Transportation Research Part C-Emerging Technologies最新文献

{"title":"An integrated multi-objective model for demand-capacity balancing and strategic de-confliction under autonomous aircraft flight","authors":"Ziang Liu ,&nbsp;Gang Xiao ,&nbsp;Jizhi Mao","doi":"10.1016/j.trc.2025.105102","DOIUrl":"10.1016/j.trc.2025.105102","url":null,"abstract":"<div><div>To support the continued growth of the air transportation industry, Air Traffic Management (ATM) systems are evolving towards Trajectory Based Operations (TBO). Under TBO, ATM components at different levels transcend traditional spatial–temporal boundaries and become interdependent; and the capability of autonomous aircraft flight is developed and integrated into ATM systems. However, these components have been addressed in isolation, and trajectory uncertainty under autonomous aircraft flight has not been fully considered. In this paper, we first consider the impact of trajectory uncertainty on strategic de-confliction under autonomous aircraft flight, present a conflict detection approach and associated concepts for modeling trajectory conflicts to ensure the robustness of strategic de-confliction. Next, we propose a multi-objective integer programming model for tactical planning in high-density en-route airspace. This model synchronizes demand-capacity balancing and strategic de-confliction, while simultaneously optimizing the three key ATM performance metrics: the operating cost of airspace users, the service cost of air navigation service provider and the number of trajectory conflicts. This multi-objective model is solved using an exact tri-objective integer programming algorithm. We conduct several sets of stochastic numerical experiments in a high-density, complex en-route airspace to test the robustness, performance benefits and computational efficiency of the proposed approach. The results demonstrate that this approach ensures the robustness of strategic de-confliction under autonomous aircraft flight in an environment with wind disturbances. It also simultaneously enhances the optimized performance metrics, yielding considerable potential benefits. Additionally, about 20 Pareto-optimal solutions can be obtained within 10 min. Finally, we analyze the interactions between these performance metrics and derive valuable managerial insights.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"174 ","pages":"Article 105102"},"PeriodicalIF":7.6,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143714555","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Scaling from macro to micro: A novel approach to bridging gaps in multiple pavement texture scales using generative neural networks","authors":"Lintao Yang,&nbsp;Huizhao Tu,&nbsp;Hongren Gong,&nbsp;Hao Li,&nbsp;Lijun Sun","doi":"10.1016/j.trc.2025.105108","DOIUrl":"10.1016/j.trc.2025.105108","url":null,"abstract":"<div><div>Both pavement macrotexture and microtexture impact skid resistance, which is vital to driving safety. Current laser-based texture measurement methods struggle to balance efficiency and accuracy in large-scale surveys. Static laser scanners offer highly precise texture data but slow in operation, while vehicle-mounted 3D lasers work at traffic speeds but are inferior in precision. To address this trade-off, a series of generative neural networks called Pavement Texture Scaling Networks (PTSNs) are introduced to scale pavement texture across both macro and micro scales. PTSNs feature a multi-layer invertible architecture where each layer doubles or halves the texture resolution, progressively upscaling lower-resolution data to the desired level. The model was trained on texture data from four asphalt surface types at ten resolutions and evaluated with six texture descriptors and wavelet coherence (WTC). At scaling factors of 8×, 64×, and 512×, PTSNs achieved mean profile depth errors of 2.98 %, 3.91 %, and 4.99 %, respectively. The actual and predicted texture power spectral densities coincide at macrotexture scales but diverge at finer microtexture scales (wavelength <span><math><mrow><mi>q</mi><mo>&gt;</mo><msup><mrow><mn>10</mn></mrow><mn>5</mn></msup></mrow></math></span> m⁻¹). Additionally, PTSNs’ performance varied over polishing levels, with the highest errors observed on unpolished surfaces and the lowest on highly polished surfaces. The WTC analysis found that actual and predicted textures correlated strongly across the lane at frequencies below 32 kHz. Overall, PTSNs effectively reconstruct multi-resolution texture across scales, bridging the resolution gap and offering a fast, cost-effective alternative for high-precision pavement texture measurement.