Search Results (991)

Timely and accurate traffic information is crucial for maintaining safety and efficiency on motorway networks. This research examines time delays in traffic information transmission through intelligent transport systems (ITSs) and cooperative intelligent transport systems (C-ITSs) on the Slovenian motorway network. The aim of the research is to assess the effectiveness of existing notification systems and the impact of time delays on the timely informing of drivers in the event of an accident in a tunnel. Using real-world data from Regional Traffic Center (RCC) in Vransko, manual and automated activations of traffic portals and different update frequencies of the Promet+ mobile application were analyzed during peak hours. Results show that automated activation reduces delays from 34 to 25 s at portals and from 27 to 18 s in the Promet+ app. Continuous updates in the app provided the highest driver coverage, leaving only 15 uninformed drivers in the morning peak and 8 in the afternoon, whereas 60 s update intervals left up to 71 drivers uninformed. These findings highlight the effectiveness of automation and continuous updates in minimizing delays and improving driver awareness. The research contributes by quantifying latency in ITSs and C-ITSs and demonstrating that their combined use offers the most reliable information delivery. Future improvements should focus on hybrid integration of ITS and C-ITS, dynamic update intervals, and infrastructure upgrades to ensure consistent real-time communication, shorter response times, and enhanced motorway safety. Full article

Bridges play an increasingly indispensable role in endorsing the economic and social development of societies by linking highways and facilitating the mobility of people and goods. Concurrently, they are susceptible to high traffic volumes and an intricate service environment over their lifespans, resulting in undergoing a progressive deterioration process. Hence, efficient measures of maintenance, repair, and rehabilitation planning are critical to boost the performance condition, safety, and structural integrity of bridges while evading less costly interventions. To this end, this research paper furnishes a mixed review method, comprising systematic literature and scientometric reviews, for the meticulous examination and analysis of the existing research work in relation with maintenance fund allocation models of bridges (BriMai_all). With that in mind, Scopus and Web of Science databases are harnessed collectively to retrieve peer-reviewed journal articles on the subject, culminating in 380 indexed journal articles over the study period (1990–2025). In this respect, VOSviewer and Bibliometrix R package are utilized to create a visualization network of the literature database, covering keyword co-occurrence analysis, country co-authorship analysis, institution co-authorship analysis, journal co-citation analysis, journal co-citation, core journal analysis, and temporal trends. Subsequently, a rigorous systematic literature review is rendered to synthesize the adopted tools and prominent trends of the relevant state of the art. Particularly, the conducted multi-dimensional review examines the six dominant methodical paradigms of bridge maintenance management: (1) multi-criteria decision making, (2) life cycle assessment, (3) digital twins, (4) inspection planning, (5) artificial intelligence, and (6) optimization. It can be argued that this research paper could assist asset managers with a practical guide and a protocol to plan maintenance expenditures and implement sustainable practices for bridges under deterioration. Full article

With the increasing demand for intelligent mobility assistance among the visually impaired, machine guide dogs based on computer vision have emerged as an effective alternative to traditional guide dogs, owing to their flexible deployment and scalability. To enhance their visual perception capabilities in complex urban environments, this paper proposes an improved YOLOv8-based detection algorithm, termed TFP-YOLO, designed to recognize traffic signs such as traffic lights and crosswalks, as well as small obstacle objects including pedestrians and bicycles, thereby improving the target detection performance of machine guide dogs in complex road scenarios. The proposed algorithm incorporates a Triplet Attention mechanism into the backbone network to strengthen the perception of key regions, and integrates a Triple Feature Encoding (TFE) module to achieve collaborative extraction of both local and global features. Additionally, a P2 detection head is introduced to improve the accuracy of small object detection, particularly for traffic lights. Furthermore, the WIoU loss function is adopted to enhance training stability and the model’s generalization capability. Experimental results demonstrate that the proposed algorithm achieves a detection accuracy of 93.9% and a precision of 90.2%, while reducing the number of parameters by 17.2%. These improvements significantly enhance the perception performance of machine guide dogs in identifying traffic information and obstacles, providing strong technical support for subsequent path planning and embedded deployment, and demonstrating considerable practical application value. Full article

