Search Results (379)

Traffic state estimation (TSE) is a core task in intelligent transportation systems (ITSs) that seeks to infer key operational parameters—such as speed, flow, and density—from limited observational data. Existing methods often face challenges in practical deployment, including limited estimation accuracy, insufficient physical consistency, and weak generalization capability. To address these issues, this paper proposes a hybrid estimation framework that integrates multi-agent reinforcement learning (MARL) with the Lighthill–Whitham–Richards (LWR) traffic flow model. In this framework, each roadside detector is modeled as an agent that adaptively learns fundamental diagram (FD) parameters—the free-flow speed and jam density—by fusing local detector measurements with global CAV trajectory sequences via an interactive attention mechanism. The learned parameters are then passed to an LWR solver to perform sequential (rolling) prediction of traffic states across the entire road segment. We design a reward function that jointly penalizes estimation error and violations of physical constraints, enabling the agents to learn accurate and physically consistent dynamic traffic state estimates through interaction with the physics-based LWR environment. Experiments on simulated and real-world datasets demonstrate that the proposed method outperforms existing models in estimation accuracy, real-time performance, and cross-scenario generalization. It faithfully reproduces dynamic traffic phenomena, such as shockwaves and queue waves, demonstrating robustness and practical potential for deployment in complex traffic environments. Full article

Accurate traffic input data are essential for reliable road noise mapping within the CNOSSOS-EU framework. However, European countries often rely on heterogeneous data sources and measurement practices, which may introduce uncertainties in noise estimates and reduce the comparability of results across regions. This study evaluates the performance of three traffic data collection methods, specifically microwave radar traffic counters, artificial intelligence-based cameras, and Google API-derived flows, in three representative test sites located in Italy and Romania. Traffic flows and vehicle category distributions obtained from each method were used as inputs for noise simulations, and predicted levels were compared with in situ noise measurements. A second analytical approach was developed to estimate short-term noise levels at a 10’ resolution by combining CNOSSOS-EU power models with propagation matrices computed using commercial sound propagation software. The results show that both radar counters and cameras provide reliable inputs for day/evening/night indicators, although counters may miss flows under complex traffic conditions, and cameras may overestimate counts at high volumes. Google API-derived flows perform well only when traffic exceeds approximately 150 vehicles per hour and when the traffic model is carefully calibrated. Manual counting confirmed that all three input data collection methods exhibit non-negligible traffic loss, which contributes to a systematic underestimation of simulated noise levels when using average flow-based modeling. Differences between methods become more pronounced when analyzing short time intervals rather than aggregated indicators. Overall, this study highlights the strengths and limitations of each data source and provides guidance on their appropriate use for road noise assessment and strategic mapping. Full article

Mid-sized Philippine cities commonly rely on fixed-time traffic signal plans that cannot respond to short-term, demand-driven surges, resulting in measurable idle time at stop lines, increased delay, and unnecessary emissions, while adaptive signal control has demonstrated performance benefits, many existing solutions depend on centralized infrastructure and high-bandwidth connectivity, limiting their applicability for resource-constrained local government units (LGUs). This study reports a field deployment of TrafficEZ, a lightweight edge AI signal controller that reallocates green splits locally using traffic-density approximations derived from cabinet-mounted cameras. The controller follows a macroscopic, cycle-level control abstraction consistent with Transportation System Models (TSMs) and does not rely on stationary flow–density–speed (fundamental diagram) assumptions. The system estimates queued demand and discharge efficiency on-device and updates green time each cycle without altering cycle length, intergreen intervals, or pedestrian safety timings. A quasi-experimental pre–post evaluation was conducted at three signalized intersections in El Salvador City using an existing 125 s, three-phase fixed-time plan as the baseline. Observed field results show average per-vehicle delay reductions of 18–32%, with reclaimed effective green translating into approximately 50–200 additional vehicles per hour served at the busiest approaches. Box-occupancy durations shortened, indicating reduced spillback risk, while conservative idle-time estimates imply corresponding CO₂ savings during peak periods. Because all decisions run locally within the signal cabinet, operation remained robust during backhaul interruptions and supported incremental, intersection-by-intersection deployment; per-cycle actions were logged to support auditability and governance reporting. These findings demonstrate that density-driven edge AI can deliver practical mobility, reliability, and sustainability gains for LGUs while supporting evidence-based governance and performance reporting. Full article

