Bicyclist injury severity in traffic crashes: A spatial approach for geo-referenced crash data to uncover non-stationary correlates

Identifying factors related to pedestrian and cyclist crashes in ACT, Australia with an extended crash dataset

As vulnerable road users, pedestrians and cyclists are facing a growing number of injuries and fatalities, which has raised increasing safety concerns globally. Based on the crash records collected in the Australian Capital Territory (ACT) in Australia from 2012 to 2021, this research firstly establishes an extended crash dataset by integrating road network features, land use features, and other features. With the extended dataset, we further explore pedestrian and cyclist crashes at macro- and micro-levels. At the macro-level, random parameters negative binomial (RPNB) model is applied to evaluate the effects of Suburbs and Localities Zones (SLZs) based variables on the frequency of pedestrian and cyclist crashes. At the micro-level, binary logit model is adopted to evaluate the effects of event-based variables on the severity of pedestrian and cyclist crashes. The research findings show that multiple factors are associated with high frequency of pedestrian total crashes and fatal/injury crashes, including high population density, high percentage of urban arterial road, low on-road cycleway density, high number of traffic signals and high number of schools. Meanwhile, many factors have positive relations with high frequency of cyclist total crashes and fatal/injury crashes, including high population density, high percentage of residents cycling to work, high median household income, high percentage of households with no motor vehicle, high percentage of urban arterial road and rural road, high number of bus stops and high number of schools. Additionally, it is found that more severe pedestrian crashes occur: (i) at non-signal intersections, (ii) in suburb areas, (iii) in early morning, and (iv) on weekdays. More severe cyclist crashes are observed when the crash type is overturned or struck object/pedestrian/animal; when more than one cyclist is involved; and when crash occurs at park/green space/nature reserve areas.

Exploring spatial heterogeneity in factors associated with injury severity in speeding-related crashes: An integrated machine learning and spatial modeling approach

Speeding, a risky act of driving a vehicle at a speed exceeding the posted limit, has consistently emerged as a leading contributor to traffic fatalities. Identifying the risk factors associated with injury severity in speeding-related crashes is essential for implementing countermeasures aimed at preventing severe injury incidents and achieving Vision Zero goals. With the wealth of traffic crash data collected by various agencies, researchers have a valuable opportunity to conduct data-driven studies and employ various modeling methods to gain insights into the correlated factors affecting injury severity in traffic crashes. Machine learning models, owing to their superior predictive power compared to statistical models, are increasingly being adopted by researchers. These models, in conjunction with interpretation techniques, can reveal potential relationships between crash injury severity and contributing factors. Traffic crashes are inherently tied to geographic locations, distributed across road networks influenced by diverse socioeconomic and geographical factors. Recognizing spatial heterogeneity in traffic safety is crucial for tailored safety measures to address speeding-related crashes, as a one-size-fits-all approach may not work effectively everywhere. However, most existing machine learning models are unable to incorporate the spatial dependency among observations, such as traffic crashes, which hinders their ability to uncover spatial heterogeneity in traffic safety. To address this gap, this study introduces the Geographically Weighted Neural Network (GWNN) model, a spatial machine-learning model that integrates neural network (NN) and geographically weighted modeling approaches to investigate spatial heterogeneity in speeding-related crashes. Unlike the traditional NN model, which trains a single set of model parameters for all observations, the GWNN trains a local NN model for each crash location using a spatially weighted subsample of nearby crashes, allowing for the quantification of corresponding local effects of features through calculating local marginal effects. To understand the spatial heterogeneity in speeding-related crashes, this study extracted two years (2020 and 2021) of speeding-related crash data from Alabama for the development of the GWNN local models. The modeling results show significant spatial variability among several factors contributing to injury severity in speeding-related crashes. These factors include driver condition, vehicle type, crash type, speed limit, weather, crash time and location, roadway alignment, and traffic volume. Based on the GWNN modeling results, this study identified three types of spatial variations in relationships between contributing factors and crash injury severity: consistent positive associations, consistent negative associations, and inverse associations (i.e., marginal effects can vary between positive and negative depending on the location). This study contributes by integrating advanced machine learning and spatial modeling approaches to uncover intricate spatial patterns and factors influencing injury severity in speeding-related crashes, thereby facilitating the development of targeted policy implementations and safety interventions.

A spatial autocorrelation analysis of road traffic crash by severity using Moran's I spatial statistics: A comparative study of Addis Ababa and Berlin cities

