Search Results (185)

When emergency incidents, such as bridge damage, abruptly occur on highways and lead to traffic disruptions, the multidimensionality and complexity of driver behaviors present significant challenges to the design of effective emergency response mechanisms. This study introduces a multi-level collaborative emergency mechanism grounded in driver behavior characteristics, aiming to enhance both traffic safety and emergency response efficiency through hierarchical collaboration and dynamic optimization strategies. By capitalizing on human drivers’ perception and decision-making attributes, a driver behavior classification model is developed to quantitatively assess the risk response capabilities of distinct behavioral patterns (conservative, risk-taking, and conformist) under emergency scenarios. A multi-tiered collaborative framework, comprising an early warning layer, a guidance layer, and an interception layer, is devised to implement tailored emergency strategies. Additionally, a rear-end collision risk propagation model is constructed by integrating the risk field model with probabilistic risk assessment, enabling dynamic adjustments to interception range thresholds for precise and real-time emergency management. The efficacy of this mechanism is substantiated through empirical case studies, which underscore its capacity to substantially reduce the occurrence of secondary accidents and furnish scientific evidence and technical underpinnings for emergency management pertaining to highway bridge damage. 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

This study investigates the underlying causes of pier displacement and cracking in a highway link bridge. The initial geological assessment ruled out slope instability as a contributing factor to pier movement. Subsequently, a comprehensive analysis, integrating in situ soil investigation and finite element modeling, was conducted to evaluate the influence of additional fill loads on the piers. The findings reveal that the additional filled soil loads were the primary driver of pier tilting and lateral displacement, leading to a significant risk of cracking, particularly in the mid-section of the piers. Following the removal of the filled soil, visual inspection of the piers confirmed the development of circumferential cracks on the columns of Pier 7, with the crack distribution closely aligning with the high-risk zones predicted by the finite element analysis. To address the observed damage and residual displacement, a reinforcement strategy combining column strengthening and alignment correction was proposed and validated through load-bearing capacity calculations. This study not only provides a scientific basis for analyzing the causes of accidents and bridge reinforcement but, more importantly, it provides a systematic method for analyzing the impact of additional filled soil loads on bridge piers, offering guidance for accident analysis and risk assessment in similar engineering projects. Full article

Driving under the influence of alcohol (DUI) remains a leading cause of accidents globally, with accident risk rising exponentially with blood alcohol concentration (BAC). This study aims to distinguish between sober and intoxicated drivers using driving behavior analysis and driver monitoring system (DMS), technologies that align with emerging EU regulations. In a driving simulator, twenty-three participants (average age: 32) completed five drives (one practice and two each while sober and intoxicated) on separate days across city, rural, and highway settings. Each 30-minute drive was analyzed using eye-tracking and driving behavior data. We applied significance testing and classification models to assess the data. Our study goes beyond the state of the art by a) combining data from various sensors and b) not only examining the effects of alcohol on driving behavior but also using these data to classify driver impairment. Fusing gaze and driving behavior data improved classification accuracy, with models achieving over 70% accuracy in city and rural conditions and a Long Short-Term Memory (LSTM) network reaching up to 80% on rural roads. Although the detection rate is, of course, still far too low for a productive system, the results nevertheless provide valuable insights for improving DUI detection technologies and enhancing road safety. Full article

Tunnels are commonly found in small and enclosed environments on highways, roads, or city streets. They are constructed to pass through mountains or beneath crowded urban areas. To prevent accidents in these confined environments, lane changes, slow driving, or speeding are prohibited on single- or multi-lane one-way roads. We developed a foreground detection algorithm based on the K-nearest neighbor (KNN) and Gaussian mixture model and 400 collected images. The KNN was used to gather the first 200 image data, which were processed to remove differences and estimate a high-quality background. Once the background was obtained, new images were extracted without the background image to extract the vehicle’s foreground. The background image was processed using Canny edge detection and the Hough transform to calculate road lines. At the same time, the oriented FAST and rotated BRIEF (ORB) algorithm was employed to track vehicles in the foreground image and determine positions and lane deviations. This method enables the calculation of traffic flow and abnormal movements. We accelerated image processing using xfOpenCV on the PYNQ-Z2 and FPGA Xilinx platforms. The developed algorithm does not require pre-labeled training models and can be used during the daytime to automatically collect the required footage. For real-time monitoring, the proposed algorithm increases the computation speed ten times compared with YOLO-v2-tiny. Additionally, it uses less than 1% of YOLO’s storage space. The proposed algorithm operates stably on the PYNQ-Z2 platform with existing surveillance cameras, without additional hardware setup. These advantages make the system more appropriate for smart traffic management than the existing framework. 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