Pedestrian safety in school zones is shaped by traffic conditions and street design characteristics, whose combined effects involve uncertainty and gradual transitions rather than sharp thresholds. This study presents an integrated assessment framework based on the analytic hierarchy process (AHP) and fuzzy logic to evaluate pedestrian traffic stress level (PTSL) at the street-segment scale in school environments. AHP is used to derive input-variable weights from expert judgments, while a Mamdani-type fuzzy inference system models the relationships between traffic and geometric variables and pedestrian stress. The model incorporates vehicle density, pedestrian density, lane width, sidewalk width, buffer zone, and estimated traffic flow speed as input variables, represented using triangular membership functions. Genetic Algorithm (GA) optimization is applied to calibrate membership-function parameters, improving numerical consistency without altering the linguistic structure of the model. A comprehensive rule base is implemented in MATLAB (R2024b) to generate a continuous traffic stress score ranging from 0 to 10. The framework is applied to street segments surrounding major schools in the study area, enabling comparison of spatial variations in pedestrian stress. The results demonstrate how combinations of traffic intensity and street geometry influence stress levels, supporting data-driven pedestrian safety interventions for sustainable school environments and low-stress urban mobility. Full article

This study investigates flow resistance in thin water films on road surfaces during rainfall, which is essential for assessing aquaplaning risk. A one-dimensional surface runoff model based on the diffusion-wave approach is used to compare existing equations for the Darcy–Weisbach friction factor and Manning’s roughness coefficient. Laboratory data from three experimental cases support the analysis. The first case assesses the accuracy of existing equations and develops a new regression-based equation. The second case validates this new model for predicting water film thickness. Findings show that many existing equations poorly estimate water film thickness under high-intensity rainfall conditions relevant for aquaplaning analysis, often under- or overestimating it compared to measurements. Results indicate that flow resistance is mainly influenced by the Froude number, which is defined using the mean macro-texture depth of the pavement. The study emphasizes that accurate estimation of flow resistance parameters is critical in water film modelling, as it directly affects the reliability of traffic safety assessments. Full article

Road dust resuspension is widely recognized as a major contributor to traffic-related particulate matter (PM) in urban environments. Nevertheless, reported emission factors exhibit substantial variability. These discrepancies stem not only from the intrinsic complexity of the resuspension process but also from limitations in measurement techniques, which often fail to adequately control or characterize the influencing parameters. As a result, the contribution of each parameter remains difficult to isolate, leading to inconsistencies across studies. This study presents an experimental protocol developed to quantify PM10 and PM2.5 emission factors associated with vehicle-induced road dust resuspension. Experiments were conducted on a dedicated test track seeded with alumina particles of controlled mass and size distribution to simulate road dust. A network of microsensors was strategically deployed at multiple upwind and downwind locations to continuously monitor particle concentration variations during vehicle passages. Emission factors were derived through time integration of the mass flow rate of resuspended dust measured by the sensor network. The estimated PM10 emission factor showed excellent agreement, within 2.5%, with predictions from a literature-based formulation, thereby validating the accuracy and external relevance of the proposed protocol. In contrast, comparisons with U.S. EPA formulas and other empirical equations revealed substantially larger discrepancies, particularly for PM2.5, highlighting the persistent limitations of current modeling approaches. Full article

Traffic state estimation (TSE) is crucial for intelligent transportation systems, as it provides unobserved parameters for traffic management and control. In this paper, we propose a novel physics-guided graph neural network for TSE that integrates traffic flow theory into an estimation framework. First, we constructed wave-informed anisotropic temporal graphs to capture the time-delayed correlations across the road network, which were then merged with spatial graphs into a unified spatiotemporal structure for subsequent graph convolution operations. Then, we designed a four-layer diffusion graph convolutional network. Each layer is enhanced with squeeze-and-excitation attention mechanism to adaptively capture dynamic directional correlations. Furthermore, we introduced the fundamental diagram equation into the loss function, which guided the model toward physically consistent estimations. Experimental evaluations on a real-world highway dataset demonstrated that the proposed model achieved a higher accuracy than benchmark methods, confirming its effectiveness in capturing complex traffic dynamics. Full article