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"174 ","pages":"Article 105108"},"PeriodicalIF":7.6,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143680486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A data-driven preference learning approach for multi-objective vehicle routing problems in last-mile delivery","authors":"Zahra Nourmohammadi ,&nbsp;Bohan Hu ,&nbsp;David Rey ,&nbsp;Meead Saberi","doi":"10.1016/j.trc.2025.105101","DOIUrl":"10.1016/j.trc.2025.105101","url":null,"abstract":"<div><div>Last-mile delivery service providers and drivers often choose routes deviating from the shortest distance, influenced by personal preferences and various business-level factors. This study introduces an innovative data-driven optimization approach for learning preferences of decision-makers (DMs) in multi-objective vehicle routing problems. Utilizing real-world historical data from a last-mile delivery logistics platform, we develop a machine-learning framework to learn DMs’ preferences in designing delivery routes. To design our approach we focus on a multi-objective capacitated vehicle routing problem with time windows and develop an integrated framework that combines supervised learning models, sampling techniques, and optimization methods to determine preference weights for objective functions based on selected features. We conduct extensive numerical experiments to test the proposed data-driven optimization approach. Our findings suggest that analyzing historical planned and actual routes reveals DMs’ preferences, such as prioritizing workload balance and minimizing fleet usage over travel distance alone. Furthermore, this study offers insights into key factors shaping last-mile delivery logistics, including workload distribution and deviations from pre-planned routes, enabling more informed and human-centered decision-making in logistics optimization.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"174 ","pages":"Article 105101"},"PeriodicalIF":7.6,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143680490","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TMS-GNN: Traffic-aware Multistep Graph Neural Network for bus passenger flow prediction","authors":"Asiye Baghbani ,&nbsp;Saeed Rahmani ,&nbsp;Nizar Bouguila ,&nbsp;Zachary Patterson","doi":"10.1016/j.trc.2025.105107","DOIUrl":"10.1016/j.trc.2025.105107","url":null,"abstract":"<div><div>Bus network plays a critical role in urban transportation affecting the use of private vehicles, traffic congestion, and urban accessibility. The accurate prediction of bus passenger flow is key to improving transit passenger experience and increasing the efficiency of bus network operations. In line with recent advances in deep learning for passenger flow prediction, graph neural networks (GNNs) have become increasingly popular due to their ability to account for the network structure between stops. Existing GNN-based models for bus passenger flow prediction, however, face several limitations. First, they do not take into account some distinctive characteristics of bus networks, such as their coexistence with vehicular traffic and their high sensitivity to urban traffic conditions. Moreover, sequence prediction models that have been widely applied to multistep passenger flow prediction suffer from a critical issue, called “exposure bias.” This results in the propagation and accumulation of errors through prediction steps while making predictions for farther time horizons. To address these issues, this study presents the Traffic-Aware multistep Graph Neural Network (TMS-GNN) model with Scheduled Sampling, a graph-based deep-learning framework designed to forecast multistep bus passenger flows at individual stops across a bus network. The model takes into account factors such as bus stop connectivity, urban traffic impacts, and multi-dimensional temporal patterns; and addresses exposure bias by employing a curriculum learning strategy called Scheduled Sampling. The comparison between the proposed model and other popular baseline models on two real-world networks with different geographical and urban patterns in Canada and USA shows that TMS-GNN outperforms the baselines in both the overall network-wide task, as well as multistep prediction. Also, to verify the contribution of the proposed components of the model, an ablation study is conducted. The results of the ablation study validate the design choices as well.