International Journal of Transportation Science and Technology最新文献

{"title":"Smartphone-based image analysis method for estimating moisture content in subgrade filling","authors":"Huiyi Ouyang,&nbsp;Jinsong Qian,&nbsp;Hong Lang,&nbsp;Jiake Zhang,&nbsp;Yu Zhang","doi":"10.1016/j.ijtst.2025.06.010","DOIUrl":"10.1016/j.ijtst.2025.06.010","url":null,"abstract":"<div><div>Accurate and efficient estimation of moisture content during subgrade compaction is critical for ensuring compaction quality and structural integrity. Traditional measurement methods, however, are often lab-intensive, time-consuming, and costly. This study proposes a smartphone-based approach to estimate moisture content in subgrade filling, addressing these limitations. Laboratory experiments captured images of subgrade filling with varying moisture content, gradation and compaction levels. A color correction method based on a color calibration card was adopted to mitigate illumination-induced deviations, and an image segmentation technique was used to remove anomalous pixels such as cracks and pores. Feature importance was analyzed using five different methods to identify key variables, which were then used to train and evaluate multiple machine learning (ML) models. The proposed approach demonstrated high accuracy in estimating moisture content, offering a practical and scalable solution for subgrade compaction quality monitoring using smartphones.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"23 ","pages":"Pages 191-206"},"PeriodicalIF":5.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149078680","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"EcoRouteQ: a reinforcement learning framework for green route recommendations","authors":"Mahdi Mohammadizadeh,&nbsp;Arash Mozhdehi,&nbsp;Xin Wang","doi":"10.1016/j.ijtst.2025.06.001","DOIUrl":"10.1016/j.ijtst.2025.06.001","url":null,"abstract":"<div><div>This paper presents EcoRouteQ, a reinforcement learning-based framework designed to address the time-dependent green route recommendation problem (TDGRRP) in urban road networks. As urban congestion and environmental concerns grow, minimizing travel time and CO₂ emissions has become a critical goal for sustainable transportation. TDGRRP captures this challenge by seeking optimal routing decisions that account for time-varying traffic conditions and environmental impact, making the problem inherently dynamic and multi-objective.</div><div>The framework consists of three key components. First, in the preprocessing stage, raw global positioning system (GPS) data is segmented into trips and processed using map-matching to align trajectories with the road network. This is followed by the construction of a time-dependent dataset and corresponding road network graph based on extracted travel time, speed, and CO₂ emission data. A graph simplification algorithm is then applied to reduce network complexity while preserving critical topology, enabling more efficient learning. Second, the framework incorporates a policy training with adaptive reward system, which includes (i) an initialization module, (ii) a policy training loop employing <em>Q</em>-learning to learn optimal multi-objective routing policies over time-dependent networks, and (iii) a reward recalibration mechanism that refines immediate rewards based on the best historical trajectories at the end of each episode. The routing task is formulated as a Markov decision process (MDP) to enable sequential decision-making under dynamic traffic conditions. Together, these components address the curse of dimensionality, mitigate slow convergence, and reduce path deviations caused by dense reward structures. Finally, the eco-route prediction module uses the trained policy models to generate personalized, multi-objective routing decisions in response to user queries, balancing travel time and CO₂ emissions according to user preferences.</div><div>Extensive experiments on real-world datasets from Calgary and Edmonton demonstrate that EcoRouteQ reduces travel time by up to 30.63% and 30.74%, and CO₂ emissions by up to 31.15% and 30.02%, respectively. On synthetic simulations, the framework consistently out-performs Dijkstra, A^∗ and ADRL-TSC (a reinforcement learning-based baseline), achieving travel time improvements of 41.55%, 23.73%, and 10.00%, and CO₂ emission reductions of 61.54%, 28.57%, and 23.08%, respectively. These results highlight EcoRouteQ’s effectiveness in reducing travel and emissions costs by jointly optimizing multiple objectives under time-dependent traffic conditions.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"23 ","pages":"Pages 36-53"},"PeriodicalIF":5.