Methodological advancements in road safety research reveal an increasing inclination toward integrating spatial approaches in hot spot identification, spatial pattern analysis, and developing spatially lagged models. Previous studies on hot spot identification and spatial pattern analysis have overlooked crash severities and the spatial autocorrelation of crashes by severity, missing valuable insights into crash patterns and underlying factors. This study investigates the spatial autocorrelation of crash severity by taking two capital cities, Addis Ababa and Berlin, as a case study and compares patterns in low and high-income countries. The study used three-year crash data from each city. It employed the average nearest neighbor distance (ANND) method to determine the significance of spatial clustering of crash data by severity, Global Moran's I to examine the statistical significance of spatial autocorrelation, and Local Moran's I to identify significant cluster locations with High-High (HH) and Low-Low (LL) crash severity values. The ANND analysis reveals a significant clustering of crashes by severity in both cities, except in Berlin's fatal crashes. However, different Global Moran's I results were obtained for the two cities, with a strong and statistically significant value for Addis Ababa compared to Berlin. The Local Moran's I result indicates that the central business district and residential areas have LL values, while the city's outskirts exhibit HH values in Addis Ababa. With some persistent HH value locations, Berlin's HH and LL grid clusters are intermingled on the city's periphery. Socio-economic factors, road user behavior and roadway factors contribute to the difference in the result. Nevertheless, it is interesting to note the similarity of significant HH value locations on the outskirts of both cities. Finally, the results are consistent with previous studies and indicate the need for further investigation in other locations.

Analysis of factors influencing the degree of accidental injury of bicycle riders considering data heterogeneity and imbalance

Bicycle safety has emerged as a pressing concern within the vulnerable transportation community. Numerous studies have been conducted to identify the significant factors that contribute to the severity of cyclist injuries, yet the findings have been subject to uncertainty due to unobserved heterogeneity and class imbalance. This research aims to address these issues by developing a model to examine the impact of key factors on cyclist injury severity, accounting for data heterogeneity and imbalance. To incorporate unobserved heterogeneity, a total of 3,895 bicycle accidents were categorized into three homogeneous sub-accident clusters using Latent Class Cluster Analysis (LCA). Additionally, five over-sampling techniques were employed to mitigate the effects of data imbalance in each accident cluster category. Subsequently, Bayesian Network (BN) structure learning algorithms were utilized to construct 32 BN models after pairing the accident data from the four accident cluster types before and after sampling. The optimal BN models for each accident cluster type provided insights into the key factors associated with cyclist injury severity. The results indicate that the key factors influencing serious cyclist injuries vary heterogeneously across different accident clusters. Female cyclists, adverse weather conditions such as rain and snow, and off-peak periods were identified as key factors in several subclasses of accident clusters. Conversely, factors such as the week of the accident, characteristics of the trafficway, the season, drivers failing to yield to the right-of-way, distracted cyclists, and years of driving experience were found to be key factors in only one subcluster of accident clusters. Additionally, factors such as the time of the crash, gender of the cyclist, and weather conditions exhibit varying levels of heterogeneity across different accident clusters, and in some cases, exhibit opposing effects.

Self-reported cycling behavior and previous history of traffic accidents of cyclists

BACKGROUND

Cyclists are vulnerable traffic users and studying the cycling behavior of professional and elite cyclists, their previous history of traffic accidents combined with the current knowledge on high-risk behaviors of this group can be a useful basis for further studies on ordinary cyclists. This study aimed to determine the relationship between cycling behavior and the previous history of traffic accidents among members of the Cycling Federation of Guilan province in 2022.

METHODS

A descriptive-analytical study was performed in which the Bicycle Rider Behavior Questionnaire (BRBQ) constructed in the Porsline platform was distributed using the WhatsApp social network. All participants were asked to self-report their cycling behavior. The final analysis was performed by using STATA software (version 14).

RESULTS

The study subjects included a total of 109 cyclists with a mean age of 38.62 ± 10.94 years and a mean cycling experience of 13.75 ± 11.08 years. Using the logistic regression model, the relationship between gender (P = 0.039), years of cycling experience (P = 0.000), and education level (P ≤ 0.00), with previous traffic accidents, was found significant. There was also a significant relationship between stunts and distractions (P = 0.005), signaling violation (P = 0.000), and control error (P = 0.011) with previous traffic accidents. A significant association existed between stunts and distractions (P = 0.001) and signaling violation (P = 0.001) with a previous history of traffic injury within the last 3 years.

CONCLUSIONS

The findings of this study can be used to establish cyclist safety and preventative planning in society. In behavior change intervention programs, it is best to target male cyclists with higher-level education. In addition, the behavior of the cyclists whose predominant term of signaling violations must be corrected should be targeted. It is necessary to shape information campaigns and educational programs aimed for cyclists with common high-risk behaviors, especially signaling violations.

Factors associated with different types of freight crashes: A macro-level analysis

INTRODUCTION

Despite evidence showing higher fatality rates in freight-related crashes, there has been limited exploration of their spatial distribution and factors associated with such distribution. This gap in the literature primarily stems from the focus of existing studies on micro-level factors predicting the frequency or severity of injuries in freight crashes. The present study delves into the factors contributing to freight crashes at the neighborhood level, particularly focusing on different types of freight crashes: collisions involving a freight vehicle and a passenger vehicle, crashes between freight vehicles, and freight vehicle-non-motorized crashes.

METHOD

This study analyzes traffic crash data from the urbanized region of Seoul, collected between 2016 and 2019. To effectively deal with spatial autocorrelation and model different types of crashes in a unified framework, a Bayesian multivariate conditional autoregressive model was employed.

