Search Results (215)

Road surface hazards remain a persistent concern for vehicle safety, passenger comfort, and the operational continuity of transport infrastructure. Among these hazards, potholes are particularly significant because they can cause tire damage, suspension wear, wheel misalignment, and sudden vehicle instability. In addition to direct mechanical damage, potholes may reduce driving comfort, increase maintenance costs, and degrade traffic efficiency in urban environments where roads are heavily used and rapidly deteriorate. For these reasons, the timely detection of potholes is an important requirement for road safety and infrastructure management. This work presents a tailor-made dataset for road pothole detection in urban environments, referred to as the Bridgestone Dataset (BS Dataset). The dataset was designed to support object detection from vehicle-mounted imagery collected from a test vehicle under realistic road conditions, thereby aligning the training data more closely with the target deployment scenario. The resulting dataset is intended to support real-time monitoring systems for road hazard detection and maintenance planning. The dataset was also designed as a multimodal resource. In addition to pothole bounding-box annotations, it provides accelerometer and GPS signals to characterize the vehicle dynamics during operation which might help identifying hazard severity and the potential risk to the vehicle. To collect the dataset, the authors developed a smartphone application, which supports the acquisition of both images and vehicle telemetry by leveraging the device’s internal sensors. Full article

Connected vehicles and vehicle-to-everything (V2X) communication create new opportunities for estimating urban origin–destination (OD) demand from continuously collected mobility data. However, in realistic deployment conditions, only a fraction of vehicles may be connected, making OD reconstruction a highly underdetermined problem under low penetration rates. This paper proposes a supervised deep-learning framework that reconstructs full OD matrices from synthetic connected-vehicle data in a simulated Manhattan network from New York City. Vehicle movement information is aggregated into intra-zonal and adjacent-zone traffic counts using K-means traffic analysis zones. These partial connected-vehicle observations, represented by the zonal movement matrix, outgoing and incoming zonal-movement summaries, diagonal movement counts, and penetration-rate features, form a compact input to a conditional Multi-Layer Perceptron (MLP) that predicts the complete OD matrix of all vehicles. The training objective separates OD spatial shape from total traffic volume and adds losses on marginals, diagonal elements, and log-space reconstruction to embed basic flow-conservation properties. A single conditional MLP is trained across multiple connected-vehicle penetration-rate scenarios by appending the penetration rate $\rho$ and $\log \left(\rho \right)$ to the input representation. The model is evaluated over ten random connected-vehicle sampling seeds. Results show that the proposed estimator remains stable down to 20% penetration, with test sMAPE increasing only from $20.70\pm 0.00\%$ at full penetration to $21.71\pm 0.38\%$ at 20% penetration. Marginal and total-flow errors increase more gradually as penetration decreases, while clear degradation appears below approximately 2–1% penetration. Baseline and ablation comparisons further show that penetration-rate conditioning and the conservation-aware loss are essential for improving OD reconstruction and total-flow consistency. Within the evaluated simulated Manhattan scenarios, these findings suggest the potential of conditional neural estimators for OD reconstruction under limited connected-vehicle penetration. Validation across longer periods, additional demand regimes, and real-world data is required before the results can be generalized to broader urban traffic conditions. Full article

This paper investigates the use of unmanned aerial vehicles (UAVs) as flying base stations (BSs) to enhance fifth generation (5G) vehicular communications on highways, where traffic congestion and fluctuating user demand can challenge the capacity of terrestrial infrastructure. While UAV-assisted vehicular networking has attracted significant attention, many existing studies rely on simplified mobility, propagation, or communication models that limit the assessment of practical deployment performance. To address these limitations, we develop a realistic UAV-assisted vehicular networking framework that integrates microscopic traffic simulation through Simulation of Urban MObility (SUMO), network control via Traffic Control Interface (TraCI), and standard-compliant 5G communication modeling using MATLAB R2025b 5G Toolbox. The framework incorporates a 3rd Generation Partnership Project (3GPP) rural macro cell (RMa) highway scenario, detailed clustered delay line (CDL)-based channel characterization, and cross-layer communication procedures. Within this framework, we propose a low-complexity trajectory optimization strategy that adapts the UAV position in real time to maximize the average received signal to noise ratio (SNR) while respecting practical motion constraints. Simulation results demonstrate that adaptive UAV positioning enhances communication performance, achieving mean SNR gains of up to 2.04 dB, throughput improvement of up to 11.2%, and block error rate (BLER) reductions of up to 27.3%. These findings highlight the potential of UAV-assisted communications to enhance user-perceived quality of service (QoS) for bandwidth-demanding vehicular applications under realistic 5G highway operating conditions. Full article

