Development of probabilistic pedestrian fatality model for characterizing pedestrian-vehicle collisions

Pedestrian-related accidents are considered to be the most serious of traffic accidents due to the associated high fatality rates. In Korea, pedestrian fatalities accounted for approximately 40% of all traffic-related fatalities in 2004. Significant efforts have been made to develop effective countermeasures for pedestrian-vehicle collisions. A basis for devising such countermeasures is to understand the characteristics of pedestrian-vehicle collisions. This study develops a pedestrian fatality model capable of predicting the probability of fatality in pedestrian-vehicle collisions. Binary logistic regression and a probabilistic neural network (PNN) are employed to estimate the probability of pedestrian fatality. Pedestrian age, vehicle type and collision speed are used as independent variables of the fatality model. The models developed herein are valuable tools that can be used to direct safety policies and technologies associated with pedestrian safety.     

Road traffic crashes and risk groups in India: Analysis,interpretations, and prevention strategies

Current literature does not adequately discuss India's quickly changing transportation scenario, especially road traffic crash (RTC) concerns. The objectives of this work were to (a) present the national RTC framework and a case study of Andhra Pradesh (AP); (b) analyze and identify risk types; (c) discuss trends and data deficiencies; and (d) recommend prevention strategies. During the period 1970–2009, the nation's road length increased at a compounded annual growth rate (CAGR) of 3.2%, whereas the number of registered vehicles, RTCs, and fatalities grew at 12%, 3.8%, and 5.7% CAGR respectively. Exposure risk dropped from 103 to 11 fatalities per 10 000 vehicles but increased from 2.7 to 10.8 fatalities per 100 000 people.     

Did the COVID-19 pandemic influence traffic fatalities in 2020? A presentation of first findings

The year 2020 was an extraordinary year due to the COVID-19 pandemic. This pandemic resulted in lockdowns and confinements globally and emptier streets and roads. Traffic patterns and traffic composition (modal split) changed considerably during the pandemic and as a consequence the number of people killed and injured in road crashes. The aim of this research is to present the number of road fatalities and the fatality rates (fatalities per kilometer driven) in 2020 and to compare these numbers and rates with the previous period (2017–2019), a baseline. An online questionnaire was distributed among the forty countries that are members of the International Safety Data and Analysis Group (IRTAD) in the International Transport Forum and 24 were in a position to submit the requested information before the 1st of June 2021. The questionnaire requested information on the monthly number of fatalities on a national level for four years, (2017–2020) and on kilometres driven. The number of fatalities in 2020 was 17.3% lower in the 24 participating countries compared with the baseline period and the reduction is almost seven times higher than annually in these countries in the period 2010–2019. The reduction took place in spring 2020 and not so much in the remainder of the year. The highest reduction were measured among young (0–17) and elderly people (75 and older), with public transport and on motorways. With the exception of one country, reductions in fatalities have been measured in all countries, however we observe major differences between countries. Regarding fatality rates (fatalities per vehicle kilometer travelled), we also observe major differences between countries and not a stable pattern over 2020 and a remarkable increase in April 2020, the month with the largest fatality reduction. Countries with severe COVID-19 restrictions do not necessarily demonstrate the greatest reductions in road fatalities. It is recommended to carry our further analysis to find explanations for the results and for the differences between the countries.     

