International Journal of Transportation Science and Technology最新文献_第4页

Demand-aware distributed pathfinding for repositioning vehicles in shared-use autonomous mobility services 基于需求感知的分布式寻路方法，用于共享自动出行服务中车辆的重新定位

IF 4.8 Q2 TRANSPORTATION

International Journal of Transportation Science and Technology

Pub Date : 2025-09-01 DOI: 10.1016/j.ijtst.2024.10.004

Haimanti Bala, Monika Filipovska

Shared-use autonomous mobility services (SAMSs) have the potential to provide accessible and demand-responsive mobility to passengers, while benefitting from autonomous vehicle (AV) technology and bypassing challenges related to supply-side incentives or individual driver goals. SAMS operators typically aim to achieve efficiency and improved service quality in their fleet operations, both of which are further enabled by the use of AVs. Specifically, fleet repositioning decisions in anticipation of future demand can improve service quality, but existing approaches in the literature seldom consider the problem of routing repositioning vehicles in a way that further improves SAMS objectives. This paper presents an approach for demand-aware distributed pathfinding for repositioning vehicles, which can supplement existing vehicle repositioning approaches. The problem is formulated with a multi-criteria objective that minimizes the vehicles’ total travel time and maximizes their total demand-serving potential, while distributing that potential equitably among the ride-seeking passengers across the transportation network. We evaluate the proposed approach via numerical experiments using an agent-based simulation of SAMS operations in the network of Manhattan in New York City. The proposed approach is compared to a baseline simple shortest path approach for routing the repositioning vehicles. The results demonstrate that mean passenger waiting times for pick-up can be reduced, while also reducing the total vehicle miles and the empty miles travelled due to repositioning. Thus, the proposed approach can help improve the overall system performance in terms of both service quality and efficiency metrics, relative to the baseline approach.

共享自动驾驶服务（sams）有潜力为乘客提供可访问和需求响应的移动性，同时受益于自动驾驶汽车（AV）技术，并绕过与供给侧激励或个人驾驶员目标相关的挑战。SAMS运营商通常的目标是提高车队运营的效率和服务质量，而使用自动驾驶汽车可以进一步实现这两个目标。具体而言，基于对未来需求的预测的车队重新定位决策可以提高服务质量，但现有文献中的方法很少考虑以进一步提高SAMS目标的方式重新定位车辆的问题。提出了一种基于需求感知的车辆重新定位分布式寻路方法，可以对现有的车辆重新定位方法进行补充。这个问题是用一个多标准目标来制定的，这个目标是最小化车辆的总旅行时间，最大化它们的总需求服务潜力，同时在整个交通网络中公平地分配这种潜力给寻求乘车的乘客。我们通过在纽约市曼哈顿网络中使用基于代理的SAMS操作模拟的数值实验来评估所提出的方法。将该方法与用于重新定位车辆的基线简单最短路径方法进行了比较。结果表明，该方法可以减少乘客平均等待接送的时间，同时也减少了车辆总里程和由于重新定位而行驶的空里程。因此，相对于基线方法，建议的方法可以在服务质量和效率度量方面帮助改进整个系统的性能。

{"title":"Demand-aware distributed pathfinding for repositioning vehicles in shared-use autonomous mobility services","authors":"Haimanti Bala, Monika Filipovska","doi":"10.1016/j.ijtst.2024.10.004","DOIUrl":"10.1016/j.ijtst.2024.10.004","url":null,"abstract":"<div><div>Shared-use autonomous mobility services (SAMSs) have the potential to provide accessible and demand-responsive mobility to passengers, while benefitting from autonomous vehicle (AV) technology and bypassing challenges related to supply-side incentives or individual driver goals. SAMS operators typically aim to achieve efficiency and improved service quality in their fleet operations, both of which are further enabled by the use of AVs. Specifically, fleet repositioning decisions in anticipation of future demand can improve service quality, but existing approaches in the literature seldom consider the problem of routing repositioning vehicles in a way that further improves SAMS objectives. This paper presents an approach for demand-aware distributed pathfinding for repositioning vehicles, which can supplement existing vehicle repositioning approaches. The problem is formulated with a multi-criteria objective that minimizes the vehicles’ total travel time and maximizes their total demand-serving potential, while distributing that potential equitably among the ride-seeking passengers across the transportation network. We evaluate the proposed approach via numerical experiments using an agent-based simulation of SAMS operations in the network of Manhattan in New York City. The proposed approach is compared to a baseline simple shortest path approach for routing the repositioning vehicles. The results demonstrate that mean passenger waiting times for pick-up can be reduced, while also reducing the total vehicle miles and the empty miles travelled due to repositioning. Thus, the proposed approach can help improve the overall system performance in terms of both service quality and efficiency metrics, relative to the baseline approach.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"19 ","pages":"Pages 240-255"},"PeriodicalIF":4.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145323785","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

Commercial adaptive cruise control (ACC) and capacity drop at freeway bottlenecks 商用自适应巡航控制（ACC）与高速公路瓶颈处的容量下降

IF 4.8 Q2 TRANSPORTATION

International Journal of Transportation Science and Technology

Pub Date : 2025-09-01 DOI: 10.1016/j.ijtst.2024.07.011

Servet Lapardhaja , Yaobang Gong , Md Tausif Murshed , Xingan (David) Kan

Vehicle automation has already become commercially available. Today’s mainstream vehicles are equipped with adaptive cruise control (ACC) to automate longitudinal car-following (CF). However, ACC’s limited detection range and delayed reaction hinder the vehicle’s ability to respond promptly to speed changes, and ACC could amplify minor disturbance into severe stop-and-go waves and form queues at bottlenecks. Consequently, the discharge flow could be lower than the maximum flow observed in absence of queues or congested conditions, also known as capacity drop. Microscopic simulation of freeway bottlenecks consisting of a single lane with reduced speed zone, a multilane with an on-ramp merge, and a multilane with an off-ramp diverge demonstrates that ACC vehicles lead to capacity drop at freeway bottlenecks. For the single lane reduced speed zone, the extent of capacity drop for ACC could be either less or more severe than that of human driven vehicles. However, the multilane freeway on-ramp and off-ramp bottlenecks are more susceptible to capacity drop than human driven vehicles, since ACC significantly amplifies disturbances caused by lane changes, merging, and diverging.