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149078708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Flexible mixed platoon driving strategy at signalized intersection based on connected and automated vehicle pair","authors":"Tianwen Yan,&nbsp;Maode Yan,&nbsp;Lei Zuo","doi":"10.1016/j.ijtst.2025.06.002","DOIUrl":"10.1016/j.ijtst.2025.06.002","url":null,"abstract":"<div><div>Nowadays, the urban intersection has become a mixed and complex scenario with connected and automated vehicles (CAVs) and human-driven vehicles (HDVs). Current studies emphasize utilizing single CAV trajectory optimization to guide the entire mixed platoon, while rarely considering the collaborative characteristics of multiple CAVs when passing signalized intersection. In this paper, a novel flexible mixed platoon intersection-passing strategy based on CAV pair is proposed. We firstly propose the notion of CAV pair-based mixed platoon for velocity optimization. A guidance strategy and a splitting strategy are developed by exploring the synergistic effects of CAV pair. Considering these dual characteristics for CAV pair, a more flexible passage for mixed platoon at signalized intersection can be achieved. Then, a piece-wise intersection-passing strategy is designed to reduce computational complexity and enhance the real-time optimization capabilities. An optimization model for flexible mixed platoon based on CAV pair is also established with the objectives of minimizing energy consumption and travel time. Finally, numerical simulations, including various traffic scenarios, are conducted in SUMO to verify the rationale and superiority of the dual characteristics for the flexible mixed platoon. The findings provide a scalable foundation for deploying CAV-enabled eco-driving systems in the mixed traffic scenario.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"23 ","pages":"Pages 54-68"},"PeriodicalIF":5.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149078747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Redefining metropolitan skies: fluid dynamics-driven air corridors for urban air mobility","authors":"Qin Xu,&nbsp;Lei Zhang,&nbsp;Qian Xu","doi":"10.1016/j.ijtst.2025.07.003","DOIUrl":"10.1016/j.ijtst.2025.07.003","url":null,"abstract":"<div><div>To address the challenges of low-altitude airspace utilization and safety in urban air mobility, this study proposes a fluid dynamics-driven framework for generating adaptive air corridors. The primary goal is to enable high-density, collision-free flight operations in complex urban environments. First, a high-density air corridor structure model for urban air mobility (UAM) is established. The urban airspace is divided into layers based on vertical height and flight direction, seamlessly integrating three-dimensional (3D) space with urban traffic. Second, easily accessible elevation data are used to map buildings, and the velocity field is obtained by iteratively solving the discretized Navier–Stokes and Poisson equations using the finite difference method. The initialized velocity field provides a starting point for the numerical simulation. The fluid dynamics simulation of the air corridor is completed by modeling the flow of an incompressible ideal fluid. Third, a rotation matrix was employed to modify the velocity field, guiding the air corridors along the desired direction of movement at each layer, and streamlines are computed using numerical integration methods. Results show that the proposed algorithm has been experimentally applied to several metropolitan areas, validating the effectiveness of the generated air corridors. Additionally, comparative experiments were conducted to analyze the influence of relevant parameters on corridor generation. The code is available at https://github.com/xuqin-opensource/AirCorridor.git.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"23 ","pages":"Pages 265-279"},"PeriodicalIF":5.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149078684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Operational analysis of the flipped left diamond interchange design for the freeways with frontage roads","authors":"Sayed Abuzar Kazimi,&nbsp;Ali Mozdabar,&nbsp;Nazmus Asif,&nbsp;Mehdi Azimi,&nbsp;Yi Qi","doi":"10.1016/j.ijtst.2025.06.007","DOIUrl":"10.1016/j.ijtst.2025.06.007","url":null,"abstract":"<div><div>Recently, an alternative design called the flipped left-turn diamond interchange (FLDI) has been recommended to enhance efficiency and increase the capacity of diamond interchanges in Texas, where most of the freeways have frontage roads. This design flips left-turn lanes in opposing directions, eliminating conflicts between opposing left-turn movements. The design can be easily implemented within the existing right-of-way (ROW) without the need for major construction. FLDI also has many advantages over other existing designs at locations where frontage roads were presented. However, a very limited number of studies have been conducted to investigate its operational impacts and the strategies for implementing this design. To fill this gap, the primary objective of this study is to investigate the operational impacts of FLDI design. It also aims to investigate the signal timing, traffic signs, and geometric design issues in implementing the FLDI design. To achieve these objectives, a diamond interchange in Fort Worth, Texas, was selected as a study site. Microscopic traffic models were then developed for this interchange under the existing condition of conventional diamond interchange (CDI) and the condition with the implementation of FLDI design. The traffic simulation results showed that FLDI can significantly reduce vehicle delay, queue length, and the number of stops at the diamond interchange under heavy traffic conditions. In addition, a new signal timing plan was developed for FLDI to improve its operational performance. Furthermore, to ensure the safe operation of this new design, some recommendations on roadway design, traffic signs, and pavement markings were also proposed. The results of this study can facilitate the implementation of FLDI design.