RESULTS

Findings show substantial differences in the factors associated with various types of freight crashes. The predictors for crashes between freight vehicles diverge significantly from those for freight vehicle-non-motorized crashes. Crashes between freight vehicles are relatively more influenced by road network structure, while freight crashes involving non-motorized users are relatively more affected by the built environment and freight facilities than the other crash types examined. Freight vehicle-passenger vehicle crashes fall into an intermediate category, sharing most predictors with either of the other two types of freight crashes.

CONCLUSIONS AND PRACTICAL APPLICATIONS

The findings of this study offer valuable lessons for transportation practitioners and policymakers. They can guide the formulation of effective land use policies and infrastructure planning, specifically designed to address the unique characteristics of different types of freight crashes.

Injury severity prediction of cyclist crashes using random forests and random parameters logit models

Cycling provides numerous benefits to individuals and to society but the burden of road traffic injuries and fatalities is disproportionately sustained by cyclists. Without awareness of the contributory factors of cyclist death and injury, the capability to implement context-specific and appropriate measures is severely limited. In this paper, we investigated the effects of the characteristics related to the road, the environment, the vehicle involved, the driver, and the cyclist on severity of crashes involving cyclists analysing 72,363 crashes that occurred in Great Britain in the period 2016-2018. Both a machine learning method, as the Random Forest (RF), and an econometric model, as the Random Parameters Logit Model (RPLM), were implemented. Three different RF algorithms were performed, namely the traditional RF, the Weighted Subspace RF, and the Random Survival Forest. The latter demonstrated superior predictive performances both in terms of F-measure and G-mean. The main result of the Random Survival Forest is the variable importance that provides a ranked list of the predictors associated with the fatal and severe cyclist crashes. For fatal classification, 19 variables showed a normalized importance higher than 5% with the second involved vehicle manoeuvring and the gender of the driver of the second vehicle having the greatest predictive ability. For serious injury classification, 13 variables showed a normalized importance higher than 5% with the bike leaving the carriageway having the greatest normalized importance. Furthermore, each path from the root node to the leaf nodes has been retraced the way back generating 361 if-then rules with fatal crash as consequent and 349 if-then rules with serious injury crash as consequent. The RPLM showed significant unobserved heterogeneity in the data finding four normal distributed indicator variables with random parameters: cyclist age ≥ 75 (fatal prediction), cyclist gender male (fatal and serious prediction), and driver aged 55-64 (serious prediction). The model's McFadden Pseudo R2 is equal to 0.21, indicating a very good fit. Furthermore, to understand the magnitude of the effects and the contribution of each variable to injury severity probabilities the pseudo-elasticity was assessed, gaining valuable insights into the relative importance and influence of the variables. The RF and the RPLM resulted complementary in identifying several roadways, environmental, vehicle, driver, and cyclist-related factors associated with higher crash severity. Based on the identified contributory factors, safety countermeasures useful to develop strategies for making bike a safer and more friendly form of transport were recommended.

Analysis of first responder-involved traffic incidents by mining news reports

Roadside service and incident response personnel face the risk of being killed or severely injured by passing vehicles when performing their duties on or along a road. This study investigated 5,113 responder-involved event news reports to understand the characteristics of first responder-involved incidents. Through text mining, this study examined and compared the characteristics of three types of responder-involved incidents: near-miss incidents, struck-by incidents, and line-of-duty-deaths (LODD). A higher proportion of struck-by and LODD incidents are associated with law enforcement agencies. In terms of the time of day, morning and night incidents are frequently reported in the news. Driving under the influence (DUI) or driving while intoxicated (DWI) is a major cause of LODD incidents. Compared to struck-by incidents, LODD incidents have a larger portion related to out-of-control vehicles. Further, this study built a logistic regression model to relate the incident characteristics to the odds of an incident being a LODD incident. The modeling result shows that tow truck drivers are associated with a greater likelihood of being involved in a news-reported LODD incident than other responders. LODD incidents are more likely to occur on early morning. Compare to entering/leaving/staying at the scene, responders are more likely to be involved in LODD event when assisting. The results offer insights into understanding the characteristics and possible reasons for first responder-involved incidents so that potential countermeasures could be developed to improve responder safety.

A hybrid clustering and random forest model to analyse vulnerable road user to motor vehicle (VRU-MV) crashes

The main goal of this study is to investigate the unobserved heterogeneity in VRU-MV crash data and to determine the relatively important contributing factors of injury severity. For this end, a latent class analysis (LCA) coupled with random parameters logit model (LCA-RPL) is developed to segment the VRU-MV crashes into relatively homogeneous clusters and to explore the differences among clusters. The random-forest-based SHapley Additive exPlanation (RF-SHAP) approach is used to explore the relative importance of the contributing factors for injury severity in each cluster. The results show that, vulnerable group (VG), intersection or not (ION) and road type (RT) clearly distinguish the crash clusters. Moto-vehicle type and functional zone have significant impact on the injury severity among all clusters. Several variables (e.g. ION, crash type [CT], season and RT) demonstrate a significant effect in a specific sub-cluster model. Results of this study provide specific and insightful countermeasures that target the contributing factors in each cluster for mitigating VRU-MV crash injury severity.

