IEEE Open Journal of Intelligent Transportation Systems最新文献_第2页

Enhancing Autonomous Vehicle Localization Through Cooperative LiDAR and Smart Infrastructure Integration 通过协同激光雷达和智能基础设施集成提高自动驾驶汽车的定位

IF 5.3

IEEE Open Journal of Intelligent Transportation Systems Pub Date : 2026-02-12 DOI: 10.1109/OJITS.2026.3664106

Yuze Jiang;Ehsan Javanmardi;Manabu Tsukada;Hiroshi Esaki

{"title":"Enhancing Autonomous Vehicle Localization Through Cooperative LiDAR and Smart Infrastructure Integration","authors":"Yuze Jiang;Ehsan Javanmardi;Manabu Tsukada;Hiroshi Esaki","doi":"10.1109/OJITS.2026.3664106","DOIUrl":"https://doi.org/10.1109/OJITS.2026.3664106","url":null,"abstract":"Autonomous driving systems rely on precise localization to ensure safety and performance in dynamic environments. However, standalone vehicle localization methods using onboard sensors often fail to deliver sufficient accuracy in adverse environments, such as tunnels or areas with limited distinguishable features. To address these challenges, we propose a novel cooperative localization framework that leverages roadside LiDAR-equipped infrastructure and vehicle-to-infrastructure (V2I) communication. In our approach, roadside LiDARs detect and estimate vehicle positions using a refined L-shape fitting algorithm, complemented by the vehicle’s geometric data shared over the V2I network. This method mitigates errors associated with partial point cloud data and improves localization precision significantly. By integrating this infrastructure-based positioning data with onboard localization modules via sensor fusion, our framework enhances overall accuracy and robustness in real-time autonomous driving scenarios. Experimental results in a digital twin environment demonstrate that our system achieves over 70% improvement in localization accuracy compared to self-localization methods. Our work highlights the potential of smart infrastructure to enhance localization, reduce onboard sensor dependency, and improve autonomous driving reliability under challenging environment for self-localization.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"7 ","pages":"551-564"},"PeriodicalIF":5.3,"publicationDate":"2026-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11395270","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146223764","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}

引用次数: 0

ASMARL: Optimizing Traffic Signal Coordination Through Multi-Agent Reinforcement Learning With Attention Mechanisms and Sequential Rollout 基于多智能体强化学习的交通信号协调优化研究

IF 5.3

IEEE Open Journal of Intelligent Transportation Systems Pub Date : 2026-02-12 DOI: 10.1109/OJITS.2026.3664105

Bo Wang;Jie Liu;Haoran Cheng;Tongchun Du

{"title":"ASMARL: Optimizing Traffic Signal Coordination Through Multi-Agent Reinforcement Learning With Attention Mechanisms and Sequential Rollout","authors":"Bo Wang;Jie Liu;Haoran Cheng;Tongchun Du","doi":"10.1109/OJITS.2026.3664105","DOIUrl":"https://doi.org/10.1109/OJITS.2026.3664105","url":null,"abstract":"In cooperative multi-agent reinforcement learning tasks, partial observability and non-stationarity from agents updating their parameters are significant challenges. A common solution is sharing all observations and actions among agents directly, but this can lead to excessive communication costs, especially with many agents, making it impractical. Hence, it’s crucial to selectively share important information to reduce redundancy and effectively represent and integrate the shared information. This paper proposes an Attention-based Shared Multi-Agent Reinforcement Learning (ASMARL) method for multi-intersection traffic signal coordination, introducing an optimal baseline to reduce variance. The approach includes constructing communication channels using attention mechanisms to integrate shared information, designing a sequential rollout mechanism to incorporate agents’ actions within the communication range into the Critic network’s input, and introducing an optimal baseline to mitigate high variance in multi-agent policy gradient. Simulations in the urban traffic software (SUMO) show that ASMARL outperforms current mainstream methods in reducing average traffic delay.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"7 ","pages":"537-550"},"PeriodicalIF":5.3,"publicationDate":"2026-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11395271","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146223721","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}

引用次数: 0

Enhancing Road Safety Through a Fuzzy-Based Adaptive Alert System for Critical Motorcycle–Car 基于模糊自适应预警系统的关键摩托车道路安全研究