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"23 ","pages":"Pages 137-153"},"PeriodicalIF":5.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149078752","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Editorial Board Information","authors":"","doi":"10.1016/S2046-0430(26)00098-5","DOIUrl":"10.1016/S2046-0430(26)00098-5","url":null,"abstract":"","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"23 ","pages":"Pages ii-iii"},"PeriodicalIF":5.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149078689","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Centralized agent-based model for efficient dispatching of autonomous taxis in smart cities","authors":"Adeel Munawar,&nbsp;Mongkut Piantanakulchai","doi":"10.1016/j.ijtst.2025.07.001","DOIUrl":"10.1016/j.ijtst.2025.07.001","url":null,"abstract":"<div><div>Transforming cities into smart cities is an important and aspirational goal in the rapidly evolving technological landscape. A key aspect of this transformation is the emergence of autonomous taxis (ATs), which hold the potential to mitigate traffic congestion and environmental pollution while enhancing urban residents’ overall quality of life. The effectiveness of taxi services significantly relies on efficient dispatching systems, which enhance service quality by minimizing waiting times and travel distances. Managing demand and supply dynamically within urban transportation presents a significant challenge. However, traditional approaches, prioritizing driver earnings and localized optimization, often fail to address the dynamic fluctuations in city-wide demand, leading to longer waiting times and travel distances. Addressing these challenges within the context of ATs, we propose a centralized agent-based model to optimize the dispatching of ATs, with an emphasis on maximizing fleet profitability while considering both minimizing distance traveled and reducing passenger waiting time. The model employs proactive decision-making to predict demand patterns and dynamically reposition vacant ATs to high-demand areas, efficiently adapting to demand fluctuations for improved dispatching. Our model is evaluated against various approaches, including random assignment, modified ant colony optimization, proximity greedy heuristic, hill climbing, and beam search models. The proposed model is illustrated through the simulation by using real-world scenarios of the demand pattern in Bangkok, Thailand. Results show that the proposed model outperforms other approaches, achieving higher fleet profitability, reduced waiting times, and shorter travel distances. This study contributes significantly to intelligent transportation systems (ITs) and supports the vision of sustainable smart cities.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"23 ","pages":"Pages 223-245"},"PeriodicalIF":5.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149078682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A detection method for rail internal defects based on data augmentation and lightweight deep network","authors":"Shihua Li,&nbsp;Lei Zhang,&nbsp;Hongliang Pan,&nbsp;Dongxiu Ou,&nbsp;Decun Dong","doi":"10.1016/j.ijtst.2025.07.002","DOIUrl":"10.1016/j.ijtst.2025.07.002","url":null,"abstract":"<div><div>Detecting internal defects in degrading rails to ensure transport capacity and safety in railway engineering has consistently been a critical concern. However, current ultrasonic-based detection methods exhibit limitations in efficiency and accuracy, especially under limited computational resources. To address this challenge, this paper proposes a method that involves a specialized B-scan image processing pipeline and a light-weight detection model for rail internal defects (LRID). Specifically, the pipeline comprises normalization, multi-channel partition filtering, and data augmentation utilizing traditional transformations and generative artificial intelligence model. The pipeline aims at enhancing signal-to-noise ratio and learnability of the B-scan dataset. For constructing the LRID, a scaled version of real-time detection transformer–large (RTDETR-L) is leveraged as the baseline. The encoder of the baseline is first pruned to reduce complexity. Then, a new convolutional block called ghost-rep-ghost (GRG) is proposed to build the backbone of the LRID, which combines compactness and multi-branch learning. Comparative evaluations of detection performance across various models demonstrate the superiority of the LRID. The model achieves a