Pub Date : 2025-06-16DOI: 10.1109/TITS.2025.3577308
Can Tan;Peng Yu;Zhaowei Qu;Lixin Zhang;Wenjing Li;Xuesong Qiu;Shaoyong Guo
The rapid development of autonomous vehicles and smart city has led to an exponential increase in data generation within Intelligent Transportation Systems (ITS). However, comprehensive extraction and utilization of these data are severely hindered by communication and energy constraints, security and privacy concerns, vehicle mobility limitations, and spatial distribution challenges. Using 6G and Digital Twin (DT) technologies offers a promising solution to these problems. In this paper, we propose a DT-based model training architecture for vehicular networks and introduce Federated Learning (FL) to preserve data privacy. While distributed model training and parameter transmission introduce challenges in delay and energy consumption, which conflict with real-time service requirements in ITS. In addition, the quality of the data and the processing capability of each vehicle varies widely, which will affect the efficiency of data sharing and model accuracy. Therefore, it is vital to select appropriate training nodes and optimize resource allocation under the constraints of task delay and energy consumption. We formulate an optimization model to improve the selection of FL participating nodes and energy management strategies, aiming to maximize accuracy while minimizing energy consumption. We then develop a DT-assisted deep reinforcement learning (DRL) method. Experiments show that our scheme achieves higher training accuracy and energy efficiency compared to the benchmark.
{"title":"Energy-Efficient Federated Learning Training Optimization for Digital Twin Driven 6G Air-Ground Integrated Vehicular Networks","authors":"Can Tan;Peng Yu;Zhaowei Qu;Lixin Zhang;Wenjing Li;Xuesong Qiu;Shaoyong Guo","doi":"10.1109/TITS.2025.3577308","DOIUrl":"https://doi.org/10.1109/TITS.2025.3577308","url":null,"abstract":"The rapid development of autonomous vehicles and smart city has led to an exponential increase in data generation within Intelligent Transportation Systems (ITS). However, comprehensive extraction and utilization of these data are severely hindered by communication and energy constraints, security and privacy concerns, vehicle mobility limitations, and spatial distribution challenges. Using 6G and Digital Twin (DT) technologies offers a promising solution to these problems. In this paper, we propose a DT-based model training architecture for vehicular networks and introduce Federated Learning (FL) to preserve data privacy. While distributed model training and parameter transmission introduce challenges in delay and energy consumption, which conflict with real-time service requirements in ITS. In addition, the quality of the data and the processing capability of each vehicle varies widely, which will affect the efficiency of data sharing and model accuracy. Therefore, it is vital to select appropriate training nodes and optimize resource allocation under the constraints of task delay and energy consumption. We formulate an optimization model to improve the selection of FL participating nodes and energy management strategies, aiming to maximize accuracy while minimizing energy consumption. We then develop a DT-assisted deep reinforcement learning (DRL) method. Experiments show that our scheme achieves higher training accuracy and energy efficiency compared to the benchmark.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 10","pages":"18116-18128"},"PeriodicalIF":8.4,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145384608","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}
Pub Date : 2025-06-13DOI: 10.1109/TITS.2025.3572987
Jianlong Wang;Chuanwei Zhang;Zhi Yang;Meng Dang
Focusing on the poor applicability of existing brake stability control methods for intelligent electric vehicles and the problem that the actual braking intention of the driver and the actual running condition of the vehicle are less considered, a layered brake stability control method for electric vehicles is proposed which considers the driver’s braking intention and vehicle state. Firstly, a GRU (Gated Recurrent Unit) neural network with SE (Squeeze Excitation) module mechanism is proposed to obtain the driver’s real braking intention, and a vehicle state recognition algorithm is designed to obtain the real-time longitudinal speed of the vehicle under complex working conditions, which form a closed-loop control structure for the braking system. Secondly, the layered control structure is used to distribute braking force, and the upper control strategy of the braking system with multi-attention mechanism is proposed to obtain the braking torque required for stable braking of the vehicle. Then, the lower level control strategy is used to coordinate the electro-hydraulic braking torque, and the dynamic coordination distribution method of motor braking and hydraulic braking is designed. Finally, the effectiveness and real-time performance of the layered braking stability control method considering driver’s braking intention and vehicle state are verified by joint simulation and real vehicle road experiments. The experiment results show that the slip rate of the proposed braking control method is about 1.5%, the SOC value of the battery increases by 0.14%~0.18%, and the stability coefficient is stable in the range of $0.02sim 0.04$ . The braking system control method can not only ensure the braking efficiency and stability of the vehicle, but also effectively recover the braking energy, which provides a new solution for the braking stability control of intelligent vehicles.