Analyzing risk coupling effects in highway accidents provides guidance for preventive decoupling measures. Existing studies rarely explore the differences in risk coupling between primary accidents (PA) and secondary accidents (SA) from a quantitative perspective. This study proposes a method to measure the risk coupling effects of PA and SA on highways and examine their differences. A domain-pretrained named entity recognition (NER) model, TRBERT-BiLSTM-CRF, is proposed to identify risk factors and risk types based on 431 accident investigation reports published by the emergency management departments in China. The N-K model was applied to calculate the risk coupling values for different coupling scenarios in PA and SA, and the Wilcoxon signed-rank test was performed on them. Finally, the differences between PA and SA were compared, and targeted accident prevention recommendations are provided. The results showed that our proposed NER model achieved the best macro-F1 score in traffic risk entity recognition. Most of the risk coupling values increased with the number of risk types, but the coupling value of the five factors in the SA was lower than that of the four factors, indicating that the risk types do not always superimpose each other in complex scenarios. Moreover, there were significant differences in the risk coupling mechanisms between PA and SA. The results suggest that the likelihood of PA and SA occurrences should be reduced through standardized vehicle inspections and flexible control measures, respectively, thereby enhancing highway safety. Full article

Autonomous driving (AD) significantly reduces road accidents, providing safer transportation while optimizing traffic flow for greater efficiency and smoothness. However, ensuring safe decision-making in dynamic and complex highway environments, especially during lane-changing maneuvers, remains a challenge. Reinforcement Learning (RL) has become a promising method for developing decision-making systems in AD, particularly Deep Reinforcement Learning (DRL). In this study, we focus on highway lane-change behaviors and propose a novel DRL algorithm, called Huber-regularized Reward-threshold Adaptive Double Deep Q-Network (HRA-DDQN). First, a reward function optimally balances speed, safety, and the necessity of lane changes, ensuring efficient and safe maneuvering in highway scenarios. Second, the dynamic target network update strategy triggered by reward difference is introduced into HRA-DDQN, which enhances the model’s adaptability to varying traffic conditions. Finally, a hybrid loss function, combining Huber loss with L2 regularization, is implemented in HRA-DDQN to improve robustness against outliers and mitigate overfitting. Simulation results demonstrate that the proposed decision framework significantly enhances both driving efficiency and safety, outperforming other methods by yielding higher rewards, lower collision rates, and more stable lane-changing decisions. Full article

Road safety is a critical concern, as accidents happen globally. Despite efforts to enhance roads and enforce stricter driving rules, the number of accidents remains high. These issues arise from distracted driving, speeding, and driving under the influence. In the United States, fatal accidents increased by 16% from 2018 to 2022. The number of deaths rose from 36,835 in 2018 to 42,795 in 2022. This trend reveals a critical need for new solutions to reduce traffic incidents and improve road safety. Machine learning (ML) can help make roads safer and reduce traffic-related deaths. This paper presents an ML-based real-time highway traffic incident forecasting system named “VehiCast”. VehiCast utilizes vehicular ad hoc networks (VANETs) and federated learning (FL) to collect real-time traffic data, such as average delay, average speed, and the total number of vehicles across several highway zones, to enhance traffic incident prediction accuracy in real-time. Our extensive experimental results showcase that VehiCast reaches an impressive prediction accuracy of 91%, highlighting the power of innovation and determination. Full article

Due to the high volume of traffic on European highways and the increased percentage of traffic accidents and fatalities, traffic safety is imperative in the planning and design of highways. While highway safety design construction standards have been extensively researched, insufficient attention has been given to the influence of the surrounding landscape on traffic safety and to drivers’ awareness about the danger of the same. Thus, the aim of the research was to assess drivers’ perceptions of various factors impacting highway traffic safety (climatic impacts from the surrounding landscape, landscape vegetation that follows the roadway, and animals) beyond specific engineering features (roadway surface, traffic signs, highway junction points). A survey of 138 drivers was conducted to assess driver awareness of traffic safety on the research section of a highway in Serbia. This highway is part of the Serbian highway that is a key connection within the European road network, forming an integral part of several major routes. The survey revealed that drivers, regardless of gender or experience, primarily associate traffic safety with well-built roads and good visibility during driving. While the impacts of climatic elements from the surrounding landscape were acknowledged, drivers do not strongly attribute any danger to traffic safety from these factors due to their lack of visibility. This is reflected in the notable number of traffic accidents, impacted by these factors, on the studied highway (e.g., 12% of the total number of accidents during 2022). Vegetation and animals did not play a significant role in the respondents’ answers, which should not be the case; however, their absence in the highway landscape and along the roadway led to a lack of observed quality by drivers. This underscores the need for the scientific community and policymakers to delve deeper into these issues with a broader perspective, and to elevate highway safety standards accordingly. Full article

