The study of traffic safety at intersections by micro-traffic simulation

Since out of a lot of traffic problems traffic accidents cause damage to life and properties of people, it stands out as one of traffic problems which needs improvement, and the loss due to traffic accident negatively affects not only the parties to the accident but also the national economy. Thus, continual concern of the government toward traffic safety is getting bigger and lately each local government is preparing a basic plan for traffic safety and vitalizing traffic safety policies. As expanding the responsibility and role of local governments for traffic safety, traffic safety measures which are based on the characteristics of each local government should be studied. Most of analytical methods in the existing traffic accidents prediction models with macroscopic vision focus on socioeconomic variables such as local population and the number of registered vehicles, and present a great deal of prediction error when they are applied in practice. In this context, this study proposed a traffic accident prediction model in respect of macroscopic level for autonomous districts (administrative districts) of Seoul City. The model development was not based on the entire city but on the type of local land usage (development density) whose relationship with traffic accident frequency was analyzed.

This paper studies the risk assessment of traffic flow on major highways under high-speed driving conditions and the safety warning after traffic incidents. Firstly, by analyzing the operation characteristics of the main line traffic flow and the evolution characteristics of the upstream traffic flow after the event, a collaborative control strategy for the dynamic assessment and accurate early warning of the main line traffic flow is proposed. Secondly, based on the operating speed, traffic flow and head-time distance state parameters of the main traffic flow, the risk assessment model of the main traffic flow is established, which provides an algorithm basis for the safe operation status evaluation and active control of the main traffic flow. Third, based on the driver’s reaction process after the traffic incident and the evolution process of main traffic flow, a traffic incident safety warning distance function is proposed, which provides a quantitative function for the accurate early warning and prevention of traffic accidents in the upstream traffic flow after traffic incidents. Through the dynamic assessment and control of operation risks of expressway main line traffic flow, the accurate risk warning of expressway main line traffic flow under the traffic event conditions will significantly improve the dynamic safety control level and risk warning ability of the expressway main line.

Accurate on-road vehicle speed prediction is important for many intelligent vehicular and transportation applications. It is also challenging because the individual vehicle speed is affected by many factors, e.g., traffic speed, vehicle type, and driver's behavior, in either deterministic or stochastic ways. This paper proposes a novel vehicle speed prediction method in the context of vehicular networks, where the real-time traffic information is accessible. Traffic speeds of following road segments are first predicted by Neural Networks (NNs) based on historical traffic data. Hidden Markov models (HMMs) are trained by the Baum-Welch algorithm with historical traffic and vehicle data to present the statistical relationship between vehicle speed and traffic speed. The forward-backward algorithm is applied on HMMs to extract vehicle's speed on each road segment along the driving route. Simulation is set up on the SUMO microscopic traffic simulator with the application of a real Luxembourg highway network and traffic count data. The vehicle speed prediction result shows that our proposed method outperforms other ones in terms of prediction accuracy.

Traffic incidents continue to cause a significant loss in deaths, injuries, and property damages. Reported traffic accident data contains a considerable amount of human errors, hindering the studies on traffic accidents. Several approaches have been developed to detect accidents using traffic data in real time. However, those approaches do not consider the spatiotemporal patterns inherent in traffic data, resulting in high false alarm rates. In this paper, we study the problem of traffic accident detection by considering multiple traffic speed time series collected from road network sensors. To capture the spatiotemporal impact of traffic accidents to upstream locations, we adopt Impact Interval Grouping (IIG), which compares real-time traffic speed with historical data, and generates impact intervals to determine the presence of accidents. Furthermore, we take a multivariate time series classification approach and extract three novel features to measure the severity of traffic accidents. We use real-world traffic speed and accident datasets in our empirical evaluation, and our solutions outperform state-of-the-art approaches in multivariate time series classification.