Recently, studies on driver inattention state recognition as an advanced mobility application technology are being actively conducted to prevent traffic accidents caused by driver drowsiness and distraction. The driver inattention state recognition system is a technology that recognizes drowsiness and distraction by using driver behavior, biosignals, and vehicle data characteristics. Existing driver drowsiness detection systems are wearable accessories that have partial occlusion of facial features and light scattering due to changes in internal and external lighting, which results in momentary image resolution degradation, making it difficult to recognize the driver’s condition. In this paper, we propose a transformer based spatial temporal fusion network (STFTransNet) that fuses multi-modality information for improved driver inattention state recognition in images where the driver’s face is partially occluded by wearing accessories and the instantaneous resolution is degraded due to light scattering from changes in lighting in a driving environment. The proposed STFTransNet consists of (i) a mediapipe face mesh-based facial landmark extraction process for facial feature extraction, (ii) an RCN-based two-stream cross-attention process for learning spatial features of driver face and body action images, (iii) a TCN-based temporal feature extraction process for learning temporal features of extracted features, and (iv) an ensemble of spatial and temporal features and a classification process to recognize the final driver state. As a result of the experiment, the proposed STFTransNet achieved an accuracy of 4.56% better than the existing VBFLLFA model in the NTHU-DDD public DB, 3.48% better than the existing InceptionV3 + HRNN model in the StateFarm public DB, and 3.78% better than the existing VBFLLFA model in the YawDD public DB. The proposed STFTransNet is designed as a two-stream network that can input the driver’s face and action images and solves the degradation in driver inattention state recognition performance due to partial facial feature occlusion and light blur through spatial feature and temporal feature fusion. Full article

Ensuring traffic safety within urban public transport systems is essential for achieving sustainable urban development, particularly in densely populated metropolitan areas. This study investigates the integration of artificial intelligence (AI) technologies to enhance safety performance in closed public transport environments, with a focus on the city of Belgrade as a representative case. The research aims to evaluate how AI-enabled systems can contribute to the early detection and reduction of traffic incidents, thereby supporting broader goals of sustainable mobility, infrastructure resilience, and urban livability. A hybrid methodological framework was developed, combining computer vision, supervised machine learning, and time series analytics to construct a real-time risk detection platform. The system leverages multi-source data—including video surveillance, onboard vehicle sensors, and historical accident logs—to identify and predict high-risk behaviors such as harsh braking, speeding, and route adherences across various public transport modes (buses, trams, trolleybuses). The AI models were empirically assessed in partnership with the Public Transport Company of Belgrade (JKP GSP Beograd), revealing that the most accurate models improved incident detection speed by over 20% and offered enhanced spatial identification of network-level safety vulnerabilities. Additionally, routes with optimized AI-driven driving behavior demonstrated fuel savings of up to 12% and a potential reduction in emissions by approximately 8%, suggesting promising environmental co-benefits. The study’s findings align with multiple United Nations Sustainable Development Goals, particularly SDG 11 (Sustainable Cities and Communities) and SDG 9 (Industry, Innovation, and Infrastructure). Moreover, the research addresses ethical, legal, and governance implications surrounding the use of AI in public infrastructure, emphasizing the importance of privacy, transparency, and inclusivity. The paper concludes with strategic policy recommendations for cities seeking to deploy intelligent safety solutions as part of their digital and green transitions in urban mobility planning. Full article