Using machine leaning techniques for evaluation of motorcycle injury severity

There is a growing interest in the application of the machine learning techniques in predicting the motorcycle crash severity. This is partly due to a progress in autonomous vehicles technology, and machine learning technique, which as a main component of autonomous vehicle could be implemented for traffic safety enhancement. Wyoming's motorcycle crash fatalities constitute a concern since the count of riders being killed in motorcycle crashes in 2014 was 11% of the total road fatalities in the state. The first step of crash reduction could be achieved through identification of contributory factors to crashes. This could be accomplished by using a right model with high accuracy in predicting crashes. Thus, this study adopted random forest, support vector machine, multivariate adaptive regression splines and binary logistic regression techniques to predict the injury severity outcomes of motorcycle crashes. Even though researchers applied all the aforementioned techniques to model motorcycle injury severities, a comparative analysis to assess the predictive power of such modeling frameworks is limited. Hence, this study contributes to the road safety literature by comparing the performance of the discussed techniques. In this study, Wyoming's motorcycle crash injury severities are modeled as functions of the characteristics that give rise to crashes. Before conducting any analyses, feature reduction was used to identify a best number of predictors to be included in the model. Also to have an unbiased estimation of the performance of different machine learning techniques, 5-fold cross-validation was used for model performance evaluation. Two measure, Area under the curve (AUC), and confusion matrix were used to compare different models' performance. The machine learning results indicate that random forest model outperformed the other models with the least misclassification and higher AUC. It was also revealed that a dichotomous response variable, with fatality and incapacitation injury in one category, along with all other categories in another group would result in a lower misclassification rate than a polychotomous response variable. This might result from the nature of motorcycle crashes, lacking a protection compared with passenger cars, preventing machine learning technique to get trained properly. Moreover, the most important variables identified by the random forest model are those related to the operating speed, resentful other party, traffic volume, truck traffic volume, riding under the influence, horizontal curvature, wide roadway with more than two lanes and rider's age.     

Pedestrian accessibility and safety around bus stops in Delhi

Safety for public transport (PT) users is least during the access and egress trips. Previous studies have established that improvement in pedestrian safety will improve the safety of PT users as well. We studied the accessibility of pedestrian infrastructure around ~360 sampled bus stops in Delhi by conducting physical audits. 15 indicators in the audit checklist were meaningfully reduced to five factors through Principal Components Analysis. We developed Poisson regression models (with their geographically-weighted counterparts) to assess the association between these five factors for each bus stop with the number of pedestrian fatalities around that stop. Two models were developed— a) for fatalities where the impacting vehicle was known, and b) for fatalities where the impacting vehicle was unknown (hit-and-run cases). For both the models, geographically-weighted Poisson regression (GWPR) performed better than their global Poisson counterparts. Overall improved access was seen to be positively associated with less pedestrian fatalities. Further, we established that the nature of hit-and-run cases differ from those where the impacting vehicle is known, through— a) difference in the effect of the exposure variable, b) different factors being significant in the respective models, especially in the GWPR. The novelty of this study is that we modelled the relationship of pedestrian fatalities around PT stops with factors related to the pedestrian access to these stops. Through the application of GWPR, we found that different types of pedestrian fatalities are related to different aspects of access. We also identified bus stops with higher risk of pedestrian fatalities. Based on this, the methodology presented in this study is useful in guiding city authorities to identify and prioritise a) specific access-related factors which require improvement, and b) bus stops which require improvement in their pedestrian-access infrastructure. These analyses can be extended to study pedestrian safety around PT stops in any city.     

Road traffic conditions in Kenya: Exploring the policies and traffic cultures from unstructured user-generated data using NLP

Road traffic accidents (RTA) are a prevalent cause of fatality with African countries having the highest fatality index (25–34 per quota). The World Health Organization estimates Kenya's fatality rate due to RTA at 28 per quota. From literature, the country's fatality and injuries have increased by 26% and 46.5%, respectively, since the year 2015. The country is faced with incomplete RTA data capturing, hindering effective planning and policy adjustments to curb the menace. In this paper, we scrapped user-generated data (Twitter) and national transport and safety authority's (NTSA) reports to shed light on traffic safety, practices, and cultures in the country. To this end, we gathered 1,000,000 tweets and 8000 speeding entries between 2015 and 2021 and performed natural language processing (NLP) and quantitative study of the data. We applied NLP and n-gram search of keywords to categorize data into 8 topics: traffic, public service vehicle (PSVs), policing, accident, infrastructure, recklessness, robbery, and corruption. From the data, policing, which touches on all police and law-enforcement-related activity was found to be highly correlated with PSVs, recklessness, accidents, traffic congestion, robbery, infrastructure, and corruption with indices of r(76) = 0.92, 0. 91, 0.87, 0.82, 0.81, 0.76, and 0.70, respectively with p < 0.001. The topic modeling confirmed the identified topics to be the latent discussion issues affecting the public. From the study, PSVs, policing and traffic flow were isolated as key issues that ought to be addressed immediately. The research recommended the integration of driver monitoring systems to strengthen policing. The research, which utilized unstructured data, points to the utility of data mining which would greatly benefit traffic research, particularly African-based studies, that suffer from data inadequacy.     