汽车自动化已经商业化。如今的主流汽车都配备了自适应巡航控制系统（ACC）来实现纵向汽车跟随（CF）的自动化。然而，ACC有限的检测范围和延迟的反应阻碍了车辆对速度变化的快速响应能力，并且ACC可能会将轻微的干扰放大为严重的走走停停波，并在瓶颈处形成队列。因此，放电流量可能低于在没有队列或拥塞条件下观察到的最大流量，也称为容量下降。高速公路瓶颈微观仿真包括单车道减速带、多车道入匝道合流和多车道出匝道分流，结果表明ACC车辆导致高速公路瓶颈处的通行能力下降。在单车道减速区，自动驾驶汽车的能力下降程度可能比人类驾驶的车辆更小，也可能更严重。然而，与人类驾驶的车辆相比，多车道高速公路的入口匝道和出口匝道瓶颈更容易受到容量下降的影响，因为ACC显著放大了车道变化、合并和分流造成的干扰。

{"title":"Commercial adaptive cruise control (ACC) and capacity drop at freeway bottlenecks","authors":"Servet Lapardhaja , Yaobang Gong , Md Tausif Murshed , Xingan (David) Kan","doi":"10.1016/j.ijtst.2024.07.011","DOIUrl":"10.1016/j.ijtst.2024.07.011","url":null,"abstract":"<div><div>Vehicle automation has already become commercially available. Today’s mainstream vehicles are equipped with adaptive cruise control (ACC) to automate longitudinal car-following (CF). However, ACC’s limited detection range and delayed reaction hinder the vehicle’s ability to respond promptly to speed changes, and ACC could amplify minor disturbance into severe stop-and-go waves and form queues at bottlenecks. Consequently, the discharge flow could be lower than the maximum flow observed in absence of queues or congested conditions, also known as capacity drop. Microscopic simulation of freeway bottlenecks consisting of a single lane with reduced speed zone, a multilane with an on-ramp merge, and a multilane with an off-ramp diverge demonstrates that ACC vehicles lead to capacity drop at freeway bottlenecks. For the single lane reduced speed zone, the extent of capacity drop for ACC could be either less or more severe than that of human driven vehicles. However, the multilane freeway on-ramp and off-ramp bottlenecks are more susceptible to capacity drop than human driven vehicles, since ACC significantly amplifies disturbances caused by lane changes, merging, and diverging.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"19 ","pages":"Pages 65-77"},"PeriodicalIF":4.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145323652","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

Improved model for pavement performance prediction based on recurrent neural network using LTPP database 基于LTPP数据库的递归神经网络路面性能预测改进模型

IF 4.8 Q2 TRANSPORTATION

International Journal of Transportation Science and Technology

Pub Date : 2025-09-01 DOI: 10.1016/j.ijtst.2024.08.005

Luchuan Chen , Hui Li , Shuo Wang , Fei Shan , Yuzhao Han , Guoqiang Zhong

Accurate pavement performance prediction plays a critical role in formulating maintenance and repair strategies for transportation departments, enabling the achievement of better pavement performance with limited financial resources. However, due to the intricate influence of numerous factors on pavement performance deterioration, improving the accuracy of pavement performance prediction poses a challenge for conventional models. Therefore, the aim of this study is to establish a machine learning-based pavement performance prediction model. First, this study considers five factors that affect pavement performance, including pavement initial performance indicators, traffic loads, weather, pavement structure, and maintenance measures, and identifies 15 specific indicators that affect pavement performance based on these five factors. Then, based on the the long-term pavement performance (LTPP) database, the study screens and summarizes these indicators, obtaining 2 464 high-quality pavement performance data for pavement conditions index (PCI) prediction and 3 238 high-quality pavement performance data for international roughness index (IRI) prediction. Finally, three distinct prediction models are established, namely, the fully connected neural network (FCNN) model, the long short-term memory (LSTM) model, and the combined LSTM-attention model. The study shows that the LSTM-attention model performs significantly better than the FCNN and LSTM models, with an R² coefficient of determination of 0.81 for PCI and 0.79 for IRI. The innovation of this paper is that the authors have introduced the attention mechanism on the basic of the LSTM model, which makes the fitting accuracy of the prediction model further improved.