Accurate prediction of road traffic crash severity is essential for developing data-driven safety strategies and optimizing resource allocation. This study presents a predictive modeling framework that utilizes Random Forest (RF), Gradient Boosting (GB), and K-Nearest Neighbors (KNN) to estimate segment-level frequencies of fatalities, serious injuries, and slight injuries on Hungarian roadways. The model integrates an extensive array of predictor variables, including roadway geometric design features, traffic volumes, and traffic composition metrics. To address class imbalance, each severity class was modeled using resampled datasets generated via the Synthetic Minority Over-sampling Technique (SMOTE), and model performance was optimized through grid-search cross-validation for hyperparameter optimization. For the prediction of serious- and slight-injury crash counts, the Random Forest (RF) ensemble model demonstrated the most robust performance, consistently attaining test accuracies above 0.91 and coefficient of determination (R²) values exceeding 0.95. In contrast, for fatalities count prediction, the Gradient Boosting (GB) model achieved the highest accuracy (0.95), with an R² value greater than 0.87. Feature importance analysis revealed that heavy vehicle flows consistently dominate crash severity prediction. Horizontal alignment features primarily influenced fatal crashes, while capacity utilization was more relevant for slight and serious injuries, reflecting the roles of geometric design and operational conditions in shaping crash occurrence and severity. The proposed framework demonstrates the effectiveness of machine learning approaches in capturing non-linear relationships within transportation safety data and offers a scalable, interpretable tool to support evidence-based decision-making for targeted safety interventions. Full article

As the primary collision patterns on China’s freeways, in-depth exploration of the influencing factors of rear-end and sideswipe crashes has long been crucial for implementing targeted countermeasures. However, the structural and traffic flow continuity of freeways endows crash data with complex spatial and site correlations, which—if neglected in safety modeling—can lead to biased estimates of safety effects. To address this issue, this study develops a bivariate conditional autoregressive (CAR) model based on the Poisson lognormal (PLN) distribution: the copula joint distribution captures the site correlation between the two crash types, while the CAR model addresses spatial correlations across adjacent segments. Compared with univariate models and bivariate models with jointly distributed residuals, the proposed model achieves optimal performance and reveals the distinct determinants of the two crash types. For instance, factors such as spiral curve length and mean speed affect both crash types but to varying degrees, while continuous horizontal curve length only influences rear-end crashes. The proposed model and the identified influencing factors provide significant support for engineers to improve road safety. Full article

This study confronts the significant challenges inherent in Traffic State Estimation (TSE) for rural arterial networks, where sparse sensor coverage and complex, dynamic traffic flows complicate effective management and safety assurance. Traditional TSE methodologies, often dependent on single-source data streams, fail to accurately model the intricate spatiotemporal dependencies present in such environments. This fundamental limitation precipitates critical safety hazards, including pervasive over speeding and dangerous queue spillback phenomena at intersections. To address these deficiencies, we introduce a novel hybrid intelligence framework that synergistically combines a Graph Attention Temporal Convolutional Network (GAT-TCN) with advanced Kalman Filter variants, specifically the Extended, Unscented, and Sliding Window Kalman Filters. The GAT-TCN component is engineered to excel at learning complex, non-linear correlations across both space and time through multi-source data fusion. Empirical validation conducted on a real-world rural toll corridor demonstrates that our proposed model achieves a statistically significant superiority over conventional benchmarks, as rigorously quantified by substantial reductions in both Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). Beyond mere predictive accuracy, the framework delivers transformative safety enhancements by facilitating the proactive identification of hazardous events, enabling earlier detection of over speeding and queue spillback compared to existing methods. Consequently, this research provides a scalable and robust framework for proactive rural traffic management, fundamentally shifting the paradigm from achieving incremental predictive improvements to generating decisive, safety-actionable insights for infrastructure operators. Full article

Accurate estimation of branch-level traffic flows at urban Y-intersections from limited mainline measurements remains a critical challenge in intelligent transportation systems. Y-intersections, with their symmetric geometric configuration where multiple branches converge, pose unique challenges from flow coupling, signal-induced periodicity, and merging delays. This study develops a hybrid mathematical modeling framework that integrates piecewise linear segments with periodic components for each branch flow. The model enforces physical constraints including flow conservation, non-negativity, and segment continuity, while incorporating operational features such as signal timing and merging delays. Parameter estimation employs a two-stage optimization approach combining least-squares fitting with constrained nonlinear programming, utilizing sparse mainline detector data and minimal historical priors. Experimental validation across five progressive problem formulations demonstrates robust performance, achieving RMSE values of 3.3432 and 5.4467 for complex multi-branch scenarios while accurately capturing 10-min green/8-min red signal cycles and 2-min merging delays. The method successfully reconstructs branch flow profiles at required time points (07:30 and 08:30), reducing observation requirements by 60–80% while maintaining estimation accuracy. The proposed framework provides a practical and interpretable solution for branch flow estimation under sparse sensing conditions, bridging physics-based modeling with data-driven techniques and offering transportation agencies a deployable tool for intersection monitoring without extensive instrumentation. Full article

