Crash Severity Modeling in Urban Highways Using Backward Regression Method

Identifying and classifying intersections according to severity is very important problem for implementation of safety related counter measures and effective models are needed to compare and assess the severity. Highway safety organizations have considered intersection safety among their priorities. In spite of significant advances in highways safety, the large numbers of crashes with high severities still occur in the highways. Investigation of influential factors on crashes enables engineers to carry out calculations in order to reduce crash severity. In the previous studies, there are no perfect models which are capable to illustrate the influence of human factors, road, vehicle, weather conditions and traffic features including traffic volume and flow speed on the crash severity. Therefore, this paper is aimed to develop the models for illustration of the simultaneous influence of these variables on the crash severity in urban highways. The models represented in this study have been developed using binary Logit Models. SPSS software has been used to calibrate the models. It must be mentioned that backward regression method in SPSS was used to identify the significant variables in the model. Consider to obtained results it can be concluded that the main factor in increasing of crash severity in urban highways are driver age, movement with reverse gear, technical defect of the vehicle, vehicle collision with motorcycle and bicycle, bridge, frontal impact collisions, frontal-lateral collisions and multi-vehicle crashes in urban highways which always increase the crash severity in urban highways. Obtained results show the effectiveness and capability of the developed models.

Modeling traffic barriers crash severity by considering the effect of traffic barrier dimensions

Traffic barriers are in widespread all around the USA as safety countermeasures for reducing the severity of run-off-road crashes. The effect of traffic barriers’ dimension had been ignored in past real-world crash studies due to the considerable cost and time needed for collecting field data. This paper presented two new analytical models to investigate the effect of different variables on the severity of crashes involving traffic barriers, and end treatments. For this reason, a field survey was conducted on over 1.3 million linear feet of traffic barriers (approximately 4,176 miles road) in Wyoming to measure traffic barriers’ geometric features like height, length, offset, and slope rate. The collected data included 55% of all non-interstate roads of Wyoming. Based on results, the crashes involving box beam barriers were less severe than the crashes involved with W-beam or concrete barriers. The traffic barriers with a height between 28 and 31 in. were found safer than the traffic barriers shorter than 28 in., while there was no significant difference between the traffic barriers taller than 31 in. to those shorter than 28 in. in terms of crash severity. The end treatments located nearer to the traffic lane had lower crash severity.

Estimating the severity levels of road traffic crashes in Bahrain with crash costs estimated with different approaches

An important issue in analyzing accident blackspots is the estimation of severity levels of different types of accidents.This study aims to estimate the severity level of accidents in Bahrain using crash costs.These crash costs were calculated by the Human Capital Approach(HCA)and total reported costs from the victims.The data was collected from the General Directorate of Traffic,insurance companies,Ministry of Works(MoW)and Ministry of Health.It was found,from the survey responses,that there was no significant effect of victim characteristics on the total cost of the accidents.The severity levels were found to be higher than those found in previous literature or adopted by local authorities which could be attributed to the economic conditions of Bahrain.Moreover,the weights found by both approaches were different from each other.Therefore,it is recommended to use the HCA approach due to its comprehensive calculations involving future costs.

Intersection Related Crash Injuries: A Study on Factors Contributing to Injury Severity among Younger and Older Drivers in Summer and Winter

Older drivers and younger drivers are affected differently both in summer and winter. Different factors affect each level of severity differently;some factors affect a particular level of injury severity differently from when the same factor is analyzed for another injury severity. The goal of this study is to identify the factors that contribute to injury severity among older drivers (65+) and young drivers (16 - 25) considering two seasons namely, summer and winter at intersections. Binary ordered probit models were used to develop four models to identify the contributing factors, two models for each season, namely winter and summer. A statistical t-test has been done to identify the statistically significant variables @ 90% confidence interval. Based on the developed models, in summer, three contributing factors, driving too fast condition, rear-end crashes, and followed too close are associated with younger drivers injury severity, while two contributing factors, rear-end crashes and followed too close are associated with older drivers injury severity. In winter, five factors, made an improper turn, E Failed to Yield Right-of-Way from Traffic Signal, rear end (front to rear), gender like male and lighting condition like dark and dusk light condition, are associated with younger drivers injury severity, while three factors such as made improper turn, rear-end crashes, and followed too close are associated with older drivers injury severity. Contributing factors in summer are the same for both younger and older drivers, but different in winter for both younger and older drivers. This indicates that older drivers and younger drivers are affected differently both in summer and winter.

Role of street patterns in zone-based traffic safety analysis

Although extensive analyses of road segments and intersections located in urban road networks have examined the role of many factors that contribute to the frequency and severity of crashes, the explicit relationship between street pattern characteristics and traffic safety remains underexplored. Based on a zone-based Hong Kong database, the Space Syntax was used to quantify the topological characteristics of street patterns and investigate the role of street patterns and zone-related factors in zone-based traffic safety analysis. A joint probability model was adopted to analyze crash frequency and severity in an integrated modeling framework and the maximum likelihood estimation method was used to estimate the parameters. In addition to the characteristics of street patterns, speed, road geometry, land-use patterns, and temporal factors were considered. The vehicle hours was also included as an exposure proxy in the model to make crash frequency predictions. The results indicate that the joint probability model can reveal the relationship between zone-based traffic safety and various other factors, and that street pattern characteristics play an important role in crash frequency prediction.