{"title":"A Layered EV Braking Stability Control Approach Considering the Driver’s Braking Intention and Vehicle Condition","authors":"Jianlong Wang;Chuanwei Zhang;Zhi Yang;Meng Dang","doi":"10.1109/TITS.2025.3572987","DOIUrl":"https://doi.org/10.1109/TITS.2025.3572987","url":null,"abstract":"Focusing on the poor applicability of existing brake stability control methods for intelligent electric vehicles and the problem that the actual braking intention of the driver and the actual running condition of the vehicle are less considered, a layered brake stability control method for electric vehicles is proposed which considers the driver’s braking intention and vehicle state. Firstly, a GRU (Gated Recurrent Unit) neural network with SE (Squeeze Excitation) module mechanism is proposed to obtain the driver’s real braking intention, and a vehicle state recognition algorithm is designed to obtain the real-time longitudinal speed of the vehicle under complex working conditions, which form a closed-loop control structure for the braking system. Secondly, the layered control structure is used to distribute braking force, and the upper control strategy of the braking system with multi-attention mechanism is proposed to obtain the braking torque required for stable braking of the vehicle. Then, the lower level control strategy is used to coordinate the electro-hydraulic braking torque, and the dynamic coordination distribution method of motor braking and hydraulic braking is designed. Finally, the effectiveness and real-time performance of the layered braking stability control method considering driver’s braking intention and vehicle state are verified by joint simulation and real vehicle road experiments. The experiment results show that the slip rate of the proposed braking control method is about 1.5%, the SOC value of the battery increases by 0.14%~0.18%, and the stability coefficient is stable in the range of <inline-formula> <tex-math>$0.02sim 0.04$ </tex-math></inline-formula>. The braking system control method can not only ensure the braking efficiency and stability of the vehicle, but also effectively recover the braking energy, which provides a new solution for the braking stability control of intelligent vehicles.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 10","pages":"18083-18100"},"PeriodicalIF":8.4,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145405257","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}
Pub Date : 2025-06-13DOI: 10.1109/TITS.2025.3572623
Mohammad Ali Arman;Chris M. J. Tampère
Whereas on many motorways, traffic operations are permanently monitored, and long historical logs of such data exist, they are not directly usable for lane change studies, as they only register local passages and speeds. This study proposes a novel method to transform discrete vehicle passage records of individual vehicle data (IVD) into approximations of vehicle trajectories and inference of lane change maneuvers (LCMs), such that large-scale LCM dataset can be retrieved from existing infrastructures where IVD is recorded at sufficiently close spacings (~600 meters). The method’s core is a probabilistic re-identification of individual vehicles in successive, lane-specific loop detectors. Dubbed Traffic Flow Crystallization (TFC), the methodology enhances traffic monitoring by providing vast and diverse LCM datasets. It consists of two key re-identification (ReID) modules: a lane-restricted module that matches vehicles strictly within the same lane and a non-lane-restricted module that recursively identifies lane-changing vehicles using boundary conditions imposed by previously matched vehicles. This recursive process resembles crystal growth, inspiring the method’s name. The ReID methodology is based on a weighted likelihood function consisting of Bayesian probability estimators that integrate three similarity measures: vehicle length, passage time, and passage speed. A lane-change feasibility filter ensures that re-identified vehicles satisfy plausible spatiotemporal constraints. The final module resolves inconsistencies and infers LCMs. The proposed method is trained and validated using CCTV footage, where visually-identified vehicles serve as ground truth. Validation results demonstrate a vehicle ReID success rate exceeding 96% and an inferred LCM rate with only a 2% underestimation compared to ground truth.