Opportunistic networks, as an emerging ad hoc networking technology, the sparse distribution of nodes poses significant challenges to data transmission. Additionally, unlike static nodes in traditional ad hoc networks that can replenish energy on demand, the inherent mobility of nodes further complicates energy management. Thus, selecting an energy-efficient neighbor discovery algorithm is critical. Passive listening conserves energy by continuously monitoring channel activity, but it fails to detect inactive neighboring nodes. Conversely, active probing discovers neighbors by broadcasting probe packets, which increases energy consumption and may lead to network congestion due to excessive probe traffic. As the primary communication nodes in the maritime environment, vessels exhibit high mobility, and networks in oceanic regions often operate as opportunistic networks. To address the challenge of limited energy in maritime opportunistic networks, this paper proposes a hybrid neighbor discovery method that combines both passive and active discovery mechanisms. The method optimizes passive listening duration and employs Q-learning for adaptive power control. Furthermore, a more suitable wireless communication model has been adopted. Simulation results demonstrate its effectiveness in enhancing neighbor discovery performance. Notably, the proposed scheme improves network throughput while achieving up to 29% energy savings at most during neighbor discovery. Full article

Traffic congestion is a primary obstacle to sustainable mobility, leading to increased fuel consumption, harmful emissions, and significant economic losses. Effective and timely congestion detection is therefore a critical enabler for proactive traffic management strategies that can mitigate these negative impacts. This study contributes to this goal by conducting a rigorous comparative analysis of two key detection paradigms: a modern, vehicle-centric approach using a Cooperative Intelligent Transportation Systems (C-ITS) service, and a traditional, infrastructure-based method relying on the fundamental diagram (FD). Using a comprehensive simulation campaign on a bottleneck scenario, we evaluate the performance of both methods under various conditions. The results demonstrate that while the FD-based method can offer faster detection under optimal sensor placement for severe events, the C-ITS approach provides fundamentally greater spatial flexibility and reliability across a wider range of congestion severities. Our techno-economic analysis further reveals that the paradigms rely on distinct investment models, with C-ITS offering superior scalability and a promising path toward network-wide coverage. This highlights the complementary nature of the two approaches and underscores the potential of C-ITS as a key technology to support dynamic, efficient, and sustainable transportation networks. Full article

Connected Autonomous Vehicles (CAVs) are expected to reshape transportation systems, yet their role in enhancing network robustness remains underexplored. This research intends to fill this gap by conducting a systematic review based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses protocol (PRISMA) to analyze 21 peer-reviewed publications identified from Scopus, Web of Science, and ScienceDirect. Articles were classified into five thematic areas: (1) system robustness, (2) infrastructure adaptation, (3) traffic flow and behavior, (4) security and communication, and (5) environmental impact. The results show that CAVs have the potential to improve robustness in transportation networks, thus helping the efficiency of transportation networks, reducing cyber vulnerability, and mitigating environmental impact. However, despite several advantages, CAVs also present challenges, including new infrastructure or updates to cybersecurity standards. This review contributes to the literature by consolidating current approaches, highlighting knowledge gaps, and offering methodological insights to guide research and policy development toward resilient, sustainable, and connected mobility systems. Full article

The study investigates the disconnect between formal urban planning standards and experiential walkability outcomes in Viranşehir, a planned neighborhood in Mersin, Türkiye. Although the area complies with national regulations on the provision of public services, it exhibits systemic limitations, including car-oriented street layouts, fragmented pedestrian networks, and underutilized public spaces. Employing a mixed-methods case study, the research integrates archival sources (aerial imagery, zoning plans, satellite data) with field observations to assess pedestrian environments. A light coding of sidewalk continuity, crossings, and edge conditions indicates that many streets are bounded by extensive inactive walls, protected crossings are absent along critical routes such as the school–park axis, and sidewalks are frequently narrow, obstructed, or discontinuous. These built-form features undermine safety, comfort, and social interaction despite formal regulatory compliance. The findings demonstrate how grid-pattern street systems prioritize vehicular mobility, while gated developments restrict permeability and diminish everyday encounters. In response, the study proposes a hierarchy of interventions: immediate measures such as school streets, protected crossings, and traffic calming, followed by medium- to long-term strategies including shaded seating, sidewalk widening, and participatory design guidelines. By linking statutory standards with lived experience, the paper conceptualizes walkability not only as a technical planning requirement but also as a socio-cultural right, offering transferable insights for the creation of more inclusive urban environments. Full article