准确的路面性能预测对于交通部门制定维护和维修策略起着至关重要的作用，可以在有限的财政资源下实现更好的路面性能。然而，由于多种因素对路面性能恶化的影响错综复杂，提高路面性能预测的准确性对传统模型提出了挑战。因此，本研究的目的是建立一个基于机器学习的路面性能预测模型。首先，本研究考虑了影响路面性能的5个因素，包括路面初始性能指标、交通荷载、天气、路面结构和养护措施，并根据这5个因素确定了影响路面性能的15个具体指标。然后，基于长期路面性能（LTPP）数据库，对这些指标进行筛选和总结，获得路面状况指数（PCI）预测的高质量路面性能数据2 464个，国际粗糙度指数（IRI）预测的高质量路面性能数据3 238个。最后，建立了三种不同的预测模型，即全连接神经网络（FCNN）模型、长短期记忆（LSTM）模型和长短期记忆-注意力组合模型。研究表明，LSTM-注意力模型的表现明显优于FCNN和LSTM模型，PCI和IRI的R2决定系数分别为0.81和0.79。本文的创新之处在于作者在LSTM模型的基础上引入了注意机制，使得预测模型的拟合精度进一步提高。

{"title":"Improved model for pavement performance prediction based on recurrent neural network using LTPP database","authors":"Luchuan Chen , Hui Li , Shuo Wang , Fei Shan , Yuzhao Han , Guoqiang Zhong","doi":"10.1016/j.ijtst.2024.08.005","DOIUrl":"10.1016/j.ijtst.2024.08.005","url":null,"abstract":"<div><div>Accurate pavement performance prediction plays a critical role in formulating maintenance and repair strategies for transportation departments, enabling the achievement of better pavement performance with limited financial resources. However, due to the intricate influence of numerous factors on pavement performance deterioration, improving the accuracy of pavement performance prediction poses a challenge for conventional models. Therefore, the aim of this study is to establish a machine learning-based pavement performance prediction model. First, this study considers five factors that affect pavement performance, including pavement initial performance indicators, traffic loads, weather, pavement structure, and maintenance measures, and identifies 15 specific indicators that affect pavement performance based on these five factors. Then, based on the the long-term pavement performance (LTPP) database, the study screens and summarizes these indicators, obtaining 2 464 high-quality pavement performance data for pavement conditions index (PCI) prediction and 3 238 high-quality pavement performance data for international roughness index (IRI) prediction. Finally, three distinct prediction models are established, namely, the fully connected neural network (FCNN) model, the long short-term memory (LSTM) model, and the combined LSTM-attention model. The study shows that the LSTM-attention model performs significantly better than the FCNN and LSTM models, with an <em>R</em><sup>2</sup> coefficient of determination of 0.81 for PCI and 0.79 for IRI. The innovation of this paper is that the authors have introduced the attention mechanism on the basic of the LSTM model, which makes the fitting accuracy of the prediction model further improved.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"19 ","pages":"Pages 128-138"},"PeriodicalIF":4.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145323644","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

Collaborative rescheduling of train timetables to relieve passenger congestions in an urban rail transit network: a rolling horizon approach 协同调整列车时刻表以缓解城市轨道交通网络中的乘客拥堵：滚动地平线方法

IF 4.8 Q2 TRANSPORTATION

International Journal of Transportation Science and Technology

Pub Date : 2025-09-01 DOI: 10.1016/j.ijtst.2024.09.001

Fangsheng Wang , Pengling Wang , Xiaoyu Hao , Rudong Yang , Ruihua Xu

At certain urban rail transit (URT) stations, large events, emergencies, or holidays often cause a rapid surge in passenger flow, referred to as large passenger flow (LPF) events. The passenger congestion will spread quickly via transfer stations and affect other stations and lines in the URT network. This study develops a timetable rescheduling and coordinating method for the URT network under LPF events. Firstly, a collaborative adjustment model of train timetables with a backup-vehicle strategy is formulated to simultaneously consider rescheduling and coordinating problems, to reduce the congestion influence for a URT network. Then, a rolling horizon approach is developed to divide the whole adjustment problem into several decision-making stages to ensure solution efficiency. In each decision-making stage, the influence of LPF propagation within the URT network is firstly evaluated. Based on the congestion evaluation results, the proposed method determines whether it is necessary to adjust timetables of the LPF line or other lines. The proposed method is applied to the Xi’an Metro network in China. The results indicate that the proposed method can effectively evaluate and adjust the train timetables for large URT networks under LPF events.

在某些城市轨道交通（URT）站点，大型事件、突发事件或节假日通常会导致客流快速激增，称为大客流（large passenger flow， LPF）事件。客流拥堵将通过中转站迅速蔓延，并影响轨道交通网络中的其他车站和线路。本研究提出了一种LPF事件下轨道交通网络的时间重新调度和协调方法。首先，建立了具有后备车辆策略的列车时刻表协同调整模型，同时考虑了重调度和协调问题，以减少拥堵对轨道交通网络的影响；然后，采用滚动视界法将整个调整问题划分为多个决策阶段，以保证求解效率。在每个决策阶段，首先评估LPF在URT网络内传播的影响。该方法根据拥塞评估结果，确定是否需要调整LPF线路或其他线路的时刻表。该方法在西安地铁网络中得到了应用。结果表明，该方法可以有效地评估和调整LPF事件下的大型轨道交通网络的列车时刻表。

