocated on the basis of the proposed scheme can satisfy the policy criteria incorporated into the scheme. The proposed modeling framework is flexible, and therefore, local governments can easily incorporate policy criteria into the scheme according to their own interests and needs.</div></div>","PeriodicalId":48974,"journal":{"name":"Transportation Letters-The International Journal of Transportation Research","volume":"16 8","pages":"Pages 814-828"},"PeriodicalIF":3.3,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49162188","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

What causes severe truck crashes on the flat and mountainous expressways? A comparative study in China 是什么导致卡车在平坦多山的高速公路上发生严重车祸？中国比较研究

IF 3.3 3区工程技术 Q2 TRANSPORTATION

Transportation Letters-The International Journal of Transportation Research

Pub Date : 2024-09-13 DOI: 10.1080/19427867.2023.2254126

The severity of collisions involving heavy trucks exhibits a difference between the flat and mountainous expressways. Based on 1,175 records of truck crashes from 2015 to 2020 on two typical expressways in China, a heteroskedastic ordered probit model was applied to determine the significant factors among driver-vehicle-roadway-environment interactions and their marginal effects on the collision severity outcomes. The modeling results demonstrated that some variables (i.e. speeding and risky following behaviors of drivers, existence of curves and downgrades, adverse weather, etc.) are significant predictors of truck crashes on both flat and mountainous expressways. In contrast, some variables were significantly correlated with truck crashes on only the flat expressway (upgrade section) or the mountainous expressway (involvement of multiple vehicles, truck’s overloading status, nighttime period). The findings, taken collectively, may be valuable as a reference for drafting traffic rules and implementing technical solutions to ensure a safer traffic environment for heavy trucks on expressways.

涉及重型卡车的碰撞事故的严重程度在平坦高速公路和山区高速公路之间存在差异。基于 2015 年至 2020 年在中国两条典型高速公路上发生的 1175 起卡车碰撞记录，应用异方差有序 probit 模型确定了驾驶员-车辆-道路-环境交互作用中的重要因素及其对碰撞严重性结果的边际效应。建模结果表明，一些变量（即驾驶员的超速和危险跟车行为、弯道和下坡的存在、恶劣天气等）对卡车在平坦和多山高速公路上的碰撞具有显著的预测作用。与此相反，一些变量只与卡车在平坦高速公路（升级路段）或山区高速公路（涉及多辆车、卡车超载状态、夜间时段）上的碰撞事故有显著相关性。综合上述研究结果，我们认为这些研究结果对于制定交通规则和实施技术解决方案以确保重型卡车在高速公路上享有更安全的交通环境具有重要的参考价值。

{"title":"What causes severe truck crashes on the flat and mountainous expressways? A comparative study in China","authors":"","doi":"10.1080/19427867.2023.2254126","DOIUrl":"10.1080/19427867.2023.2254126","url":null,"abstract":"<div><div>The severity of collisions involving heavy trucks exhibits a difference between the flat and mountainous expressways. Based on 1,175 records of truck crashes from 2015 to 2020 on two typical expressways in China, a heteroskedastic ordered probit model was applied to determine the significant factors among driver-vehicle-roadway-environment interactions and their marginal effects on the collision severity outcomes. The modeling results demonstrated that some variables (i.e. speeding and risky following behaviors of drivers, existence of curves and downgrades, adverse weather, etc.) are significant predictors of truck crashes on both flat and mountainous expressways. In contrast, some variables were significantly correlated with truck crashes on only the flat expressway (upgrade section) or the mountainous expressway (involvement of multiple vehicles, truck’s overloading status, nighttime period). The findings, taken collectively, may be valuable as a reference for drafting traffic rules and implementing technical solutions to ensure a safer traffic environment for heavy trucks on expressways.</div></div>","PeriodicalId":48974,"journal":{"name":"Transportation Letters-The International Journal of Transportation Research","volume":"16 8","pages":"Pages 883-893"},"PeriodicalIF":3.3,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45871023","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 a pedestrian call extension and cancelation system at a signalized midblock crossing 在有信号的街区中间交叉路口的行人呼叫延长和取消系统的评估

