Inclusion of phone use while driving data in predicting distraction-affected crashes

Introduction: Given the tremendous number of lives lost or injured, distracted driving is an important safety area to study. With the widespread use of cellphones, phone use while driving has become the most common distracted driving behavior. Although researchers have developed safety performance functions (SPFs) for various crash types, SPFs for distraction-affected crashes are rarely studied in the literature. One possible reason is the lack of critical distracted behavior information in the commonly used safety data (i.e., roadway inventory, traffic, and crash counts). Recently, the frequency of phone use while driving (referred to as phone use data) is recorded by mobile application companies and has become available to safety researchers. The primary objective of this study is to examine if phone use data can potentially predict distracted-affected crashes. Method: The authors first integrated phone use data with roadway inventory, traffic, and crash data in Texas. Then, the Random Forest (RF) algorithm was applied to assess the significance of the feature - phone use while driving - for predicting the number of distraction-affected crashes on a road segment. Further, this study developed two SPFs for distraction-affected crashes with and without the phone use data, separately. Both SPFs were assessed in terms of model fitting and prediction performances. Results: RF results rank the frequency of phone use as an important factor contributing to the number of distraction-affected crashes. Performance evaluations indicated that the inclusion of phone use data in the SPFs consistently improved both fitting and prediction abilities to predict distracted-affected crashes. Practical Applications: The phone use data provide new insights into the safety analyses of distraction-affected crashes, which cannot be achieved by only using the conventional roadway inventory and crash data. Therefore, safety researchers and practitioners are encouraged to incorporate the emerging data sources in reducing distraction-affected crashes.     

Application of Bayesian informative priors to enhance the transferability of safety performance functions

IntroductionSafety performance functions (SPFs) are essential tools for highway agencies to predict crashes, identify hotspots and assess safety countermeasures. In the Highway Safety Manual (HSM), a variety of SPFs are provided for different types of roadway facilities, crash types and severity levels. Agencies, lacking the necessary resources to develop own localized SPFs, may opt to apply the HSM’s SPFs for their jurisdictions. Yet, municipalities that want to develop and maintain their regional SPFs might encounter the issue of the small sample bias. Bayesian inference is being conducted to address this issue by combining the current data with prior information to achieve reliable results. It follows that the essence of Bayesian statistics is the application of informative priors, obtained from other SPFs or experts’ experiences.MethodIn this study, we investigate the applicability of informative priors for Bayesian negative binomial SPFs for rural divided multilane highway segments in Florida and California. An SPF with non-informative priors is developed for each state and its parameters’ distributions are assigned to the other state’s SPF as informative priors. The performances of SPFs are evaluated by applying each state’s SPFs to the other state. The analysis is conducted for both total (KABCO) and severe (KAB) crashes.Results, conclusions and practical applicationsAs per the results, applying one state’s SPF with informative priors, which are the other state’s SPF independent variable estimates, to the latter state’s conditions yields better goodness of fit (GOF) values than applying the former state’s SPF with non-informative priors to the conditions of the latter state. This is for both total and severe crash SPFs. Hence, for localities where it is not preferred to develop own localized SPFs and adopt SPFs from elsewhere to cut down on resources, application of informative priors is shown to facilitate the process.     

Influence of built environment and roadway characteristics on the frequency of vehicle crashes caused by driver inattention: A comparison between rural roads and urban roads