Urban traffic congestion remains a major challenge for modern cities, requiring intelligent traffic signal control (TSC) strategies capable of adapting to dynamic traffic conditions. This paper proposes a hybrid reinforcement learning approach for traffic signal control that combines the complementary learning mechanisms of Q-learning, SARSA, and Monte Carlo algorithms to improve both learning efficiency and control performance. The proposed approach is implemented and evaluated using the Simulation of Urban MObility (SUMO) simulator on a realistic road network corresponding to the “Route de Sefrou” in Fez, Morocco. The traffic signal controller is trained through continuous interaction with the simulated environment and compared with the three individual reinforcement learning algorithms under identical experimental conditions. The experimental results demonstrate that the proposed hybrid approach provides more efficient traffic management, faster convergence, and greater learning stability than the individual algorithms. These findings demonstrate the potential of hybrid reinforcement learning as an effective solution for adaptive traffic signal control in realistic urban environments. Full article

Compared to conventional signalised intersections, roundabouts are increasingly recognised for their ability to improve traffic safety and operational efficiency. However, accurately modelling their complex traffic dynamics remains challenging, particularly in multilane configurations characterised by lane-changing manoeuvres and gap-acceptance interactions. This study presents a behaviour-driven microscopic simulation framework based on agent-based modelling (ABM) for evaluating roundabout performance under varying geometric and traffic demand conditions. In the proposed framework, each vehicle is represented as an autonomous agent capable of route selection, yielding, lane-changing, and speed adaptation according to predefined behavioural rules. This enables a detailed representation of local traffic interactions and operational conflicts that are not fully captured by traditional aggregate traffic models. The simulation environment is used to analyse idealised one-, two-, and three-lane roundabout configurations and to assess the operational impact of targeted geometric modifications. The proposed methodology is further validated using real-world traffic data collected from the Brașov Central Roundabout, Romania. Simulation results demonstrate that the ABM framework can realistically reproduce traffic throughput, average speed, number of stops, and travel time under high traffic demand conditions. Furthermore, the introduction of a channelised right-turn lane resulted in measurable operational improvements, including increased average speed and reduced delay. The findings highlight the applicability of agent-based simulation as a decision-support tool for roundabout design, traffic management, and infrastructure optimisation, contributing to safer and more efficient urban mobility systems. Full article

Autonomous vehicles operating at signalized intersections face fundamental challenges arising from queue dynamics, signal-phase transitions, and tightly coupled multi-vehicle interactions. Conventional motion-planning methods, which rely primarily on instantaneous perception, are inherently reactive and struggle to reason about short-term traffic evolution. This paper presents a Transformer-based predictive motion-planning framework that embeds short-term traffic state prediction directly into the structure of the planning problem. A lightweight spatial–temporal Transformer model is designed to forecast traffic occupancy, queue evolution, and interaction patterns using historical trajectories, signal-phase information, and road topology. By converting predicted traffic dynamics into explicit spatial–temporal constraints, a hierarchical motion planner jointly optimizes path geometry and speed profiles through dynamically constructed feasible corridors. The proposed framework is evaluated using a joint SUMO–CARLA simulation platform under realistic traffic conditions derived from real-world datasets, including pNEUMA and CitySim. The experimental results across straight-through, queueing, and turning scenarios show that prediction-aware planning significantly reduces high-risk driving time and intersection travel time while maintaining stable real-time computational performance. Beyond scenario-level improvements, the results indicate that transforming traffic prediction into planning constraints provides a generalizable paradigm for proactive, feasibility-aware autonomous driving at signalized intersections. From a methodological perspective, the proposed framework can be interpreted through the lens of symmetry and asymmetry in intelligent transportation systems: the conventional symmetric decoupling between prediction and planning modules is deliberately broken by embedding predicted traffic states as time-varying, directionally asymmetric constraints, while the permutation symmetry of the multi-head attention mechanism is preserved over lane-segment tokens to provide a structured inductive bias for traffic state forecasting. This symmetry-aware design highlights how controlled symmetry breaking in modeling and optimization can yield safer, more efficient, and more adaptive autonomous driving behaviors in signalized urban environments. Full article