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"174 ","pages":"Article 105107"},"PeriodicalIF":7.6,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143680489","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intelligent testing environment generation for autonomous vehicles with implicit distributions of traffic behaviors","authors":"Kun Ren,&nbsp;Jingxuan Yang,&nbsp;Qiujing Lu,&nbsp;Yi Zhang,&nbsp;Jianming Hu,&nbsp;Shuo Feng","doi":"10.1016/j.trc.2025.105106","DOIUrl":"10.1016/j.trc.2025.105106","url":null,"abstract":"<div><div>The advancement of autonomous vehicles hinges significantly on addressing safety concerns and obtaining reliable evaluation results. Testing the safety of autonomous vehicles is challenging due to the complexity of the high-dimensional traffic environment and the rarity of safety-critical events, often requiring billions of miles to achieve comprehensive validation, which is inefficient and costly. Current approaches, such as accelerated testing using importance sampling, aim to provide unbiased estimates of the performance of autonomous vehicles by generating a new distribution of background vehicles’ behaviors based on an initial nominal distribution. However, these methods require knowledge of the original distribution of traffic behaviors, which is often difficult to obtain in practice. In response to these challenges, we introduce a novel methodology termed implicit importance sampling (IIS). Unlike traditional methods, IIS is designed to generate intelligent driving environments based on implicit distributions of traffic behaviors where the true distributions are unknown or not explicitly defined. IIS method leverages accept-reject sampling to construct an unnormalized proposal distribution, which increases the likelihood of sampling adversarial cases. Through applying importance sampling technique with unnormalized proposal distribution, IIS enhances testing efficiency and obtains reliable and representative evaluation results as well. The bias caused by unnormalization is also proved to be controlled and bounded.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"174 ","pages":"Article 105106"},"PeriodicalIF":7.6,"publicationDate":"2025-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143680485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Harmonizing recurring patterns and non-recurring trends in traffic datasets for enhanced estimation of missing information","authors":"Shubham Sharma ,&nbsp;Richi Nayak ,&nbsp;Ashish Bhaskar","doi":"10.1016/j.trc.2025.105083","DOIUrl":"10.1016/j.trc.2025.105083","url":null,"abstract":"<div><div>Traffic datasets commonly comprise missing information due to sensor malfunctions, environmental conditions, security concerns, and technical/data quality issues. These challenges are inherent in real-world traffic data collection systems. Despite numerous imputation algorithms proposed in the literature, concerns persist about selecting a reliable algorithm that consistently performs well across diverse missing data scenarios. This is crucial for two main reasons. Firstly, real-world traffic datasets often exhibit a range of missing gaps with varying temporal durations, encompassing both short and long gaps within a single dataset. Secondly, in spatio-temporal traffic datasets, both recurring and non-recurring traffic conditions coexist. Since different data imputation principles reported in the literature suit either type of missing data (short or long gaps) and traffic conditions (recurring or non-recurring) better than others, algorithms often output sub-optimal estimates for network-wide datasets characterized by multiple types of missing gaps and traffic conditions.</div><div>To address the issue, this paper proposes a tensor decomposition algorithm named SINTD (Stochastic Informed Non-Negative Tensor Decomposition) and logically integrates it with a spline regression model in a novel data imputation framework called SPRINT (Spline-powered Informed Non-negative Tensor Decomposition). Where SINTD mines dominant patterns in the traffic datasets, effective in estimating missing gaps under recurring traffic conditions, integration of spline with tensor decomposition helps <em>a) capturing the time-localized trends unaccounted by tensor decomposition, aiding in approximating better the non-recurring component of the traffic states</em>, and <em>b) complementing SINTD for improved mining of recurring patterns in the subsequent iterations</em> of SPRINT. Although the two algorithms have distinct limitations when used separately, their harmonization allows us to effectively utilize their respective strengths and overcome individual limitations. This paper, through extensive experimentation on six traffic datasets and benchmarking against nine baseline algorithms, demonstrates the efficacy of SPRINT in consistently producing high-accuracy missing data estimates across five diverse missing data scenarios. These include a) experiments on datasets exhibiting a mix of short and long-duration missing gaps—mimicking the intricate missing data structure of real-world traffic datasets, and b) a Logan City (Australia) case study highlighting the imputation of missing data under potential non-recurring traffic conditions resulting from road incidents.