Traffic prediction is a task where the goal is to determine the number and type of vehicles, or some other traffic related metric, at certain time point. In addition to predicting the short-term evolution of traffic, prediction can be done for estimating traffic for distant future based on the trends found in historical traffic data, which is a critical component of traffic simulators being able to spawn realistic number of vehicles under prevailing situation. Such prediction system needs to be dependent on the characteristics of the situation and not the preceding traffic flow. This work presents a deep learning based prediction pipeline that uses a Long Short Term Memory (LSTM) network to map temporal, weather and traffic accident data accurately into traffic flow to predict traffic flow over multiple timesteps from various non-traffic inputs. Traffic data can then be produced based on independent data like weather forecasts and be used for other applications. As far as we know, no previous traffic predictor combines so many input variables to predict traffic flow with vehicle type information. To make the event based traffic accident dataset compatible with time series data, a novel preprocessing step based on power law decay phenomenon is added. Quantitative experiments show that the proposed preprocessing step and optimized hyperparameters improve the accuracy of the predictor on multiple metrics compared to a model without accident information. In two established statistical evaluation metrics, Mean Absolute Error and Mean Squared Error, the improvement was over 20% for certain vehicle types.

In this paper, the characteristics of traffic flow on urban expressway in Beijing are investigated. Based on the real data, some classical traffic flow models are used to explore the relationships among traffic flow, speed and time occupancy. The FCM (fuzzy C-means method) clustering algorithm is applied to classify the traffic flow state. The results show that the Greenshields model is the best suitable model for the mathematical description of traffic flow, i.e. traffic speed and time occupancy is in linear relation while traffic volume and time occupancy (traffic speed) is in parabolic relation. Four different traffic flow states, including free flow, steady flow, synchronized flow and congested flow, are identified according to the FCM clustering method. For the free traffic flow, the time occupancy cluster center is equal to 0.16, and the traffic volume cluster center is equal to 980 pcu/h. For the steady traffic flow, the time occupancy cluster center is equal to 0.30, and the traffic volume cluster center is equal to 1737 pcu/h. For the synchronized traffic flow, the time occupancy cluster center is equal to 0.50, and the traffic volume cluster center is equal to 1896 pcu/h. For the congested traffic flow, the time occupancy cluster center is equal to 0.79, and the traffic volume cluster center is equal to 1184 pcu/h. The analysis of traffic flow characteristics in this study can provide the method and data foundation to evaluate the traffic service level and enhance the traffic organization and management.

The use of traffic simulation to analyze traffic safety and performance has become common in transportation engineering. Microsimulation methods are increasingly used to analyze driving performance for different road geometries and environmental elements. Drivers’ perception has an important impact on driving performance factors contributing to traffic safety on transportation facilities (highways, arterials, intersections, etc.). Impaired vision leads to failure in drivers’ perception and making right decisions. Various studies investigated the impact of environmental elements (fog, rain, snow, etc.) on driving performance. However, there is limited research examining the potentially detrimental effects on driving capabilities due to differing exposure to natural light brightness, in particular sun exposure. Autonomous vehicles (AVs) showed a significant impact enhancing traffic capacity and improving safety margins in car-following models. AVs may also enhance and/or complement human driving under deteriorated driving conditions such as sun glare. This study uses a calibrated traffic simulation and surrogate safety assessment model to improve traffic operations and safety performance under impaired visibility using different types of autonomous vehicles. A combination of visibility reduction, traffic flow characteristics, and autonomy levels of AVs was simulated and assessed in terms of the number of conflicts, severity level, and traffic operations. The simulation analysis results used to reveal the contribution of conflicts to the risk of crashes varied based on the influence of autonomy level on safe driving during sun glare exposure. The outcome of this study indicates the benefits of using different levels of AVs as a solution to driving under vision impairment situations that researchers, traffic engineers, and policy makers can use to enhance traffic operation and road safety in urban areas.