Rapid urban growth in Middle Eastern cities has intensified congestion-related challenges, yet traffic data-based decision making remains limited. This study leverages crowd-sourced travel time data from the Google Maps API to evaluate temporal and spatial patterns of congestion across multiple strategic routes in Jeddah, Saudi Arabia, a coastal metropolis with a complex road network characterized by narrow, high-traffic corridors and limited public transit. A real-time Congestion Index quantifies traffic flow, incorporating free-flow speed benchmarking, dynamic profiling, and temporal classification to pinpoint congestion hotspots. The analysis identifies consistent peak congestion windows and route-specific delays that are critical for travel behavior modeling. In addition to congestion monitoring, the framework contributes to urban sustainability by supporting reductions in traffic-related emissions, enhancing mobility equity, and improving economic efficiency through data-driven transport management. To our knowledge, this is the first study to systematically use the validated, real-time Google Maps API to quantify route-specific congestion in a Middle Eastern urban context. The approach provides a scalable and replicable framework for evaluating urban mobility in other data-sparse cities, especially in contexts where traditional traffic sensors or GPS tracking are unavailable. The findings support evidence-based transport policy and demonstrate the utility of publicly accessible traffic data for smart city integration, real-time traffic monitoring, and assisting transport authorities in enhancing urban mobility. Full article

Many algorithms related to vehicular applications, such as enhanced perception of the environment, benefit from frequent updates and the use of data from multiple vehicles. Federated learning is a promising method to improve the accuracy of algorithms in the context of vehicular networks. However, limited communication bandwidth, varying wireless channel quality, and potential latency requirements may impact the number of vehicles selected for training per communication round and their assigned radio resources. In this work, we characterize the vehicles participating in federated learning based on their importance to the learning process and their use of wireless resources. We then address the joint vehicle selection and resource allocation problem, considering multi-cell networks with multi-user multiple-input multiple-output (MU-MIMO)-capable base stations and vehicles. We propose a “vehicle-beam-iterative” algorithm to approximate the solution to the resulting optimization problem. We then evaluate its performance through extensive simulations, using realistic road and mobility models, for the task of object classification of European traffic signs. Our results indicate that MU-MIMO improves the convergence time of the global model. Moreover, the application-specific accuracy targets are reached faster in scenarios where the vehicles have the same training data set sizes than in scenarios where the data set sizes differ. Full article

Next-point-of-interest (POI) recommendation aims to model user preferences based on historical information to predict future mobility behavior, which has significant application value in fields such as urban planning, traffic management, and optimizing business decisions. However, existing methods often overlook the differences in location, time, and category information features, fail to fully utilize information from various modalities, and lack effective solutions for addressing users’ incidental behavior. Additionally, existing methods are somewhat lacking in capturing users’ personalized preferences. To address these issues, we propose a new method called Multi-Branch Spectral Network with Contrastive Learning (MBSCL-Net) for next-POI recommendation. We use a multihead attention mechanism to separately capture the distinct features of location, time, and category information, and then fuse the captured features to effectively integrate cross-modal features, avoid feature confusion, and achieve effective modeling of multi-modal information. We propose converting the time-domain information of user check-ins into frequency-domain information through Fourier transformation, directly enhancing the low-frequency signals of users’ periodic behavior and suppressing occasional high-frequency noise, thereby greatly alleviating noise interference caused by the introduction of too much information. Additionally, we introduced contrastive learning loss to distinguish user behavior patterns and better model personalized preferences. Extensive experiments on two real-world datasets demonstrate that MBSCL-Net outperforms state-of-the-art (SOTA) methods. Full article