{"title":"Collaborative rescheduling of train timetables to relieve passenger congestions in an urban rail transit network: a rolling horizon approach","authors":"Fangsheng Wang , Pengling Wang , Xiaoyu Hao , Rudong Yang , Ruihua Xu","doi":"10.1016/j.ijtst.2024.09.001","DOIUrl":"10.1016/j.ijtst.2024.09.001","url":null,"abstract":"<div><div>At certain urban rail transit (URT) stations, large events, emergencies, or holidays often cause a rapid surge in passenger flow, referred to as large passenger flow (LPF) events. The passenger congestion will spread quickly via transfer stations and affect other stations and lines in the URT network. This study develops a timetable rescheduling and coordinating method for the URT network under LPF events. Firstly, a collaborative adjustment model of train timetables with a backup-vehicle strategy is formulated to simultaneously consider rescheduling and coordinating problems, to reduce the congestion influence for a URT network. Then, a rolling horizon approach is developed to divide the whole adjustment problem into several decision-making stages to ensure solution efficiency. In each decision-making stage, the influence of LPF propagation within the URT network is firstly evaluated. Based on the congestion evaluation results, the proposed method determines whether it is necessary to adjust timetables of the LPF line or other lines. The proposed method is applied to the Xi’an Metro network in China. The results indicate that the proposed method can effectively evaluate and adjust the train timetables for large URT networks under LPF events.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"19 ","pages":"Pages 193-210"},"PeriodicalIF":4.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145323788","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

Hierarchical dynamic modeling for highway network real-time risk forecasting with digitalized vehicle data 基于数字化车辆数据的公路网实时风险预测分层动态建模

IF 4.8 Q2 TRANSPORTATION

International Journal of Transportation Science and Technology

Pub Date : 2025-09-01 DOI: 10.1016/j.ijtst.2024.10.011

Donghyoek Park , Nuri Park , Songha Lee , Juneyoung Park , Ducknyung Kim

In traffic safety management, identifying high-risk areas prone to traffic crashes is crucial. Road authorities focus on these high-risk segments to implement strategies that mitigate the impact of recurring crashes. However, errors in identifying these hotspots can lead to inefficient resource allocation for safety improvements. These errors often stem from the reliance on aggregated traffic data for predicting crash frequency (CF). The road traffic system is characterized by the interaction of human, vehicle, and road factors, and is inherently complex. While many researchers have used components of the road traffic systems in safety evaluation studies, the use of recurrent traffic patterns remains underexplored. To address this issue, this study proposes a method for hotspot identification that utilizes safety performance analysis derived from real-time traffic data and a model with various crash factors. This paper proposes a hotspot identification approach using a real-time crash prediction model for high-risk traffic patterns. Specifically, a real-time crash prediction model is developed using logistic regression to estimate the likelihood of crashes under high-risk traffic patterns. The model integrates real-time data on traffic, weather, and road geometry to estimate these probabilities. Spearman’s correlation analysis was performed to validate the proposed method. This study reveals a strong correlation between the target frequency—a measure combining crashes and hard braking events—and the number of hazardous traffic patterns identified by the real-time crash prediction model.

在交通安全管理中，识别容易发生交通事故的高风险区域至关重要。道路管理部门将重点放在这些高风险路段，以实施减轻反复发生碰撞影响的战略。然而，在识别这些热点时出现的错误可能会导致为改进安全性而分配的资源效率低下。这些错误通常源于对预测碰撞频率（CF）的聚合交通数据的依赖。道路交通系统具有人、车、路三者相互作用的特点，具有内在的复杂性。虽然许多研究人员在安全评价研究中使用了道路交通系统的组成部分，但对经常性交通模式的使用仍未充分探索。为了解决这一问题，本研究提出了一种基于实时交通数据的安全性能分析和包含各种碰撞因素的模型的热点识别方法。本文提出了一种基于实时碰撞预测模型的高风险交通模式热点识别方法。具体来说，利用逻辑回归建立了一个实时碰撞预测模型来估计高风险交通模式下碰撞的可能性。该模型集成了交通、天气和道路几何形状的实时数据，以估计这些概率。采用Spearman相关分析验证该方法的有效性。这项研究揭示了目标频率（一种结合碰撞和急刹车事件的测量方法）与实时碰撞预测模型识别的危险交通模式数量之间的强烈相关性。

{"title":"Hierarchical dynamic modeling for highway network real-time risk forecasting with digitalized vehicle data","authors":"Donghyoek Park , Nuri Park , Songha Lee , Juneyoung Park , Ducknyung Kim","doi":"10.1016/j.ijtst.2024.10.011","DOIUrl":"10.1016/j.ijtst.2024.10.011","url":null,"abstract":"<div><div>In traffic safety management, identifying high-risk areas prone to traffic crashes is crucial. Road authorities focus on these high-risk segments to implement strategies that mitigate the impact of recurring crashes. However, errors in identifying these hotspots can lead to inefficient resource allocation for safety improvements. These errors often stem from the reliance on aggregated traffic data for predicting crash frequency (CF). The road traffic system is characterized by the interaction of human, vehicle, and road factors, and is inherently complex. While many researchers have used components of the road traffic systems in safety evaluation studies, the use of recurrent traffic patterns remains underexplored. To address this issue, this study proposes a method for hotspot identification that utilizes safety performance analysis derived from real-time traffic data and a model with various crash factors. This paper proposes a hotspot identification approach using a real-time crash prediction model for high-risk traffic patterns. Specifically, a real-time crash prediction model is developed using logistic regression to estimate the likelihood of crashes under high-risk traffic patterns. The model integrates real-time data on traffic, weather, and road geometry to estimate these probabilities. Spearman’s correlation analysis was performed to validate the proposed method. This study reveals a strong correlation between the target frequency—a measure combining crashes and hard braking events—and the number of hazardous traffic patterns identified by the real-time crash prediction model.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"19 ","pages":"Pages 256-268"},"PeriodicalIF":4.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145323786","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

Modelling of Marshall stability of polypropylene fibre reinforced asphalt concrete using support vector machine and artificial neural network 基于支持向量机和人工神经网络的聚丙烯纤维增强沥青混凝土马歇尔稳定性建模