{"title":"Traffic Flow Crystallization Method for Trajectory Approximation and Lane Change Inference","authors":"Mohammad Ali Arman;Chris M. J. Tampère","doi":"10.1109/TITS.2025.3572623","DOIUrl":"https://doi.org/10.1109/TITS.2025.3572623","url":null,"abstract":"Whereas on many motorways, traffic operations are permanently monitored, and long historical logs of such data exist, they are not directly usable for lane change studies, as they only register local passages and speeds. This study proposes a novel method to transform discrete vehicle passage records of individual vehicle data (IVD) into approximations of vehicle trajectories and inference of lane change maneuvers (LCMs), such that large-scale LCM dataset can be retrieved from existing infrastructures where IVD is recorded at sufficiently close spacings (~600 meters). The method’s core is a probabilistic re-identification of individual vehicles in successive, lane-specific loop detectors. Dubbed Traffic Flow Crystallization (TFC), the methodology enhances traffic monitoring by providing vast and diverse LCM datasets. It consists of two key re-identification (ReID) modules: a lane-restricted module that matches vehicles strictly within the same lane and a non-lane-restricted module that recursively identifies lane-changing vehicles using boundary conditions imposed by previously matched vehicles. This recursive process resembles crystal growth, inspiring the method’s name. The ReID methodology is based on a weighted likelihood function consisting of Bayesian probability estimators that integrate three similarity measures: vehicle length, passage time, and passage speed. A lane-change feasibility filter ensures that re-identified vehicles satisfy plausible spatiotemporal constraints. The final module resolves inconsistencies and infers LCMs. The proposed method is trained and validated using CCTV footage, where visually-identified vehicles serve as ground truth. Validation results demonstrate a vehicle ReID success rate exceeding 96% and an inferred LCM rate with only a 2% underestimation compared to ground truth.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 7","pages":"9305-9325"},"PeriodicalIF":7.9,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144536404","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}
Pub Date : 2025-06-13DOI: 10.1109/TITS.2025.3575812
Jingang Zhao;Wei Sun;Wei Ding;Yadan Li;Pengxiang Sun;Peilun Sun
Cooperative positioning technology based on multi-vehicle information fusion is essential for advanced applications in intelligent transportation systems (ITS). The integration of global navigation satellite systems (GNSS), inertial navigation system (INS), and ultra-wideband (UWB) technology holds significant promise for enhancing the continuity and reliability of vehicle cooperative positioning. In tightly coupled GNSS/INS/UWB integration, the tolerance against measurement outliers and state model perturbations is pivotal for fulfilling the specific requirements of critical ITS applications. To optimize the comprehensive performance of vehicle cooperative positioning under uncertain sensor observation environments, this paper proposes a robust multiple fading factors unscented Kalman filtering (RMFUKF) algorithm based on adaptive cost function. The proposed solution incorporates Huber M-estimation with an adaptive tuning strategy to perform measurement-specific outliers processing. Furthermore, the improved multiple fading factors based on an exponential weighting method are implemented to mitigate the effects of dynamic model mismatches. Experimental results from vehicular field experiments demonstrate that the proposed RMFUKF scheme significantly improves the robustness and adaptive performance of vehicle cooperative positioning under unpredictable, real-world operating conditions.
{"title":"Vehicle Cooperative Positioning With Tightly Coupled GNSS/INS/UWB Integration Based on Improved Multiple Fading Factors and Adaptive Cost Function","authors":"Jingang Zhao;Wei Sun;Wei Ding;Yadan Li;Pengxiang Sun;Peilun Sun","doi":"10.1109/TITS.2025.3575812","DOIUrl":"https://doi.org/10.1109/TITS.2025.3575812","url":null,"abstract":"Cooperative positioning technology based on multi-vehicle information fusion is essential for advanced applications in intelligent transportation systems (ITS). The integration of global navigation satellite systems (GNSS), inertial navigation system (INS), and ultra-wideband (UWB) technology holds significant promise for enhancing the continuity and reliability of vehicle cooperative positioning. In tightly coupled GNSS/INS/UWB integration, the tolerance against measurement outliers and state model perturbations is pivotal for fulfilling the specific requirements of critical ITS applications. To optimize the comprehensive performance of vehicle cooperative positioning under uncertain sensor observation environments, this paper proposes a robust multiple fading factors unscented Kalman filtering (RMFUKF) algorithm based on adaptive cost function. The proposed solution incorporates Huber M-estimation with an adaptive tuning strategy to perform measurement-specific outliers processing. Furthermore, the improved multiple fading factors based on an exponential weighting method are implemented to mitigate the effects of dynamic model mismatches. Experimental results from vehicular field experiments demonstrate that the proposed RMFUKF scheme significantly improves the robustness and adaptive performance of vehicle cooperative positioning under unpredictable, real-world operating conditions.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 7","pages":"9740-9754"},"PeriodicalIF":7.9,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144536578","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}