Urban congestion continues to worsen worldwide, underscoring the need for efficient traffic management models. In this study, we extend the existing kinematic theory (KT) cellular automata (CA) model by incorporating a traffic-light module to systematically evaluate how key parameters affect traffic flow and average velocity on a one-lane road containing multiple signalized intersections. Simulations are primarily conducted under periodic boundary conditions to isolate and examine the influence of each parameter. All original KT model features—including the safety-analysis-based determination of velocity and acceleration at each time step—are retained, enabling realistic heterogeneous driving behavior. Additionally, we analyze arrival and departure dynamics under semi-open boundary conditions to gain deeper insight into urban traffic behavior. The results indicate that the maximum traffic flow at a maximum velocity of 60 km/h and a reaction time of 1.0 s is 794 vehicles/h at a density of 0.4 vehicle/cell. Adaptive acceleration increases traffic flow by up to 20% for densities below 0.7 vehicle/cell and even more at higher densities, while reducing the reaction time by 0.2 s increases traffic flow by up to 17%. Increasing the maximum acceleration by 1 m/s² yields only a modest rise of up to 5%. At a maximum velocity of 80 km/h, traffic flow is up to 46% higher relative to 40 km/h, although the effect diminishes at higher densities. Furthermore, semi-open boundary conditions produce consistently higher traffic flow than periodic boundaries. These findings demonstrate that the enhanced KT–CA model can capture the effects of driver behavior and traffic-signal timing, offering an improved framework for analyzing and optimizing urban traffic systems. Full article

Tire and road wear particles (TRWPs) are major sources of non-exhaust traffic emissions. However, a limited understanding of their generation mechanisms and the lack of efficient collection methods under realistic driving conditions hinder accurate assessment. This study addresses these challenges by developing a vehicle-based methodology for the controlled recovery and characterization of TRWPs in the near-field region, rather than for direct quantification of real-world emissions. An autonomous electric vehicle was employed to ensure stable driving conditions and eliminate exhaust interference. Near-field distribution of TRWPs was visualized using a high-sensitivity optical scattering system. Based on this, a sealed tire enclosure with a high-power on-vehicle vacuum collection system was designed to enhance particle containment and recovery. Controlled circular driving tests were conducted on a dedicated outdoor test track under well-defined and repeatable conditions to enable system-level evaluation of TRWP generation and collection relative to measured tire wear. Particles were analyzed by thermogravimetric analysis, microscopy, scanning electron microscopy–energy-dispersive X-ray spectroscopy, and particle imaging. The results demonstrated stable, reproducible TRWP generation with ~60% collection efficiency relative to tire mass loss. These values are reported as system-dependent recovery indicators rather than precise emission estimates. Additional tests with an expanded recovery protocol indicated that collection efficiency can increase to ~81% (range: 73–91%), highlighting the influence of collection coverage. The collected TRWPs exhibited heterogeneous morphology, bimodal size distribution, and a mixed rubber–mineral composition in the 10–100 μm range. Spatial analysis revealed that TRWPs predominantly accumulated within a narrow zone around the driving lane. While the controlled experimental configuration enables reproducible particle generation and high-efficiency recovery, it represents a simplified driving scenario and may not fully capture the variability of real-world traffic conditions, including straight-line driving and transient maneuvers. Overall, this study demonstrates a technical framework for reproducible and comparative recovery of tire-associated particles under identical, well-defined conditions. The approach is intended to support controlled characterization studies while explicitly acknowledging limitations related to representativeness, particle origin attribution, and quantitative emission relevance, rather than to establish emission factors or mechanistic descriptions of TRWP generation. Full article