IF 4.8 Q2 TRANSPORTATION

International Journal of Transportation Science and Technology

Pub Date : 2025-09-01 DOI: 10.1016/j.ijtst.2024.08.001

Samrity Jalota, Manju Suthar

The present study assesses the proficiency of support vector machine (SVM) models utilizing four kernel functions, i.e., normalized polynomial kernel function (SVM-NormPoly), radial basis kernel function (SVM-RBF), polynomial kernel function (SVM-Poly) and Pearson universal VII kernel function (SVM-PUK), as well as artificial neural network (ANN) models in predicting the Marshall stability of Polypropylene fibre (PPF) reinforced asphalt concrete. A total of five statistical performance indices including coefficient of correlation (CC), mean absolute error (MAE), root mean square error (RMSE), Nash-Sutcliffe model efficiency coefficient (NSE), and scattering index (SI) are employed to statistically assess each model’s performance. The statistical indicators reveal that the ANN based model demonstrates superior performance, as evidenced by their following values: CC (0.893 5), MAE (1.329 8), RMSE (1.830 3), NSE (0.7975 43), and SI (0.133 084), while SVM-PUK based model demonstrates viable prediction performance over SVM-Poly, SVM-RBF, and SVM-NormPoly based models. Likewise, sensitivity analysis performed to investigate the significance of individual input parameter suggests that bitumen content (BC) has the utmost dominance in Marshall stability prediction while on the contrary, other parameters such as polypropylene fibre length (L_PPF), polypropylene fibre percentage (P_PPF), and bitumen grade (BG) are least dominating parameters. From the findings of the models that have been implemented in the present study, it can be deduced that the Marshall Stability values can be effectively calculated using soft computing techniques in situations when doing so experimentally would be impractical due to the associated costs, time, or labour.

本研究利用归一化多项式核函数（SVM- normpoly）、径向基核函数（SVM- rbf）、多项式核函数（SVM- poly）和Pearson通用VII核函数（SVM- puk）四种核函数，以及人工神经网络（ANN）模型来评估支持向量机（SVM）模型预测聚丙烯纤维（PPF）增强沥青混凝土马歇尔稳定性的能力。采用相关系数（CC）、平均绝对误差（MAE）、均方根误差（RMSE）、Nash-Sutcliffe模型效率系数（NSE）、散射指数（SI）等5个统计性能指标对各模型的性能进行统计评价。统计指标显示，基于人工神经网络的模型的预测性能优于基于SVM-Poly、SVM-RBF和SVM-NormPoly的模型，分别为CC（0.893 5）、MAE（1.329 8）、RMSE（1.830 3）、NSE（0.7975 43）和SI（0.133 084）。同样，对单个输入参数的敏感性分析表明，沥青含量（BC）在马歇尔稳定性预测中具有最大的主导作用，而聚丙烯纤维长度（LPPF）、聚丙烯纤维百分比（PPPF）和沥青等级（BG）等其他参数在马歇尔稳定性预测中的主导作用最小。从本研究中实施的模型的结果可以推断，在由于相关成本、时间或劳动力而无法通过实验进行计算的情况下，可以使用软计算技术有效地计算马歇尔稳定性值。

{"title":"Modelling of Marshall stability of polypropylene fibre reinforced asphalt concrete using support vector machine and artificial neural network","authors":"Samrity Jalota, Manju Suthar","doi":"10.1016/j.ijtst.2024.08.001","DOIUrl":"10.1016/j.ijtst.2024.08.001","url":null,"abstract":"<div><div>The present study assesses the proficiency of support vector machine (SVM) models utilizing four kernel functions, i.e., normalized polynomial kernel function (SVM-NormPoly), radial basis kernel function (SVM-RBF), polynomial kernel function (SVM-Poly) and Pearson universal VII kernel function (SVM-PUK), as well as artificial neural network (ANN) models in predicting the Marshall stability of Polypropylene fibre (PPF) reinforced asphalt concrete. A total of five statistical performance indices including coefficient of correlation (CC), mean absolute error (MAE), root mean square error (RMSE), Nash-Sutcliffe model efficiency coefficient (NSE), and scattering index (SI) are employed to statistically assess each model’s performance. The statistical indicators reveal that the ANN based model demonstrates superior performance, as evidenced by their following values: CC (0.893 5), MAE (1.329 8), RMSE (1.830 3), NSE (0.7975 43), and SI (0.133 084), while SVM-PUK based model demonstrates viable prediction performance over SVM-Poly, SVM-RBF, and SVM-NormPoly based models. Likewise, sensitivity analysis performed to investigate the significance of individual input parameter suggests that bitumen content (BC) has the utmost dominance in Marshall stability prediction while on the contrary, other parameters such as polypropylene fibre length (<em>L</em><sub>PPF</sub>), polypropylene fibre percentage (<em>P</em><sub>PPF</sub>), and bitumen grade (BG) are least dominating parameters. From the findings of the models that have been implemented in the present study, it can be deduced that the Marshall Stability values can be effectively calculated using soft computing techniques in situations when doing so experimentally would be impractical due to the associated costs, time, or labour.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"19 ","pages":"Pages 78-98"},"PeriodicalIF":4.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145323642","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

Evaluating the role of AI and empirical models for predicting regional economic growth and transportation dynamics: an application of advanced AI approaches 评估人工智能和经验模型在预测区域经济增长和交通动态方面的作用：先进人工智能方法的应用

