Search Results (23)

Critical Internet of Things (IoT) data in Fifth Generation Vehicular Ad Hoc Networks (5G VANETs) demands Ultra-Reliable Low-Latency Communication (URLLC) to support mission-critical vehicular applications such as autonomous driving and collision avoidance. Achieving the stringent Quality of Service (QoS) requirements for these applications remains a significant challenge. This paper proposes a novel framework integrating Software-Defined Networking (SDN) and Network Functions Virtualisation (NFV) as embedded functionalities in connected vehicles. A lightweight SDN Controller model, implemented via vehicle on-board computing resources, optimised QoS for communications between connected vehicles and the Next-Generation Node B (gNB), achieving a consistent packet delivery rate of 100%, compared to 81–96% for existing solutions leveraging SDN. Furthermore, a Software-Defined Wide-Area Network (SD-WAN) model deployed at the gNB enabled the efficient management of data, network, identity, and server access. Performance evaluations indicate that SDN and NFV are reliable and scalable technologies for virtualised and distributed 5G VANET infrastructures. Our SDN-based in-vehicle traffic classification model for dynamic resource allocation achieved 100% accuracy, outperforming existing Artificial Intelligence (AI)-based methods with 88–99% accuracy. In addition, a significant increase of 187% in flow rates over time highlights the framework’s decreasing latency, adaptability, and scalability in supporting URLLC class guarantees for critical vehicular services. Full article

The Internet of Vehicles (IoV) presents a vast opportunity for optimised traffic flow, road safety, and enhanced usage experience with the influence of Federated Learning (FL). However, the distributed nature of IoV networks creates certain inherent problems regarding data privacy, security from adversarial attacks, and the handling of available resources. This paper introduces Fed-DTB, a new dynamic trust-based framework for FL that aims to overcome these challenges in the context of IoV. Fed-DTB integrates the adaptive trust evaluation that is capable of quickly identifying and excluding malicious clients to maintain the authenticity of the learning process. A performance comparison with previous approaches is shown, where the Fed-DTB method improves accuracy in the first two training rounds and decreases the per-round training time. The Fed-DTB is robust to non-IID data distributions and outperforms all other state-of-the-art approaches regarding the final accuracy (87–88%), convergence rate, and adversary detection (99.86% accuracy). The key contributions include (1) a multi-factor trust evaluation mechanism with seven contextual factors, (2) correlation-based adaptive weighting that dynamically prioritises trust factors based on vehicular conditions, and (3) an optimisation-based client selection strategy that maximises collaborative reliability. This work opens up opportunities for more accurate, secure, and private collaborative learning in future intelligent transportation systems with the help of federated learning while overcoming the conventional trade-off of security vs. efficiency. Full article

This study evaluates the potential of IoT-enabled adaptive traffic management systems for mitigating urban congestion, enhancing mobility, and reducing environmental impacts in densely populated cities. Using London as a case study, the research develops a multiagent simulation framework to assess the effectiveness of advanced traffic management strategies—including adaptive signal control and dynamic rerouting—under varied traffic scenarios. Unlike conventional models that rely on static or reactive approaches, this framework integrates real-time data from IoT-enabled sensors with predictive analytics to enable proactive adjustments to traffic flows. Distinctively, the study couples this integration with a multiagent simulation environment that models the traffic actors—private vehicles, buses, cyclists, and emergency services—as autonomous, behaviourally dynamic agents responding to real-time conditions. This enables a more nuanced, realistic, and scalable evaluation of urban mobility strategies. The simulation results indicate substantial performance gains, including a 30% reduction in average travel times, a 50% decrease in congestion at major intersections, and a 28% decline in CO₂ emissions. These findings underscore the transformative potential of sensor-driven adaptive systems for advancing sustainable urban mobility. The study addresses critical gaps in the existing literature by focusing on scalability, equity, and multimodal inclusivity, particularly through the prioritisation of high-occupancy and essential traffic. Furthermore, it highlights the pivotal role of IoT sensor networks in real-time traffic monitoring, control, and optimisation. By demonstrating a novel and practical application of sensor technologies to traffic systems, the proposed framework makes a significant and timely contribution to the field and offers actionable insights for smart city planning and transportation policy. Full article

