Transportation Research Part C-Emerging Technologies最新文献

{"title":"Lane level traffic flow prediction in urban networks with missing data — a time accessibility based multi-task learning framework","authors":"Hong Zhu ,&nbsp;Fengmei Sun ,&nbsp;Keshuang Tang ,&nbsp;Guoyang Qin ,&nbsp;Edward Chung","doi":"10.1016/j.trc.2025.105343","DOIUrl":"10.1016/j.trc.2025.105343","url":null,"abstract":"<div><div>Deep learning-based traffic flow prediction (TFP) methods have gained significant traction recently, owing to their ability to extract spatiotemporal correlation features from multi-source big data, such as floating car data and loop detector measurements. Despite the widespread popularity of deep learning in TFP, its application to signalized networks in urban areas remains constrained by two critical challenges. First, signal-induced interruptions and queuing at approaches result in discontinuities in traffic flow, which makes it difficult for prediction tasks to capture the data correlation features among other spatially adjacent segments. Second, unavoidable communication and equipment failures lead to severe random data loss (sometimes exceeding 50 %) in urban road network detector readings, which further complicates the extraction of traffic flow patterns and key features. To address these challenges, this study proposes the <strong>T</strong>ime <strong>A</strong>ccessibility-based <strong>M</strong>ulti-task <strong>L</strong>earning <strong>F</strong>ramework for Missing Data <strong>I</strong>mputation (MDI) and TF<strong>P</strong> (TAMLF-I&amp;P). The TAMLF-I&amp;P leverages multi-source data and domain-specific knowledge to dynamically construct time accessibility-based adjacency matrixes, which effectively capture real-time topological relationships between approach lanes. Building on this matrix, a multi-task framework is introduced to simultaneously optimize the MDI and TFP tasks, helping to prevent potential error accumulation when MDI and TFP tasks are executed separately. Additionally, a novel deep learning approach combining Diffusion Graph Convolutional Network (DGCN) and Long Short-Term Memory (LSTM) is employed to capture complex spatiotemporal dependencies. Experiments on two real-world datasets demonstrate that the TAMLF-I&amp;P model significantly enhances prediction accuracy, particularly in scenarios with 70 % missing data, achieving up to 7.79 % reduction in Mean Absolute Error (MAE) compared to traditional models. Ablation experiments indicate that the time accessibility-based adjacency matrix and the multi-task learning framework significantly enhance the accuracy of TFP with substantial data missing.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105343"},"PeriodicalIF":7.6,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145120848","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":"Joint optimization of multi-trip vehicle scheduling, passenger assignment, and timetable for on-demand customized bus services","authors":"Peng Wu ,&nbsp;Qi Wang ,&nbsp;Tommaso Bosi ,&nbsp;Andrea D’Ariano","doi":"10.1016/j.trc.2025.105346","DOIUrl":"10.1016/j.trc.2025.105346","url":null,"abstract":"<div><div>On-demand customized bus (CB) services represent an emerging form of demand-responsive public transportation, providing unique advantages in addressing passengers’ diverse travel needs and advancing sustainable mobility. To enhance operational efficiency and improve passenger satisfaction, this paper investigates a new CB service problem. The goal is to minimize total vehicle operating costs and penalties for unserved orders by jointly optimizing multi-trip vehicle scheduling, passenger assignment, and timetabling. We first formulate the problem into a mixed-integer nonlinear programming model, which is then linearized into an equivalent one. To efficiently solve this model, we develop a tailored adaptive large neighborhood search algorithm, which incorporates a three-stage heuristic algorithm, a stop assignment strategy, and a set of customized operators. Extensive experiments on Sioux Falls and New York City cases validate the proposed algorithm’s effectiveness and efficiency. Furthermore, we demonstrate that multi-trip vehicle scheduling can reduce total costs compared to single-trip vehicle scheduling, with a reduction of 11.5%. Additionally, we derive management insights for CB operators by conducting sensitivity analysis experiments on critical parameters. Our findings indicate that adopting multi-trip scheduling, optimizing the number and spatial distribution of candidate stops, and adjusting trip frequency according to demand levels can effectively lower the operational costs of CB services.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105346"},"PeriodicalIF":7.6,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145120846","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":"Cooperative control method for connected and automated vehicle platoon based on arbitrary time headway switched system","authors":"Gongzhe Liu ,&nbsp;Nan Zheng ,&nbsp;Hao Wang","doi":"10.1016/j.trc.2025.105353","DOIUrl":"10.1016/j.trc.2025.105353","url":null,"abstract":"<div><div>The cooperative control of connected and automated vehicle (CAV) platoons plays a significant role in enhancing traffic efficiency and ensuring safety. In complex traffic environments, platoon dynamics frequently change due to external disturbances and varying traffic demands. These changes manifest as acceleration and deceleration, speed variations, and headway adjustments. This paper proposes a cooperative control method to manage the performance and stability of the platoon during state changes. Based on optimal control theory and arbitrary time headway (ATH) policy, a linear quadratic regulator (LQR) is constructed with safety, efficiency, and stability as objectives. The controller enables