Search Results (2,074)

In signalized urban road networks, periodic signal phase switching is a key factor influencing traffic-flow stability and operational efficiency. With the rapid development of Connected and Automated Vehicle (CAV) technologies, exploiting their enhanced perception, communication, and cooperative control capabilities has become an important research topic. To characterize the acceleration, deceleration, queueing, and discharge disturbances induced by signal phase transitions, this study proposes a Signal-Constrained Optimal Velocity Model (SC-OVM). By introducing a continuous signal decision function, the proposed model dynamically couples traffic signal states with vehicle-following behavior, including preceding-vehicle following and stop-line tracking within a unified optimal-velocity framework. Furthermore, linear stability analysis, boundary critical condition analysis, and disturbance probability modeling are integrated to reveal the instability mechanism caused by abrupt signal phase transitions, with extensions to stochastic prediction errors and adaptive Signal Phase and Timing (SPaT) inputs. Numerical simulations show that SC-OVM-controlled CAVs can smooth vehicle trajectories, reduce average delay, improve end-of-green passing performance, and achieve a balanced performance in efficiency, stability, and safety compared with the Full Velocity Difference Model (FVDM), Virtual Leading Vehicle model (VLV), and Intelligent Driver Model (IDM). The findings provide theoretical support and practical insights for stability modeling and cooperative control of mixed-traffic flow at signalized intersections. Full article

The growing deployment of right-turn warning zones (RTWZs) at urban intersections in China aims to enhance the operational safety of urban traffic systems, yet encroachment upon these zones by pedestrians and non-motorized vehicle (NMV) users remains a practical concern. This study combined a field observation at two intersections in Hefei, China, to examine these vulnerable road users’ actual unsafe RTWZ encroachment behaviors, with an extended theory of planned behavior (TPB) questionnaire survey to explore the cognitive mechanisms underlying intentions of such encroachment. Observational results showed that NMV riders encroached on RTWZs significantly more frequently than pedestrians, and such encroachments occurred more often during morning peak hours. The questionnaire survey on 402 respondents revealed that attitude, perceived behavioral control (PBC), and past behavior showed the strongest positive effect on encroachment intention, both directly and indirectly through PBC. In contrast, perceived risk and safety knowledge negatively predicted intention indirectly, while also showing significant indirect effects on intention impacting attitude. Subjective norm, sociodemographic characteristics, and travel patterns were not significant predictors. These findings not only provide a deeper understanding of the real-world effectiveness of RTWZs, but also offer an evidence-based basis for developing countermeasures to improve operational safety of urban slow traffic systems. Full article

Managing vehicle speeds in rural-to-urban transition zones—where two-lane roads traverse small population centres—remains a critical challenge for road safety engineering. While various traffic calming measures (TCMs) are employed to enforce speed limits, empirical evidence comparing their relative effectiveness in sequential applications is often limited. This study presents a field analysis conducted on the BI-2604 road in Gordexola (Spain). Using radar counters at 24 sequential control points, a dataset of 23,021 valid vehicle passages was analysed to evaluate seven distinct calming configurations. The results indicate that, within this corridor, purely visual countermeasures were associated with high non-compliance: standard crosswalks (paint only) recorded a non-compliance rate of 92.9%, while the Speed Monitoring Display (SMD) registered a 72.1% violation rate. Regarding physical measures, a safety–compliance paradox was identified. Speed humps located in 50 km/h zones achieved the highest statistical compliance (41.7% violation). However, raised crosswalks in 30 km/h zones, despite registering higher non-compliance (63.6%), achieved the lowest mean speeds (approximately 34 km/h; V85 ≈ 45 km/h), a range that the previous literature associates with lower pedestrian injury risk. The findings suggest that, within the investigated corridor, physical vertical deflection was associated with lower speeds than the analysed visual/signalling measures, although it remains an imperfect solution that generates significant negative externalities (noise, emissions, and discomfort) and fails to guarantee strict legal adherence to 30 km/h limits. These limitations highlight the urgent need for alternative solutions, setting the stage for future research on optimised perceptual countermeasures. Full article