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"174 ","pages":"Article 105083"},"PeriodicalIF":7.6,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143680483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The container drayage problem for electric trucks with charging resource constraints","authors":"Liyang Xiao ,&nbsp;Luxian Chen ,&nbsp;Peng Sun ,&nbsp;Gilbert Laporte ,&nbsp;Roberto Baldacci","doi":"10.1016/j.trc.2025.105100","DOIUrl":"10.1016/j.trc.2025.105100","url":null,"abstract":"<div><div>Amidst the ongoing green transformation in transportation, the electrification of trucks has emerged as a pivotal strategy to address climate-related issues. This paper introduces the container drayage problem for electric trucks, considering the charging resource constraints. Electric trucks are assigned to serve a series of origin–destination tasks between terminals and customers. Each truck can opt between battery swapping and two charging modes: normal and fast, each featuring a nonlinear charging process. The paper addresses the charging queueing problem arising from limitations in charging resources, presenting a novel mixed integer programming model tailored to container drayage challenges for electric trucks. To tackle this challenging problem, we propose an enhanced adaptive large neighborhood search algorithm that integrates an exact method. In the first stage, routes are generated based on customized procedures without considering queueing charging to minimize overall operation costs. The second stage is triggered by the call frequency and condition coefficient, utilizing CPLEX to optimize further queueing charging strategies. The algorithm is applied to instances based on real-world task data obtained from logistics companies. A series of comparative experiments are conducted to validate the efficacy and ascertain the parameter configuration of the algorithm. Furthermore, we examine the influence of charge levels and numbers of replaceable batteries on overall expenses and conduct a comprehensive analysis of the application influence of electric trucks compared to conventional fuel trucks in terms of cost and emissions.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"174 ","pages":"Article 105100"},"PeriodicalIF":7.6,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143680484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Alert modalities in connected and smart work zones to enhance workers’ safety from traffic accidents using virtual reality (VR) experiments","authors":"Gajanand Sharma ,&nbsp;Sabyasachee Mishra","doi":"10.1016/j.trc.2025.105085","DOIUrl":"10.1016/j.trc.2025.105085","url":null,"abstract":"<div><div>Connected and Smart Work Zones (CSWZ) represent the future of work zones, utilizing technology to enhance safety, efficiency, and productivity among workers. However, research on leveraging technologies to communicate hazards and systematically evaluate different alert modalities to enhance safety remains limited. Assessing and understanding such hazards from the worker’s perspective is highly challenging, making virtual reality (VR) a promising solution that provides flexibility in assessing complex and influencing factors. In this paper, a set of 12 VR evaluation tasks for alert technology-assisted work zones are developed, encompassing various attributes by applying orthogonal design principles. Participants are exposed to these VR evaluation tasks, generating a dataset comprising 222 distinct scenarios. A proximity-based threshold is used to quantify a critical event based on worker and vehicle interaction orientations. The impact of different alert modalities (no alert, centralized, and personalized alert systems) on critical safety outcomes (reaction time and reaching safe region) using discrete choice modelling framework and kinematic behavior (temporal variation of evasive speed and relative distance) are comprehensively evaluated. The personalized alert consistently demonstrated its effectiveness by facilitating faster reactions and more effective evasive actions, significantly improving safety outcomes through a three-phase sequential motion pattern of acceleration, speed maintenance, and deceleration. This study provides a comprehensive assessment of the effectiveness of different alert systems, offering valuable insights for mitigating risks associated with intruding vehicles, especially in scenarios involving high vehicle speeds and worker involvement levels.