all vehicles in the platoon to maintain the desired time headway and synchronize their movements. To accommodate varying headway requirements, the model is further extended to a switched system, allowing stable transitions between arbitrary desired time headways. The stability of the optimal control and switched system is proved using transfer function and Lyapunov methods. Considering the inaccuracies in lower-level response, an active disturbance rejection controller (ADRC) is designed to refine control inputs and mitigate tracking errors. To validate the model in practical applications, simulation experiments incorporating vehicle dynamics are conducted using CarSim and MATLAB. Simulation results indicate that under the proposed control model, followers in the platoon respond more rapidly and safely to changes in the leader’s state. During transitions between arbitrary desired time headways, the platoon reconfigures more efficiently while ensuring improved safety and stability.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105353"},"PeriodicalIF":7.6,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145120850","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":"Dynamic cybersecurity resource allocation in connected and automated vehicles","authors":"Yiyang Wang ,&nbsp;Ethan Zhang ,&nbsp;Neda Masoud ,&nbsp;Anahita Khojandi","doi":"10.1016/j.trc.2025.105352","DOIUrl":"10.1016/j.trc.2025.105352","url":null,"abstract":"<div><div>This paper presents a framework for dynamic security resource allocation in Connected and Automated Vehicles (CAVs), focusing on the challenge of cybersecurity amidst resource limitations. Given that CAVs rely on finite energy supplies for various essential functions–such as propulsion, sensing, computing, and security monitoring–we address the trade-offs involved in allocating resources to an onboard security monitor in the face of potential cyberattacks. A key challenge is the imperfect detection of attacks, where the CAV’s security system can only partially observe the attack state through a detection algorithm. To address this, we formulate the problem as a Partially Observable Markov Decision Process (POMDP), aimed at minimizing the total discounted cost over a finite horizon by dynamically allocating security resources, ensuring both safety and successful trip completion. Additionally, we propose a Q-learning-based approach for approximating optimal policies in large-scale systems. Through numerical experiments, we demonstrate the effectiveness of our approach in both small and large-scale settings, comparing it with benchmark policies. Our results show that the proposed framework successfully balances security monitoring and energy efficiency, with the Q-learning approach offering a scalable solution for larger systems. This work provides a novel contribution to security-aware resource allocation in CAVs, with implications for future transportation systems.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105352"},"PeriodicalIF":7.6,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145120901","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":"Can human drivers and connected autonomous vehicles co-exist in lane-free traffic? A microscopic simulation perspective","authors":"Arslan Ali Syed,&nbsp;Majid Rostami-Shahrbabaki,&nbsp;Klaus Bogenberger","doi":"10.1016/j.trc.2025.105315","DOIUrl":"10.1016/j.trc.2025.105315","url":null,"abstract":"<div><div>Recent advancements in connected autonomous vehicle (CAV) technology have sparked growing research interest in lane-free traffic (LFT). LFT envisions a scenario where all vehicles are CAVs, coordinating their movements without lanes to achieve smoother traffic flow and higher road capacity. This potentially reduces congestion without building new infrastructure. However, the transition phase will likely involve non-connected actors such as human-driven vehicles (HDVs) or independent AVs sharing the roads. This raises the question of how LFT performance is impacted when not all vehicles are CAVs, as these non-connected vehicles may prioritize their own benefits over system-wide improvements. This paper addresses this question through microscopic simulation on a ring road, where CAVs follow the potential lines (PL) controller for LFT, while HDVs adhere to a strip-based car-following model. The PL controller is also modified for safe velocities to prevent collisions. The results reveal that even a small percentage of HDVs can significantly disrupt LFT flow: 5% HDVs can reduce LFT’s maximum road capacity by 20% and a 40% HDVs nearly halves it, up until 100% HDVs where it drops by nearly 60%. The study also develops an adaptive potential line (APL) controller that forms APL corridors in the surroundings of HDVs. APL shows a peak traffic flow improvement of nearly 10% over the PL controller. The study indicates that a penetration rate of approximately 60% CAVs is required to start observing the major LFT benefits. These findings open a new research direction on minimizing the adverse effects of non-connected vehicles on LFT.