detection speed of 130 <span><math><mrow><msub><mi>τ</mi><mrow><mi>F</mi><mi>P</mi><mi>S</mi></mrow></msub></mrow></math></span> and exhibits a significant improvement in <span><math><mrow><msub><mi>θ</mi><mrow><mi>m</mi><mi>A</mi><mi>P</mi></mrow></msub></mrow></math></span>(0.5:0.95) from 64.5% to 68.2% and a decrease in giga floating point operations per second (GFLOPs) from 17.3 to 16.8, relative to the baseline. Ablation experiments further reveal that the backbone contributes a 4.8% improvement in <span><math><mrow><msub><mi>θ</mi><mrow><mi>m</mi><mi>A</mi><mi>P</mi></mrow></msub></mrow></math></span>(0.5:0.95), and elucidate the structural design of the backbone. Ultimately, the detection accuracy for most defect classes within B-scan dataset approaches 90%, indicating the effectiveness and feasibility of the proposed method.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"23 ","pages":"Pages 246-264"},"PeriodicalIF":5.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149078683","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Using machine learning to investigate user behavior on Tyne and Wear Metro","authors":"Huseyin Ayan,&nbsp;Muhammed Cavus,&nbsp;Yusuf Furkan Ugurluoglu,&nbsp;Cafer Deniz,&nbsp;Dilum Dissanayake,&nbsp;Margaret Bell","doi":"10.1016/j.ijtst.2025.09.001","DOIUrl":"10.1016/j.ijtst.2025.09.001","url":null,"abstract":"<div><div>This study investigates the factors influencing passenger satisfaction on the Tyne and Wear Metro system, a key public transportation network in North East England. The research explores how various service attributes, such as accessibility, reliability, and comfort, contribute to overall user satisfaction. Data from 850 passengers were collected through a structured questionnaire and analyzed using advanced machine learning (ML) and deep learning (DL) techniques, including random forest, gradient boosting, and neural networks. This study addresses a gap in the literature by applying a multi-model ML/DL approach to a hybrid light rail system, incorporating sustainability-oriented variables such as environmental concern into the analysis of passenger satisfaction. The random forest model demonstrated high predictive accuracy, achieving area under the curve scores of 0.93 and 0.91 for specific user classes. The findings highlight critical areas for improvement, particularly in service reliability and comfort, while also underscoring the potential of the metro to increase ridership and reduce emissions through enhanced service quality. The findings can guide operators such as Nexus in prioritising service improvements, particularly in reliability and comfort, to boost ridership and support the region’s net zero targets. This research provides valuable insights for transit authorities aiming to enhance user satisfaction and promote sustainable urban mobility.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"23 ","pages":"Pages 330-355"},"PeriodicalIF":5.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149078687","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advancing pavement management systems using a two-tier probabilistic performance modeling approach for improved condition forecasting and budgeting analysis","authors":"Carlos M. Chang,&nbsp;Raoul Salas,&nbsp;Roger E. Smith","doi":"10.1016/j.ijtst.2025.06.003","DOIUrl":"10.1016/j.ijtst.2025.06.003","url":null,"abstract":"<div><div>Pavement management systems (PMSs) are essential tools for transportation agencies to develop maintenance and rehabilitation programs for their pavement networks. These systems use prediction models to forecast future pavement conditions, which can be deterministic, probabilistic, or increasing, based on artificial intelligence (AI). While deterministic models are common, they do not account for uncertainties in pavement performance forecasting. This paper presents a two-tier probabilistic modeling approach to advance PMSs by addressing variability while improving prediction accuracy. The first tier develops probabilistic-based pavement performance curves (PBPPCs) using statistical percentiles to represent pavement sections with high, medium, or low performance. The second tier applies a dynamic calibration method that adjusts performance curves for individual pavement sections using data from condition field inspections. A comparative analysis between deterministic budget estimates and those derived from the two-tier probabilistic model revealed substantial differences, reinforcing the value of incorporating uncertainty into the modeling process. By integrating this probabilistic modeling approach into PMSs, agencies can make more informed decisions, improve budget allocation strategies, and promote proactive asset management practices to maintain pavement networks in a state of good repair.</div></div>","PeriodicalId":52282,"journal":{"name":"International Journal of Transportation Science and Technology","volume":"23 ","pages":"Pages 69-85"},"PeriodicalIF":5.1,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149078748","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}