Road traffic accident consequences are multidimensional, involving fatalities, injuries, and property loss. Existing studies have mainly focused on single outcomes, limiting the understanding of heterogeneous mechanisms across different consequence dimensions. Based on road accident data from Yancheng City in 2022, this study develops an integrated framework combining multi-output prediction, NSGA-II multi-objective optimization, SHAP-based interpretation, LOWESS nonlinear analysis, and DirectLiNGAM causal inference. The results show that the optimized Voting ensemble achieved competitive and comparatively balanced performance across the three accident-consequence dimensions. Road category, traffic control type, junction/road-segment type, and crash-cause category are identified as key influencing factors, with differentiated effects across accident consequences. POI variables exhibit nonlinear and threshold effects, while causal analysis further indicates that road infrastructure and traffic control conditions are positioned upstream in the formation mechanism of accident consequences. This study provides evidence for multidimensional accident-consequence category prediction and differentiated traffic safety management, rather than traditional continuous regression-based modeling. Full article

Pedestrian safety represents a critical priority for the development of sustainable urban mobility systems. This study proposes an innovative methodological framework integrating supervised and unsupervised learning techniques with econometric modeling to identify and interpret risk scenarios. Using the Italian national dataset from 2010 to 2023, an XGBoost model has been initially trained and tested. Then, SHapley Additive exPlanations (SHAPs) have been applied to highlight contributing factors. Using the resulting SHAP values, a K-Means clustering algorithm was finally employed to segment crashes into homogeneous clusters. For each cluster, a Generalized Linear Mixed Model incorporating geographic random intercepts and temporal random slopes was calibrated. Through this hybrid-stratified approach, three risk scenarios have been identified, primarily driven by demographic vulnerability. For elderly pedestrians, the involvement of heavy vehicles nearly doubles the odds of a fatal outcome. Crash dynamics varied significantly: heavy vehicles and speeding nearly double the fatality risk for elderly pedestrians; nighttime represents a severe hazard for adults (OR = 3.87) and youths (OR = 7.99), with the latter also highly penalized by unsafe road behaviors (OR = 3.12). From a spatio-temporal perspective, random effects revealed that the Islands (Sicily and Sardinia) are the most critical macro-areas (+55.2% baseline risk for adults) and the North-West the safest. Furthermore, the COVID-19 pandemic mitigated fatal risk for young pedestrians nationwide, had a neutral impact on the elderly, and for adults was protective in Southern regions but corresponded to higher odds of mortality in the North, reflecting altered traffic dynamics. Full article

Developing countries, including Indonesia, are characterized by Heterogeneous Disordered Traffic (HDT), making traditional technology adoption models for autonomous vehicles (AVs) unsuitable. To bridge this gap, this study surveyed 204 urban early adopters using a rigorous psycho-statistical framework. Utilizing t-tests, ANOVA, and bootstrapped ordinal regression, we validated three behavioral pillars: safety-first prioritization, educated critical adoption, and a direct mode shift to shared AVs. Subsequent market segmentation via a CHAID decision tree yielded empirical AV market penetration rates (MPR) of 20%, 40%, and 70%. MPRs were evaluated in a calibrated PTV VISSIM microsimulation of the A.P. Pettarani Arterial Road in Makassar, Indonesia. A tree-based ensemble framework (XGBoost, CatBoost, and Random Forest) with SHAP diagnostics and a Double Machine Learning causal protocol assessed infrastructure trade-offs. With an R² of 0.99 and MAPE of 9.9%, XGBoost strongly predicted intersection delays and road section speeds. Causal analysis shows that putting dedicated lanes in place too soon, when the penetration rate is low (≤20% MPR), makes traffic worse. At an intermediate 40% MPR, dedicated lanes reduce intersection bottlenecks. Mixed non-dedicated traffic wins at 70% widespread saturation. The AV fleet acts as macroscopic pacemakers, smoothing traffic shockwaves and reducing intra-lane oversaturation to maximize global network efficiency without spatial segregation. Full article

Novice drivers often exhibit poor lane-changing competence due to ineffective risk identification and control instability. Existing driver training primarily focuses on mechanical skills, lacking systematic psychological interventions. To address this gap, this study constructs a four-stage intervention program (attention, retention, reproduction, and motivation) utilizing Bandura’s observational learning theory. A within-subject pre–post design driving simulator experiment was conducted with 46 drivers (16 experienced and 30 novices). Multimodal data—including eye movements, physiological responses, and vehicle kinematics—were collected and analyzed. The results demonstrate that the proposed intervention effectively bridged the initial significant capability gap between the two groups. Post-intervention, novice drivers exhibited significantly optimized visual search strategies, reduced mental workload, and enhanced vehicle control stability during lane-changing maneuvers. Ultimately, no statistical differences remained between novices and experienced drivers across all core indicators, fully validating the research hypotheses. These findings offer robust theoretical support and a practical paradigm for reforming novice driver training, contributing to reduced lane-changing accidents and enhanced active road safety. Full article

