Search Results (200)

Road traffic accidents are a leading cause of injury and death among adolescents, making road safety education crucial. This study assesses the performance of and users’ opinions on the Route 2 School (R2S) traffic safety education program, designed for secondary school students (13–17 years) in Belgium. The program incorporates gamified e-learning modules containing, among others, podcasts, interactive 360° visuals, and virtual reality (VR), to enhance traffic knowledge, situation awareness, risk detection, and risk management. This study was conducted across several cities and municipalities within Belgium. More than 600 students from school years 3 to 6 completed the platform and of these more than 200 students filled in a comprehensive questionnaire providing detailed feedback on platform usability, preferences, and behavioral risk assessments. The results revealed shortcomings in traffic knowledge and skills, particularly among older students. Gender-based analysis indicated no significant performance differences overall, though females performed better in risk management and males in risk detection. Furthermore, students from cities outperformed those from municipalities. Feedback on the R2S platform indicated high usability and engagement, with VR-based simulations receiving the most positive reception. In addition, it was highlighted that secondary school students are high-risk groups for distraction and red-light violations as cyclists and pedestrians. This study demonstrates the importance of gamified, technology-enhanced road safety education while underscoring the need for module-specific improvements and regional customization. The findings support the broader application of e-learning methodologies for sustainable, behavior-oriented traffic safety education targeting adolescents. Full article

This work focuses on the possibilities of generating synthetic data for machine learning in hazard prediction in area-based speed monitoring systems. The purpose of the research conducted was to develop a methodology for generating realistic synthetic data to support the design of a continuous vehicle speed monitoring system to minimize the risk of traffic accidents caused by speeding. The SUMO traffic simulator was used to model driver behavior in the analyzed area and within a given road network. Data from OpenStreetMap and field measurements from over a dozen speed detectors were integrated. Preliminary tests were carried out to record vehicle speeds. Based on these data, several simulation scenarios were run and compared to real-world observations using average speed, the percentage of speed limit violations, root mean square error (RMSE), and percentage compliance. A new metric, the Combined Speed Accuracy Score (CSAS), has been introduced to assess the consistency of simulation results with real-world data. For this study, a basic hazard prediction model was developed using LoRaWAN sensor network data and environmental contextual variables, including time, weather, location, and accident history. The research results in a method for evaluating and selecting the simulation scenario that best represents reality and drivers’ propensities to exceed speed limits. The results and findings demonstrate that it is possible to produce synthetic data with a level of agreement exceeding 90% with real data. Thus, it was shown that it is possible to generate synthetic data for machine learning in hazard prediction for area-based speed control systems using traffic simulators. Full article

This study developed and validated an integrated theoretical framework combining the Theory of Planned Behavior (TPB) and the Technology Acceptance Model (TAM) to investigate how driving assistance technologies (DATs) influence risky driving behaviors among young urban Chinese drivers. Based on this framework, we proposed and tested several hypotheses regarding the effects of psychological and technological factors on risky driving intentions and behaviors. A survey was conducted with 495 young drivers in Shaoguan, Guangdong Province, examining psychological factors, technology acceptance, and their influence on risky driving behaviors. Structural equation modeling revealed that the integrated TPB-TAM explained 58.3% of the variance in behavioral intentions and 42.6% of the variance in actual risky driving behaviors, significantly outperforming single-theory models. Attitudes toward risky driving (β = 0.287) emerged as the strongest TPB predictor of behavioral intentions, while perceived usefulness (β = −0.172) and perceived ease of use (β = −0.113) of driving assistance technologies negatively influenced risky driving intentions. Multi-group analysis identified significant gender and driving experience differences. Logistic regression analyses demonstrated that model constructs significantly predicted actual traffic violations and accidents. These findings provide theoretical insights into risky driving determinants and practical guidance for developing targeted interventions and effective traffic safety policies for young drivers in urban China. Full article

In Italy, the law on road homicide (Law no. 41/2016) introduced specific provisions for drivers who cause severe injuries or death to a person due to the violation of the Highway Code. The use of alcohol or drugs while driving constitutes an aggravating circumstance of the offence and provides for a tightening of penalties. Our study aims to report on the analysis performed on blood samples collected between January 2018 and December 2024 from drivers convicted of road homicide and who tested positive for alcohol and/or drugs. The majority of the involved subjects were males belonging to the 18–30 and 41–50 age groups. Alcohol, cocaine and cannabinoids were the most detected substances and the most frequent polydrug combination was alcohol and cocaine. We also investigated other influencing factors in road traffic accidents as the day of the week and the time of the day in which fatal road traffic accident occurred, and the time elapsed between the road accident and the collection of biological samples. Our data, in line with the international scenario, strongly support that, in addition to the tightening of penalties, raising awareness plays a key role in preventing alcohol- and drug-related traffic accidents by increasing risk perception and encouraging safer driving behaviors. Full article