Introduction: With prevalent and increased attention to driver inattention (DI) behavior, this research provides a comprehensive investigation of the influence of built environment and roadway characteristics on the DI-related vehicle crash frequency per year. Specifically, a comparative analysis between DI-related crash frequency in rural road segments and urban road segments is conducted. Method: Utilizing DI-related crash data collected from North Carolina for the period 2013–2017, three types of models: (1) Poisson/negative binomial (NB) model, (2) Poisson hurdle (HP) model/negative binomial hurdle (HNB) model, and (3) random intercepts Poisson hurdle (RIHP) model/random intercepts negative binomial hurdle (RIHNB) model, are applied to handle excessive zeros and unobserved heterogeneity in the dataset. Results: The results show that RIHP and RIHNB models distinctly outperform other models in terms of goodness-of-fit. The presence of commercial areas is found to increase the probability and frequency of DI-related crashes in both rural and urban regions. Roadway characteristics (such as non-freeways, segments with multiple lanes, and traffic signals) are positively associated with increased DI-related crash counts, whereas state-secondary routes and speed limits (higher than 35 mph) are associated with decreased DI-related crash counts in rural and urban regions. Besides, horizontal curved and longitudinal bottomed segments and segments with double yellow lines/no passing zones are likely to have fewer DI-related crashes in urban areas. Medians in rural road segments are found to be effective to reduce DI-related crashes. Practical Applications: These findings provide a valuable understanding of the DI-related crash frequency for transportation agencies to propose effective countermeasures and safety treatments (e.g., dispatching more police enforcement or surveillance cameras in commercial areas, and setting more medians in rural roads) to mitigate the negative consequences of DI behavior.     

Investigation of injury severities in single-vehicle crashes in North Carolina using mixed logit models

IntroductionRoadway departure (RwD) crashes, comprising run-off-road (ROR) and cross-median/centerline head-on collisions, are one of the most lethal crash types. According to the FHWA, between 2015 and 2017, an average of 52 percent of motor vehicle traffic fatalities occurred each year due to roadway departure crashes. An avoidance maneuver, inattention or fatigue, or traveling too fast with respect to weather or geometric road conditions are among the most common reasons a driver leaves the travel lane. Roadway and roadside geometric design features such as clear zones play a significant role in whether human error results in a crash. Method: In this paper, we used mixed-logit models to investigate the contributing factors on injury severity of single-vehicle ROR crashes. To that end, we obtained five years' (2010–2014) of crash data related to roadway departures (i.e., overturn and fixed-object crashes) from the Federal Highway Administration's Highway Safety Information System Database. Results: The results indicate that factors such as driver conditions (e.g., age), environmental conditions (e.g., weather conditions), roadway geometric design features (e.g., shoulder width), and vehicle conditions significantly contributed to the severity of ROR crashes. Conclusions: Our results provide valuable information for traffic design and management agencies to improve roadside design policies and implementing appropriately forgiving roadsides for errant vehicles. Practical applications: Our results show that increasing shoulder width and keeping fences at the road can reduce ROR crash severity significantly. Also, increasing road friction by innovative materials and raising awareness campaigns for careful driving at daylight can decrease the ROR crash severity.     

Modeling crash severity by considering risk indicators of driver and roadway: A Bayesian network approach

Introduction: Traffic crashes could result in severe outcomes such as injuries and deaths. Thus, understanding factors associated with crash severity is of practical importance. Few studies have deeply examined how prior violation and crash experience of drivers and roadways are associated with crash severity. Method: In this study, a set of risk indicators of road users and roadways were developed based on their prior violation and crash records (e.g., cumulative crash frequency of a roadway), in order to reflect certain aspect or degree of their driving risk. To explore the impacts of those indicators on crash severity and complex interactions among all contributing factors, a Bayesian network approach was developed, based on citywide crash data collected in Kunshan, China from 2016 to 2018. A variable selection procedure based on Information Value (IV) was developed to identify significant variables, and the Bayesian network was employed to explicitly explore statistical associations between crash severity and significant variables. Results: In terms of balanced accuracy and AUCs, the proposed approach performed reasonably well. Bayesian modeling results indicated that the prior crash/violation experiences of road users and roadways were very important risk indicators. For example, migrant workers tend to have high injury risk due to their dangerous violation behaviors, such as retrograding, red-light running, and right-of-way violation. Furthermore, results showed that certain variable combinations had enhanced impacts on severity outcome than single variables. For example, when a migrant worker and a non-motorized vehicle are involved in a crash happening on a local road with high cumulative violation frequency in the previous year, the probability for drivers suffering serious injury or fatality is much higher than that caused by any single factor. Practical applications: The proposed methodology and modeling results provide insights for developing effective countermeasures to reduce crash severity and improve traffic system safety performance.     