Sustainable traffic management relies on accurate traffic flow prediction to reduce congestion, fuel consumption, and emissions and minimise the external environmental impacts of traffic operations. This study contributes to this objective by developing and evaluating advanced machine learning models that leverage multisource data to predict traffic patterns more effectively, allowing for the deployment of proactive measures to prevent or reduce traffic congestion and idling times, leading to enhanced eco-friendly mobility. Specifically, this paper evaluates the impact of multisource sensor inputs and spatial detector interactions on machine learning-based traffic flow prediction. Using a dataset of 839,377 observations from 14 detector stations along Melbourne’s Eastern Freeway, Bidirectional Long Short-Term Memory (BiLSTM) models were developed to assess predictive accuracy under different input configurations. The results demonstrated that incorporating speed and occupancy inputs alongside traffic flow improves prediction accuracy by up to 16% across all detector stations. This study also investigated the role of spatial flow input interactions from upstream and downstream detectors in enhancing prediction performance. The findings confirm that including neighbouring detectors improves prediction accuracy, increasing performance from 96% to 98% for eastbound and westbound directions. These findings highlight the benefits of optimised sensor deployment, data integration, and advanced machine-learning techniques for smart and eco-friendly traffic systems. Additionally, this study provides a foundation for data-driven, adaptive traffic management strategies that contribute to sustainable road network planning, reducing vehicle idling, fuel consumption, and emissions while enhancing urban mobility and supporting sustainability goals. Furthermore, the proposed framework aligns with key United Nations Sustainable Development Goals (SDGs), particularly those promoting sustainable cities, resilient infrastructure, and climate-responsive planning. Full article

Nowadays, when battery-powered electric vehicles (EVs) travel along motorways, their drivers decide where to recharge their cars’ batteries with no or scarce information on the occupancy status of the next charging stations. While this may still be acceptable in most countries, due to the limited number of EVs on motorways, long queues may build-up in the coming years with increased electric mobility, unless smart allocation strategies are designed and implemented. For instance, as we shall investigate in this manuscript, a centralised coordination of the charging strategies of individual EVs has the potential to significantly reduce the queuing time at charging stations. In particular, in this paper we explain how the charging problem on motorways can be modelled as an optimisation problem, we propose some strategies based on dynamic optimisation to solve it, and we explain how this may be implemented in practice using a centralised charge manager that exchanges information with the EVs and solves the optimisation problems. Finally, we compare in a realistic scenario the current decentralised recharging strategies with a centralised one, and we show that, under simplifying assumptions, queueing times can be reduced by more than 50%. Such a significant reduction allows one to greatly improve vehicular flows and general journey durations without requiring building new infrastructure. Reducing queuing times has a positive impact on traffic congestion and emissions, and the more geographically balanced energy demand of the proposed methodology mitigates energy consumption peaks. Full article

Magnetic levitation (maglev) technology offers significant advantages for rail transport, including frictionless propulsion, reduced noise, and lower maintenance costs. However, its widespread adoption has been limited due to the need for a dedicated infrastructure incompatible with conventional rail networks. The MaDe4Rail project, funded by Europe’s Rail Joint Undertaking (ERJU), explores Maglev-Derived Systems (MDSs) as means to integrate maglev-inspired solutions into existing railway corridors with minimal modifications. This paper focuses on the so-called “hybrid MDS” configuration, which refers to levitating systems that can operate on existing rail infrastructure. Unlike current maglev systems, which require dedicated tracks, the proposed MDS system is designed to operate on conventional rail tracks, allowing for its compatibility with traditional trains and ensuring the interoperability of lines. In order to identify the most viable solution, two different configurations have been analysed. The evaluated scenario could benefit from the introduction of hybrid MDSs based on magnetic levitation, where a group of single vehicles, also called pods, is used in a virtual coupling configuration. The objective of this case study is to increase the capacity of traffic on the existing railway line by significantly reducing travel time, while maintaining a similar energy consumption to that of the current conventional trains operating on this line. Simulation results indicate that the hybrid MDS can optimise railway operations by taking advantage of virtual coupling to improve traffic flow, reducing travel times and energy consumption with the optimisation of the aerodynamic drag. The system achieves a balance between increased speed and energy efficiency, making it a viable alternative for future rail transport. An initial cost–benefit analysis suggests that the hybrid MDS could deliver substantial economic advantages, positioning it as a promising solution for enhancing European railway networks with minimal infrastructure investment. Full article