This study analyzed traffic accident characteristics in Chungcheong Region through the factor analysis, cluster analysis and questionnaire survey using traffic accident analysis data for Chungcheong Region in order to improve Korea`s traffic safety level. Based on the analysis results, this study suggests traffic safety technologies suitable for the situation of Chungcheong Region. According to the results of the questionnaire survey carried out for transporters in Chungcheong Region, `the passage of pedestrians and aged people` and `a problem of lacking visibility` were the biggest threatening factors of major traffic accidents in Chungcheong Region. The facilities required the most were `lighting equipment in driving at night`, and the expected effect by the equipment installation was high. As a result of the factor analysis and cluster analysis using the traffic accident analysis data, traffic accident risk by city type in Chungcheong Region was higher in rural areas, compared to urban areas. Especially, this study confirmed the risks of pedestrian and agricultural machine traffic accidents were high. Therefore, this study suggests three technologies to improve traffic safety level in Chungcheong Region, based on the analysis results.

To address the challenges associated with traffic accident detection and the subsequent impact on commute times, a method combining CNN and Linear Regression models is proposed. Initially, this approach involves classifying specific accident data using images and detailed accident records. The images are then categorized into binary groups—accident and non-accident. Post-accident detection does not necessitate high-speed detection or extensive data processing; CNN are sufficiently capable for this purpose. Traffic accidents are an inevitable part of daily driving and can lead to significant delays in commuting. In rare cases, accidents may result in participants falling into a coma, further delaying rescue efforts. The proposed method aims to enhance road safety and traffic efficiency by promptly identifying accidents and minimizing the disruption caused to commute times through advanced technological solutions. By leveraging CNN for image analysis and Linear Regression for data modeling, this approach seeks to streamline accident detection processes, thereby improving overall traffic management and safety measures. This methodological framework underscores the importance of integrating cutting-edge technology to mitigate the adverse effects of traffic accidents on daily commuting.

One of the key reasons why the road capacity of urban roads in China often fails to meet the designed capacity is the mixture of heavy vehicles (slow-moving) and light vehicles (fast-moving). This paper presents a two-lane cellular automaton model suitable for simulating urban road traffic that includes intersections, based on the NaSch model. The model comprehensively takes into account multiple key factors, such as vehicle safety distance, speed differences between adjacent vehicles, the acceleration and deceleration performance of different types of vehicles, and driver reaction time, enabling it to more realistically reproduce the complex characteristics of mixed traffic flows on urban roads. The paper investigates and analyzes the influence of traffic flow density and the proportion of heavy vehicles on the moving bottleneck effect in urban roads from several aspects, including space–time evolution diagrams, traffic flow, average speed, and lane-changing rates. The results indicate that the model established in this paper successfully simulates the characteristics of mixed traffic flows on urban roads, and the simulation results align with actual traffic conditions, achieving the expected simulation effects. Before the traffic volume reaches saturation, the higher the proportion of heavy vehicles on urban roads, the stronger the moving bottleneck effect. This confirms the necessity of conducting research on the phenomenon of moving bottlenecks and the mechanisms of traffic impacts in urban roads, providing a scientific basis for formulating effective traffic dispersion measures and alleviating traffic congestion in the future. This research possesses significant practical meaning and value.

Road network traffic flow prediction: A personalized federated learning method based on client reputation