A clustering approach to integrate traffic safety in road maintenance prioritization

Objectives: We combine data on roads and crash characteristics to identify patterns in road traffic crashes with regard to road characteristics. We illustrate how combined analysis of data regarding road maintenance, maintenance costs, road characteristics, crash characteristics, and geographical location can enrich road maintenance prioritization from a traffic safety perspective.

Methods: The study is based on traffic crash data merged with road maintenance data and annual average daily traffic (AADT) collected in Denmark. We analyzed 3,964 crashes that occurred from 2010 to 2015. A latent class clustering (LCC) technique was used to identify crash clusters with different road and crash characteristics. The distribution of crash severity and estimated road maintenance costs for each cluster was found and cluster differences were compared using the chi-square test. Finally, a map matching procedure was used to identify the geographical distribution of the crashes in each cluster.

Results: Results showed that based on road maintenance levels there was no difference in the distribution of crash severity. The LCC technique revealed 11 crash clusters. Five clusters were characterized by crashes on roads with a poor maintenance level (levels 4 and 3). Only a few of these crashes included a vulnerable road user (VRU) but many occurred on roads without barriers. Four clusters included a large share of crashes on acceptably maintained roads (level 2). For these clusters only small variations in road characteristics were found, whereas the differences in crash characteristics were more dominant. The last 2 clusters included crashes that mainly occurred on new roads with no need for maintenance (level 1). Injury severity, estimated maintenance costs, and geographical location were found to be differently distributed for most of the clusters.

Conclusions: We find that focusing solely on road maintenance and crash severity does not provide clear guidance of how to prioritize between road maintenance efforts from a traffic safety perspective. However, when combined with geographical location and crash characteristics, a more nuanced picture appears that allows consideration of different target groups and perspectives.     

A conceptual framework to understand the role of built environment on traffic safety

IntroductionMany U.S. cities have adopted the Vision Zero strategy with the specific goal of eliminating traffic-related deaths and injuries. To achieve this ambitious goal, safety professionals have increasingly called for the development of a safe systems approach to traffic safety. This approach calls for examining the macrolevel risk factors that may lead road users to engage in errors that result in crashes. This study explores the relationship between built environment variables and crash frequency, paying specific attention to the environmental mediating factors, such as traffic exposure, traffic conflicts, and network-level speed characteristics. Methods: Three years (2011–2013) of crash data from Mecklenburg County, North Carolina, were used to model crash frequency on surface streets as a function of built environment variables at the census block group level. Separate models were developed for total and KAB crashes (i.e., crashes resulting in fatalities (K), incapacitating injuries (A), or non-incapacitating injuries (B)) using the conditional autoregressive modeling approach to account for unobserved heterogeneity and spatial autocorrelation present in data. Results: Built environment variables that are found to have positive associations with both total and KAB crash frequencies include population, vehicle miles traveled, big box stores, intersections, and bus stops. On the other hand, the number of total and KAB crashes tend to be lower in census block groups with a higher proportion of two-lane roads and a higher proportion of roads with posted speed limits of 35 mph or less. Conclusions: This study demonstrates the plausible mechanism of how the built environment influences traffic safety. The variables found to be significant are all policy-relevant variables that can be manipulated to improve traffic safety. Practical Applications: The study findings will shape transportation planning and policy level decisions in designing the built environment for safer travels.     

Two-way left turn lane or raised median? A truck safety based study

Introduction: Due to their size and weight, trucks require more space and time to make left turns when exiting or entering a roadway. Therefore, appropriate median treatments are critical for roadways with substantial truck traffic. The two-way left-turn lane (TWLTL) and raised median (RM) are the two types of median most commonly used to improve roadway mobility and manage roadway accessibility. However, previous studies on these median treatments have focused primarily on the general traffic conditions and geometric roadway features without considering the truck traffic impact. Method: To fill this gap, this study investigates the truck impacts on TWLTL and RM by considering two major influencing factors – truck percentage and roadway access point density. First, a negative binomial regression is developed to analyze the relationship between crash frequency and various influencing factors. Next, the crash rate difference analysis between the TWLTL and RM is conducted to identify critical points for these two factors. Results: The findings indicate that, compared with RM, TWLTL has significantly higher crash frequency, especially for roadways with a higher percentage of trucks. This suggests that the percentage of trucks should be taken into consideration when selecting an appropriate type of roadway median.     