Ubiquitous connectivity is envisioned through the integration of terrestrial (TNs) and non-terrestrial networks (NTNs). However, NTNs face multiple routing and Quality of Service (QoS) provisioning challenges due to the mobility of network nodes. Distributed Software-Defined Networking (SDN) combined with Multi-Agent Deep Reinforcement Learning (MADRL) is widely used to introduce programmability and intelligent Traffic Engineering (TE) in TNs, yet applying DRL to NTNs is hindered by frequently changing state sizes, model scalability, and coordination issues. This paper introduces 3DQR, a novel TE framework that combines hierarchical multi-controller SDN, hierarchical MADRL based on Graph Neural Networks (GNNs), and network topology predictions for QoS path provisioning, effective load distribution, and flow rejection minimisation in future 3D networks. To enhance SDN scalability, introduced are metrics and path operations abstractions to facilitate domain agents coordination by the global agent. To the best of the authors’ knowledge, 3DQR is the first routing scheme to integrate MADRL and GNNs for optimising centralised routing and path allocation in SDN-based 3D mobile networks. The evaluations show up to a 14% reduction in flow rejection rate, a 50% improvement in traffic distribution, and effective QoS class prioritisation compared to baseline techniques. 3DQR also exhibits strong transfer capabilities, giving consistent performance gains in previously unseen environments. Full article

Internet service providers allocate network resources for different network flows. Among them, video streaming requires substantial network bandwidth to provide a satisfactory user experience. The identification of video traffic is one of the tools that helps to manage and optimise network resources. However, available solutions usually focus on traffic traces from a single application and use black-box models for identification, which require labels for training. To address this issue, we proposed an unsupervised machine learning model to identify traffic generated by video applications from the three popular services, namely YouTube, Netflix, and Amazon Prime. Our methodology involves feature generation, filtering, and clustering. The clustering used the most significant features to group similar traffic patterns. We employed the following three algorithms that represent different clustering methodologies: partition-based, density-based, and probabilistic approaches. The clustering achieved precision between 0.78 and 0.93, while recall rates ranged from 0.68 to 0.84, depending on the experiment parameters, which is comparable with black-box learning models. The model presented is interpretable and scalable, which is useful for its practical application. Full article

Background: In multimodal transport the interplay of coordination methods and legal requirements is a challenging task. To address the latter, a combined approach for the coordination of a multimodal passenger transport system in accordance with European data protection law is required. Method: As a first step the paper analyses coordination related delays and outlines a combined optimisation problem. The problem formulation spans the strategic, tactical and operational level, to identify information requirements depending on coordinationmechanisms. The European legal systemregularly sets a pioneering standard, often serving as a model for other countries. Additionally, European data regulations frequently influence international data flows, as references to European traffic standards are often indispensable. To ensure compliance with data protection legislation, in a second step, this paper analyses the European Union’s legal framework for the protection of personal and non-personal data. Result: A respective system architecture for the integration of selected methods is proposed and the resulting analysis outlines the legal requirements for data usage under the Data Governance Act (DGA) and the General Data Protection Regulation (GDPR). Conclusions: Achieving a sustainable and efficient transportation system requires a balanced integration of advanced data-driven solutions and legal strategies, ensuring system efficiency and compliance with EU protection laws. Full article