Legal requirements for minimum distances between vehicles are often not met for short periods of time, especially when changing lanes on multi-lane roads. These situations are typically non-hazardous, as human drivers anticipate surrounding traffic, allowing for shorter headways and improved traffic flow. Automated vehicles (AVs), however, are typically designed to maintain strict headway limits, potentially reducing traffic efficiency. Therefore, legal questions arise as to whether mandatory gap and headway limits for AVs may be violated during periods of non-compliance. While traffic flow simulation is a common method for analyzing AV impacts, previous studies have typically modeled AV behavior using driver models originally designed to replicate human driving. These models are not well suited for representing clearly defined, structured non-compliant maneuvers, as they cannot simulate intentional, rule-deviating strategies. This paper addresses this gap by introducing a concept for AV non-compliant behavior and implementing it as a module within a pre-existing AV driver model. Simulations were conducted on a three-lane highway with an on-ramp under varying traffic volumes and AV penetration rates. The results showed that, with an AV-penetration rate of more than 25%, road capacity at highway entrances could be increased and travel times reduced by over 20%, provided that AVs were allowed to merge with a legal gap of 0.9 s and a minimum non-compliant gap of 0.6 s lasting up to 3 s. This suggests that performance gains are achievable under adjusted legal requirements. In addition, the proposed framework can serve as a foundation for further development of AV driver models aiming at improving traffic efficiency while maintaining regulatory compliance. Full article

Temporal action localization aims to identify the boundaries of the action of interest in a video. Most existing methods take a two-stage approach: first, identify a set of action proposals; then, based on this set, determine the accurate temporal locations of the action of interest. However, the diversely distributed semantics of a video over time have not been well considered, which could compromise the localization performance, especially for ubiquitous short actions or events (e.g., a fall in healthcare and a traffic violation in surveillance). To address this problem, we propose a novel deep learning architecture, namely an adaptive template-guided self-attention network, to characterize the proposals adaptively with their relevant frames. An input video is segmented into temporal frames, within which the spatio-temporal patterns are formulated by a global–Local Transformer-based encoder. Each frame is associated with a number of proposals of different lengths as their starting frame. Learnable templates for proposals of different lengths are introduced, and each template guides the sampling for proposals with a specific length. It formulates the probabilities for a proposal to form the representation of certain spatio-temporal patterns from its relevant temporal frames. Therefore, the semantics of a proposal can be formulated in an adaptive manner, and a feature map of all proposals can be appropriately characterized. To estimate the IoU of these proposals with ground truth actions, a two-level scheme is introduced. A shortcut connection is also utilized to refine the predictions by using the convolutions of the feature map from coarse to fine. Comprehensive experiments on two benchmark datasets demonstrate the state-of-the-art performance of our proposed method: 32.6% mAP@IoU 0.7 on THUMOS-14 and 9.35% mAP@IoU 0.95 on ActivityNet-1.3. Full article

Many research studies have designed intelligent traffic light scheduling algorithms. Some researchers rely on specialized sensors and hardware to gather real-time traffic data at signalized road intersections. Others benefit from artificial intelligence techniques and/or cloud computing technologies. The technology of vehicular networks has been widely used to gather the traffic characteristics of competing traffic flows at signalized road intersections. Intelligent traffic light controlling systems aim to fairly liberate competing traffic at signalized road intersections and eliminate traffic crises. These algorithms have been initially developed without focusing on the consequences of security threats or attacks. However, the accuracy of gathered traffic data at each road intersection affects its performance. Fake and corrupted packets highly affect the accuracy of the gathered traffic data. Thus, in this work, we aim to investigate the aspects of security and confidentiality of intelligent traffic light systems. The possible attacks on the confidentiality of intelligent traffic light systems are examined. Then, a confidential traffic light control system that protects the privacy of traveling vehicles and drivers is presented. The proposed algorithm mainly prevents unauthorized traceability and linkability attacks that threaten people’s lives and violate their privacy. Finally, the proposed algorithm is evaluated through extensive experiments to verify its correctness and benefits compared to traditional insecure intelligent traffic light systems. Full article