Pub Date : 2025-06-13DOI: 10.1109/TITS.2025.3570005
Rao Fu;Pengda Mao;Yangqi Lei;Kai-Yuan Cai;Quan Quan
With the rapid development of uncrewed aerial vehicle (UAV) technology in recent years, research on large-scale low-altitude UAV air traffic management (ATM) has gained attention. Unlike the traditional ATM, the number of small UAVs in the airspace may be in the millions, making air traffic management challenging. In an ATM, airspace is composed of airways, intersections, and nodes. In this paper, a three-dimensional (3-D) roundabout model is utilized as an airspace structure for air traffic intersections of known traffic network models, which is decomposed into a central island, several ramps, and buffer zones. In this paper, for simplicity, the distributed coordination of the motions of Vertical TakeOff and Landing (VTOL) UAVs to pass through a 3-D roundabout is focused on, which is formulated as a 3-D roundabout passing-through problem. The corresponding control objectives include inter-agent conflict-free, keeping within the 3-D curved virtual tube, and avoiding local minima. Lyapunov-like functions are designed elaborately, and formal analysis is made to show that all UAVs can pass through the 3-D roundabout without getting trapped. Taking the kinematic model of VTOL UAVs into consideration, the horizontal control and attitude control channels are decoupled, which is more reasonable for practical applications. Numerical simulation and real experiment are given to show the effectiveness of the proposed method.
{"title":"Practical Distributed Control for Cooperative VTOL UAVs Within a 3-D Roundabout","authors":"Rao Fu;Pengda Mao;Yangqi Lei;Kai-Yuan Cai;Quan Quan","doi":"10.1109/TITS.2025.3570005","DOIUrl":"https://doi.org/10.1109/TITS.2025.3570005","url":null,"abstract":"With the rapid development of uncrewed aerial vehicle (UAV) technology in recent years, research on large-scale low-altitude UAV air traffic management (ATM) has gained attention. Unlike the traditional ATM, the number of small UAVs in the airspace may be in the millions, making air traffic management challenging. In an ATM, airspace is composed of airways, intersections, and nodes. In this paper, a three-dimensional (3-D) roundabout model is utilized as an airspace structure for air traffic intersections of known traffic network models, which is decomposed into a central island, several ramps, and buffer zones. In this paper, for simplicity, the distributed coordination of the motions of Vertical TakeOff and Landing (VTOL) UAVs to pass through a 3-D roundabout is focused on, which is formulated as a 3-D roundabout passing-through problem. The corresponding control objectives include inter-agent conflict-free, keeping within the 3-D curved virtual tube, and avoiding local minima. Lyapunov-like functions are designed elaborately, and formal analysis is made to show that all UAVs can pass through the 3-D roundabout without getting trapped. Taking the kinematic model of VTOL UAVs into consideration, the horizontal control and attitude control channels are decoupled, which is more reasonable for practical applications. Numerical simulation and real experiment are given to show the effectiveness of the proposed method.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 7","pages":"9341-9357"},"PeriodicalIF":7.9,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144536447","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}
Pavement cracks have a highly complex spatial structure, a low contrasting background and a weak spatial continuity, posing a significant challenge to an effective crack detection method. To precisely localize crack from an image, it is critical to effectively extract and aggregate multi-granularity context, including the fine-grained local context around the cracks (in spatial-level) and the coarse-grained semantics (in semantic-level). In this paper, we apply the dilated convolution as the backbone feature extractor to model local context, then we build a context guidance module to leverage semantic context to guide local feature extraction at multiple stages. To handle label alignment between stages, we apply the Multiple Instance Learning (MIL) strategy to align the feature between two stages. In addition, to our best knowledge, we have released the largest, most complex and most challenging Bitumen Pavement Crack (BPC) dataset. The experimental results on the three crack datasets demonstrate that the proposed method performs well and outperforms the current state-of-the-art methods. On BPC, the proposed model achieved AP 88.32% with the 16.89 M parameters under the 45.36 GFlops runing speed. Datset and code are publicly available at: https://github.com/pangjunbiao/BPC-Crack-Dataset.