Systematic literature review of 10 years of cyclist safety research

Cyclist safety is a research field that is gaining increasing interest and attention, but still offers questions and challenges open to the scientific community. The aim of this study was to provide an exhaustive review of scientific publications in the cyclist safety field. For this purpose, Bibliometrix-R tool was used to analyse 1066 documents retrieved from Web of Science (WoS) between 2012 and 2021. The study examined published sources and productive scholars by exposing their most influential contributions, presented institutions and countries most contributing to cyclist safety and explored countries open towards international collaborations. A keywords analysis provided the most frequent author keywords in cyclist safety shown in a word cloud with E-bike, behaviour, and crash severity representing the primary keywords. Furthermore, a thematic map of cyclist safety field drafted from the author's keywords was identified. The strategic diagram is divided in four quadrants and, according to both density and centrality, the themes can be classified as follows: 1) motor themes, characterized by high value of both centrality and density; 2) niche themes, defined by high density and low centrality; 3) emerging or declining themes, featured by low value of both centrality and density; and 4) basic themes, distinguished by high centrality and low density. The motor themes (i.e., the main topics in cyclist safety field) crash severity and bike network were further explored. The research findings will be useful to develop strategies for making bike a safer and more confident form of transport as well as to guide researchers towards the future scientific knowledge.

Localizing safety performance functions for two-way STOP-controlled (TWST) three-leg intersections on rural two-lane two-way (TLTW) roadways in Alabama: A geospatial modeling approach with clustering analysis

Safety Performance Functions (SPFs) can be used to predict the number of crashes for highway facilities by site characteristics, including traffic exposures and other specific site factors. The traditional approach to developing SPFs relies on factors that are observed in the data and has an unstated assumption that the relationships between safety performance and observed factors are stationary. However, there might be factors that are not captured by the data but also have significant impacts on roadway safety performance. These factors can lead to significant unobserved heterogeneity in safety performance at different sites. Failure to capture such unobserved heterogeneity in developing SPFs may result in biases and decrease the predictive accuracy. Given the interactions between highway traffic and roadway environments, the unobserved heterogeneity is likely related to the geographic space of the highway network. This study employs a spatial modeling approach, namely Geographically Weighted Negative Binomial Regression (GWNBR), to incorporate spatial heterogeneity into SPF model estimation. The GWNBR model can generate a local SPF for every site instead of a global SPF for one entire jurisdiction (e.g., a state) from the traditional approach. Local SPFs (or l-SPFs) are high-resolution and may be difficult for practitioners to use. To support the implementation of l-SPFs, this study proposes a method to aggregate l-SPFs to various geographic levels. This study first uses the 2014-2018 geo-referenced crash data from Alabama to develop l-SPFs for two-way STOP-controlled (TWST) three-leg intersections on rural two-lane two-way (TLTW) roadways in the state. The results show that l-SPFs vary substantially across Alabama. For example, the coefficients of traffic volume (AADT) on major roads range from 0.126 to 1.203 across different areas of the state. Then, an aggregation method based on K-means clustering is demonstrated to aggregate l-SPFs to various geographic levels of interest. The l-SPFs and their aggregation provide geographic flexibility in developing countermeasures and allocating funds to improve traffic safety considering local conditions.

AI Enabled Accident Detection and Alert System Using IoT and Deep Learning for Smart Cities

As the number of vehicles increases, road accidents are on the rise every day. According to the World Health Organization (WHO) survey, 1.4 million people have died, and 50 million people have been injured worldwide every year. The key cause of death is the unavailability of medical care at the accident site or the high response time in the rescue operation. A cognitive agent-based collision detection smart accident alert and rescue system will help us to minimize delays in a rescue operation that could save many lives. With the growing popularity of smart cities, intelligent transportation systems (ITS) are drawing major interest in academia and business, and are considered as a means to improve road safety in smart cities. This article proposed an intelligent accident detection and rescue system which mimics the cognitive functions of the human mind using the Internet of Things (IoTs) and the Artificial Intelligence system (AI). An IoT kit is developed that detects the accident and collects all accident-related information, such as position, pressure, gravitational force, speed, etc., and sends it to the cloud. In the cloud, once the accident is detected, a deep learning (DL) model is used to validate the output of the IoT module and activate the rescue module. Once the accident is detected by the DL module, all the closest emergency services such as the hospital, police station, mechanics, etc., are notified. Ensemble transfer learning with dynamic weights is used to minimize the false detection rate. Due to the dataset’s unavailability, a personalized dataset is generated from the various videos available on the Internet. The proposed method is validated by a comparative analysis of ResNet and InceptionResnetV2. The experiment results show that InceptionResnetV2 provides a better performance compared to ResNet with training, validation, and a test accuracy of 98%, respectively. To measure the performance of the proposed approach in the real world, it is validated on the toy car.