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105315"},"PeriodicalIF":7.6,"publicationDate":"2025-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145099632","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":"Stop-and-go wave super-resolution reconstruction via iterative refinement","authors":"Junyi Ji ,&nbsp;Alex Richardson ,&nbsp;Derek Gloudemans ,&nbsp;Gergely Zachár ,&nbsp;Matthew Nice ,&nbsp;William Barbour ,&nbsp;Jonathan Sprinkle ,&nbsp;Benedetto Piccoli ,&nbsp;Daniel B. Work","doi":"10.1016/j.trc.2025.105313","DOIUrl":"10.1016/j.trc.2025.105313","url":null,"abstract":"<div><div>Stop-and-go waves are a fundamental phenomenon in freeway traffic flow, contributing to inefficiencies, crashes, and emissions. Recent advancements in high-fidelity sensor technologies have improved the ability to capture detailed traffic dynamics, yet such systems remain scarce and costly. In contrast, conventional traffic sensors are widely deployed but suffer from relatively coarse-grain data resolution, potentially impeding accurate analysis of stop-and-go waves. This article explores whether generative AI models can enhance the resolution of conventional traffic sensor to approximate the quality of high-fidelity observations. We present a novel approach using a conditional diffusion denoising model, designed to reconstruct fine-grained traffic speed field from radar-based conventional sensors via iterative refinement. We introduce a new dataset, <span>WaveX</span> (<span><span>Ji et al., 2025a</span></span>), comprising 132 hours of data from both low and high-fidelity sensor systems, totaling over 2 million vehicle miles traveled. Our approach leverages this dataset to formulate the traffic state refinement problem as a spatio-temporal super-resolution task. We demonstrate that our model can effectively reproduce the patterns of stop-and-go waves, achieving high accuracy in capturing these critical traffic dynamics. Our results show promising advancements in traffic state refinement, offering a cost-effective way to leverage existing low spatio-temporal resolution sensor networks for improved traffic analysis and management. We also open-source our dataset, trained model and code to enable further research and applications.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105313"},"PeriodicalIF":7.6,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145099631","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":"Reconstructing physics-informed machine learning for traffic flow modeling: a multi-gradient descent and pareto learning approach","authors":"Yuan-Zheng Lei ,&nbsp;Yaobang Gong ,&nbsp;Dianwei Chen ,&nbsp;Yao Cheng ,&nbsp;Xianfeng Terry Yang","doi":"10.1016/j.trc.2025.105344","DOIUrl":"10.1016/j.trc.2025.105344","url":null,"abstract":"<div><div>Physics-informed machine learning (PIML) has been widely adopted for traffic flow modeling in recent studies, due to its potential in combining the benefits of both physics-based and data-driven approaches. In conventional PIML, physics information from classical traffic flow models is typically incorporated by constructing a hybrid loss function that combines data-driven loss and physics loss through linear scalarization. The goal is to find a trade-off between these two objectives to improve the accuracy of model predictions. However, from a mathematical perspective, linear scalarization is limited to identifying only the convex region of the Pareto front, as it treats data-driven and physics losses as separate objectives. Given that most PIML loss functions are non-convex, linear scalarization restricts the achievable trade-off solutions. Moreover, tuning the weighting coefficients for the two loss components can be both time-consuming and computationally challenging. To address these limitations, this paper introduces a paradigm shift in PIML by reformulating the training process as a multi-objective optimization problem, treating data-driven loss and physics loss independently. We apply several multi-gradient descent algorithms (MGDAs), including traditional multi-gradient descent (TMGD) and dual cone gradient descent (DCGD), to explore the Pareto front in this multi-objective setting. These methods are evaluated on both macroscopic and microscopic traffic flow models. In the macroscopic case, MGDAs achieved comparable performance to traditional linear scalarization methods. Notably, in the microscopic case, MGDAs significantly outperformed their scalarization-based counterparts, demonstrating the advantages of a multi-objective optimization approach in complex PIML scenarios.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105344"},"PeriodicalIF":7.6,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145099630","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":"Dynamic coordinated routing and charging navigation system for traffic congestion mitigation: A game theoretical modelling and asynchronous distributed optimization approach","authors":"Yuqiang Ning ,&nbsp;Lili Du","doi":"10.1016/j.trc.2025.105308","DOIUrl":"10.1016/j.trc.2025.105308","url":null,"abstract":"<div><div>As the world embraces sustainable transportation, electric vehicles (EVs) have emerged as a promising solution. However, their increasing popularity brings forth new challenges, particularly concerning congestion at charging stations and on roads. Recent advancements in wireless communication and sensing technologies enable travelers to access real-time traffic and charging station availability information via navigation systems, allowing them to make informed routing and charging decisions to avoid congestion. However, this real-time information can sometimes be counterproductive. If travelers react independently and selfishly to similar traffic information, it can exacerbate congestion due to the flash crowd effect. This study aims to alleviate such problems by developing a navigation system based on dynamic coordinated joint routing and en-route charging mechanism (DcRC) to provide coordinated routing and charging guidance for both EVs and internal combustion engine (ICE) vehicles, thereby reducing congestion on roads and at charging stations. Specifically, by incorporating traffic flow and charging station queue dynamics, the DcRC is formulated as a mixed strategy congestion game with an equivalent mathematical programming model, which generates equilibrium routing and charging decisions to mitigate the flash crowd effect and reduce traffic congestion without violating each vehicle’s self-interest. To integrate the DcRC into online navigation services, this study develops an asynchronous distributed ADMM-aided Branch-and-Bound (DAB) solution algorithm to efficiently solve the DcRC with hundreds of participants. The DAB draws upon a customized branch and bound algorithm to decompose the complex mathematical program into manageable sub-problems, and utilizes an asynchronous distributed ADMM to solve each sub-problem efficiently with privacy protection, leveraging individual vehicles’ computing resources while sustaining robustness against their unstable and stochastic computing and communication performance. Numerical experiments confirm the DcRC’s effectiveness in reducing congestion and system costs, as well as the DAB’s efficiency in supporting real-time navigation services for hundreds of participants with unstable computation and communication performance.