Combining public transportation (PT) with Bike-Sharing Systems (BSSs) offers a pathway toward the sustainable development of urban mobility. These systems can reduce fuel consumption, air pollution, and street congestion, especially during peak hours. Moreover, PT and BSS are frequently used by individuals without access to private vehicles, including low-income groups and students. Whereas increasing PT network infrastructure is constrained by issues such as high capital costs and limited street space (which inhibits mass transit options like BRT or trams), BSS can be used as an adaptable and affordable solution to fill these gaps. In particular, BSS can facilitate the “first-mile–last-mile” legs of PT journeys. However, many transit agencies still rely on traditional joint service planning and overlook BSS as a critical mode in integrated travel chains. This paper proposes that PT and BSS be considered as a unified network and introduces a framework to assess whether access to this integrated system is equitably distributed across urban areas. The framework estimates demand for travel using public mobility options and supply at the level of Traffic Analysis Zones (TAZs), treating PT and BSS as complementary modes. Spatial accessibility analysis is employed to examine connectivity using factors that affect access to both PT and BSS. The proposed approach is tested by taking Tehran as the focus of the case analysis. The results identify the most accessible areas and highlight those that require improved PT-BSS integration. These findings provide policy-relevant suggestions to promote equity and efficiency in urban transport planning. The outcomes reveal that central TAZs in Tehran receive the highest level of PT-BSS integration, while the western and southern TAZs are in urgent need of adjustment to ensure better distribution of integrated public transportation and bike-sharing services. Full article

Urban growth and rising vehicle usage have intensified congestion, accidents, and environmental impact, exposing the limitations of traditional traffic management systems. This study introduces a dual-incident simulation framework to investigate the potential of Vehicle-to-Everything (V2X) technologies in enhancing urban mobility. Using the Eclipse MOSAIC platform integrated with SUMO, a realistic network in Iași, Romania, was modeled under single- and dual-incident scenarios with three V2X penetration levels: 0%, 50%, and 100%. Unlike prior works that focus on single-incident cases or assume full penetration, our approach evaluates cascading disruptions under partial adoption, providing a more realistic transition path for mid-sized European cities. Key performance indicators, i.e., average speed, vehicle density, time loss, and waiting time, were calculated using mathematically defined formulas and validated across multiple simulation runs. Results demonstrate that full V2X deployment reduces average time loss by 18% and peak density by more than 70% compared to baseline conditions, while partial adoption delivers measurable yet limited benefits. The dual-incident scenario shows that V2X-enabled rerouting significantly mitigates cascading congestion effects. These contributions advance the state of the art by bridging microscopic vehicle dynamics with network-level communication modeling, offering quantitative insights for phased V2X implementation and the design of resilient, sustainable intelligent transportation systems. Full article

To improve the traffic efficiency of connected and automated vehicles (CAVs) in on-ramp merging areas, this study proposes a novel region-level multi-agent reinforcement learning framework, Regionally Coordinated Nash-Advantage Decomposition Deep Q-Network with Conflict-Aware Q Fusion (RC-NashAD-DQN). Unlike existing vehicle-level control methods, which suffer from high computational overhead and poor scalability, our approach abstracts on-ramp and main road areas as region-level control agents, achieving coordinated yet independent decision-making while maintaining control precision and merging efficiency comparable to fine-grained vehicle-level approaches. Each agent adopts a value–advantage decomposition architecture to enhance policy stability and distinguish action values, while sharing state–action information to improve inter-agent awareness. A Nash equilibrium solver is applied to derive joint strategies, and a conflict-aware Q-fusion mechanism is introduced as a regularization term rather than a direct action-selection tool, enabling the system to resolve local conflicts—particularly at region boundaries—without compromising global coordination. This design reduces training complexity, accelerates convergence, and improves robustness against communication imperfections. The framework is evaluated using the SUMO simulator at the Taishan Road interchange on the S1 Yongtaiwen Expressway under heterogeneous traffic conditions involving both passenger cars and container trucks, and is compared with baseline models including C-DRL-VSL and MADDPG. Extensive simulations demonstrate that RC-NashAD-DQN significantly improves average traffic speed by 17.07% and reduces average delay by 12.68 s, outperforming all baselines in efficiency metrics while maintaining robust convergence performance. These improvements enhance cooperation and merging efficiency among vehicles, contributing to sustainable urban mobility and the advancement of intelligent transportation systems. Full article