This article presents a geospatial model for identifying and assessing the risk of hazardous locations in the road network, developed to predict traffic safety hazards in areas with complex infrastructure where traditional methods, such as the Highway Safety Manual, are insufficient. The objective of the study was to develop a model that classifies road segments into five risk categories based on environmental and infrastructural characteristics, without using accident or traffic volume data. The model accounts for speed limits, road geometry, and the proximity of facilities that generate pedestrian traffic (schools, preschools, stores) and infrastructure elements (crosswalks, intersections). A hybrid approach was used, combining proprietary methods for determining distances from objects: vector-based (geodetic distance), route-based (road graph), and geometric (classification of a road segment’s shape), using QGIS, OpenStreetMap, and custom Python scripts. The results enabled assigning a risk category to each road segment, and validation was performed by comparing them with the locations of actual accidents resulting in serious injuries or fatalities. The developed model for identifying hazardous locations is a scalable tool that supports sensor-network-based area-based speed control systems, infrastructure planning, and safety management in regions with diverse road networks. Full article

Driver behavior is a critical factor in road safety, contributing to the majority of traffic crashes. The i-DREAMS project introduced the concept of a Safety Tolerance Zone (STZ) to enhance driving safety through real-time and post-trip interventions. This study develops and evaluates three hybrid machine learning models—(i) Deep Neural Network–Random Forest (DNN-RF), (ii) Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM), and (iii) Recurrent Neural Network–AdaBoost (RNN-AdaBoost)—to classify risky driving behavior into three safety levels using naturalistic driving data from Belgium and the UK. The dataset includes 69 drivers, 15,389 trips, and 265,512 min of driving data. Among the models tested, the DNN-RF model demonstrated the highest accuracy, reaching 98% in Belgium and 97% in the United Kingdom, outperforming other approaches. Feature importance analysis identified harsh acceleration and braking as the most critical factors in Belgium, while total trip distance and harsh acceleration were predominant in the UK. To enhance model transparency, we applied the Local Interpretable Model-agnostic Explanations (LIME) algorithm, providing valuable insights into model predictions. The findings support the potential of hybrid deep learning models in improving road safety by accurately detecting risky driving behaviors. These insights can inform targeted interventions and driver assistance technologies to mitigate crash risks and promote safer driving practices. Full article

Reliable traffic scenario initialization is essential for autonomous driving simulation, safety evaluation, and scenario completion. Most learning-based initializers rely on high-definition map priors to constrain agent placement and attribute generation. However, in practical deployment, map priors may be unavailable, incomplete, outdated, or inconsistent with temporary road changes. This study investigates traffic scenario initialization under strict map-prior removal, where both external HD-map inputs and agent-internal road-related cues are masked to reduce implicit structural leakage. We propose an interaction-only initialization framework, InterInit, which retains a fixed decoding-slot space and conditions initialization on observed agent states and multi-agent interactions. Experiments on the Waymo Open Motion Dataset first provide a vertical prior-removal analysis from full-map-prior initialization to weak-map initialization and then to strict map-prior removal. The results reveal attribute-asymmetric degradation: position and heading remain relatively stable, whereas speed becomes the dominant failure dimension. Further diagnostic analysis shows that the speed degradation is mainly caused by speed-magnitude collapse, characterized by nearly zero predicted variance rather than a large mean-speed bias. Based on this diagnosis, InterInit-SpeedFix is introduced as a localized repair strategy that models speed probabilistically in log-speed space without changing the overall architecture or inference pipeline. It reduces global Speed MMD from 0.2461 to 0.1210, corresponding to a 50.9% improvement, while maintaining stable position and heading performance. Density-stratified Speed MMD and absolute speed-magnitude error statistics further verify that the repair is consistent across different scene-density regimes and improves both typical and high-error cases. These results provide an application-oriented diagnosis-and-repair workflow for traffic scenario initialization when map priors are unavailable, and clarify the practical boundary of interaction-only initialization under strict map-prior removal. Full article