Bicyclists injury severities: An empirical assessment of temporal stability

Cyclists are among the most vulnerable participants in road traffic, making their safety a top priority. Riding behavior of bicyclists could shift over time, affecting the level of injuries sustained in bicyclist-involved crashes. Many studies have been done to identify the factors influencing bicyclist injury severity, but the temporal stability of these variables over time needs further study. The temporal instability of components that affect the cyclist injury levels in bicycle collisions is explored in this paper. To obtain potential unobserved heterogeneity, yearly models of cyclist-injury levels (including potential consequences of no, minor, and severe injury) were measured separately applying a random parameters logit model that allows for potential heterogeneity in estimated parameters' means and variances. Employing a data source on bicycle collisions in Los Angeles, California, over the course of six years (January 1, 2012 to December 31, 2017), several variables which may impact the injury level of cyclists were explored. This paper has also employed a set of likelihood ratio tests assessing the temporal instability of the models. The temporal instability of the explanatory parameters has been evaluated with marginal effects. The results of the model assessment indicate that several factors may raise the chances of severe bicyclist injuries in collisions, including cyclists older than 55 years old, cyclists who were identified to be at-fault in crashes, rear-end collisions, cyclists who crossed into opposing lane before the collision, crashes occurring early mornings (i.e., 00:00 to 06:00) and so on. The results also showed that the details and estimated parameters of the model do not remain stable over the years, however the source of this instability is unclear. In addition, the findings of model estimation demonstrate that considering the heterogeneity in the random parameter means and variances will enhance the overall model fit. This study also emphasizes the significance of accounting for the transferability of estimated models and the temporal instability of parameters influencing the injury severity outcomes in order to dynamically examine the collected data and adjust safety regulations according to new observations.

Integrating machine learning into path analysis for quantifying behavioral pathways in bicycle-motor vehicle crashes

The behavioral pathways in traffic crashes describe the chained linkages among contributing factors, pre-crash road user behaviors, and crash outcomes. Bicyclists are more vulnerable than motorists on road and their pre-crash behaviors play an essential role in the pathways leading to injuries. The objective of this study is to develop a methodological framework that integrates machine learning with path analysis to quantify behavioral pathways in bicycle-motor vehicle crashes. Specifically, two sets of models are developed for predicting: 1) pre-crash behaviors given contributing factors and 2) bicyclist injury severity given contributing factors including pre-crash behaviors. The path analysis chains machine learning models to establish the indirect linkages between contributing factors and injury severities through correlates of pre-crash behaviors. This study explored five machine learning methods, including Random Forest (RF), Categorical Naive Bayes (CNB), Support vector machine (SVM), AdaBoost (Boost), and Neural network (NN). To reduce the bias of any single model, this study proposes a technique to combine model estimates by averaging marginal effects. This study used a dataset containing 9,296 bicycle-motor vehicle crashes to demonstrate the application of the framework. Across five machine learning models, the signs of marginal effects generally agree but their magnitudes vary substantially. The pre-crash behavior of "bicyclist failed to yield" increases bicyclist injury severity by 1.11%. The path analysis results highlighted contributing factors related to risky pre-crash behaviors that lead to severe injuries, such as bicyclist intoxication. The framework is expected to support agencies' decision-making to improve cycling safety by reducing unsafe behaviors on roads.

Bayesian spatial analysis of crash severity data with the INLA approach: Assessment of different identification constraints

Multinomial logit models have been widely used in the analysis of categorical crash data. When the regional information of the data is available, the dependence structure needs to be incorporated into the model to accommodate for spatial heterogeneity. We consider a Bayesian multinomial structured additive regression model to analyze categorical spatial crash data and compare its performance with a fractional split multinomial model. We use the multinomial-Poisson transformation to apply the integrated nested Laplace approximation method for fitting the proposed model efficiently and fast. Moreover, we consider two different types of identifiability constraints to deal with the inherent identifiability problem of the multinomial models. The proposed models are studied through simulated examples and applied to a road traffic crash dataset from Mazandaran province, Iran.

From the past to the future: Modeling the temporal instability of safety performance functions

In roadway safety management, safety performance functions (SPFs) are widely used by state and local agencies to predict crashes for base site conditions. SPFs are developed based on historical traffic safety data and are used to make predictions for anticipated site characteristics in the future. An underlying assumption in SPF development is that the relationships between crash frequency and site conditions are stationary from the past (when the model data were collected) to the future (for which SPFs are applied). The assumption using the past to represent the future could be fundamentally problematic. This study proposes a modeling framework that can relax this assumption. Specifically, this framework integrates temporal modeling with time-series analysis to strengthen the current SPF estimation methods. The temporal modeling approach is Temporally Weighted Negative Binomial Regression (TWNBW), and the time-series analysis is tried by employing the Seasonal Autoregressive Integrated Moving Average (SARIMA) and Artificial Neural Networks (ANN) methods. The temporal modeling is to uncover the temporal variations of SPFs and the time-series analysis explains and predicts the relationship between the SPF's temporal variation and time. The outcome of the framework is a set of Future SPFs that capture the temporal unobserved heterogeneity in safety data and describe the predicted relationships between safety performance and site characteristics in the future. A case study using six-year safety datasets from Georgia was conducted to illustrate the key components of the modeling framework. The temporal modeling results showed significant variations in SPFs across time. The parameters for traffic volume, i.e., Average Annual Daily Traffic (AADT), and segment length are associated with an increasing trend with time, and for access point density there is a descending trend. The SPF parameters are found to have a strong seasonality. Both time-series modeling methods appear to be appropriate to explain the temporal variations of SPF parameters, and the models are able to predict SPF parameters with acceptable errors smaller than 1% on average. Future SPFs can be used to support the roadway safety management that affects future traffic safety performance.