IF 3.3 3区工程技术 Q2 TRANSPORTATION

Transportation Letters-The International Journal of Transportation Research

Pub Date : 2024-09-13 DOI: 10.1080/19427867.2023.2254959

Unnecessary vehicular delay occurs at actuated signalized intersections during ‘ghost’ pedestrian intervals when a pedestrian activates the pushbutton then jaywalks. Safety issues arise when pedestrians remain in the crosswalk at the end of the Flashing Don’t Walk phase, and vehicles receive a circular green. A Pedestrian Call Extension and Cancelation System was evaluated at a signalized midblock crossing in Hillsboro, OR. Thermal sensors and controller logic were implemented to detect pedestrians and passively cancel or extend calls. A Case 1-after study was conducted to evaluate how vehicular delay and pedestrian behavior was impacted by the system. 1,649 observations Case 1 and 3,002 observations after system installation were recorded. Pedestrian delay did not change, but average vehicular stop time delay significantly decreased by 12 sec. 76 extensions occurred with 99.2% accuracy. Findings suggest that transportation agencies could improve driver waiting time and pedestrian safety by using dynamic passive pedestrian detection.

在 "幽灵 "行人间隔期间，当行人启动按钮然后乱穿马路时，就会在启用信号灯的交叉路口出现不必要的车辆延误。当行人在 "闪灯禁止通行 "阶段结束时仍留在人行横道上，而车辆获得环形绿灯时，就会出现安全问题。在俄勒冈州希尔斯伯勒的一个信号灯控制的中间街区交叉路口，对行人呼叫延长和取消系统进行了评估。采用热传感器和控制器逻辑来检测行人，并被动取消或延长呼叫。进行了案例 1 后研究，以评估该系统对车辆延误和行人行为的影响。共记录了 1649 次案例 1 观察和系统安装后的 3002 次观察。行人延迟时间没有变化，但车辆平均停车延迟时间显著减少了 12 秒。76 次延长时间的准确率为 99.2%。研究结果表明，交通机构可以通过使用动态被动行人检测来改善驾驶员等待时间和行人安全。

引用次数: 0

Improving bus arrival time predictors using only public transport API data 改进仅使用公共交通API数据的巴士到达时间预测

IF 3.3 3区工程技术 Q2 TRANSPORTATION

Transportation Letters-The International Journal of Transportation Research

Pub Date : 2024-09-13 DOI: 10.1080/19427867.2023.2245994

Accurate prediction of bus arrival times can greatly benefit public transport users, allowing them to better plan their journeys in cities. The usual Expected Time of Arrival (ETA) estimators provided to citizens use all the information available to the bus service provider (vehicle position, traffic, etc.); in this paper we propose a procedure to improve these estimators that relies solely on historical ETA records provided by public transport councils through application programming interfaces (APIs). This improvement is achieved by means of a machine learning scheme that predicts and corrects the systematic errors of the available ETA estimators. Significant improvements in terms of error mean and standard deviation are achieved for the Madrid and Paris bus fleets. These robust results and the fact that the proposed scheme uses only historical and online information provided by APIs, without requiring the cooperation of the service provider, support the suitability of the proposed method for general public benefit applications toward the sustainability of cities.

准确预测公交车的到达时间对公共交通用户大有裨益，可以让他们更好地规划自己在城市中的行程。通常提供给市民的预计到达时间（ETA）估算器使用的是公交服务提供商可获得的所有信息（车辆位置、交通状况等）；在本文中，我们提出了一种改进这些估算器的程序，该程序仅依赖于公共交通委员会通过应用程序接口（API）提供的历史 ETA 记录。这种改进是通过一种机器学习方案来实现的，该方案可预测并纠正现有 ETA 估算器的系统误差。马德里和巴黎公交车队在误差平均值和标准偏差方面均有显著改善。这些稳健的结果，以及拟议方案仅使用由应用程序接口（API）提供的历史和在线信息，而无需服务提供商的合作这一事实，都证明了拟议方法适用于促进城市可持续发展的一般公益应用。

引用次数: 0

The development of automated driving in China: a comparison to Germany regarding the government policies, laws and regulations, and industries 自动驾驶在中国的发展:与德国在政府政策、法律法规和行业方面的比较

IF 3.3 3区工程技术 Q2 TRANSPORTATION

Transportation Letters-The International Journal of Transportation Research

Pub Date : 2024-09-13 DOI: 10.1080/19427867.2023.2238467

Autonomous technologies have developed incrementally, especially in the car industry. Countries worldwide are giving impetus to developing automated driving (AD) and autonomous vehicles (AVs). China is used as an example of an innovative development model for autonomous driving that has significant practical implications for AD’s development in the global context. Germany also keeps its role as a global hub for the AVs industry, and it has released the most advanced AD laws. This research conducted a thorough comparison of related policies, regulations, and industries in China and Germany in an effort to support the development of AD in China. Further, AD’s advantages, disadvantages, opportunities, and threats in China and Germany are discussed. It sought to identify any shortages of AD in China and find an efficient way to enhance AD cooperation between China and Germany. Based on the dissimilarity of the current status and the disparity in policies, a series of countermeasures and suggestions for the development of the Chinese AD are presented in this study.