Vehicular ad hoc networks (VANETs), as a key communication component of the Internet of Vehicles (IoV), enable vehicles and roadside infrastructure to exchange information efficiently, thereby supporting road safety and traffic management. However, because these communications take place over open wireless channels, VANETs are exposed to message forgery, replay, identity disclosure, and unauthorised access by revoked vehicles. To address these issues, this paper proposes EPAF, an efficient privacy-preserving batch authentication scheme with revocation support for fog-enabled VANETs. EPAF uses roadside fog nodes to distribute update keys and report information related to misbehaving vehicles, thereby reducing reliance on remote centralised processing. Rather than assuming ideal tamper-proof devices that store system-wide secrets, EPAF requires protected storage only for vehicle-local certificates, limiting the impact of compromising an individual vehicle device. The scheme employs batch verification to authenticate multiple messages from different vehicles in a single procedure, reducing verification overhead in message-intensive traffic conditions. It further introduces an update-key mechanism through which legitimate vehicles obtain current authentication keys, whereas revoked vehicles are prevented from generating valid authentication messages in subsequent revocation periods. Under the honest-authority model, the security analysis establishes the EUF-CMA security of an authentication packet in the random-oracle model and separately addresses conditional identity privacy, traceability, and unlinkability across different pseudonym periods. Performance evaluation examines the trade-off among authentication efficiency, communication overhead, and revocation performance, showing that EPAF is a practical solution for fog-enabled vehicular communication. Full article

The incorporation of bio-derived modifiers in bitumen binders presents a practical pathway toward sustainable, carbon-sequestering road pavement infrastructure. This study evaluates commercially produced ECHO2 softwood biochar as a modifier for Australian viscosity-graded C170 bitumen, combining microstructural, thermal, physical, and rheological characterization to assess its suitability as a high-temperature reinforcing modifier. In this study, biochar was incorporated at 3%, 6%, 9%, and 12% by weight, utilizing particles smaller than 75 µm to maximize interfacial interaction. Characterization via SEM-EDS, XRD, and TGA revealed a highly stable, carbon-rich, amorphous material with a rough, porous morphology, favourable for physical interlocking with the bitumen matrix. Physical and rheological investigations demonstrated that ECHO2 biochar measurably enhances binder stiffness and high-temperature deformation resistance. Compared with the control, 12% biochar modification reduced penetration by approximately 27% and increased the softening point by approximately 10%, indicating a reduction in temperature susceptibility. Dynamic shear rheometer (DSR) temperature sweeps highlighted substantial increases in the complex shear modulus (G*) and rutting factor (G*/sinδ) without altering the phase angle (δ), confirming the modifier acts as a rigid, particulate reinforcing agent rather than an elastomer. Multiple stress creep recovery (MSCR) testing supported these findings; non-recoverable creep compliance (J_nr) decreased progressively. Critically, under the AASHTO M 332 specification, while the neat bitumen binder barely met the standard traffic (S) criteria, the progressive reduction in J_nr (particularly at 12%) delivered a substantially higher factor of safety against rutting within the standard traffic designation. Finally, ECHO2 biochar demonstrates strong potential as a sustainable modifier that restricts viscous flow through particulate stiffening, enhancing high-temperature rutting resistance at elevated temperatures. Full article

Vehicle-to-everything (V2X)-enabled cooperative adaptive cruise control (CACC) is a key technology for improving both traffic efficiency and driving safety in vehicle-platooning scenarios. However, real-world platoons consist of heterogeneous vehicles with different actuation, computation, and mechanical delays, and communication latency also varies over time. Therefore, conventional approaches based on homogeneous vehicles and fixed-delay assumptions may fail to guarantee physical rear-end collision avoidance under severe driving conditions. This paper proposes Safe PF-CACC, a predictor-feedback-based CACC framework that integrates a V2X-aware safe inter-vehicle distance (Safe IV Distance) model with adaptive time-headway scheduling for heterogeneous vehicle platoons. The proposed Safe IV Distance is computed by considering communication latency, vehicle dynamic delays, and friction-dependent braking limits. It consists of three components: a minimum margin (MM) for low-speed and standstill conditions, a response-lag loss (RLL) induced by communication and vehicle dynamic delays, and a braking-performance limit (BPL) caused by road-friction-dependent braking capability. The resulting Safe IV Distance is converted into a dynamic effective time headway and incorporated into the predictor-feedback (PF) controller, while a filtering process is applied to suppress abrupt gain-scheduling variations. To evaluate the proposed framework, three representative CACC scenarios were considered: heterogeneous passenger-vehicle platooning, emergency vehicle platooning, and truck platooning. The simulation results show that overly short spacings without real-time delay awareness can cause collisions in high-speed and emergency driving scenarios, whereas overly conservative spacings improve safety at the cost of increased road occupancy. In the heterogeneous passenger-vehicle scenario, the proposed Safe PF-CACC reduces the maximum jerk and mean spacing by 20.6% and 49.4%, respectively, compared with the existing conservative method. In the emergency vehicle scenario, it achieved collision-free operation while reducing the maximum jerk and mean spacing by 18.6% and 53.2%, respectively. In the truck-platooning scenario, stable jerk and acceleration responses are maintained while the mean spacing is reduced by 59.6%. These results demonstrate that the proposed framework provides a practical integrated control approach for maintaining both control stability and physical safety in CACC systems under time-varying communication delays and road friction uncertainty. Full article