Investigation on occupant injury severity in rear-end crashes involving trucks as the front vehicle in Beijing area, China

Purpose： Rear-end crashes attribute to a large portion of total crashes in China, which lead to many casualties and property damage, especially when involving commercial vehicles. This paper aims to investigate the critical factors for occupant injury severity in the specific rear-end crash type involving trucks as the front vehicle （W）. Methods： This paper investigated crashes occurred from 2011 to 2013 in Beijing area, China and selected 100 qualified cases i.e., rear-end crashes involving trucks as the FV. The crash data were supplemented with interviews from police officers and vehicle inspection. A binary logistic regression model was used to build the relationship between occupant injury severity and corresponding affecting factors. More- over, a multinomial logistic model was used to predict the likelihood of fatal or severe injury or no injury in a rear-end crash. Results： The results provided insights on the characteristics of driver, vehicle and environment, and the corresponding influences on the likelihood of a rear-end crash. The binary logistic model showed that drivers＇ age, weight difference between vehicles, visibility condition and lane number of road signifi- cantly increased the likelihood for severe injury of rear-end crash. The multinomial logistic model and the average direct pseudo-elasticity of variables showed that night time, weekdays, drivers from other provinces and passenger vehicles as rear vehicles significantly increased the likelihood of rear drivers being fatal. Conclusion： All the abovementioned significant factors should be improved, such as the conditions of lighting and the layout of lanes on roads. Two of the most common driver factors are drivers＇ age and drivers＇ original residence. Young drivers and outsiders have a higher injury severity. Therefore it is imperative to enhance the safety education and management on the young drivers who steer heavy duty truck from other cities to Beiiing on weekdays.

Factors associated with crash severities in built-up areas along rural highways of Nevada:A case study of 11 towns

In 2014, 32,675 deaths were recorded in vehicle crashes within the United States. Out of these, 51% of the fatalities occurred in rural highways compared to 49% in urban highways. No specific crash data are available for the built-up areas along rural highways. Due to high fatalities in rural highways, it is important to identify the factors that cause the vehicle crashes. The main objective of this study is to determine the factors associated with se- verities of crashes that occurred in built-up areas along the rural highways of Nevada. Those factors could aid in making informed decisions while setting up speed zones in these built-up areas. Using descriptive statistics and binary logistic regression model, 337 crashes that occurred in 11 towns along the rural highways from 2002 to 2010 were analyzed. The results showed that more crashes occurred during favorable driving conditions, e.g., 87% crashes on dry roads and 70% crashes in clear weather. The binary logistic regression model showed that crashes occurred from midnight until 4 a.m. were 58.3% likely to be injury crashes rather than property damage only crashes, when other factors were kept at their mean values. Crashes on weekdays were three times more likely to be injury crashes than that occurred on weekends. When other factors were kept at their mean value, crashes involving motorcycles had an 80.2% probability of being injury crashes. Speeding was found to be 17 times more responsible for injury crashes than mechanical defects of the vehicle. As a result of this study, the Nevada Department of Transportation now can take various steps to improve public safety, including steps to reduce speeding and encourage the use of helmets for motorcycle riders.

Machine learning applied to road safety modeling:A systematic literature review

Road safety modeling is a valuable strategy for promoting safe mobility,enabling the development of crash prediction models(CPM)and the investigation of factors contributing to crash occurrence.This modeling has traditionally used statistical techniques despite acknowledging the limitations of this kind of approach(specific assumptions and prior definition of the link functions),which provides an opportunity to explore alternatives such as the use of machine learning(ML)techniques.This study reviews papers that used ML techniques for the development of CPM.A systematic literature review protocol was conducted,that resulted in the analysis of papers and their systematization.Three types of models were identified:crash frequency,crash classification by severity,and crash frequency and severity.The first is a regression problem,the second,a classificatory one and the third can be approached either as a combination of the preceding two or as a regression model for the expected number of crashes by severity levels.The main groups of techniques used for these purposes are nearest neighbor classification,decision trees,evolutionary algorithms,support-vector machine,and artificial neural networks.The last one is used in many kinds of approaches given the ability to deal with both regression and classification problems,and also multivariate response models.This paper also presents the main performance metrics used to evaluate the models and compares the results,showing the clear superiority of the ML-based models over the statistical ones.In addition,it identifies the main explanatory variables used in the models,which shows the predominance of road-environmental aspects as the most important factors contributing to crash occurrence.The review fulfilled its objective,identifying the various approaches and the main research characteristics,limitations,and opportunities,and also highlighting the potential of the usage of ML in crash analyses.