It is crucial for both traffic management organisations and individual commuters to be able to forecast traffic flows accurately. Graph neural networks made great strides in this field owing to their exceptional capacity to capture spatial correlations. However, existing approaches predominantly focus on local geographic correlations, ignoring cross-region interdependencies in a global context, which is insufficient to extract comprehensive semantic relationships, thereby limiting prediction accuracy. Additionally, most GCN-based models rely on pre-defined graphs and unchanging adjacency matrices to reflect the spatial relationships among node features, neglecting the dynamics of spatio-temporal features and leading to challenges in capturing the complexity and dynamic spatial dependencies in traffic data. To tackle these issues, this paper puts forward a fresh approach: a new self-supervised dynamic spatio-temporal graph convolutional network (SDSC) for traffic flow forecasting. The proposed SDSC model is a hierarchically structured graph–neural architecture that is intended to augment the representation of dynamic traffic patterns through a self-supervised learning paradigm. Specifically, a dynamic graph is created using a combination of temporal, spatial, and traffic data; then, a regional graph is constructed based on geographic correlation using clustering to capture cross-regional interdependencies. In the feature learning module, spatio-temporal correlations in traffic data are subjected to recursive extraction using dynamic graph convolution facilitated by Recurrent Neural Networks (RNNs). Furthermore, self-supervised learning is embedded within the network training process as an auxiliary task, with the objective of enhancing the prediction task by optimising the mutual information of the learned features across the two graph networks. The superior performance of the proposed SDSC model in comparison with SOTA approaches was confirmed by comprehensive experiments conducted on real road datasets, PeMSD4 and PeMSD8. These findings validate the efficacy of dynamic graph modelling and self-supervision tasks in improving the precision of traffic flow prediction. Full article

Connected and automated vehicles (CAVs) represent a significant development in the transport industry owing to their intelligent and interconnected features. Potential field theory has been extensively used to model CAV driving behaviour owing to its objectivity, universality, and measurability. However, existing car-following models do not consider the impact of time delays and the influence of information from multiple vehicles ahead and behind. This paper focuses on the driving-safety risks associated with CAVs, aiming to enhance vehicle safety and reliability during travelling. We developed a multi-vehicle car-following model based on safety potential fields (MIDM-SPF), taking into account the characteristics of multi-vehicle connected information and time delays. To enhance the model’s precision, real-world data from urban roads were employed, alongside an improved optimisation algorithm to fine-tune the car-following model. The simulation experiment revealed that MIDM-SPF significantly reduces stop-and-go traffic, thereby improving traffic flow stability in urban areas. Additionally, we validated the stability of our model under varying market penetration rates in large-scale mixed traffic. Our findings indicate that increasing the CAV proportion improves the stability of mixed traffic flows, which has important implications for alleviating traffic congestion and guiding the large-scale implementation of autonomous driving in the future. Full article

The Auckland Harbour Bridge (AHB) utilises a movable concrete barrier (MCB) to regulate the uneven bidirectional flow of daily traffic. In addition to the risk of human error during regular visual inspections, staff members inspecting the MCB work in diverse weather and light conditions, exerting themselves in ergonomically unhealthy inspection postures with the added weight of protection gear to mitigate risks, e.g., flying debris. To augment visual inspections of an MCB using computer vision technology, this study introduces a hybrid deep learning solution that combines kernel manipulation with custom transfer learning strategies. The video data recordings were captured in diverse light and weather conditions (under the safety supervision of industry experts) involving a high-speed (120 fps) camera system attached to an MCB transfer vehicle. Before identifying a safety hazard, e.g., the unsafe position of a pin connecting two 750 kg concrete segments of the MCB, a multi-stage preprocessing of the spatiotemporal region of interest (ROI) involves a rolling window before identifying the video frames containing diagnostic information. This study utilises the ResNet-50 architecture, enhanced with 3D convolutions, within the STENet framework to capture and analyse spatiotemporal data, facilitating real-time surveillance of the Auckland Harbour Bridge (AHB). Considering the sparse nature of safety anomalies, the initial peer-reviewed binary classification results (82.6%) for safe and unsafe (intervention-required) scenarios were improved to 93.6% by incorporating synthetic data, expert feedback, and retraining the model. This adaptation allowed for the optimised detection of false positives and false negatives. In the future, we aim to extend anomaly detection methods to various infrastructure inspections, enhancing urban resilience, transport efficiency and safety. Full article