International analysis on social and personal determinants of traffic violations and accidents employing logistic regression with elastic net regularization

While the number of road fatalities is declining in developed countries, it is still increasing globally, especially in middle-and low-income countries. In addition to the driver's individual awareness and attitude toward traffic safety, various factors such as the development of road infrastructure and the legal system may have a significant influence on the occurrence of traffic accidents. Thus, it is essential to consider these factors to enhance traffic safety and achieve Sustainable Development Goal (SDG) Targets of 3.6.In this study, we developed an Elastic Net Regression model to evaluate the factors that influence an individual's traffic violations and accidents based on an international questionnaire on traffic safety attitude, country fact survey data on traffic regulations, and other statistical databases. As a result, it was revealed that: i) In addition to country-level factors, the individual's attributes and attitudes toward traffic safety have an influence on the experience of traffic violations and accidents. and ii) While the same variables regarding individual attributes and attitudes are selected for both traffic violations and accidents, the selected variables relating to country factors differ between violations and accidents.     

What affects pedestrian crossing difficulty at urban intersections in a developing country?

In developing countries, road traffic crashes involving pedestrians have become a foremost concern. At present, road safety assessment plans and selection of interventions are primarily restricted to traditional approaches that depend on the investigations of historical crash data. However, in developing countries such as India, the availability, consistency, and accuracy of crash data are major concerns. In contrast, proactive approaches such as studying road users' risk perception have emerged as a substitute method of examining potential risk factors. An individual's risk perception offers vital information on probable crash risk, which may be beneficial in detecting high-risk locations and major causes of crashes. Since the pedestrian fatality risk is not uniform across the urban road network level, it may be expected that pedestrians' perceived risk measured in terms of “crossing difficulty” would also vary across the sites. In this perspective, the present paper establishes a mathematical association between the pedestrians' perceived “crossing difficulty” and actual crashes. The model outcome confirms that pedestrians' perceived crossing difficulty is a good surrogate of fatal pedestrian crashes at the intersection level in Kolkata City, India. Subsequently, to examine the impact of traffic exposures, road infrastructure, land use, spatial factors, and pedestrian-level attributes on pedestrians' “crossing difficulty”; a set of Ordered Logit models are developed. The model outcomes show that high vehicle and pedestrian volume, vehicular speed, absence of designated bus stop, the presence of inaccessible pedestrian crosswalk, on-street parking, lack of signalized control (for both vehicle and pedestrian), inadequate sight distance, land use pattern, slum population, pedestrian-vehicular post encroachment time, waiting time before crossing, road width, and absence of police enforcement at an intersection significantly and positively increase pedestrian's crossing difficulty at urban intersections. To end, the model findings are advantageously utilized to develop a set of countermeasures across 3E's of road safety.     

Motorcycle fatalities in Malaysia

Malaysia has the highest road fatality risk (per 100,000 population) among the ASEAN countries and more than 50% of the road accident fatalities involve motorcyclists. This study has collected and analysed data from the police, government authorities, and national and international research institutes. Only fatality data are used due to the severe underreporting of severe injuries (up to 600%) and slight injuries (up to 1400%). The analysis reveals that the highest numbers of motorcycle fatalities occur in rural locations (61%), on primary roads (62%) and on straight road sections (66%). The majority are riders (89%), 16 to 20 years old (22.5%), and 90% of the motorcycles are privately owned. Of those involved in fatal accidents, 75% of the motorcyclists wear helmets, and 35% do not have proper licences. The highest number of fatalities by type of collision is ‘angular or side’ (27.5%). Although fatal motorcyclist crashes mostly involve ‘passenger cars’ (28%), motorcyclists are responsible for 50% of the collisions either by crashing singly (25%) or with other motorcyclists (25%). While male motorcyclists predominate (94% of fatalities), female motorcyclists aged 31 to 70, possessing ‘no licence’, not wearing helmets and travelling during the day, account for a higher percentage than male motorcyclists. Malaysia must acquire more motorcycle exposure data and establish an injury recording system and database based on hospital-records. To reduce motorcycle fatalities, it first has to understand why young male motorcyclists are prone to fatal crashes in the evenings and on weekends on rural primary roads, especially on straight road sections.     