Accurate traffic light status detection and the appropriate response to changes in that status are crucial for autonomous driving systems (ADSs) starting from SAE Level 3 automation. The dilemma zone problem occurs during the amber phase of traffic lights, when the ADS must decide whether to stop or proceed through the intersection. This paper proposes a methodology for developing a runtime monitor that addresses the dilemma zone problem and monitors the autonomous vehicle’s behavior at traffic lights, ensuring that the ADS’s decisions align with the system’s safety requirements. This methodology yields a set of safety requirements formulated in controlled natural language, their formal specification in linear temporal logic (LTL), and the implementation of a corresponding runtime monitor. The monitor is integrated within a safety-oriented software architecture through a modular autonomous driving system pipeline, enabling real-time supervision of the ADS’s decision-making at intersections. The results show that the monitor maintained stable and fast reaction times between 40 ms and 65 ms across varying speeds (up to 13 m/s), remaining well below the 100 ms threshold required for safe autonomous operation. At speeds of 30, 50, and 70 km/h, the system ensured correct behavior with no violations of traffic light regulations. Furthermore, the monitor achieved 100% detection accuracy of the relevant traffic lights within 76 m, with high spatial precision (±0.4 m deviation). While the system performed reliably under typical conditions, it showed limitations in disambiguating adjacent, irrelevant signals at distances below 25 m, indicating opportunities for improvement in dense urban environments. Full article

Ultra-reliable low-latency communication (URLLC) is a cornerstone of beyond 5G and future 6G networks, particularly for mission-critical applications such as the healthcare Internet of Things. In applications such as remote surgery, emergency services, and real-time health monitoring, it is imperative to ensure stringent latency and reliability requirements. However, the energy constraints of wearable and implantable medical devices pose stringent challenges to conventional URLLC methods. This paper proposes an energy-aware URLLC framework that dynamically prioritizes healthcare traffic to optimize transmission energy and reliability. The framework integrates a priority-aware packet scheduler, adaptive transmission control, and edge-enabled reliability management. Extensive Monte Carlo simulations are carried out on various network loads and varying edge computing delays to evaluate performance metrics, like latency, throughput, reliability score, energy consumption, delay violation rate, and Jain’s fairness index. Results illustrate that the suggested technique achieves lower latency, energy consumption, and delay violation rates and higher throughput and reliability scores, sacrificing Jain’s fairness index graciously at peak network overload. This study is a potential research lead for green URLLC in healthcare IoT systems to come. Full article

Inland waterway navigation involves complex traffic conditions with frequent multi-ship encounters. Benefiting from its straightforward structure and robust adaptability, reinforcement learning has found applications in navigation. This article proposes a deep actor–critic collision avoidance model which is based on the weighted summation of intrinsic reward and extrinsic reward, overcoming the sparsity of the reward function in navigation tasks. For the proposed algorithm, the extrinsic reward considers factors of collision risk, economic reward, and penalties for violating collision avoidance rules, while the intrinsic reward explores the novelty of agent states. The optimization of the own ship’s actions is achieved through the utilization of a weighted summation of these two types of rewards, providing valuable guidance for decision-making in a symmetrical interaction framework. To validate the performance of the proposed multi-ship collision avoidance model, simulations of both two-ship encounters and complex multi-ship scenarios involving dynamic and static obstacles are conducted. The following conclusions can be drawn: (1) The proposed model could provide effective decisions for ship navigation in inland waterways, maintaining symmetrical coordination between vessels. (2) The hybrid reward mechanism successfully guides ship behavior in collision avoidance scenarios. Full article

Road traffic accidents pose a significant global public health and economic challenge. In Saudi Arabia, rapid motorization and urbanization have contributed to one of the world’s highest traffic fatality rates. This study evaluates the effectiveness of the Saher traffic enforcement system in the Dammam Metropolitan Area (DMA) by gathering insights from road safety experts through structured questionnaires and interviews. Findings indicate that Saher has improved traffic law compliance and enhanced perceptions of road safety. Key accident causes include driver distractions, speeding, and sudden lane changes, with younger drivers being disproportionately involved. Experts recommend expanding Saher’s capabilities by addressing violations like aggressive driving and increasing coverage of cameras, with responses of 21% and 25%, respectively. They also stress the need for better highway coverage, with a response of 32%. Proposed strategies include integrating the Saher system into urban planning, combining automated enforcement with public education, and enhancing traffic infrastructure, such as signage and signal systems. This study offers actionable insights for policymakers to improve road safety and promote sustainable urban mobility in Saudi Arabia. Full article