An application of in-vehicle recording technologies to analyze injury severity in crashes between taxis and two-wheelers

Conventionally, the crash data used in traffic safety analysis have been collected by the police dispatched to the crash scene. Therefore, crash information inevitably includes errors that influence traffic safety analysis. Such errors can include the crash speed, crash time, crash location, and other crash characteristics. The advances in in-vehicle video recording (IVVR) technologies have recently enabled traffic safety professionals to use more accurate crash information based on crash data reconstruction methods. Although a few studies have been conducted to identify the factors affecting the crash injury severity using such detailed crash data, there was no effort to analyze the factors affecting the injury severity in crashes between taxis and two-wheelers (TWs), including bicycles and motorcycles. Therefore, this study analyzes the injury severity of TW riders in taxi-TW crashes with the accurate crash data collected by taxis equipped with IVVR devices in Incheon, Korea. Two hundred and forty-eight crash data from two years (2010-2011) were used to perform this objective. The factors affecting the injury severity to TW riders were identified based on a partial proportional odds model for these data. Seven variables were found to affect the injury severity significantly: crash speed, second collision, third collision, Delta-V, crashes that occurred with a non-helmeted motorcycle rider, crashes where the collision type was sideswipe, and crashes under rainy or snowy weather conditions. On the other hand, two variables regarding crashes, where the taxi driver behavior helped reduce visible and severe injuries, were changing lanes and the young TW riders (<18 years).

Spatiotemporal analysis of crash severity on rural highway: A case study in Anhui, China

Traffic crashes are the result of the interaction between human activities and different socio-economic, geographical, and environmental factors, showing a temporal and spatial relationship. The temporal and spatial correlations must be characterized in crash severity studies, for which the geographically and temporally weighted ordered logistic regression (GTWOLR) model is an effective approach. However, existing studies using the GTWOLR model only subjectively selected a type of kernel function and kernel bandwidth, which cannot determine the best expression of the spatiotemporal relationship between crashes. This paper explores the optimal kernel function and kernel bandwidth considering the aforementioned problem to obtain the best GTWOLR model to analyze the crash data based on the crash data of rural highways in Anhui Province, China, from 2014 to 2017. First, the GTWOLR models with Gaussian or Bi-square kernel function and fixed (the spatiotemporal distance remains constant of local sample) or adaptive (the quantity of the local sample is constant) bandwidth are compared. Second, the log-likelihood and Akaike information criterion are used to compare the GTWOLR model with the ordered logistic regression (OLR) model. Finally, the spatial and temporal characteristics of the contributing factors in the best GTWOLR model are analyzed, and corresponding countermeasures for improving traffic safety on rural highways are proposed. Model comparison results reveal that although the difference was insignificant, the Bi-square kernel function with fixed bandwidth (BF)- GTWOLR model has a better goodness of fit than the GTWOLR models with other types of kernel function and bandwidth and the OLR model. The BF-GTWOLR model estimation results showed that eight factors, including pedestrian-vehicle crash, middle-aged driver, hit-and-run, truck, motorcycle, curve, slope and mountainous, passed the non-stationary test, indicating their varying effects on the crash severity across space and over time. As a crash severity modeling approach that effectively quantifies the spatiotemporal relationships in crashes, the BF-GTWOLR model, which adapts to crash data, may have implications for future research. In addition, the findings of this paper can help traffic management departments to propose progressive and targeted policies or countermeasures, so as to reduce the severity of rural highway crashes.

Using latent class clustering and binary logistic regression to model Australian cyclist injury severity in motor vehicle-bicycle crashes

INTRODUCTION

In recent years, Australia is seeing an increase in the total number of cyclists. However, the rise of serious injuries and fatalities to cyclists has been a major concern. Understanding the factors affecting the fatalities and injuries of bicyclists in crashes with motor vehicles is important to develop effective policy measures aimed at improving the safety of bicyclists. This study aims to identify the factors affecting motor vehicle-bicycle (MVB) crashes in Victoria, Australia and introducing effective countermeasures for the identified risk factors.

METHOD

A data set of 14,759 MVB crash records from Victoria, Australia between 2006 and 2019 was analyzed using the binary logit model and latent class clustering.

RESULTS

It was observed that the factors that increase the risk of fatalities and serious injuries of bicyclists (FSI) in all clusters are: elderly bicyclist, not using a helmet, and darkness condition. Likewise, in areas with no traffic control, clear weather, and dry surface condition (cluster 1), high speed limits increase the risk of FSI, but the occurrence of MVB crashes in cross intersection and T-intersection has been significantly associated with a reduction in the risk of FSI. In areas with traffic control and unfavorable weather conditions (cluster 2), wet road surface increases the risk of FSI, but the areas with give way sign and pedestrian crossing signs reduce the risk of FSI. Practical Applications: Recommendations to reduce the risk of fatalities or serious injury to bicyclists are: improvement of road lighting and more exposure of bicyclists using reflective clothing and reflectors, separation of the bicycle and vehicle path in mid blocks especially in high-speed areas, using a more stable bicycle for the older people, monitoring helmet use, improving autonomous emergency braking, and using bicyclist detection technology for vehicles.