Cox Regression模型在交通事件持续时间研究中的应用

有效的交通事件管理要求交通管理者全面了解交通事件的各种特征才能准确估计事件持续时间,从而及时地疏导交通拥堵。利用某高速公路应急指挥中心管理系统中记录的近3 a的交通事件持续时间数据,建立Cox Regression模型探索影响持续时间的危险因素并评价其作用强度和方向。研究表明,日夜、报警方式、事件类型、占用车道数、涉及车辆数、涉及死亡、救护车、牵引车、吊车、驳车、涉及货车等11项是交通事件持续时间的显著影响因素,因此,交通管理者对这些因素进行改善可有效提高交通事件管理效率和安全性。     

Off-road vehicle fatalities: A comparison of all-terrain vehicle and snowmobile accidents in Sweden

This study investigates accident fatalities involving two types of off-road vehicles: snowmobiles and all-terrain vehicles (ATVs). All snowmobile fatalities in Sweden from the 2006/2007 season through the 2011/2012 season, and all ATV fatalities from 2007 through 2012, were retrospectively examined. A total of 107 fatalities—57 snowmobile-related and 50 ATV-related—were found. Most deaths occurred on weekends (71% of the snowmobile-related and 72% of the ATV-related). A majority of the fatalities were males (91% and 94%), with the largest share in the age group 40–49 years (19% and 24%). The most common causes of death were blunt trauma (56% and 66%), drowning (30% vs 6%), and traumatic asphyxia (9% vs 14%). Among victims who were tested (95% vs 92%), a very high share was found to be inebriated (59% vs 61%), and mean blood alcohol concentration was also high (1.9 vs 1.7 g/l). Forty-seven percent of snowmobile-related fatalities and 48% of ATV-related fatalities had a blood alcohol concentration above 1.0 g/l. This means that there was a very strong association between off-road vehicle fatalities and drunken riding; steps to prevent riding while intoxicated seem to be the most important preventive measure. Automatic measures such as alcolocks are probably the most effective. The obvious at-risk group to target is middle-aged men with high alcohol consumption.     

A study on the causes of rear-end collision based on an analysis of driver behavior

The increasing number of traffic fatalities in recent years has become a serious social problem, making it imperative to find scientific and effective ways of preventing accidents on the road. An important step in this direction is to identify the causes underlying each accident pattern. This paper presents a study of the causes of rear-end collision, focusing on the danger of the driver's mis-judgment of the brake timing in approaching a preceding vehicle. The results indicated that drivers showed inappropriate judgment in some situations.     

Spatial Dynamics of Multibody Tracked Vehicles Part II: Contact Forces and Simulation Results

In this part of the paper, three dimensional computational capabilities, that includes significant details, are developed for the nonlinear dynamic analysis of large scale spatial tracked vehicles. Three dimensional nonlinear contact force models that describe the interaction between the track links and the vehicle components such as the rollers, sprockets, and idlers as well as the interaction between the track links and the ground are developed and used to define the generalized contact forces associated with the vehicle generalized coordinates. Tangential friction and contact forces are developed in order to maintain the stability of the track motion and avoid the slippage of the track or its rotation as a rigid body. Body and surface coordinate systems are introduced in order to define the spatial contact conditions. The nonlinear equations of motion of the tracked vehicle are solved using the velocity transformation procedure developed in the first part of this paper. This procedure is used in order to obtain a minimum set of differential equations, and avoid the use of the iterative Newton-Raphson algorithm. A computer simulation of a tracked vehicle that consists of one hundred and six bodies and has one hundred and sixteen degrees of freedom is presented in order to demonstrate the use of the formulations presented in this study.     