IF 5.3

IEEE Open Journal of Intelligent Transportation Systems Pub Date : 2026-02-12 DOI: 10.1109/OJITS.2026.3663001

Carlos V. S. Augusto;Pietro L. Campos;Johannes Lochter;Felipe P. Santos;Lester A. Faria

{"title":"Enhancing Road Safety Through a Fuzzy-Based Adaptive Alert System for Critical Motorcycle–Car","authors":"Carlos V. S. Augusto;Pietro L. Campos;Johannes Lochter;Felipe P. Santos;Lester A. Faria","doi":"10.1109/OJITS.2026.3663001","DOIUrl":"https://doi.org/10.1109/OJITS.2026.3663001","url":null,"abstract":"Ensuring safety in road traffic remains a critical challenge, particularly in scenarios involving motorcycles approaching the blind spot of larger vehicles. This paper proposes an intelligent, context-aware alert system based on Fuzzy Logic, capable of generating gradual warning signals to assist car drivers in anticipating potential collisions. Grounded in real-world accident data, the system integrates Responsibility-Sensitive Safety (RSS) equations with the ISO 17387 safety standard to define critical interaction zones. A custom simulation environment was developed using the CARLA platform, enabling realistic vehicle dynamics and sensor modeling. The proposed fuzzy controller processes longitudinal and lateral safety parameters, along with real-time inter-vehicle distance, to classify the level of danger and modulate the alert intensity accordingly. Unlike traditional binary systems, the fuzzy engine provides a continuous output ranging from low to high criticality, ensuring timely and non-intrusive driver assistance. Simulation results across nine accident-based scenarios demonstrate the system’s effectiveness in anticipating risks, minimizing false positives, and enhancing driver response time. This work contributes to a scalable, human-centric safety mechanism for Advanced Driver-Assistance Systems (ADAS), with strong potential for real-world application in environments involving mixed traffic and vulnerable road users.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"7 ","pages":"658-668"},"PeriodicalIF":5.3,"publicationDate":"2026-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11395257","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147299570","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}

引用次数: 0

Trust Management in the Internet of Vehicles: A Survey of the State-of-the-Art 车联网中的信任管理：现状综述

IF 5.3

IEEE Open Journal of Intelligent Transportation Systems Pub Date : 2026-02-10 DOI: 10.1109/OJITS.2026.3663495

Yingxun Wang;Adnan Mahmood;Mohamad Faizrizwan Mohd Sabri;Hushairi Zen

{"title":"Trust Management in the Internet of Vehicles: A Survey of the State-of-the-Art","authors":"Yingxun Wang;Adnan Mahmood;Mohamad Faizrizwan Mohd Sabri;Hushairi Zen","doi":"10.1109/OJITS.2026.3663495","DOIUrl":"https://doi.org/10.1109/OJITS.2026.3663495","url":null,"abstract":"The Internet of Vehicles (IoV) represents a transformative paradigm within the context of Intelligent Transportation System (ITS) with the aim to enhance road safety, traffic efficacy, environmental sustainability, and user convenience. However, as IoV networks increase in scale and complexity, ensuring trustworthy interactions among vehicles, infrastructure, and service providers becomes paramount. This paper, therefore, presents a comprehensive review of trustworthiness management for an IoV network. Firstly, the transition of Vehicular Ad hoc Networks (VANETs) to IoV followed by an examination of the notion of trust in various domains has been explored. Subsequently, the characteristics of trust, salient constituents of trust, key trust attributes, trust evaluation parameters, and trust-based attacks in the context of an IoV network have been delineated. Moreover, the five key processes involved in the trust management, i.e., trust formation, trust propagation, trust aggregation, trust update, and trust decision, have been investigated vis-à-vis the state-of-the-art. Furthermore, the advanced trust management models, i.e., conventional and artificial intelligence-based ones, have been analyzed in-depth. Finally, simulation tools and datasets employed in IoV-based trust management models have been introduced, along with an outline of key open research directions in this domain.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"7 ","pages":"516-536"},"PeriodicalIF":5.3,"publicationDate":"2026-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11389818","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146223833","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}

引用次数: 0

Active Disturbance Observer-Based Fuzzy Finite-Time Following Control for Teleoperation Heterogeneous Multi-UAV With Various Disturbances 基于有源干扰观测器的异构多无人机远操作模糊有限时间跟踪控制