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"174 ","pages":"Article 105085"},"PeriodicalIF":7.6,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143680482","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrated train rescheduling and speed management in a railway network: A meso-micro approach based on direct multiple shooting and alternating direction method of multipliers","authors":"Cong Xiu ,&nbsp;Jinyi Pan ,&nbsp;Andrea D’Ariano ,&nbsp;Shuguang Zhan ,&nbsp;Tao Feng ,&nbsp;Qiyuan Peng","doi":"10.1016/j.trc.2025.105076","DOIUrl":"10.1016/j.trc.2025.105076","url":null,"abstract":"<div><div>The performance of high-speed railway systems is often affected by unavoidable disruptions, which impact the reliability of train operations and passenger satisfaction. In contrast to most existing studies, which focus on either train rescheduling or speed management in separate or sequential frameworks, this paper addresses the integrated train rescheduling and speed management problem during severe disruptions, considering power supply constraints on a bidirectional railway network. Specifically, this problem incorporates detailed train speed control into the rescheduling process and involves train rerouting strategies and flexible stops to mitigate disruption effects. To characterize the integrated problem, we develop a three-dimensional space–time-state network, where each arc corresponds to a detailed driving strategy. We then propose a mixed-integer nonlinear programming (MINLP) model to simultaneously optimize the train schedule (i.e., train order, departure and arrival times, and routes) and train speed profiles, with the goal of reducing both total passenger delays and train energy consumption. To efficiently solve the integrated model, we propose a two-stage approach based on the direct multiple shooting method and the alternating direction method of multipliers (ADMM). This approach is implemented by combining offline and online computing to meet real-time requirements. The effectiveness and efficiency of the proposed model and algorithm are verified through numerous experiments using real-world data from Chinese high-speed railways. Experimental results demonstrate that our integrated approach improves energy efficiency by an average of 19.40% in complete section blockage scenarios and 7.69% in temporary speed restriction scenarios, compared to methods that do not incorporate speed management.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"174 ","pages":"Article 105076"},"PeriodicalIF":7.6,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143680627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel AVI sensor location model for individual vehicle path reconstruction on urban road networks","authors":"Keshuang Tang ,&nbsp;Qiushan Zhang ,&nbsp;Yumin Cao ,&nbsp;Jiahao Liu ,&nbsp;Junping Xiang ,&nbsp;Hong Zhu","doi":"10.1016/j.trc.2025.105103","DOIUrl":"10.1016/j.trc.2025.105103","url":null,"abstract":"<div><div>Advances in traffic detection technology have enabled the transition from traditional counting detectors to vehicle identification detectors in many cities across the world. This shift has facilitated the collection of high-dimensional network traffic data through Automatic Vehicle Identification (AVI) systems, significantly advancing areas such as path flow estimation and individual vehicle path reconstruction. However, due to the high cost of fully deploying AVI sensors across urban road networks, reconstructing individual vehicle paths with limited sensor data remains a significant challenge. While existing research has focused primarily on Network Sensor Location Problem (NSLP) models for path flow estimation, their application to individual vehicle path reconstruction is less explored. Inspired by system entropy theory in information science, this study introduces a novel metric called Path Reconstruction Entropy (PRE) to quantify the uncertainty in vehicle path choices as observed by AVI sensors. Leveraging this metric, we propose a novel non-linear integer programming AVI-NSLP model that follows the Minimum PRE principle, optimizing the placement of AVI sensors for enhanced vehicle path reconstruction. The model incorporates a composite objective function that considers network benefits, including the uncertainty of vehicle path reconstruction for observed vehicles and coverage of observed vehicles, across two scenarios: with and without prior path flow information. Numerical studies conducted on two networks—a small-sized Sioux Falls network and a large-sized Xujiahui network in Shanghai—demonstrate that the proposed model consistently outperforms existing models in terms of PRE and other sensor deployment metrics on the smaller network and shows a modest advantage on the larger network. The experimental results demonstrate that the AVI sensor placement strategy developed by the proposed model can significantly improve the accuracy of individual vehicle path reconstruction on urban road networks.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"174 ","pages":"Article 105103"},"PeriodicalIF":7.6,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143680626","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}