Capacity–flow balance constitutes the primary challenge in strategic slot allocation. Both air traffic flow and airport flow are significantly influenced by departure/arrival times of flights. However, due to various uncontrollable factors such as flow control, delay propagation, and weather conditions, the actual departure/arrival times of flights inevitably deviate from their schedules. This reflects the inherent uncertainty in flight slot execution, which directly introduces uncertainty into capacity–flow analysis. In this paper, we develop an uncertainty slot allocation model for the multi-airport system (MAS), which incorporates slot execution deviation as an uncertainty factor with fix capacity restrictions formulated as chance constraints to balance robustness and optimality. To solve the model, we employ an equivalent model transformation approach and develop a scenario generation methodology. We applied our model to the MAS of Beijing–Tianjin for slot allocation. The results show that when the violation probability $\alpha \in [0,0.2]$ , the model achieved fully robust optimization. Even when $\alpha$ increases to 0.4, under all scenario combinations, at the selected fix, compared with the results of the deterministic model and original schedules, the number of peak flow time windows in the expected traffic statistics decreased by 84.6% and 75%, respectively, and the average maximum values of traffic in the maximum traffic statistics decreased by 31.1% and 33.5%, respectively. Furthermore, the incorporation of the chance constraint provides slot coordinators with flexible optimization solutions based on their acceptable risk levels. Full article

This paper provides a study on safety metrics that are used to describe the airspace and identified as important factors influencing and characterizing the safety in airspace considering the traffic of aircraft in different flight phases. Different capabilities, frequently monitored, support the safety warning systems for the airspace, where precursory metrics within the barrier model presented by EUROCONTROL indicate the stages in the evolution of a possible barrier violation, triggering actions by Air Traffic Control and collaborative decision-making when airspace is degrading in terms of safety. The identified metrics have been analyzed, taking into account the overall scenario of aircraft evolution in an air traffic sector related to the intrinsic characteristics of airspace. A case study is presented related to separation minima infringements, and it addresses safety metrics based on the different tactic geometries in en-route ATM. Full article

Motorcycles are a prominent contributor to most fatalities arising from traffic incidents, primarily due to drivers’ failure to adhere to traffic laws. Notably, differences in traffic violation frequency between urban and rural motorcyclists can be ascribed to variations in law enforcement practices and security budget allocations between these areas. This study aims to identify the key determinants influencing the frequency of traffic violations across these distinct geographical regions. The investigation incorporates independent variables such as personal demographics (including gender and age), driving experience, and attitudes toward traffic regulations. The analysis involved the formulation and examination of two separate logit models, each corresponding to urban and non-urban characteristics. The outcomes of a transferability test highlighted distinct disparities between the two models, with the rural model demonstrating a higher number of significant variables. In both models, certain variables consistently influenced the frequency of traffic violations. Lower violation frequencies were associated with factors such as specific age ranges, frequency of driving, and possession of a driver’s license. The insights derived from this study were leveraged to formulate policy recommendations to curb traffic violations among motorcyclists, contributing to enhancing overall traffic safety. Full article

Traffic accidents have become a pressing global public health concern, contributing to millions of deaths and injuries each year. Similar to many countries, the Kingdom of Saudi Arabia is facing significant challenges to overcome the burden of traffic-related injuries and fatalities, prompting the need for effective intervention measures. With the latest advances in sensor fusions, detection, and communication technologies, Automated Traffic Enforcement Systems (ATES) have gained widespread popularity as a solution to improve road safety by ensuring compliance with traffic laws. The objective of this study is to review the effectiveness of ATES in reducing traffic accidents and improving road safety and to identify the challenges and prospects it faced during its implementation. This review uses a detailed overview of different types of ATES deployment, including speed cameras, red-light cameras, and mobile enforcement units, and a comparison between global case studies and local research findings, with special emphasis on the context of Saudi Arabia. This study uses a systematic literature review methodology, using the PRISMA 2020 Protocol, and conducts a scientific literature database search using specific keywords. This study finds that ATES has emerged as an effective tool to ensure traffic compliance and improve overall traffic safety and that various ATES devices have been profoundly effective in reducing traffic crashes. This review concludes that ATES can be an effective solution to improve road safety, but ongoing evaluations and adjustments are necessary to address public perceptions and ensure equitable enforcement. Full article