{"title":"Modeling Multi-Granularity Context Information Flow for Pavement Crack Detection","authors":"Junbiao Pang;Baocheng Xiong;Jiaqi Wu;Qingming Huang","doi":"10.1109/TITS.2024.3438883","DOIUrl":"https://doi.org/10.1109/TITS.2024.3438883","url":null,"abstract":"Pavement cracks have a highly complex spatial structure, a low contrasting background and a weak spatial continuity, posing a significant challenge to an effective crack detection method. To precisely localize crack from an image, it is critical to effectively extract and aggregate multi-granularity context, including the fine-grained local context around the cracks (in spatial-level) and the coarse-grained semantics (in semantic-level). In this paper, we apply the dilated convolution as the backbone feature extractor to model local context, then we build a context guidance module to leverage semantic context to guide local feature extraction at multiple stages. To handle label alignment between stages, we apply the Multiple Instance Learning (MIL) strategy to align the feature between two stages. In addition, to our best knowledge, we have released the largest, most complex and most challenging Bitumen Pavement Crack (BPC) dataset. The experimental results on the three crack datasets demonstrate that the proposed method performs well and outperforms the current state-of-the-art methods. On BPC, the proposed model achieved AP 88.32% with the 16.89 M parameters under the 45.36 GFlops runing speed. Datset and code are publicly available at: <uri>https://github.com/pangjunbiao/BPC-Crack-Dataset</uri>.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 7","pages":"9165-9174"},"PeriodicalIF":7.9,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144536408","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}
Pub Date : 2025-06-12DOI: 10.1109/TITS.2025.3574837
Yi Rong;Yingchi Mao;Yinqiu Liu;Ling Chen;Xiaoming He;Guojian Zou;Shahid Mumtaz;Dusit Niyato
Traffic speed prediction is significant for intelligent navigation and congestion alleviation. However, making accurate predictions is challenging due to three factors: 1) traffic diffusion, i.e., the spatial and temporal causality existing between the traffic conditions of multiple neighboring roads, 2) the poor interpretability of traffic data with complicated spatio-temporal correlations, and 3) the latent pattern of traffic speed fluctuations over time, such as morning and evening rush. Jointly considering these factors, in this paper, we present a novel architecture for traffic speed prediction, called Interpretable Causal Spatio-Temporal Diffusion Network (ICST-DNET). Specifically, ICST-DNET consists of three parts, namely the Spatio-Temporal Causality Learning (STCL), Causal Graph Generation (CGG), and Speed Fluctuation Pattern Recognition (SFPR) modules. First, to model the traffic diffusion within road networks, an STCL module is proposed to capture both the temporal causality on each individual road and the spatial causality in each road pair. The CGG module is then developed based on STCL to enhance the interpretability of the traffic diffusion procedure from the temporal and spatial perspectives. Specifically, a time causality matrix is generated to explain the temporal causality between each road’s historical and future traffic conditions. For spatial causality, we utilize causal graphs to visualize the diffusion process in road pairs. Finally, to adapt to traffic speed fluctuations in different scenarios, we design a personalized SFPR module to select the historical timesteps with strong influences for learning the pattern of traffic speed fluctuations. Extensive experimental results on two real-world traffic datasets prove that ICST-DNET can outperform all existing baselines, as evidenced by the higher prediction accuracy, ability to explain causality, and adaptability to different scenarios.