In recent years, an increasing number of accidents at ski resorts have raised significant safety concerns. To address these issues, it is essential to understand skiing traffic and the underlying dynamics. We collected 225 trajectories, which were analyzed after a correction process. To obtain a quantitative classification of typical trajectories we focus on three main quantities: turning points, minimum distance, and the fundamental diagram. Our objective was to analyze these trajectories in depth and identify key statistical properties. Our findings indicate that three factors—turning angle, curvature, and velocity change—can be used to accurately identify turning points and classify skiers’ movement styles. We found that aggressive skiers tend to exhibit larger and less stable turning angles, while conservative skiers demonstrate a more controlled style, characterized by smaller, more stable turns. This is consistent with observations made for the distribution of the minimum distance to other skiers. Furthermore, we have derived a fundamental diagram which is an important characteristic of any traffic system. It is found share more similarities with the fundamental diagram of ant trails than those of highway traffic. Full article

Globally, and specifically in Poland and Lithuania, the incidence of road accidents has been on a decline over the years. The overall figures remain significantly high. Thus, it is imperative to take substantial measures to further decrease these statistics. The objective of this article is to estimate the future frequency of traffic accidents in both countries. To achieve this, a comprehensive yearly analysis of traffic incidents in Poland and Lithuania was performed. Using police records, forecasts for the years from 2024 to 2030 were established. Various neural network models were employed to predict the number of accidents. The results suggest that there remains potential for stabilization in traffic accident rates. It is undeniable that the increasing volume of vehicles on the roads, along with the development of new highways and expressways, plays a crucial role in this scenario. The result obtained depends on the model parameters (testing, validation, and training phases). Sustainable development requires comprehensive solutions, which also include improving road safety. Our research contributes to this goal by creating a tool that provides insight into the number of road accidents in analyzed countries. Full article

As the automotive industry moves toward fully autonomous driving, the goal is to enable vehicles to operate safely without human control in all environments. Implementing Vehicle-to-Everything (V2X) communications in highway environments poses considerable challenges. Several critical services have strict network performance requirements as they deal with safety features. Existing fifth-generation (5G) base station schedulers do not discriminate among critical and non-critical automated driving functions. Therefore, in cases of increased traffic load, there is a significant drop in their performance, and, consequently, increased risk for accidents. Our paper discusses these issues and provides an adaptive scheduler called SOVANET+. The new scheduler acknowledges the Radio Access Network (RAN) load, and the requirements of critical, automated driving applications, together with channel quality, and optimizes the allocation of resources to critical services. The performance of SOVANET+ is evaluated through extensive simulations in the highway environment, an area less examined than urban scenarios. Results indicate that the adoption of SOVANET+ presents clear advantages to critical services compared to existing solutions. Full article

Vehicular Ad Hoc Networks play a crucial role in enabling Smart City applications by facilitating seamless communication between vehicles and infrastructure. This study evaluates the throughput performance of different routing protocols, specifically AODV, AODV:TOM, AODV:DEM, GPSR, GPSR:TOM, and GPSR:DEM, under various city and highway scenarios in complex networks. The analysis covers key parameters including traffic generation, packet sizes, mobility speeds, and pause times. Results indicate that TOM and DEM profiles significantly improve throughput compared to traditional AODV and GPSR protocols. GPSR:TOM achieves the highest throughput across most scenarios, making it a promising solution for high-performance data transmission in Smart Cities. For instance, GPSR:TOM achieves an average throughput of 3.2 Mbps in city scenarios compared to 2.8 Mbps for GPSR, while in highway scenarios, the throughput increases to 3.6 Mbps. Additionally, AODV:DEM records a throughput of 3.4 Mbps for high traffic generation, outperforming AODV:TOM at 3.1 Mbps and baseline AODV at 2.7 Mbps. The findings highlight the importance of optimizing data throughput to ensure reliability and efficiency in complex vehicle interconnection systems, which are critical for traffic management, accident prevention, and real-time communication in smart urban environments. Full article

The effective selection of highway projects is essential for driving economic growth and facilitating trade in Saudi Arabia’s cities. However, current studies lack a comprehensive approach that assesses highways based on a full spectrum of economic, environmental, and social cost–benefit factors tailored to Saudi Arabia’s construction industry. This study addresses this gap by developing a framework that incorporates the aspects. The methodology comprises five steps: (1) a literature review to identify benefit and cost criteria; (2) expert surveys to select significant criteria; (3) the application of the stepwise weight assessment ratio analysis (SWARA) method to determine criteria weights; (4) structured expert interviews to establish criteria quality weights; and (5) validation through application to three case studies, comparing the results with those obtained using the ANP method. The findings show that economically efficient road choices yield increased productivity and support industrial growth, while the most significant environmental benefit is reducing carbon emissions. Social benefits, as emphasized by experts, include accident reduction. Cost factors are also considered, with savings on vehicle operation costs identified as the most significant, as opined by the expert surveyed. Among the analyzed highways, Khurais Road, Riyadh, was the most efficient from the SWARA approach, with a value of 0.8, and the ANP case study conducted, with a normalized score of 0.045 and 0.230 for both benefits and cost criteria. Full article