自动驾驶技术是逐步发展起来的，尤其是在汽车行业。世界各国都在大力发展自动驾驶（AD）和自动驾驶汽车（AV）。中国是自动驾驶创新发展模式的典范，对全球自动驾驶的发展具有重要的现实意义。德国也保持着全球自动驾驶汽车产业中心的地位，并发布了最先进的自动驾驶汽车法律。本研究对中德两国的相关政策、法规和产业进行了深入比较，以期为中国的自动驾驶发展提供支持。此外，还讨论了中德两国在反倾销方面的优势、劣势、机遇和威胁。研究试图找出中国在反倾销方面的不足，并找到加强中德反倾销合作的有效途径。基于现状的差异和政策的不统一，本研究提出了一系列促进中国反倾销发展的对策和建议。

{"title":"The development of automated driving in China: a comparison to Germany regarding the government policies, laws and regulations, and industries","authors":"","doi":"10.1080/19427867.2023.2238467","DOIUrl":"10.1080/19427867.2023.2238467","url":null,"abstract":"<div><div>Autonomous technologies have developed incrementally, especially in the car industry. Countries worldwide are giving impetus to developing automated driving (AD) and autonomous vehicles (AVs). China is used as an example of an innovative development model for autonomous driving that has significant practical implications for AD’s development in the global context. Germany also keeps its role as a global hub for the AVs industry, and it has released the most advanced AD laws. This research conducted a thorough comparison of related policies, regulations, and industries in China and Germany in an effort to support the development of AD in China. Further, AD’s advantages, disadvantages, opportunities, and threats in China and Germany are discussed. It sought to identify any shortages of AD in China and find an efficient way to enhance AD cooperation between China and Germany. Based on the dissimilarity of the current status and the disparity in policies, a series of countermeasures and suggestions for the development of the Chinese AD are presented in this study.</div></div>","PeriodicalId":48974,"journal":{"name":"Transportation Letters-The International Journal of Transportation Research","volume":"16 8","pages":"Pages 933-941"},"PeriodicalIF":3.3,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46066674","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

Quantum computing to solve scenario-based stochastic time-dependent shortest path routing 用量子计算解决基于场景的随机时变最短路径路由问题

IF 3.3 3区工程技术 Q2 TRANSPORTATION

Transportation Letters-The International Journal of Transportation Research

Pub Date : 2024-09-13 DOI: 10.1080/19427867.2023.2238461

Networks are inherently uncertain and require scenario-based approaches to handle variability. In stochastic and time-dependent networks, optimal solutions cannot always be found using deterministic algorithms. Furthermore, Stochastic Time Dependent Shortest Path problems are known to be NP-hard. Emerging Quantum Computing Methods are providing new ways to address these problems. In this paper, the STDSP problem is formulated as a Quadratic Constrained Binary Optimization Problem. We show that in the case of independent link costs, the size of the problem increases exponentially. Finally, we find that using the quantum solver provides a linear computational experience with respect to the size of the problem. The proposed solution has implications for stochastic networks across different contexts including communications, traffic, industrial operations, electricity, water, broader supply chains, and epidemiology.

网络本身具有不确定性，需要基于情景的方法来处理可变性。在随机和随时间变化的网络中，使用确定性算法不一定能找到最优解。此外，随机时变最短路径问题是众所周知的 NP 难问题。新兴的量子计算方法为解决这些问题提供了新的途径。本文将 STDSP 问题表述为二次约束二元优化问题。我们发现，在链路成本独立的情况下，问题的规模会呈指数级增长。最后，我们发现，使用量子求解器可提供与问题规模相关的线性计算体验。所提出的解决方案对通信、交通、工业运营、电力、水、更广泛的供应链和流行病学等不同领域的随机网络都有影响。

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.

﹀