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105308"},"PeriodicalIF":7.6,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145060499","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":"Strategizing equitable transit evacuations: A data-driven reinforcement learning approach","authors":"Fang Tang ,&nbsp;Han Wang ,&nbsp;Maria Laura Delle Monache","doi":"10.1016/j.trc.2025.105342","DOIUrl":"10.1016/j.trc.2025.105342","url":null,"abstract":"<div><div>As natural disasters become increasingly frequent, the need for efficient and equitable evacuation planning has become more critical. This paper proposes a data-driven, reinforcement learning (RL)-based framework to optimize public transit operations for bus-based evacuations in transportation networks with an emphasis on improving both efficiency and equity. We model the evacuation problem as a Markov Decision Process (MDP) solved by RL, using real-time transit data from General Transit Feed Specification (GTFS) and transportation networks extracted from OpenStreetMap (OSM). The RL agent dynamically reroutes buses from their scheduled location to minimize total passenger travel time and vehicle routing costs while ensuring equitable transit service distribution across communities. Simulations on the San Francisco Bay Area transportation network indicate that the proposed framework achieves significant improvements in both evacuation efficiency and equitable service distribution compared to traditional rule-based and random strategies. These results highlight the potential of RL to enhance system performance and urban resilience during emergency evacuations, offering a scalable solution for real-world applications in intelligent transportation systems.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105342"},"PeriodicalIF":7.6,"publicationDate":"2025-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145057288","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 operation of ride-hailing and shared micromobility services in multimodal transportation networks with public transit: The unintended consequences of regulations","authors":"Jing Gao ,&nbsp;Sen Li","doi":"10.1016/j.trc.2025.105340","DOIUrl":"10.1016/j.trc.2025.105340","url":null,"abstract":"<div><div>This paper investigates the integrated operation of ride-hailing and shared micromobility services provided by transportation network companies (TNCs) such as Uber, Lyft, and Didi, and examines the policy implications of prevalent TNC regulations under complex multimodal interactions. We consider a TNC platform that simultaneously coordinates a fleet of for-hire vehicles and deploys micromobility infrastructures to offer both ride-hailing and shared micromobility services, in conjunction with a public transit agency operating in the same transportation network. To capture the key elements of such a multimodal system, we develop a market equilibrium model that incorporates ride-hailing waiting times, micromobility access and egress times, the spatial distribution of micromobility infrastructure, passenger demand, platform pricing and fleet sizing, vehicle repositioning, and traffic congestion. The platform’s decision-making problem is formulated as a non-convex program, and a tailored solution method is proposed to efficiently compute the solution through problem reformulation and dimensionality reduction. Using the developed model, we analyze the implications of two prevalent TNC regulations: (a) a congestion charge on ride-hailing services aimed at mitigating traffic congestion; and (b) a vehicle density floor for shared micromobility services to promote spatial equity. Our results reveal several unintended consequences of these regulations due to the interplay between ride-hailing, shared micromobility, and public transit in a multimodal transportation network. Interestingly, we find that how the congestion charge on ride-hailing trips influences public transit ridership crucially depends on micromobility’s role as a feeder mode: when micromobility serves as a significant transit feeder, the congestion charge increases transit ridership; otherwise, the congestion charge on ride-hailing services could inadvertently reduce transit ridership. Furthermore, we find that imposing a vehicle density floor for micromobility services, while improving the spatial equity of micromobility, may inadvertently reduce the equity of ride-hailing services, ultimately widening the overall equity gap across the multimodal transportation network. These unintended consequences are observed only when all three modes-ride-hailing, shared micromobility, and public transit-are jointly modeled, underscoring the critical importance of accounting for multimodal interactions in the design and evaluation of TNC regulations.</div></div>","PeriodicalId":54417,"journal":{"name":"Transportation Research Part C-Emerging Technologies","volume":"180 ","pages":"Article 105340"},"PeriodicalIF":7.6,"publicationDate":"2025-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145048889","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}