基于稳定性和宏观交通流模型的车辆路径规划

为了提升车辆的安全性和能量利用率,从路径规划的层面出发,针对避免车辆遇到极端工况及低效率工况的问题,提出将车辆稳定性判据模型和交通流模型相结合的方法来规划车辆路径,使得车辆在路面湿滑情况下实现快速、安全的行驶。使用交通流模型预测车辆未来将要面临的交通环境变化,再使用稳定性判据模型评估未来交通的安全性,以便为混合动力车辆规划出最快且最安全的路径。具体来讲,为了预测混合动力车辆未来将要面临的车速及车流密度的变化,使用通量矢量分裂格式求解广义Aw-Rascle-Zhang（GARZ）宏观交通流模型。此外,使用驾驶人在环仿真平台PreScan,收集了同一驾驶人在不同车速及不同相对前车距离时给出的前轮转向角响应。基于前轮驱动（FWD）前轮转向（FWS）车辆和全轮转向（AWS）分布式驱动车辆（DDV）的Simulink模型,给出了不同前轮转向角对应的轮胎力饱和因子（δ_TFSC）响应。使用人工神经网络训练不同车速和车流密度对应的δ_TFSC,建立了车辆的稳定性判据模型。使用新建立的稳定性判据模型对交通流模型预测的参数（车流速及车流密度）进行稳定性评估。然后,基于以上的方法优化了车辆行驶路径,以确保车辆在湿滑路面上的行驶安全。最后,使用US-101真实交通流数据来验证交通流模型的预测结果。经实例验证得出：交通流模型与车辆横向稳定性判据模型相结合可以从路径规划的层面保证车辆安全行驶并提升交通系统的通行效率。     

Bayesian network for red-light-running prediction at signalized intersections

Abstract

Red-light-running (RLR) is an important reason for the large number of intersection-related fatalities, injuries, and other losses. The accurate RLR prediction can effectively reduce crashes caused by RLR behavior. The RLR prediction is usually composed of two parts: the vehicle’s stop-or-go behavior and the arrival time when the vehicle reaches the stop line. Previous stop-or-go prediction models are usually based on embedded traffic sensors using machine learning algorithms. While based on the continuous trajectories collected by radar sensors, RLR prediction can be conducted more effectively. In this paper, a probabilistic stop-or-go prediction model based on the Bayesian network (BN) is proposed for RLR prediction. We extend the deterministic output into the probabilistic output, which provides decision-makers with greater autonomy. The causality of BN improves the interpretability of the prediction model. The BN model is calibrated and tested by the continuous trajectories data measured by radar sensors installed at a signalized intersection. We not only consider the movement measurements of individual vehicles (e.g., speed and acceleration), but also take into account the car-following behavior. As a comparison, different machine learning models and the model based on the inductive loop detection (ILD) are adopted. The results show that the proposed BN model has a high prediction accuracy and performs better in the feature interpretation. This paper provides a new way for probabilistic RLR prediction based on continuous trajectories, which will significantly improve traffic safety of signalized intersections.     

某车型Glonass紧急呼叫系统的布置及应用

根据俄罗斯法规TP TC 2018/2011轮式交通安全规则规定,出口到俄罗斯的车型均需要配备有ERA-Glonass系统。目前,大部分进入俄罗斯市场的新车,采用俄罗斯当地供应商开发的成套Glonass系统,以后装模式安装到整车上。本文阐述的是一种新的开发模式以及系统零部件的布置及应用。     

A study of the environmental impacts of intelligent automated vehicle control at intersections via V2V and V2I communications