IF 4.8 Q2 TRANSPORTATION

International Journal of Transportation Science and Technology

Pub Date : 2025-09-01 DOI: 10.1016/j.ijtst.2024.08.007

Xinyuan Wang , Xingyi Zhu , Muhammad Kashif Anwar , Qingwei Meng , Ninghua Zhong

The advent of the artificial intelligence (AI) age offers substantial potentials for predicting regional gross domestic product (GDP) growth and transportation dynamics. This article presents an in-depth overview of the AI and empirical modeling techniques used in this area, emphasizing the significant possibilities that AI presents and discussing potential obstacles. The use of AI is essential in managing complicated data, allowing for effective analysis of detailed regional economic trends. This capacity will be essential for making economic policies and plans that respond to each region’s specific needs and capabilities. This paper first explores the relationship and impact of different modes of transportation and regional economic growth. Subsequently, various empirical models and methodological frameworks, including the factors employed for studied economic analysis were comprehensively discussed and summarized. In the last part, the discussion focuses on the potential role of AI to revolutionize regional economic research using different AI approaches. This includes its capacity to handle vast and intricate databases, its ability to forecast future patterns using historical and current data, and its assistance in advanced decision making. The present study enhances our awareness of how AI is revolutionizing the field of regional economic growth study, shedding light on both its current application and future possibilities. This study contributes to the advancement of AI predictive models in decision making for predicting regional economic growth across the globe.

人工智能（AI）时代的到来为预测地区国内生产总值（GDP）增长和交通动态提供了巨大的潜力。本文对该领域使用的人工智能和经验建模技术进行了深入的概述，强调了人工智能呈现的重要可能性，并讨论了潜在的障碍。人工智能的使用对于管理复杂的数据至关重要，可以有效地分析详细的区域经济趋势。这种能力对于制定符合各区域具体需要和能力的经济政策和计划至关重要。本文首先探讨了不同交通方式与区域经济增长的关系和影响。随后，对各种实证模型和方法框架，包括用于研究经济分析的因素进行了全面的讨论和总结。在最后一部分中，讨论的重点是人工智能在使用不同的人工智能方法革新区域经济研究中的潜在作用。这包括它处理庞大和复杂数据库的能力，它利用历史和当前数据预测未来模式的能力，以及它在高级决策方面的协助。本研究增强了我们对人工智能如何变革区域经济增长研究领域的认识，揭示了人工智能的当前应用和未来可能性。该研究有助于推进人工智能预测模型在预测全球区域经济增长决策中的应用。

{"title":"Evaluating the role of AI and empirical models for predicting regional economic growth and transportation dynamics: an application of advanced AI approaches","authors":"Xinyuan Wang , Xingyi Zhu , Muhammad Kashif Anwar , Qingwei Meng , Ninghua Zhong","doi":"10.1016/j.ijtst.2024.08.007","DOIUrl":"10.1016/j.ijtst.2024.08.007","url":null,"abstract":"<div><div>The advent of the artificial intelligence (AI) age offers substantial potentials for predicting regional gross domestic product (GDP) growth and transportation dynamics. This article presents an in-depth overview of the AI and empirical modeling techniques used in this area, emphasizing the significant possibilities that AI presents and discussing potential obstacles. The use of AI is essential in managing complicated data, allowing for effective analysis of detailed regional economic trends. This capacity will be essential for making economic policies and plans that respond to each region’s specific needs and capabilities. This paper first explores the relationship and impact of different modes of transportation and regional economic growth. Subsequently, various empirical models and methodological frameworks, including the factors employed for studied economic analysis were comprehensively discussed and summarized. In the last part, the discussion focuses on the potential role of AI to revolutionize regional economic research using different AI approaches. This includes its capacity to handle vast and intricate databases, its ability to forecast future patterns using historical and current data, and its assistance in advanced decision making. The present study enhances our awareness of how AI is revolutionizing the field of regional economic growth study, shedding light on both its current application and future possibilities. This study contributes to the advancement of AI predictive models in decision making for predicting regional economic growth across the globe.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"19 ","pages":"Pages 156-174"},"PeriodicalIF":4.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145323789","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

Evaluation of equivalent axle load factors for multi axles based on fatigue tests using actual strain waveforms 基于实际应变波形的疲劳试验评估多轴等效轴载荷系数

IF 4.8 Q2 TRANSPORTATION

International Journal of Transportation Science and Technology

Pub Date : 2025-09-01 DOI: 10.1016/j.ijtst.2024.07.005

Huailei Cheng, Lijun Sun, Yue Hu, Zhang Chen, Xiaoying Tong

Equivalent axle load factor (EALF) is used to characterize the fatigue damage effect of multi-axle loads on asphalt pavement. EALF is calculated as the ratio of the pavement’s fatigue resistance under a single axle load to that under a multi-axle load. Existing studies use the same fatigue life function to predict the fatigue life of asphalt mixture under both single- and multi-axle loads, primarily focusing on the differences in pavement strains under these two configurations. However, strain waveforms in asphalt pavement caused by multi-axle loads differ from those under single-axle loads, altering the mixture’s fatigue behavior. To address this issue, this research tests the fatigue responses of asphalt mixtures under actual loading waveforms from single-axle, tandem-axle, and tridem-axle loads. Based on the test results, fatigue life functions are developed for each axle configuration and used to establish an updated EALF model. Since the applied fatigue life functions are based on test results from more realistic strain waveforms, the calculated EALFs provide more reliable predictions of the damaging effect of multi-axle loads on asphalt mixtures.