{"title":"ICST-DNET: An Interpretable Causal Spatio-Temporal Diffusion Network for Traffic Speed Prediction","authors":"Yi Rong;Yingchi Mao;Yinqiu Liu;Ling Chen;Xiaoming He;Guojian Zou;Shahid Mumtaz;Dusit Niyato","doi":"10.1109/TITS.2025.3574837","DOIUrl":"https://doi.org/10.1109/TITS.2025.3574837","url":null,"abstract":"Traffic speed prediction is significant for intelligent navigation and congestion alleviation. However, making accurate predictions is challenging due to three factors: 1) traffic diffusion, i.e., the spatial and temporal causality existing between the traffic conditions of multiple neighboring roads, 2) the poor interpretability of traffic data with complicated spatio-temporal correlations, and 3) the latent pattern of traffic speed fluctuations over time, such as morning and evening rush. Jointly considering these factors, in this paper, we present a novel architecture for traffic speed prediction, called Interpretable Causal Spatio-Temporal Diffusion Network (ICST-DNET). Specifically, ICST-DNET consists of three parts, namely the Spatio-Temporal Causality Learning (STCL), Causal Graph Generation (CGG), and Speed Fluctuation Pattern Recognition (SFPR) modules. First, to model the traffic diffusion within road networks, an STCL module is proposed to capture both the temporal causality on each individual road and the spatial causality in each road pair. The CGG module is then developed based on STCL to enhance the interpretability of the traffic diffusion procedure from the temporal and spatial perspectives. Specifically, a time causality matrix is generated to explain the temporal causality between each road’s historical and future traffic conditions. For spatial causality, we utilize causal graphs to visualize the diffusion process in road pairs. Finally, to adapt to traffic speed fluctuations in different scenarios, we design a personalized SFPR module to select the historical timesteps with strong influences for learning the pattern of traffic speed fluctuations. Extensive experimental results on two real-world traffic datasets prove that ICST-DNET can outperform all existing baselines, as evidenced by the higher prediction accuracy, ability to explain causality, and adaptability to different scenarios.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 7","pages":"9781-9798"},"PeriodicalIF":7.9,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144536695","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}
Pub Date : 2025-06-12DOI: 10.1109/TITS.2025.3576220
Marzieh Jalal Abadi;Sara Khalifa;Mahbub Hassan;Salil Kanhere;Mohamed Ali Kaafar
Vibration energy harvesting (VEH) has emerged as a viable option for mobile devices that serves the dual purpose of generating power and sensing ambient vibrations. This paper highlights the location privacy leakage resulting from unrestricted access to seemingly innocuous VEH data on mobile devices. We present VEH-Attack, a side-channel attack that exploits an inference model and VEH data patterns generated from train vibrations, enabling precise tracking of train passengers. VEH-Attack achieves an accuracy of 97% and 83.13% for VEH derived data and actual VEH data, respectively, for trip length of 6 stations with the accuracy reaching 100% for longer trip lengths.
{"title":"VEH-Attack: Stealthy Tracking of Train Passengers With Side-Channel Attack on Vibration Energy Harvesting Wearables","authors":"Marzieh Jalal Abadi;Sara Khalifa;Mahbub Hassan;Salil Kanhere;Mohamed Ali Kaafar","doi":"10.1109/TITS.2025.3576220","DOIUrl":"https://doi.org/10.1109/TITS.2025.3576220","url":null,"abstract":"Vibration energy harvesting (VEH) has emerged as a viable option for mobile devices that serves the dual purpose of generating power and sensing ambient vibrations. This paper highlights the location privacy leakage resulting from unrestricted access to seemingly innocuous VEH data on mobile devices. We present VEH-Attack, a side-channel attack that exploits an inference model and VEH data patterns generated from train vibrations, enabling precise tracking of train passengers. VEH-Attack achieves an accuracy of 97% and 83.13% for VEH derived data and actual VEH data, respectively, for trip length of 6 stations with the accuracy reaching 100% for longer trip lengths.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 7","pages":"9669-9681"},"PeriodicalIF":7.9,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144536440","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}
Pub Date : 2025-06-11DOI: 10.1109/TITS.2025.3574789
Ruxin Wang;Lei Nie;Yuyan Tan
In the process of railway operation planning, it is essential to take into account both railway capacity and origin to destination (OD) passenger demand. Stop plan plays a vital role in generating a train timetable with maximum railway capacity and ensuring high-quality service to transport passengers. Therefore, we are addressing the challenge of optimizing both the stop plan and timetable for a group of trains on a railway line, focusing on railway capacity estimation and passenger demand satisfaction. To provide realistic and precise passenger distribution, the preferences of different categories of passengers are given due regard. A classic time-space network describes the integrated problem, based on which a mathematical model is formulated to minimize train occupancy time on the high-speed railway line and maximize passenger kilometers at the same time. A decomposition approach based on Lagrangian relaxation (LR) is suggested to address the problem, which decomposes the integrated scheduling problem into two sub-problems: a train timetabling sub-problem, and a stop planning and passenger distributing sub-problem by dualizing constraints linking the two. A heuristic approach based on genetic algorithms is designed to obtain feasible solutions. The proposed model and approach are shown to generate good solutions efficiently. A series of real-world instances are conducted on the Beijing-Shanghai high-speed railway line in China, and the experimental outcomes show the benefits of optimizing the stop plan. Other related analyses are discussed by comparing results with different total number of stops, heterogeneous and homogeneous cases.