Understanding how relationships between crash frequency and correlates vary for multilane rural highways: Estimating geographically and temporally weighted regression models

Safety Performance Functions (SPFs) are critical tools in the management of highway safety projects. SPFs are used to predict the average number of crashes per year at a location, such as a road segment or an intersection. The Highway Safety Manual (HSM) provides default safety performance functions (SPFs), but it is recommended that states in the U.S. develop jurisdiction-specific SPFs using local crash data. To do this for the state of Tennessee, crash and road inventory data were integrated for multi-lane rural highway segments for the years 2013-2017. In addition to developing SPFs similar to those contained in the HSM, this study applied a new methodology to capture variation in crashes in both space and time. Specifically, Geographically and Temporally Weighted Regression (GTWR) models for the localization of SPFs were developed. The new methodology incorporates temporal aspects of crashes in the models because the impact of a specific variable on crash frequency may vary over time due to several reasons. Results indicate that GTWR models remarkably outperform the traditional regression models by capturing spatio-temporal heterogeneity. Most parameter estimates were found to vary substantially across space and time. In other words, the association of contributing variables with the number of crashes can vary from one region or period of time to another. This finding weakens the idea of transferring default SPFs to other states and applying a single localized SPF to all regions of a state. Enabled by growing computational power, these results emphasize the importance of accounting for spatial and temporal heterogeneity and developing highly localized SPFs. The methodology of this study can be used by researchers to follow the temporal trend and location of critical factors to identify sites for safety improvements.

A spatiotemporal analysis of motorcyclist injury severity: Findings from 20 years of crash data from Pennsylvania

Motorcyclists face higher risks of severe injuries in crashes compared to motor vehicle drivers who are often protected by seatbelts and airbags during collisions. A report by the National Highway Traffic Safety Administration reveals that motorcyclists have 27 times the risk of fatality in traffic crashes as much as motor vehicle drivers. Previous studies have identified a list of risk factors associated with motorcyclist injury severity and generated valuable insights for countermeasures to protect motorcyclists in crashes. These studies have shown that wearing helmets and/or motorcycle-specific reflective clothing and boots, driving alcohol/drug-free, and obeying traffic regulations are good practices for safe motorcycling. However, these practices and other risk factors are likely to interact with local geographic, socio-economic, and cultural contexts, leading to diversified correlations with motorcyclist injury severity, which remains under-explored. Such correlations may exhibit variations across space and time. The objective of this study is to revisit the correlates of motorcyclist injury severity with a focus on the spatial and temporal variations of correlations between risk factors and injury severity. This study employed an integrated spatiotemporal analytical approach to mine comprehensive statewide 20 years' motorcycle-involved traffic crashes (N = 50,823) in Pennsylvania. Non-stationarity tests were performed to examine the significance of variations in spatially and temporally local correlations. The results show that most factors, such as helmet, engine size, vehicle age, pillion passenger, at-fault striking, and speeding, hold significant non-stationary relationships with motorcyclist injury severity. Furthermore, cluster analysis of estimations reveals the regional similarities of correlates, which may help practitioners develop regional motorcyclist safety countermeasures.

Analysis of the severity of vehicle-bicycle crashes with data mining techniques

INTRODUCTION

Although cycling is increasingly being promoted for transportation, the safety concern of bicyclists is one of the major impediments to their adoption. A thorough investigation on the contributing factors to fatalities and injuries involving bicyclist.

METHOD

This paper designs an integrated data mining framework to determine the significant factors that contribute to the severity of vehicle-bicycle crashes based on the crash dataset of Victorian, Australia (2013-2018). The framework integrates imbalanced data resampling, learning-based feature extraction with gradient boosting algorithm and marginal effect analysis. The top 10 significant predictors of the severity of vehicle-bicycle crashes are extracted, which gives an area under ROC curve (AUC) value of 0.8236 and computing time as 37.8 s.

RESULTS

The findings provide insights for understanding and developing countermeasures or policy initiatives to reduce severe vehicle-bicycle crashes.

Exploring bicyclist injury severity in bicycle-vehicle crashes using latent class clustering analysis and partial proportional odds models

INTRODUCTION

Bicyclists are more vulnerable compared to other road users. Therefore, it is critical to investigate the contributing factors to bicyclist injury severity to help provide better biking environment and improve biking safety. According to the data provided by National Highway Traffic Safety Administration (NHTSA), a total of 8,028 bicyclists were killed in bicycle-vehicle crashes from 2007 to 2017. The number of fatal bicyclists had increased rapidly by approximately 11.70% during the past 10 years (NHTSA, 2019).