IF 5.3

IEEE Open Journal of Intelligent Transportation Systems Pub Date : 2026-02-06 DOI: 10.1109/OJITS.2026.3661155

Chih-Lyang Hwang;Chi-Wei Hsieh;Chih-Han Lin;Hailay Berihu Abebe

{"title":"Active Disturbance Observer-Based Fuzzy Finite-Time Following Control for Teleoperation Heterogeneous Multi-UAV With Various Disturbances","authors":"Chih-Lyang Hwang;Chi-Wei Hsieh;Chih-Han Lin;Hailay Berihu Abebe","doi":"10.1109/OJITS.2026.3661155","DOIUrl":"https://doi.org/10.1109/OJITS.2026.3661155","url":null,"abstract":"Most of the previous studies for the trajectory tracking control of UAV need the original nonlinear complex dynamics. Nevertheless, their real implementations are a challenge. To overcome this difficulty, outer loop control of a commercial UAV described by a second-order model with sensor noises, uncertain accelerations, input fault/constraint, and unmodeled dynamics is considered. To tackle these uncertainties of the outdoor multi-UAV following control problems, an active disturbance observer-based fuzzy finite-time control (ADO-FFC) for the teleoperation heterogenous multi-UAV is designed. The leader UAV will track the planned 3D pose and the followers are one, another, and the others with the relative pose such that the planned task in a global area is obtained. Not only are the uncertainties actively compensated by estimation but also the connected following error in the vicinity of zero is enhanced by the fuzzy finite-time control with a new nonlinear output scaling factor. These simultaneous compensations of uncertainties can enhance the following performance. In simulation, the average 3D pose of our ADO-FFC is respectively (2.77cm, <inline-formula> <tex-math>$2.66mathbf {^{circ }}$ </tex-math></inline-formula>) and (1.82cm, <inline-formula> <tex-math>$0.07mathbf {^{circ }}$ </tex-math></inline-formula>) better than the disturbance observer-based finite-time following control and the ADO-FFC without disturbance compensation. Likewise, the average 3D position and orientation for the teleoperated multi-UAV with nearby and far-distance ground stations by the ADO-FFC are respectively 130cm better than and almost the same as the inner PID control loop (IPIDCL).","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"7 ","pages":"584-599"},"PeriodicalIF":5.3,"publicationDate":"2026-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11373160","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146223722","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}

引用次数: 0

Structure-Aware Deep Image Alignment for Automatic Wayside Rail Freight Vision 基于结构感知的铁路货运自动视觉深度图像对齐

IF 5.3

IEEE Open Journal of Intelligent Transportation Systems Pub Date : 2026-02-06 DOI: 10.1109/OJITS.2026.3662026

Yong Shi;Mengjin Lyu;Jie Yang;Zhiquan QI

{"title":"Structure-Aware Deep Image Alignment for Automatic Wayside Rail Freight Vision","authors":"Yong Shi;Mengjin Lyu;Jie Yang;Zhiquan QI","doi":"10.1109/OJITS.2026.3662026","DOIUrl":"https://doi.org/10.1109/OJITS.2026.3662026","url":null,"abstract":"The wayside rail freight machine vision system is widely used to facilitate the inspection and condition monitoring of freight trains, supporting safe operations and efficient maintenance. Within this system, image alignment or registration plays a crucial role, serving as a precursor to various downstream functions such as change detection, state tracking, and defect inspection. However, this task is severely challenged by the demanding 3L conditions—low texture, low illumination, and large displacement—which are prevalent in real-world inspection scenarios and cause significant performance degradation in existing alignment methods. To address these challenges, this paper introduces a novel structure-aware learning paradigm for deep image alignment. The core innovation is to explicitly guide the network to prioritize robust structural features over unreliable texture or intensity information. Specifically, we propose a synergistic combination of a structure-aware loss function and a structure learning module; the former directs the loss computation toward structurally salient regions, while the latter regularizes the backbone network to inherently comprehend image geometry. These modules are designed to be architecture-agnostic and work synergistically to embed structural knowledge into the alignment process. We instantiate this paradigm within two foundational deep alignment architectures. Experimental results on a challenging freight train dataset demonstrate that our approach not only establishes a new state-of-the-art in alignment accuracy under 3L conditions but also maintains highly competitive efficiency, providing a robust and practical solution for enhancing the reliability of wayside rail freight inspection and maintenance.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"7 ","pages":"680-693"},"PeriodicalIF":5.3,"publicationDate":"2026-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11373558","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147362491","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}