This article presents a novel intersection traffic management system for automated vehicles and quantifies its impact on fuel consumption and greenhouse gas emissions of CO₂ relative to traditional traffic signal and roundabout intersection control. The developed intelligent traffic management (ITM) techniques, which are based on a spatiotemporal reservation scheme, ensure that vehicles proceed through the intersection without colliding with other vehicles while at the same time reducing the intersection delay and environmental impacts. Specifically, the spatiotemporal reservation scheme provides each vehicle a collision-free path that is decomposed into a speed profile along with navigational instructions. The integration of the developed microscopic traffic simulator with instantaneous emission model, provides improved assessments of the environmental impact of traffic control strategies at intersections. The simulator architecture integrates several ITM algorithms, vehicle sensors, V2V/V2I communications, and emission and fuel consumption models. Each vehicle is modeled by an agent and each agent provides information depending on the specific vehicle sensors. The ITM system is supported by V2V and V2I communications, allowing the exchange of information among vehicles and infrastructure. The data include the estimated vehicle position and speed. Compared with traditional traffic management techniques, the simulation results prove that the proposed ITM system reduces CO₂ emissions significantly. The research also shows that these reductions are more significant when the traffic flow increases.     

城市道路车辆排放测试与模拟

以长春市部分主干道为试验研究路段,采用一种车载排放测量仪器在实际道路上进行了单车排放试验,运用多项式回归的方法,整合车辆运行状况和排放数据,建立了单车实际道路微观排放模型。利用合作开发的基于路径的微观交通仿真系统与单车微观排放模型的有机结合,开发了一种可预测不同交通状况下交通干道排放的有效系统,并进行了仿真计算。结果表明:该系统不但可估算并预测车辆在某一路段的污染物排放水平,还可评价交通管理改进措施对车辆排放的影响。     

Characteristics of collision damage mitigation braking system for pedestrian protection

The vehicle travel velocity at pedestrian contact is considered to be an important parameter that affects the crash outcome. To reduce vehicle/pedestrian impact velocity, a collision damage mitigation braking system (CDMBS) using a sensor for pedestrian protection could be an effective countermeasure. The first purpose of this study is to clarify the relation between vehicle travel velocity and pedestrian injury severity due to differences in pedestrians’ ages in actual traffic accidents. The accident analyses were performed using vehicle-pedestrian accident data in 2009 from the database of the Institute for Traffic Accident Research and Data Analysis (ITARDA) in Japan. The result revealed that the fatality risk became higher with the increase in vehicle travel velocity. The second purpose of this study is to determine the safety performance of production vehicles equipped with the CDMBS for pedestrian protection. It was found that the CDMBS was highly effective in reducing the impact velocity from 50 km/h (vehicle travel velocity) to below 17 km/h, that could result in a significant decrease in fatality risk to be 2% or less. Additionally, the authors investigated a detectable zone with respect to a pedestrian’s position in relation to the vehicle. It was shown that the detectable zones for production vehicles tested were limited to be inside the vehicle front width.     

车车通信环境下考虑交通拥堵状态的碰撞时间混合分布建模研究

碰撞时间（TTC）是评价车车碰撞风险的有效指标，然而该指标分布规律受到交通状态影响。为研究车车（V2V）通信环境下不同交通状态的TTC分布规律，通过构建基于LTE-V技术的车车通信环境，开展实车实验获取4种典型城市道路中的驾驶数据。考虑加速度和航向角建立动态冲突辨识模型，计算车辆以任意角度接近时的TTC值；针对TTC值的结果出现多峰值现象，将交通流分为“拥堵、缓行、畅通”这3种状态，构建了考虑交通流状态的高斯混合模型以描述不同交通状态下的TTC分布规律，并采用最大期望（EM）算法进行参数求解。将所建高斯混合模型与负指数分布、对数正态分布、负指数/对数正态混合分布这3种传统的TTC分布模型进行对比，采用校正决定系数R2评价模型的拟合优度，并通过K-S检验验证模型的有效性。在此基础上，将所建高斯混合模型应用于非车车通信条件下不同交通状态的TTC分布拟合描述，进一步验证模型的适用性。结果表明:车车通信环境下“拥堵、缓行、畅通”这3种交通状态下的高斯分布均值逐渐增大，所处交通场景的碰撞风险依次降低；考虑交通状态的TTC高斯混合模型拟合优度为0.950 5，相较于其他TTC混合分布模型，拟合优度提升了0.057 5。