采用等效轴载系数（EALF）来表征多轴载荷作用下沥青路面的疲劳损伤效应。EALF计算为路面在单轴载荷下的疲劳抗力与多轴载荷下的疲劳抗力之比。现有研究使用相同的疲劳寿命函数来预测沥青混合料在单轴和多轴载荷下的疲劳寿命，主要关注两种配置下路面应变的差异。然而，沥青路面在多轴载荷作用下的应变波形与单轴载荷作用下的应变波形不同，从而改变了混合料的疲劳行为。为了解决这个问题，本研究测试了沥青混合料在单轴、串联轴和三轴载荷的实际加载波形下的疲劳响应。根据试验结果，建立了不同车轴结构的疲劳寿命函数，并用于建立更新的EALF模型。由于应用的疲劳寿命函数是基于更真实的应变波形的测试结果，因此计算出的疲劳寿命函数可以更可靠地预测多轴载荷对沥青混合料的破坏作用。

{"title":"Evaluation of equivalent axle load factors for multi axles based on fatigue tests using actual strain waveforms","authors":"Huailei Cheng, Lijun Sun, Yue Hu, Zhang Chen, Xiaoying Tong","doi":"10.1016/j.ijtst.2024.07.005","DOIUrl":"10.1016/j.ijtst.2024.07.005","url":null,"abstract":"<div><div>Equivalent axle load factor (EALF) is used to characterize the fatigue damage effect of multi-axle loads on asphalt pavement. EALF is calculated as the ratio of the pavement’s fatigue resistance under a single axle load to that under a multi-axle load. Existing studies use the same fatigue life function to predict the fatigue life of asphalt mixture under both single- and multi-axle loads, primarily focusing on the differences in pavement strains under these two configurations. However, strain waveforms in asphalt pavement caused by multi-axle loads differ from those under single-axle loads, altering the mixture’s fatigue behavior. To address this issue, this research tests the fatigue responses of asphalt mixtures under actual loading waveforms from single-axle, tandem-axle, and tridem-axle loads. Based on the test results, fatigue life functions are developed for each axle configuration and used to establish an updated EALF model. Since the applied fatigue life functions are based on test results from more realistic strain waveforms, the calculated EALFs provide more reliable predictions of the damaging effect of multi-axle loads on asphalt mixtures.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"19 ","pages":"Pages 17-32"},"PeriodicalIF":4.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141843059","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 spatial relationship between urban built environment and green travel: an improved semi-parametric GWR approach 探索城市建筑环境与绿色出行之间的空间关系：改进的半参数 GWR 方法

IF 4.8 Q2 TRANSPORTATION

International Journal of Transportation Science and Technology

Pub Date : 2025-09-01 DOI: 10.1016/j.ijtst.2024.07.008

Zongshi Liu , Ye Li , Dominique Gruyer , Mahdi Zargayouna , Meiting Tu

Public transit and non-motorized travel offer numerous environmental, social, and public health benefits. Existing literature focuses on the correlation between the built environment and green travel in metropolitan centers, with limited studies on suburban new towns, essential for comprehensive urban expansion and sustainable development. This paper examines the effect of the built environment on public transit and non-motorized travel by using point of interest (POI) data and household economic data from Jiading District, Shanghai. An innovative framework is introduced, based on the geographically weighted regression (GWR) model, which captures spatial heterogeneity while balancing the inequality and directionality of different areas in the transportation network. The results demonstrate that the proposed improved semi-parametric geographically weighted regression (ISGWR) outperforms the traditional GWR model in evaluation capabilities. A distinct spatial heterogeneity in travel patterns is identified between central and peripheral areas. The densely populated central zones exhibit a preference for intra-district travel, often opting for non-motorized modes due to their convenience and health benefits while peripheral areas serve as crucial connectors, facilitating long-distance travel within the metropolitan area through public transit and multimodal transportation. Regional transportation infrastructure construction and socioeconomic factors also affect the choice of green travel. The findings could provide theoretical references and policy implications to the development of green transportation and urban sustainability.

公共交通和非机动出行提供了许多环境、社会和公共健康方面的好处。现有文献主要关注大都市中心的建成环境与绿色出行之间的关系，对城郊新城的研究较少，而城郊新城对于城市的全面扩张和可持续发展至关重要。本文利用上海市嘉定区的兴趣点（POI）数据和家庭经济数据，研究了建成环境对公共交通和非机动出行的影响。提出了一种基于地理加权回归（GWR）模型的创新框架，该框架捕捉了空间异质性，同时平衡了交通网络中不同区域的不平等和方向性。结果表明，改进的半参数地理加权回归（ISGWR）在评价能力上优于传统的GWR模型。在中心和外围地区之间，旅行模式具有明显的空间异质性。人口密集的中心区表现出对区域内旅行的偏好，由于其便利和健康效益，往往选择非机动方式，而外围地区则是关键的连接点，通过公共交通和多式联运便利了大都市区内的长途旅行。区域交通基础设施建设和社会经济因素也会影响绿色出行的选择。研究结果可为绿色交通的发展和城市可持续发展提供理论参考和政策启示。