Recent advances in roadside sensing technologies, including camera-based systems, radar, and LiDAR, have enabled high-resolution sampling of vehicle trajectories, overcoming the temporal and spatial limitations of traditional data collection methods. Among these, LiDAR sensing has been widely adopted for traffic monitoring and surrogate safety analysis due to its high spatial accuracy and temporal resolution. However, sensor noise and occlusion in roadside LiDAR frequently introduce tracking point offsets and trajectory discontinuities, reducing the reliability of vehicle counts, traffic state estimation, and conflict analysis. To address these challenges, this study proposes a post-processing method based on time–space analysis to detect and correct occlusion-induced trajectory discontinuities. By exploiting the inherent spatiotemporal consistency of vehicle movements, the proposed approach identifies fragmented trajectories, reconstructs continuous vehicle paths, and recovers realistic traffic patterns. Validated on real-world LiDAR data collected at an urban intersection in Reno, Nevada, across four 30 min traffic periods covering AM and PM peak conditions on weekdays and weekends, the proposed method achieves an average precision of 0.989 and an average F1-score of 0.948, outperforming IMM, GNN-RM, and HMM + Viterbi benchmark methods. Count accuracy improved from 85.5% to 97.4% across all evaluated periods, confirming the method’s effectiveness under occlusion conditions. Full article

This study investigates data augmentation as a strategy for addressing dataset scarcity in Internet of Medical Things (IoMT) cybersecurity and improving intrusion-detection system performance. Four augmentation methods—Rule-Based, Tabular Variational Autoencoder (TVAE), Conditional Tabular Generative Adversarial Network (CTGAN), and Gaussian Copula—were applied to two publicly available IoMT datasets (ECU-IoHT and WUSTL-EHMS) to generate augmented training data with differing class distributions and feature characteristics. Eleven machine learning algorithms were evaluated using Matthews Correlation Coefficient (MCC), F1-score, accuracy, and error-based metrics. Results showed consistent performance improvements across all evaluated models relative to the baseline datasets. The Rule-Based method produced the strongest overall results, achieving the highest MCC (0.9757), F1-score (99.19%), and accuracy (99.18%) with LightGBM, alongside low false-positive and false-negative rates. Among the generative approaches, TVAE delivered the strongest overall practical performance (F1-score = 96.94%, accuracy = 96.92%), while CTGAN achieved a marginally higher MCC (0.9047) and also produced competitive results with balanced class representation. Gaussian Copula generated the weakest overall outcomes, primarily due to highly skewed class distributions. Traditional models, such as Logistic Regression and Naive Bayes, recorded the largest relative gains, indicating that augmentation can substantially improve simpler classifiers in data-scarce environments. Overall, the findings demonstrate that augmentation quality depends not only on dataset expansion, but also on preserving class balance, feature diversity, and realistic traffic relationships. These results provide practical guidance for strengthening IoMT intrusion-detection systems in healthcare environments. Full article