Modelling the relationship of driver license and offense history with fatal and serious injury (FSI) crash involvement

Introduction: Previous research has indicated that increases in traffic offenses are linked to increased crash involvement rates, making reductions in offending an appropriate measure for evaluating road safety interventions in the short-term. However, the extent to which traffic offending predicts fatal and serious injury (FSI) crash involvement risk is not well established, prompting this new Victorian (Australia) study. Method: A preliminary cluster analysis was performed to describe the offense data and assess FSI crash involvement risk for each cluster. While controlling demographic and licensing variables, the key traffic offenses that predict future FSI crash involvement were then identified. The large sample size allowed the use of machine learning methods such as random forests, gradient boosting, and Least Absolute Shrinkage and Selection Operator (LASSO) regression. This was done for the ‘all driver’ sample and five sometimes overlapping groups of drivers; the young, the elderly, and those with a motorcycle license, a heavy vehicle license endorsement and/or a history of license bans. Results: With the exception of the group of drivers who had a history of bans, offense history significantly improved the accuracy of models predicting future FSI crash involvement using demographic and licensing data, suggesting that traffic offenses may be an important factor to consider when analyzing FSI crash involvement risk and the effects of road safety countermeasures. Conclusions: The results are helpful for identifying driver groups to target with further road safety countermeasures, and for showing that machine learning methods have an important role to play in research of this nature. Practical Application: This research indicates with whom road safety interventions should particularly be applied. Changes to driver demerit policies to better target offenses related to FSI crash involvement and repeat traffic offenders, who are at greater risk of FSI crash involvement, are recommended.     

Built environment effects on bike crash frequency and risk in Beijing

IntroductionBuilding a safe biking environment is crucial to encouraging bicycle use. In developed areas with higher density and more mixed land use, the built environment factors that pose a crash risk may vary. This study investigates the connection between biking risk factors and the compact built environment, using data for Beijing.MethodIn the context of China, this paper seeks to answer two research questions. First, what types of built environment factors are correlated with bike-automobile crash frequency and risk? Second, how do risk factors vary across different types of bikes? Poisson lognormal random effects models are employed to examine how land use and roadway design factors are associated with the bike-automobile crashes.ResultsThe main findings are: (1) bike-automobile crashes are more likely to occur in densely developed areas, which is characterized by higher population density, more mixed land use, denser roads and junctions, and more parking lots; (2) areas with greater ground transit are correlated with more bike-automobile crashes and higher risks of involving in collisions; (3) the percentages of wider streets show negative associations with bike crash frequency; (4) built environment factors cannot help explain factors contributing to motorcycle-automobile crashes.Practical ApplicationsIn China's dense urban context, important policy implications for bicycle safety improvement drawn from this study include: prioritizing safety programs in urban centers, applying safety improvements to areas with more ground transit, placing bike-automobile crash countermeasures at road junctions, and improving bicycle safety on narrower streets.     

Urban street structure and traffic safety

IntroductionThis paper reports the influence of road type and junction density on road traffic fatality rates in U.S. cities.MethodThe Fatality Analysis Reporting System (FARS) files were used to obtain fatality rates for all cities for the years 2005–2010. A stratified random sample of 16 U.S. cities was taken, and cities with high and low road traffic fatality rates were compared on their road layout details (TIGER maps were used). Statistical analysis was done to determine the effect of junction density and road type on road traffic fatality rates.ResultsThe analysis of road network and road traffic crash fatality rates in these randomly selected U.S. cities shows that, (a) higher number of junctions per road length was significantly associated with a lower motor- vehicle crash and pedestrian mortality rates, and, (b) increased number of kilometers of roads of any kind was associated with higher fatality rates, but an additional kilometer of main arterial road was associated with a significantly higher increase in total fatalities. When compared to non-arterial roads, the higher the ratio of highways and main arterial roads, there was an association with higher fatality rates.ConclusionsThese results have important implications for road safety professionals. They suggest that once the road and street structure is put in place, that will influence whether a city has low or high traffic fatality rates. A city with higher proportion of wider roads and large city blocks will tend to have higher traffic fatality rates, and therefore in turn require much more efforts in police enforcement and other road safety measures.Practical applicationsUrban planners need to know that smaller block size with relatively less wide roads will result in lower traffic fatality rates and this needs to be incorporated at the planning stage.     