引用次数: 0

Research on Mandatory Lane Changing for Exiting of Buses in V2I Environments: A Centralized Cooperative Control Framework V2I环境下公共汽车强制换道研究：一种集中协同控制框架

IF 5.3

IEEE Open Journal of Intelligent Transportation Systems Pub Date : 2026-02-06 DOI: 10.1109/OJITS.2026.3661361

Huasheng Liu;Kui Dong;Jin Li;Xuqian Zheng

{"title":"Research on Mandatory Lane Changing for Exiting of Buses in V2I Environments: A Centralized Cooperative Control Framework","authors":"Huasheng Liu;Kui Dong;Jin Li;Xuqian Zheng","doi":"10.1109/OJITS.2026.3661361","DOIUrl":"https://doi.org/10.1109/OJITS.2026.3661361","url":null,"abstract":"Bus merging maneuvres after departing stops significantly disrupt urban traffic flow, often causing interruptions and congestion. In order to solve this problem, this paper focuses on the harbour-shaped bus stop scenario and proposes a centralized control framework leveraging V2I coordination technology. This framework comprehensively incorporates multiple complex constraints during vehicle operation, enabling the accurate simulation of real-road driving behaviours. An integrated solving algorithm combining hp-adaptive pseudospectral methods with interior point methods generates optimal control trajectories for vehicles in the target section. Simulation results demonstrate that, compared to the benchmark scheme, the proposed centralized control optimized scheme significantly enhances the timeliness and comfort of bus lane-changing manoeuvres during exit from bus stops, evidenced by reduced lane-changing duration, increased lane-changing speed, and lowered trajectory curvature. Meanwhile, the scheme strictly guarantees the safety of the lane-changing process. Furthermore, the optimization scheme effectively mitigates the interference caused by bus exit manoeuvres on the traffic flow of the road section, leading to a cascading improvement in the travel efficiency of surrounding vehicles. This manifests as shortened average travel time and increased average travel speed for surrounding vehicles. This proves that the method proposed in this paper is beneficial to the overall traffic operation while optimizing the bus operation.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"7 ","pages":"492-507"},"PeriodicalIF":5.3,"publicationDate":"2026-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11373238","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146175906","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}

引用次数: 0

Estimating the Joint Probability of Scenario Parameters With Gaussian Mixture Copula Models 高斯混合Copula模型估计情景参数的联合概率

IF 5.3

IEEE Open Journal of Intelligent Transportation Systems Pub Date : 2026-02-06 DOI: 10.1109/OJITS.2026.3661396

Christian Reichenbächer;Philipp Rank;Jochen Hipp;Oliver Bringmann

{"title":"Estimating the Joint Probability of Scenario Parameters With Gaussian Mixture Copula Models","authors":"Christian Reichenbächer;Philipp Rank;Jochen Hipp;Oliver Bringmann","doi":"10.1109/OJITS.2026.3661396","DOIUrl":"https://doi.org/10.1109/OJITS.2026.3661396","url":null,"abstract":"This paper presents the first application of Gaussian Mixture Copula Models to the statistical modeling of driving scenarios for the safety validation of automated driving systems. Knowledge of the joint probability distribution of scenario parameters is essential for scenario-based safety assessment, where risk quantification depends on the likelihood of concrete parameter combinations. Gaussian Mixture Copula Models bring together the multimodal expressivity of Gaussian Mixture Models and the flexibility of copulas, enabling separate modeling of marginal distributions and dependence. We benchmark Gaussian Mixture Copula Models against previously proposed approaches—Gaussian Mixture Models and Gaussian Copula Models—using real-world driving data drawn from two scenarios defined in United Nations Regulation No. 157. Our evaluation on approximately 18 million instances of these two scenarios demonstrates that Gaussian Mixture Copula Models consistently surpass Gaussian Copula Models and perform competitively with Gaussian Mixture Models, as measured by both log-likelihood and Sinkhorn distance, with relative performance depending on the scenario. The results are promising for the adoption of Gaussian Mixture Copula Models as a statistical foundation for future scenario-based validation frameworks.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"7 ","pages":"508-515"},"PeriodicalIF":5.3,"publicationDate":"2026-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11373040","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146175916","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}