{"title":"Exploring the spatial relationship between urban built environment and green travel: an improved semi-parametric GWR approach","authors":"Zongshi Liu , Ye Li , Dominique Gruyer , Mahdi Zargayouna , Meiting Tu","doi":"10.1016/j.ijtst.2024.07.008","DOIUrl":"10.1016/j.ijtst.2024.07.008","url":null,"abstract":"<div><div>Public transit and non-motorized travel offer numerous environmental, social, and public health benefits. Existing literature focuses on the correlation between the built environment and green travel in metropolitan centers, with limited studies on suburban new towns, essential for comprehensive urban expansion and sustainable development. This paper examines the effect of the built environment on public transit and non-motorized travel by using point of interest (POI) data and household economic data from Jiading District, Shanghai. An innovative framework is introduced, based on the geographically weighted regression (GWR) model, which captures spatial heterogeneity while balancing the inequality and directionality of different areas in the transportation network. The results demonstrate that the proposed improved semi-parametric geographically weighted regression (ISGWR) outperforms the traditional GWR model in evaluation capabilities. A distinct spatial heterogeneity in travel patterns is identified between central and peripheral areas. The densely populated central zones exhibit a preference for intra-district travel, often opting for non-motorized modes due to their convenience and health benefits while peripheral areas serve as crucial connectors, facilitating long-distance travel within the metropolitan area through public transit and multimodal transportation. Regional transportation infrastructure construction and socioeconomic factors also affect the choice of green travel. The findings could provide theoretical references and policy implications to the development of green transportation and urban sustainability.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"19 ","pages":"Pages 33-44"},"PeriodicalIF":4.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141845959","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

Geometric design optimization of speed tables at urban arterials using UAV assistance 基于无人机辅助的城市主干道车速表几何设计优化

IF 4.8 Q2 TRANSPORTATION

International Journal of Transportation Science and Technology

Pub Date : 2025-09-01 DOI: 10.1016/j.ijtst.2024.10.010

Kshitij Jassal, Umesh Sharma

One of the primary risk factors at junctions on urban roads is vehicle speed. To curb over-speeding and road crashes at intersections, traffic calming measures are introduced. Current research aims at studying the impact of different geometries of recently constructed speed tables on the operational speed over such intersections. Since these treatments have been widely used to regulate speed in other countries, evaluating their efficacy in the Indian context was required. This study utilises 6 000 vehicle samples of four different vehicle classes (two-wheeler, three-wheeler, cars, and buses) from 12 speed tables in total. The speed and acceleration kinematics in addition to the high-quality trajectory data over long road segments were extracted from the video recordings of an unmanned aerial vehicle (UAV). Multi-factor response surface methodology (RSM) was utilized to optimize the geometric parameters (variables) of the speed tables to achieve the requisite operational speed (predictor) at the considered measure. The box plots are provided to indicate descriptives of the parameters regarding the 85th percentile speed. Multiple linear regression and analysis-of-variance (ANOVA) identified the variables that were significant and fit to devise the required optimization model. This study can help in identifying the influence zone, concerning physical characteristics of speed tables and their effect on the design speed at the approaches of intersections at urban arterials. The outcomes of the study will cater to enhance the current guidelines and standards in India regarding speed table geometry for urban road sections.

城市道路交叉口的主要危险因素之一是车速。为遏止超速行驶及在交叉路口发生交通意外，当局采取了减慢车速的措施。目前的研究旨在研究不同几何形状的速度表对此类交叉路口运行速度的影响。由于这些治疗方法已在其他国家广泛用于调节速度，因此需要评估其在印度情况下的功效。本研究共从12个速度表中使用了4种不同车辆类别（两轮车、三轮车、汽车和公共汽车）的6000辆车辆样本。从无人机的视频记录中提取速度和加速度运动学以及高质量的长路段轨迹数据。利用多因素响应面法（RSM）对速度表的几何参数（变量）进行优化，以达到考虑措施所需的运行速度（预测因子）。箱形图表示关于第85百分位速度的参数描述。多元线性回归和方差分析（ANOVA）识别显著和拟合的变量，以设计所需的优化模型。本文的研究有助于确定车速表的物理特性及其对城市主干道交叉口入口设计车速的影响范围。这项研究的结果将有助于提高印度目前关于城市路段速度表几何形状的指导方针和标准。

{"title":"Geometric design optimization of speed tables at urban arterials using UAV assistance","authors":"Kshitij Jassal, Umesh Sharma","doi":"10.1016/j.ijtst.2024.10.010","DOIUrl":"10.1016/j.ijtst.2024.10.010","url":null,"abstract":"<div><div>One of the primary risk factors at junctions on urban roads is vehicle speed. To curb over-speeding and road crashes at intersections, traffic calming measures are introduced. Current research aims at studying the impact of different geometries of recently constructed speed tables on the operational speed over such intersections. Since these treatments have been widely used to regulate speed in other countries, evaluating their efficacy in the Indian context was required. This study utilises 6 000 vehicle samples of four different vehicle classes (two-wheeler, three-wheeler, cars, and buses) from 12 speed tables in total. The speed and acceleration kinematics in addition to the high-quality trajectory data over long road segments were extracted from the video recordings of an unmanned aerial vehicle (UAV). Multi-factor response surface methodology (RSM) was utilized to optimize the geometric parameters (variables) of the speed tables to achieve the requisite operational speed (predictor) at the considered measure. The box plots are provided to indicate descriptives of the parameters regarding the 85th percentile speed. Multiple linear regression and analysis-of-variance (ANOVA) identified the variables that were significant and fit to devise the required optimization model. This study can help in identifying the influence zone, concerning physical characteristics of speed tables and their effect on the design speed at the approaches of intersections at urban arterials. The outcomes of the study will cater to enhance the current guidelines and standards in India regarding speed table geometry for urban road sections.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"19 ","pages":"Pages 269-281"},"PeriodicalIF":4.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145323782","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