Investigating the effect of geometric dimensions of median traffic barriers on crashes: Crash analysis of interstate roads in Wyoming using actual crash datasets

IntroductionDespite the numerous safety studies done on traffic barriers’ performance assessment, the effect of variables such as traffic barrier’s height has not been identified considering a comprehensive actual crash data analysis. This study seeks to identify the impact of geometric variables (i.e., height, post-spacing, sideslope ratio, and lateral offset) on median traffic barriers’ performance in crashes on interstate roads.MethodGeometric dimensions of over 110 miles median traffic barriers on interstate Wyoming roads were inventoried in a field survey between 2016 and 2018. Then, the traffic barrier data collected was combined with historical crash records, traffic volume data, road geometric characteristics, and weather condition data to provide a comprehensive dataset for the analysis. Finally, an ordered logit model with random-parameters was developed for the severity of traffic barrier crashes. Based on the results, traffic barrier’s height was found to impact crash severity.ResultsCrashes involving cable barriers with a height between 30″ and 42″ were less severe than other traffic barrier types, while concrete barriers with a height shorter than 32″ were more likely involved with severe injury crashes. As another important finding, the post-spacing of 6.1–6.3 ft. was identified as the least severe range in W-beam barriers.Practical applicationsThe results show that using flare barriers should reduce the number of crashes compared to parallel barriers.     

Safety effects of street lighting on roadway segments: Development of a crash modification function

Objective: Nighttime crashes are overrepresented on the U.S. highway system. Roadway lighting, which provides additional visibility by supplementing vehicle headlights, has been identified as an effective countermeasure to improve nighttime safety. However, the existing literature does not provide a thorough understanding of the effects of street lighting photometric characteristics on nighttime crash occurrence on roadway segments. This study aimed to investigate the relationship between lighting photometric measures and nighttime crash risk on roadway segments and develop a crash modification function/factor (CMF).

Methods: The research team collected horizontal illuminance data on 440 roadway segments between 2 successive signalized intersections in Florida for 2012–2014 and matched 4 years of nighttime and daylight crash data (2011–2014). Random parameter negative binomial models were estimated for both nighttime and daylight crash frequencies. The expected night-to-day crash odds ratio, as an equivalent of CMF, was derived from the fitted models with the correction of estimation variances. The confidence intervals (CIs) of the developed CMF were estimated using the Cox method.

Results: The coefficient of the mean of horizontal illuminance is significantly negative in the nighttime model. The coefficients of the standard deviation of horizontal illuminance are significantly positive and normally distributed in both the nighttime and daylight models. The significance of the standard deviation in the daylight model captures the confounding effects—a high standard deviation correlates with high traffic exposures, poor safety design standards, and low maintenance quality. The CMF based on the expected daylight-to-day odds ratio was developed as an exponential function of the increments and the increment squares of the mean and the standard deviation of horizontal illuminance. Its 95% CIs indicate that the CMF is almost significant over the whole range. Other significant variables contributing to nighttime crash risk include annual average daily traffic, truck percentage, segment length, access density, undivided roads, and urban/city limits.

Conclusions: Horizontal illuminance characteristics have a significant impact on nighttime crash risk on roadway segments. An increase in the mean of horizontal illuminance, indicating an improvement in average lighting level, tends to decrease nighttime crash risk; an increase in the standard deviation, representing a poor uniformity of lighting pattern on a roadway segment, is more likely to raise nighttime crash risk. Because the 2 measures are strongly correlated in a low mean range (<0.44 fc), the 2 photometric measures need to be considered together to interpret the safety effects of lighting patterns. The standard deviation shows better performance in measuring lighting uniformity on a roadway segment than the traditional ratios (max-to-min and mean-to-min). However, a new photometric measure is needed to capture the true lighting pattern influencing driver vision at night.     