Urban traffic congestion remains a persistent challenge for conventional fixed-time signal control, particularly under fluctuating and asymmetric demand. Although multi-agent reinforcement learning (MARL) has shown promise for adaptive traffic signal control, previous studies have often focused on isolated intersections, simplified synthetic networks, or deep-learning-based controllers without systematically comparing tabular and deep-value-based multi-agent approaches under equivalent operating conditions. This study addresses this gap by comparing three traffic signal control strategies: fixed-time control, Multi-Agent Tabular Q-Learning, and multi-agent Deep Q-Network control (MADQN). The evaluation was conducted in a microscopic traffic simulation environment using two complementary testbeds: a synthetic two-intersection corridor, which enables controlled analysis of multi-agent coordination, and a real-world digital twin of the 25 January Corridor in Assiut, Egypt, which tests controller robustness under asymmetric geometry and realistic turning movements. The controllers are assessed under low-, medium-, and high-demand scenarios using queue length, cumulative delay, and Time-To-Collision as operational and safety-related indicators. The results show that MARL-based controllers generally outperform fixed-time control, but their relative performance depends on demand intensity and network complexity. MADQN provides stronger generalization in low-demand and queue-dissipation conditions, whereas Tabular Q-Learning remains highly competitive and can achieve superior delay reduction in several medium- and high-demand cases. These findings indicate that deeper MARL architectures are not universally superior; rather, adaptive signal control deployment should match the controller architecture to the operational objective, traffic demand regime, and practical complexity of the target corridor. Full article

The evolution of 5G networks has introduced new challenges in securing mobile infrastructures against increasingly sophisticated cyber threats. Intrusion detection in such environments has been widely studied using traditional datasets such as the Canadian Institute for Cybersecurity Intrusion Detection Systems CICIDS2017, the University of New South Wales-Network Behavior UNSW-NB15, and The Network Security Laboratory-Knowledge Discovery in Databases NSL-KDD; however, these benchmarks lack the architectural complexity and protocol diversity inherent to 5G networks. More recent research has adopted the 5G-NIDD dataset (5G Network Intrusion Detection Dataset), which provides realistic traffic generated from a live 5G testbed, including various attack scenarios targeting MEC servers and core network components. Nevertheless, existing works using 5G-NIDD often focus on limited subsets of attacks, rely on unsupervised or federated learning approaches, and lack comprehensive evaluations of supervised learning models. In contrast, this study leverages the entire 5G-NIDD dataset, encompassing all available attack scenarios, and conducts a systematic comparison of multiple supervised learning algorithms. A systematic evaluation of supervised learning algorithms is conducted using key performance metrics such as accuracy, precision, recall and F1-score to identify the most effective model for intrusion detection in 5G environments. Specifically, this study focuses on four supervised learning algorithms, K-Nearest Neighbors (KNNs), Support Vector Machines (SVMs), Logistic Regression (LR), and Naive Bayes (NB), to determine not only which achieves the highest detection accuracy but also which offers the best balance between predictive performance and computational efficiency in realistic 5G environments. To assess robustness and adaptability, the proposed models are further validated on two widely used benchmark datasets, namely CICIDS2017 and UNSW-NB15, as part of an extended analysis. This cross-dataset evaluation highlights each algorithm’s strengths and limitations under diverse network traffic conditions and attack scenarios. The results aim to validate the applicability of supervised learning approaches to intrusion detection in next-generation network infrastructures, while also emphasizing the importance of balancing predictive accuracy with computational efficiency for real-world deployment. Full article

Wireless networks are increasingly considered for industrial and time-critical applications, where flexible deployment must be reconciled with predictable communication behaviour. IEEE 802.11ax introduces mechanisms such as Orthogonal Frequency Division Multiple Access (OFDMA), Trigger-based Uplink Access (TUA), and Target Wake Time (TWT) as part of ongoing efforts to support bounded latency and deterministic transmissions in Wi-Fi networks. However, the practical behaviour of these mechanisms depends not only on the standard, but also on what commercial devices expose, how access points implement scheduling decisions, and how trigger-based access, RU assignment, and timing control can be configured in real deployments. This paper therefore focuses on the practical implementation and experimental assessment of OFDMA-based deterministic operation using Wi-Fi 6 commercial off-the-shelf (COTS) hardware. The proposed configuration combines driver-level enabling of high-efficiency mechanisms with controlled testbed measurements and complementary simulations, allowing OFDMA operation to be compared against conventional single-user OFDM under realistic traffic and interference conditions. The results show that coordinated OFDMA operation on COTS devices improves temporal stability, reducing jitter by up to 23% and latency by approximately 44% with respect to single-user OFDM operation. The experiments also reveal practical effects that are central to deterministic-oriented Wi-Fi: simultaneous RU-based transmissions reduce contention-driven variability, TWT-based activity windows improve temporal alignment, and RU subdivision introduces a throughput trade-off that must be considered when dimensioning industrial traffic. Overall, the study provides empirical evidence that Wi-Fi 6 can support deterministic-oriented industrial communication when OFDMA, trigger-based access, and timing mechanisms are jointly configured, while also highlighting the implementation constraints that remain when moving from standard capabilities to COTS device behaviour. Full article