1. Dinesh Mohan - Injury Control and Safety Promotion: Ethics, Science and Practice. 2. William Haddon, Jr - On the Escape of Tigers: An Ecological Note. 3. Susan P. Baker - Where Have We Been and Where are We Going With Injury Control? 4. Brian O'Neill - Reducing Injury Losses: What Private Insurers Can and Cannot Do. 5. Shrikant I. Bangdiwala - Methodlogical Considerations in the Analysis of Injury Data: A Challenge for the Injury Research Community. 6. Ted R. Miller - Assessing the Burden of Injury: Progress and Pitfalls. 7. Geetam Tiwari - Traffic Flow and Safety: Need for New Models for Heterogeneous Traffic. 8. Murray McKay - Folklore and Science in Traffic Safety: Some New Directions. 9. Dietmar Otte - Demands to Vehicle Design and Test Procedures for Injury Control of Vulnerable Road Users in Traffic Accidents. 10. James Hedlund - Risky Business: Safety Regulations, Risk Compensation and Individual Behaviour. 11. Liisa Hakamies-Blomqvist - Aging and Transportation: Mobility and Safety? 12. Anne Tursz - Adolescents' Risk-taking Behaviour, Myth or Reality: Evidence from International Data. 13. James Nixon - Injury Prevention and Children's Rights. 14. Lief Svanstrom - Evidence-based Injury Prevention and Safety Promotion - State-of-the-art. 15. Mohamed Seedat - Community Psychology and Safety: A Psychospiritual Perspective. 16. A. K.(Dunu) Roy - Labour and Safety: Science, Technology and Society. 17. Wim Rogmans - Achievements in Consumer Product Safety and the Challenges of Globalization. 18. Mathew Varghese - Technologies, Therapies, Emotions and Empericism in Pre-hospital Care. 19. Etienne Krug - The Burden of Violence: An International Public Health Perpective. 20. Mark L. Rosenberg and James A. Mercy - A New Vision for Suicide Prevention: The Public Health Approach. 21. Emmanuel Rozental-Klinger - Barbarism and Solitude: Reflections on Globalization and Violence. O'Neill, Shrikant I. Bangdiwala, Ted R. Miller, Geetam Tiwari, Murray MacKay, Dietmar Otte, James Hedlund, Liisa Hakamies-Blomqvist, Anne Tursz, James Nixon, Leif Svanstrom, Modamed Seedat, A.K(Dunu) Roy, Wim Rogmans, Mathew Varghese, Etienne Krug, Mark L. Rosenberg and James A. Mercy, Emmauel Rozental-Klinger.

This paper analyses the source and development of fault tolerance theory, and discusses the working process of fault tolerance, and illustrates the workflow and dependability of fault tolerance. So there is a widespread belief that this is feasible that fault tolerance theory is used in the traffic safety study. Base on summarizing fault tolerance factors, the paper gives fault tolerance conceptual model primarily which could be used in the road traffic safety research. Above all, the paper presents a new idea which study traffic safety issues from the perspective of fault-tolerant , and this is important core content of the paper, and is the purpose of writing this article too.

Local data are essential for the analysis of abrupt conditions in traffic flow. In this research, we address the shortcomings of real-time traffic flow detection data, which inadequately represent the density characteristics of vehicular traffic. To mitigate this issue, we establish mathematical relationships among traffic flow density, time headway, and vehicle speed, based on the fundamental characteristics of traffic flow dynamics. This framework allows for the estimation of density across various road segments. Recognizing the nonlinear dynamics that characterize traffic flow, we introduce a microscopic traffic flow cusp catastrophe potential function that incorporates headway, utilizing cusp catastrophe theory alongside microscopic traffic flow parameters to analyze real-time variations in traffic flow potential characteristics. In the experimental section, we developed fitting regression functions for traffic flow parameters using road detection data from the cities of Nanjing and Yueyang in China. We also compared outcomes derived from the theoretical model with the parameter estimation results obtained from the data, which facilitated the calculation of traffic flow characteristics, such as cusp density and volume over a one-month period. The results derived from the proposed potential function exhibit the functions’ greater capacity to capture the complex fluctuations in traffic flow compared to traditional traffic potential functions, thereby providing a valuable instrument with which to evaluate traffic flow characteristics in conjunction with real-time monitoring data.

Based on the analysis of the macroscopic characteristics of the traffic flow in a large busy airport, this paper explores the relationship between the basic parameters of the traffic flow and its phase transformation process. Firstly, considering the physical structure of airport surface and ground control rules, this paper uses the variable cell transmission model to simulate the surface operation. Then, the macro characteristics of the traffic flow in taxiway and apron area are analysed by constructing the fundamental diagrams. It is proved that there is an interconnection between the basic parameters such as flow, velocity and density. With the change of parameters, the traffic presents three phase states as free-flow state, metastable state and blocked state, and the evolution characteristics of traffic flow are different in different states. The results of this paper can provide theoretical support for airport surface operation management.