The impact of traffic barrier geometric features on crash frequency and injury severity of non-interstate highways

Introduction: The main objective of this research is to investigate the effect of traffic barrier geometric characteristics on crashes that occurred on non-interstate roads. Method: For this purpose, height, side-slope rate, post-spacing, and lateral offset of about 137 miles of traffic barriers were collected on non-interstate (state, federal aid primary, federal aid secondary, and federal aid urban) highways in Wyoming. In addition, crash reports recorded between 2008 and 2017 were added to the traffic barrier dataset. The safety performance of traffic barriers with regards to their geometric features was analyzed in terms of crash frequency and crash severity using random-parameters negative binomial, and random-parameters ordered logit models, respectively. Results: From the results, box beam barriers with a height of 27–29 inches were less likely to be associated with injury and fatal injury crashes compared to other barrier types. On the other hand, the likelihood of a severe injury crash was found to be higher for box beam barriers with a height taller than 31 inches. Both W-beam and box beam barriers with a post-spacing between 6.1 and 6.3 inches reduced the probability of severe injury crashes. In terms of the crash frequency, flare traffic barriers had a lower crash frequency compared to parallel traffic barriers. Non-interstate roads without longitudinal rumble strips were associated with a higher rate of traffic barrier crashes.     

Effects of speed humps on vehicle speed and pedestrian crashes in South Korea

Introduction: Speeding is a crucial risk factor for pedestrian safety because it shortens reaction time while increasing the impact force in collisions. Various types of traffic calming measures to prevent speeding have been devised. A speed hump—a raised bump installed in the pavement—has been widely used for this purpose. Method: To evaluate the effectiveness of speed humps, the speed profiles of vehicles passing speed humps were analyzed along with pedestrian crash records near speed humps. Results: The speed profiles showed that vehicles gradually diminished their speeds starting 30 m ahead of speed humps and, immediately after passing the humps, accelerated to regain their original speeds within a distance of 30 m. This speed reduction effect is substantial on both local and major roads: 18.4% and 24.0% reduction in speeds, respectively. The analysis of pedestrian crash records revealed that, inside the zones of speed reduction effect near speed humps (i.e., ±30 m from speed humps), fewer pedestrian crashes per roadway distance occurred and pedestrian injuries were less severe, compared with events outside the effect zones. This safety improvement was greater on major roads than local roads. Practical Applications: This work finds that the speed reductions that occurred near speed humps were gradual and influential ±30 m from their locations, suggesting that the hump installations should be close enough to the pedestrian crossings. It is noteworthy that, albeit that speed humps are more prevalent on local roads, the benefits of speed reduction effects from speed humps were more pronounced on major roads than on local roads. Therefore, speed humps on major roads can be considered a more effective measure for pedestrian safety.     

Examination of the severity of two-lane highway traffic barrier crashes using the mixed logit model

IntroductionVehicles in transport sometimes leave the travel lane and encroach onto natural or artificial objects on the roadsides. These types of crashes are called run-off the road crashes, which account for a large proportion of fatalities and severe crashes to vehicle occupants. In the United States, there are about one million such crashes, with roadside features leading to one third of all road fatalities. Traffic barriers could be installed to keep vehicles on the roadways and to prevent vehicles from colliding with obstacles such as trees, boulder, and walls. The installation of traffic barriers would be warranted if the severity of colliding with the barrier would be less severe than colliding with other fix objects on the sides of the roadway. However, injuries and fatalities do occur when vehicle collide with traffic barriers. A comprehensive analysis of traffic barrier features is lacking due to the absence of traffic barrier features data. Previous research has focused on simulation studies or only a general evaluation of traffic barriers, without accounting for different traffic barrier features.MethodThis study is conducted using an extensive traffic barrier features database for the purpose of investigating the impact of different environmental and traffic barrier geometry on this type of crash severity. This study only included data related to two-lane undivided roadway systems, which did not involve median barrier crashes. Crash severity is modeled using a mixed binary logistic regression model in which some parameters are fixed and some are random.ResultsThe results indicated that the effects of traffic barrier height, traffic barrier offset, and shoulder width should not be separated, but rather considered as interactions that impact crash severity. Rollover, side slope height, alcohol involvement, road surface conditions, and posted speed limit are some factors that also impact the severity of these crashes. The effects of gender, truck traffic count, and time of a day were found to be best modeled with random parameters in this study. The effects of these risk factors are discussed in this paper.Practical applicationsResults from this study could provide new guidelines for the design of traffic barriers based upon the identified roadway and traffic barrier characteristics.     