With renewed interest in the optimisation of the hydraulic performance of new and existing culverts, particularly relevant to South Africa’s evolving road network and anticipated climate-induced rainfall changes, this research investigated the benefit of angled wingwall and headwall combinations and considered the installation of a ventilation device in order to improve culvert performances. Through experimental modelling at the University of Pretoria Water Laboratory, the angled wingwall and headwall combinations demonstrated significant flow improvements compared to square inlets. It was also demonstrated that a ventilation device could cause flow through culverts to flow under inlet control conditions where it would otherwise have flowed under outlet control conditions. Additionally, the study proposes design coefficient adjustments for square inlet culverts operating under inlet control conditions. The proposed improvements can be applied during design stages, but the findings also propose prefabricated inlet elements as cost-effective solutions for existing culverts, thereby facilitating quick upgrades without the need for lengthy road closures while potentially enabling benefits for pedestrian traffic. Ultimately, this study underscores the potential of innovative and novel design modifications to enhance culvert performance, offering sustainable and economical alternatives to conventional replacement practices while advancing hydraulic engineering resilience in response to evolving infrastructural and environmental demands. Full article

The exchange of sensitive information between power distribution networks (PDNs) and urban transport networks (UTNs) presents a difficulty in ensuring privacy protection. This research proposes a new collaborative operation method for a coupled system. The scheme takes into account the schedulable capacity of electric vehicle charging stations (EVCSs) and locational marginal prices (LMPs) to handle the difficulty at hand. The EVCS hosting capacity model is built and expressed as the feasible area of charging power, based on AC power flow. This model is then used to offer information on the real schedulable capacity. By incorporating the charging loads into the coupling nodes between PDNs and UTNs, the issue of coordinated operation is separated and becomes equal to the optimal problem involving charging loads. Based on this premise, the most efficient operational cost of PDNs is transformed into a comparable representation of cost information in PDNs. This representation incorporates LMP information that guides charging decisions in UTNs. The suggested collaborative scheduling methodology in UTNs utilises the collected projection information from the static traffic assignment (STA) to ensure data privacy protection and achieve non-iterative calculation. Numerical experiments are conducted to illustrate that the proposed method, which uses a smaller amount of data, achieves the same level of optimality as the coordinated optimisation. Full article

Arrow signs found on roadway pavement are an important component of modern transportation systems. Given the rise in autonomous vehicles, public agencies are increasingly interested in accurately identifying and analysing detailed road pavement information to generate comprehensive road maps and decision support systems that can optimise traffic flow, enhance road safety, and provide complete official road cartographic support (that can be used in autonomous driving tasks). As arrow signs are a fundamental component of traffic guidance, this paper aims to present a novel deep learning-based approach to identify the orientation and direction of arrow signs on marked roadway pavements using high-resolution aerial orthoimages. The approach is based on convolutional neural network architectures (VGGNet, ResNet, Xception, and DenseNet) that are modified and adapted for regression tasks with a proposed learning structure, together with an ad hoc model, specially introduced for this task. Although the best-performing artificial neural network was based on VGGNet (VGG-19 variant), it only slightly surpassed the proposed ad hoc model in the average values of the R² score, mean squared error, and angular error by 0.005, 0.001, and 0.036, respectively, using the training set (the ad hoc model delivered an average R² score, mean squared error, and angular error of 0.9874, 0.001, and 2.516, respectively). Furthermore, the ad hoc model’s predictions using the test set were the most consistent (a standard deviation of the R² score of 0.033 compared with the score of 0.042 achieved using VGG19), while being almost eight times more computationally efficient when compared with the VGG19 model (2,673,729 parameters vs VGG19′s 20,321,985 parameters). Full article