METHODS

This paper conducts a latent class clustering analysis based on the police reported bicycle-vehicle crash data collected from 2007 to 2014 in North Carolina to identify the heterogeneity inherent in the crash data. First, the most appropriate number of clusters is determined in which each cluster has been characterized by the distribution of the featured variables. Then, partial proportional odds models are developed for each cluster to further analyze the impacts on bicyclist injury severity for specific crash patterns.

RESULTS

Marginal effects are calculated and used to evaluate and interpret the effect of each significant explanatory variable. The model results reveal that variables could have different influence on the bicyclist injury severity between clusters, and that some variables only have significant impacts on particular clusters.

CONCLUSIONS

The results clearly indicate that it is essential to conduct latent class clustering analysis to investigate the impact of explanatory variables on bicyclist injury severity considering unobserved or latent features. In addition, the latent class clustering is found to be able to provide more accurate and insightful information on the bicyclist injury severity analysis. Practical Applications: In order to improve biking safety, regulations need to be established to prevent drinking and lights need to be provided since alcohol and lighting condition are significant factors in severe injuries according to the modeling results.

An integrated spatio-temporal approach to examine the consequences of driving under the influence (DUI) in crashes

Driving under the influence (DUI) is illegal in the United States because a driver's mental and motor skills can be seriously impaired by alcohol or drugs. Consequently, DUI violators' involvement in severe crashes is high. Motivated by the spatial and temporal nature of traffic crashes, this study introduces an integrated spatio-temporal approach to analyzing highway safety data. Specifically, this study estimates Geographically and Temporally Weighted Regression (GTWR) models to understand the consequences of DUI in crashes. GTWR can theoretically outperform traditional regression methods by accounting for unobserved heterogeneity that may be related to the location and time of a crash. Using Southeast Michigan crash data, this study finds that DUI is associated with a 25% higher likelihood of injury in a crash. The association between injury severity and DUI varies significantly across space and time. From the spatial aspect, DUI crashes in rural or small-town areas are more likely to cause injuries than urban crashes. From the temporal aspect, different times are associated with varying relationships between injury severity and DUI. If focusing on DUI crashes in late nights and early mornings, on Fridays, the entire northeast part from Clinton Charter Township to Port Huron is associated with severer injuries than other regions including Detroit's urban area and its south. On Mondays, the DUI crashes in the northwest are also more likely to cause severe injuries. The methodology introduced in this study takes advantage of modern computational tools and localized crash/inventory data. This method offers researchers and practitioners an opportunity to understand highway safety outcomes in great spatial and temporal details and customize safety countermeasures for specific locations and times such as saturation patrols.

The novel approaches to classify cyclist accident injury-severity: Hybrid fuzzy decision mechanisms

In this study, two novel fuzzy decision approaches, where the fuzzy logic (FL) model was revised with the C4.5 decision tree (DT) algorithm, were applied to the classification of cyclist injury-severity in bicycle-vehicle accidents. The study aims to evaluate two main research topics. The first one is investigation of the effect of road infrastructure, road geometry, street, accident, atmospheric and cyclist related parameters on the classification of cyclist injury-severity similarly to other studies in the literature. The second one is examination of the performance of the new fuzzy decision approaches described in detail in this study for the classification of cyclist injury-severity. For this purpose, the data set containing bicycle-vehicle accidents in 2013-2017 was analyzed with the classic C4.5 algorithm and two different hybrid fuzzy decision mechanisms, namely DT-based converted FL (DT-CFL) and novel DT-based revised FL (DT-RFL). The model performances were compared according to their accuracy, precision, recall, and F-measure values. The results indicated that the parameters that have the greatest effect on the injury-severity in bicycle-vehicle accidents are gender, vehicle damage-extent, road-type as well as the highly effective parameters such as pavement type, accident type, and vehicle-movement. The most successful classification performance among the three models was achieved by the DT-RFL model with 72.0 % F-measure and 69.96 % Accuracy. With 59.22 % accuracy and %57.5 F-measure values, the DT-CFL model, rules of which were created according to the splitting criteria of C4.5 algorithm, gave worse results in the classification of the injury-severity in bicycle-vehicle accidents than the classical C4.5 algorithm. In light of these results, the use of fuzzy decision mechanism models presented in this study on more comprehensive datasets is recommended for further studies.

Is the front passenger seat always the "death seat"? An application of a hierarchical ordered probit model for occupant injury severity

Although many studies have investigated the correlations between injury severities and seat positions, few researchers explored the correlates of injury severities (e.g., seat positions) within a crash that results in multiple occupant injuries. Therefore, we examine the injury correlates within and between crashes, and study the correlations between seat positions and occupant injury severity by constructing a hierarchical ordered probit model. A total of 20,327 occupant injuries in 16,405 motor vehicle crashes in South Australia (2012 - 2016) are used. The results of this study indicate that the rear left passenger seat is associated with a 7.66% higher chance of getting injured (including moderate and severe injury), and the front left passenger seat is associated with a 2.94% higher chance of getting injured compared with the driver seat. Besides, the higher injury chances for other passenger seats including the rear right and rear middle seats are 4.97% and 4.74%, respectively, compared with the driver seat. Thus, this study offers passengers insightful suggestions about how to protect themselves by choosing the right passenger seat in a vehicle.