Investigation of crashes at pedestrian hybrid beacons: Results of a large-scale study in Arizona

Introduction: The pedestrian hybrid beacon (PHB) is a traffic control device used at pedestrian crossings. A recent Arizona Department of Transportation research effort investigated changes in crashes for different severity levels and crash types (e.g., rear-end crashes) due to the PHB presence, as well as for crashes involving pedestrians and bicycles. Method: Two types of methodologies were used to evaluate the safety of PHBs: (a) an Empirical Bayes (EB) before-after study, and (b) a long-term cross-sectional observational study. For the EB before-after evaluation, the research team considered three reference groups: unsignalized intersections, signalized intersections, and both unsignalized and signalized intersections combined. Results: For the signalized and combined unsignalized and signalized intersection groups, all crash types considered showed statistically significant reductions in crashes (e.g., total crashes, fatal and injury crashes, rear-end crashes, fatal and injury rear-end crashes, angle crashes, fatal and injury angle crashes, pedestrian-related crashes, and fatal and injury pedestrian-related crashes). A cross-sectional study was conducted with a larger number of PHBs (186) to identify relationships between roadway characteristics and crashes at PHBs, especially with respect to the distance to an adjacent traffic control signal. The distance to an adjacent traffic signal was found to be significant only at the α = 0.1 level, and only for rear-end and fatal and injury rear-end crashes. Conclusions: This analysis represents the largest known study to date on the safety impacts of PHBs, along with a focus on how crossing and geometric characteristics affect crash patterns. The study showed the safety benefits of PHBs for both pedestrians and vehicles. Practical Applications: The findings from this study clearly support the installation of PHBs at midblock or intersection crossings, as well as at crossings on higher-speed roads.     

城市道路交通事故地点文字表述方法研究

法律文书和交通安全分析要求事故地点记录准确、规范。为规范事故地点记录,在总结国外事故地点记录的点-线法、无规范格式法、线性参照系法、经纬度坐标法基础上,结合国内城市事故定位工作的需求,提出基于线性参照系的"五要素"事故地点文字表述方法。针对城市复杂道路网络,在道路分类的基础上,结合现场记录要求定义和说明"五要素"(事故所在道路、路侧、参照点、方位、距离),最后提出基于"五要素"的文字组合表述方法和事故地点记录实施方案。事故地点"五要素"记录法可供各地在改进事故地点记录时借鉴以提高事故数据的规范性。     

Applying machine learning approaches to analyze the vulnerable road-users' crashes at statewide traffic analysis zones

Introduction: In this paper, we present machine learning techniques to analyze pedestrian and bicycle crash by developing macro-level crash prediction models. Methods: We collected the 2010–2012 Statewide Traffic Analysis Zone (STAZ) level crash data and developed rigorous machine learning approach (i.e., decision tree regression (DTR) models) for both pedestrian and bicycle crash counts. To our knowledge, this is the first application of DTR models in the burgeoning macro-level traffic safety literature. Results: The DTR models uncovered the most significant predictor variables for both response variables (pedestrian and bicycle crash counts) in terms of three broad categories: traffic, roadway, and socio-demographic characteristics. Additionally, spatial predictor variables of neighboring STAZs were considered along with the targeted STAZ in both DTR models. The DTR model considering spatial predictor variables (spatial DTR model) were compared without considering spatial predictor variables (aspatial DTR model) and the model comparison results discovered that the prediction accuracy of the spatial DTR model performed better than the aspatial DTR model. Finally, the current research effort contributed to the safety literature by applying some ensemble techniques (i.e. bagging, random forest, and gradient boosting) in order to improve the prediction accuracy of the DTR models (weak learner) for macro-level crash count. The study revealed that all the ensemble techniques performed slightly better than the DTR model and the gradient boosting technique outperformed other competing ensemble techniques in macro-level crash prediction models.