{"title":"Train Timetabling With Stop Planning and Passenger Distributing Integration Orientated by Railway Capacity and Passenger Service","authors":"Ruxin Wang;Lei Nie;Yuyan Tan","doi":"10.1109/TITS.2025.3574789","DOIUrl":"https://doi.org/10.1109/TITS.2025.3574789","url":null,"abstract":"In the process of railway operation planning, it is essential to take into account both railway capacity and origin to destination (OD) passenger demand. Stop plan plays a vital role in generating a train timetable with maximum railway capacity and ensuring high-quality service to transport passengers. Therefore, we are addressing the challenge of optimizing both the stop plan and timetable for a group of trains on a railway line, focusing on railway capacity estimation and passenger demand satisfaction. To provide realistic and precise passenger distribution, the preferences of different categories of passengers are given due regard. A classic time-space network describes the integrated problem, based on which a mathematical model is formulated to minimize train occupancy time on the high-speed railway line and maximize passenger kilometers at the same time. A decomposition approach based on Lagrangian relaxation (LR) is suggested to address the problem, which decomposes the integrated scheduling problem into two sub-problems: a train timetabling sub-problem, and a stop planning and passenger distributing sub-problem by dualizing constraints linking the two. A heuristic approach based on genetic algorithms is designed to obtain feasible solutions. The proposed model and approach are shown to generate good solutions efficiently. A series of real-world instances are conducted on the Beijing-Shanghai high-speed railway line in China, and the experimental outcomes show the benefits of optimizing the stop plan. Other related analyses are discussed by comparing results with different total number of stops, heterogeneous and homogeneous cases.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 7","pages":"9445-9460"},"PeriodicalIF":7.9,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144536509","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}
Pub Date : 2025-06-10DOI: 10.1109/TITS.2025.3573718
Lei Liu;Zitong Zhao;Jie Feng;Feng Xu;Yue Zhang;Qingqi Pei;Ming Xiao
Benefiting from the outstanding advantages in speeding up task processing and saving energy consumption, vehicular edge computing has entered a period of rapid development. Given the sharp increase in application services, it is vital to fully utilize all available computation resources to guarantee personalized requirements from different users. Specially, a lot of idle vehicle resources can be exploited for task execution to improve the service experience. On the other hand, most works focus on the system performance and fail to guarantee diversified user demands. To this end, we propose a novel distributed collaborative computing scheme for task completion rate maximization (TCRM) in vehicular networks by taking into account both vertical and horizontal collaboration. The novelty of horizontal collaboration lies in the full use of available one-hop vehicle resources for task computing. In order to simultaneously guarantee the system-level performance and the user-level performance, TCRM aims to maximize the task completion rate while minimizing the energy consumption by intelligent resource optimization and task allocation. A TD3-based algorithm combined with the Dirichlet distribution is proposed to obtain the optimization decisions. Extensive simulations demonstrate that TCRM significantly improves performance compared to baseline algorithms.
{"title":"Distributed Collaborative Computing for Task Completion Rate Maximization in Vehicular Edge Computing","authors":"Lei Liu;Zitong Zhao;Jie Feng;Feng Xu;Yue Zhang;Qingqi Pei;Ming Xiao","doi":"10.1109/TITS.2025.3573718","DOIUrl":"https://doi.org/10.1109/TITS.2025.3573718","url":null,"abstract":"Benefiting from the outstanding advantages in speeding up task processing and saving energy consumption, vehicular edge computing has entered a period of rapid development. Given the sharp increase in application services, it is vital to fully utilize all available computation resources to guarantee personalized requirements from different users. Specially, a lot of idle vehicle resources can be exploited for task execution to improve the service experience. On the other hand, most works focus on the system performance and fail to guarantee diversified user demands. To this end, we propose a novel distributed collaborative computing scheme for task completion rate maximization (TCRM) in vehicular networks by taking into account both vertical and horizontal collaboration. The novelty of horizontal collaboration lies in the full use of available one-hop vehicle resources for task computing. In order to simultaneously guarantee the system-level performance and the user-level performance, TCRM aims to maximize the task completion rate while minimizing the energy consumption by intelligent resource optimization and task allocation. A TD3-based algorithm combined with the Dirichlet distribution is proposed to obtain the optimization decisions. Extensive simulations demonstrate that TCRM significantly improves performance compared to baseline algorithms.","PeriodicalId":13416,"journal":{"name":"IEEE Transactions on Intelligent Transportation Systems","volume":"26 10","pages":"18070-18082"},"PeriodicalIF":8.4,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145405259","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：