While Low Emission Zone (LEZ) enforcement cameras provide a constant stream of traffic data, such resources remain significantly underexploited for urban mobility planning, as their current application is restricted to enforcing vehicle access regulations and issuing fines. This paper presents MobiCugat, a framework demonstrating that Automatic Number Plate Recognition (ANPR) camera data from a municipal LEZ network can serve as the calibration backbone for high-fidelity, city-scale traffic simulations for a policy-testing Digital Twin. The case study is Sant Cugat del Vallès (Barcelona), where the local council sought to evaluate new scenarios for the area using an evidence-based, data-driven approach. Vehicle detection records from 102 LEZ ANPR cameras were processed into 15-min traffic intensity time series through a General Data Protection Regulation (GDPR)-compliant pipeline. The Realistic Urban Traffic Generator (RUTGe), a Deep Reinforcement Learning-based tool, was used to generate SUMO-compatible traffic demand whose simulated detector counts reproduce the observed camera-based intensities. The resulting simulations reproduced the observed detector-level traffic intensities with ${\mathrm{MARE}}_{\%}$ values between $2.29\%$ and $2.90\%$ across representative morning peak, midday off-peak, and evening peak traffic conditions. Additionally, camera analysis of over $470,000$ vehicle records revealed that resident traffic ($37.4\%$) dominates over through-traffic ($3.8\%$), significantly refining prior survey-based estimates. Our high-fidelity simulation tool based on SUMO, features realistic traffic patterns calibrated through AI-driven techniques, enabling the evaluation of diverse ’what-if’ scenarios—such as road closures, pedestrianization, changes in traffic direction, or relocation of bus stops. By quantifying the impact of these interventions, our tool facilitates informed decision-making prior to physical implementation. The proposed pipeline is cost-effective, privacy-preserving, and directly replicable for any municipality operating an LEZ camera network, offering a scalable template for evidence-based urban mobility planning, aligned with the European Strategy for Data and the EU Green Deal goals for sustainable mobility. Full article

Driving in snow presents major safety challenges due to reduced visibility and slippery road conditions. Simulation-based tools may help improve hazard awareness; however, their effectiveness depends on how realistically they represent real-world driving experiences. This study examines the perceived realism and learning outcomes of a browser-based snow-driving simulation. A total of 87 licensed drivers with prior snow-driving experience interacted with a first-person browser-based simulation and subsequently completed a structured questionnaire. Composite indices were developed to measure Real-World Risk Perception (RWRP), Simulation Realism (SRI), Learning and Reflection (LEARN), and Awareness and Behavioral Reconsideration (AWARE). Quantitative analyses included reliability testing, descriptive statistics, correlation analysis, and multiple regression, complemented by qualitative thematic analysis. Results showed that perceived simulation realism was significantly associated with self-reported learning and awareness outcomes, whereas prior real-world risk perception was only weakly associated with post-simulation responses. Behavioral consistency between reported real-world and simulated driving behaviors was limited, suggesting that increased cognitive awareness does not necessarily correspond to behavioral equivalence. Qualitative findings identified limitations in vehicle dynamics, environmental complexity, traffic interactions, and emotional realism. Overall, the findings suggest that perceived realism plays a central role in shaping learning and awareness outcomes in browser-based driving simulations. The study highlights the educational potential of accessible web-based simulation environments while also emphasizing limitations in behavioral realism and transfer. Full article