Road transport fuel consumption is strongly affected by pavement conditions and road infrastructure, whereas conventional normative approaches primarily consider vehicle characteristics and operating conditions while neglecting pavement friction and infrastructure-induced driving cycles. This study develops and validates an integrated physical–mechanistic model for predicting actual fuel consumption on high-category roads by combining vehicle energy-balance equations with pavement diagnostic parameters and infrastructure constraints. Unlike existing mechanistic or empirical approaches, the proposed framework explicitly incorporates pavement friction as a quantitative indicator of both skid resistance and road-related energy losses, enabling the simultaneous assessment of traffic safety and fuel efficiency within a unified engineering model. The methodology was applied to the A-350 Almaty–Taldykorgan highway using telemetry from 150 independent vehicle-route observations, 840 complete corridor transits, approximately 4.8 million CAN-GPS records, and 340 pavement friction measurements. The results indicate that actual fuel consumption exceeded normative values by an average of 9.2%, while a reduction in pavement friction below the regulatory threshold was associated with a substantial increase in fuel consumption, further amplified by pedestrian crossings and urban road sections. Model calibration and independent validation demonstrated that the proposed model achieved strong predictive performance (R² = 0.94; MAE = 1.8%) under the observed operating conditions. This study extends existing fuel consumption modeling by reinterpreting pavement friction as a dual-purpose engineering indicator for both safety assessment and energy-efficiency diagnostics. The proposed methodology provides a scientific basis for corridor-level pavement management and infrastructure-related fuel-efficiency assessment and provides a conceptual foundation for future integration into intelligent transportation systems, subject to broader multi-corridor and seasonal validation. Full article

Prolonged driver inattention significantly increases the risk of traffic accidents, necessitating continuous physiological monitoring for improved road safety and driver wellbeing. This study proposes a Self-Attention-based Hybrid Quantum Neural Network (SAHQNN), a novel framework integrating trainable Parameterized Quantum Circuits (PQCs) with selective self-attention for automated detection of phone call distraction-induced cognitive and emotional driver inattention from multimodal wearable biosignals. Multimodal physiological signals consisting of single-lead Electrocardiogram (ECG, 256 Hz) and Respiration (RSP, 128 Hz) were acquired from $N=20$ participants under Normal and Distracted-Inattention driving conditions using a textile wearable smart shirt. The Distracted-Inattention condition was induced through a hands-free phone call that simultaneously imposed cognitive load, emotional arousal, and secondary task engagement on the driver through active questioning, reflecting the multidimensional nature of driver inattention beyond speech activity alone. Multi-domain features reduced via Random Forest Feature Importance (RFF) were angle-encoded into 10-qubit PQCs with 20 trainable variational $R_Y\left(\theta \right)$ gates optimized via the parameter-shift rule, establishing inter-qubit correlations through Hadamard and Controlled-NOT (CNOT) entanglement layers. Pauli-Z measurement outputs were processed through a selective self-attention layer, producing Attentive Quantum Features (AQF) that were subsequently classified by fully connected layers. The proposed SAHQNN achieves 77.50% accuracy and 70% weighted F-measure under Leave One Subject Out Cross-Validation (LOSOCV), with statistically significant improvements over all standard classical baselines ($p<0.001$, Cohen’s $d>1.5$) and 61% fewer parameters than the strongest classical competitor, demonstrating the feasibility of parameter-efficient trainable hybrid quantum neural networks for subject-independent driver inattention detection. Full article