Accurate prediction of maximum flow latency is crucial for ensuring the efficient transport of latency-sensitive fronthaul traffic in packet-switched Xhaul networks while maintaining the reliable operation of 5G and beyond Radio Access Networks (RANs). Deterministic worst-case (WC) models provide strict latency guarantees but tend to overestimate actual delays, resulting in resource over-provisioning and inefficient network utilization. To address this limitation, this study evaluates a data-driven Quantile Regression (QR) model for latency prediction in Time-Sensitive Networking (TSN)-enabled packet-switched Xhaul networks operating under dynamic traffic conditions. The proposed QR model estimates high-percentile (tail) latency values by leveraging both deterministic and queuing-related data features. Its performance is quantitatively compared with the WC estimator across diverse network topologies and traffic load scenarios. The results demonstrate that the QR model achieves significantly higher prediction accuracy—particularly for midhaul flows—while still maintaining compliance with latency constraints. Furthermore, when applied to dynamic Xhaul network operation, QR-based latency predictions enable a reduction in active processing-node utilization compared with WC-based estimations. These findings confirm that data-driven models can effectively complement deterministic methods in supporting latency-aware optimization and adaptive operation of 5G/6G Xhaul networks. Full article

The efficiency of intelligent urban mobility increasingly depends on adaptive mathematical models that can optimize multimodal transportation resources under stochastic and heterogeneous conditions. This study proposes a Markovian stochastic modeling and metaheuristic optimization framework for the adaptive management of bus lane capacity in mixed connected traffic environments. The heterogeneous vehicle arrivals are modeled using a Markov Arrival Process (MAP) to capture correlated and busty flow characteristics, while the system-level optimization aims to minimize total fuel consumption through discrete lane capacity allocation. To support real-time adaptation, a Hidden Markov Model (HMM) is integrated for queue-length estimation under partial observability. The resulting nonlinear and nonconvex optimization problem is solved using Genetic Algorithm (GA), Differential Evolution (DE), and Particle Swarm Optimization (PSO), ensuring robustness and convergence across diverse traffic scenarios. Numerical experiments demonstrate that the proposed stochastic–adaptive framework can reduce fuel consumption and vehicle delay by up to 68% and 65%, respectively, under high saturation and connected-vehicle penetration. The findings verify the effectiveness of coupling stochastic modeling with adaptive control, providing a transferable methodology for energy-efficient and data-driven lane management in smart and sustainable cities. Full article

This article describes a model for optimizing traffic flow control and generating traffic signal phases based on the stochastic dynamics of traffic and the percolation properties of transport networks. As input data (in SUMO), we use lane-level vehicle flow rates, treating them as random processes with unknown distributions. It is shown that the percolation threshold of the transport network can serve as a reliability criterion in a stochastic model of lane blockage and can be used to determine the control interval. To calculate the durations of permissive control signals and their sequence for different directions, vehicle queues are considered and the time required for them to reach the network’s percolation threshold is estimated. Subsequently, the lane with the largest queue (i.e., the shortest time to reach blockage) is selected, and a phase is formed for its signal control, as well as for other lanes that can be opened simultaneously. Simulation results show that when dynamic traffic signal control is used and a percolation-dynamic model for balancing road traffic is applied, lane occupancy indicators such as “congestion” decrease by 19–51% compared to a model with statically specified traffic signal phase cycles. The characteristics of flow dynamics obtained in the simulation make it possible to construct an overall control quality function and to assess, from the standpoint of traffic network management organization, an acceptable density of traffic signals and unsignalized intersections. Full article

Drowsy driving is a major cause of traffic accidents worldwide, and its early detection remains essential for road safety. Conventional driver monitoring systems (DMS) primarily rely on behavioral indicators such as eye closure, gaze, or head pose, which typically appear only after a significant decline in alertness. This study explores the potential of facial near-infrared (NIR) imaging as a hypothetical physiological indicator of drowsiness. Because NIR light penetrates more deeply into biological tissue than visible light, it may capture subtle variations in blood flow and oxygenation near superficial vessels. Based on this hypothesis, we conducted a pilot feasibility study involving young adult participants to investigate whether drowsiness levels could be estimated from single-frame NIR facial images acquired at 940 nm—a wavelength already used in commercial DMS and suitable for both physiological sensitivity and practical feasibility. A convolutional neural network (CNN) was trained to classify multiple levels of drowsiness, and Gradient-weighted Class Activation Mapping (Grad-CAM) was applied to interpret the discriminative regions. The results showed that classification based on 940 nm NIR images is feasible, achieving an optimal accuracy of approximately 90% under the binary classification scheme (Pattern A). Grad-CAM revealed that regions around the nasal dorsum contributed to this, consistent with known physiological signs of drowsiness. These findings support the feasibility of NIR-based drowsiness classification in young drivers and provide a foundation for future studies with larger and more diverse populations. Full article