引用次数: 0

Modeling Driver State and Takeover Behavior in Conditional Automation Using Physiological Signals 基于生理信号的条件自动化驱动状态和接管行为建模

IF 5.3

IEEE Open Journal of Intelligent Transportation Systems Pub Date : 2026-02-06 DOI: 10.1109/OJITS.2026.3662160

Joel Andrew Miller;Soodeh Nikan;Mohamed H. Zaki

{"title":"Modeling Driver State and Takeover Behavior in Conditional Automation Using Physiological Signals","authors":"Joel Andrew Miller;Soodeh Nikan;Mohamed H. Zaki","doi":"10.1109/OJITS.2026.3662160","DOIUrl":"https://doi.org/10.1109/OJITS.2026.3662160","url":null,"abstract":"The transition of control from autonomous driving systems (ADS) to human drivers poses critical challenges for ensuring safety, comfort, and trust in autonomous vehicles (AVs). Effective takeovers require a seamless and reliable transfer of control, which depends heavily on the driver’s cognitive state and behaviour during this transitional phase. This study investigates the role of physiological signals—specifically electrodermal activity (EDA), electrocardiogram (ECG), and RSP (RSP)—in understanding and predicting driver responses during takeovers. Using data from the AdVitam dataset, we demonstrate the utility of these signals in classifying both the occurrence of a takeover and its adequate timing, achieving accuracies of 76% and 75%, respectively. Our findings highlight the critical value of physiological signals in capturing mental workload, which has been shown to influence takeover behaviour. This work forms the basis for adaptive, human-centric takeover systems designed to enhance safety, reduce cognitive strain, and build trust in AV technology. By advancing real-time physiological monitoring in ADS, this research contributes to the design of adaptive, human-centred takeover systems that may enhance trust and responsiveness in conditional AVs. The corresponding code for this study is available here","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"7 ","pages":"477-491"},"PeriodicalIF":5.3,"publicationDate":"2026-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11373589","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146175849","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}

引用次数: 0

Federated Learning for Traffic Flow Prediction With Synthetic Data Augmentation 基于综合数据增强的联邦学习交通流预测

IF 5.3

IEEE Open Journal of Intelligent Transportation Systems Pub Date : 2026-01-30 DOI: 10.1109/OJITS.2026.3659531

Fermin Orozco;Hongkai Wen;Pedro Porto Buarque de Gusmão;Johan Wahlström;Man Luo

{"title":"Federated Learning for Traffic Flow Prediction With Synthetic Data Augmentation","authors":"Fermin Orozco;Hongkai Wen;Pedro Porto Buarque de Gusmão;Johan Wahlström;Man Luo","doi":"10.1109/OJITS.2026.3659531","DOIUrl":"https://doi.org/10.1109/OJITS.2026.3659531","url":null,"abstract":"Deep learning-based traffic prediction models require vast amounts of data to learn embedded spatial and temporal dependencies. The inherent privacy and commercial sensitivity of such data has encouraged a shift towards decentralised data-driven methods, such as Federated Learning (FL). Traditional machine learning models capture spatial and temporal relationships in centralised data. In reality, traffic data is likely distributed across separate data silos owned by multiple stakeholders. In this work, a cross-silo FL setting is motivated to facilitate stakeholder collaboration for optimal traffic flow prediction applications. This work introduces FedTPS, a novel framework which augments each client’s local dataset with synthetic data generated by a federated diffusion-based model. The proposed framework is evaluated on three large-scale real-world datasets and assessed against various generative and spatio-temporal prediction models, including a novel prediction model we introduce which leverages Temporal and Graph Attention mechanisms to learn embedded Spatio-Temporal dependencies. Experimental results show that FedTPS outperforms several FL baselines with respect to global model performance.","PeriodicalId":100631,"journal":{"name":"IEEE Open Journal of Intelligent Transportation Systems","volume":"7 ","pages":"445-459"},"PeriodicalIF":5.3,"publicationDate":"2026-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11369392","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146175867","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}

引用次数: 0