Crash Severity Research Articles

Analysis of dynamic determinants of vehicles involved in crash affecting severity based on in-depth crash data

Objective The dynamic characteristics of vehicles involved in crashes may be an important factor affecting the crash severity. This study investigates the relationship between the dynamic characteristics of vehicles involved in crashes in the five seconds before the occurrence and the crash severity. The findings aim to offer insights for preventing severe crashes and advancing autonomous vehicle technology. Methods This study aims to investigate the impact of dynamic features, such as speed, acceleration, and relative distance of vehicles involved in the crash in the five seconds before the crash, on the crash severity. Five hundred ninety-six crash samples from the China In-depth Mobility Safety Study-Traffic Accident database were selected for crash reconstruction. A random parameters logit model was used to extract and analyze the effect of dynamic features of the vehicles involved in the crash on the crash severity. Results The random parameters logit model demonstrated a satisfactory fit. Analysis of the parameter estimation results of the model showed that the variables of speed, acceleration, and relative distance between vehicles involved in the crash at some time points during the five seconds before the crash significantly affected the crash severity. Notably, the coefficient of variation of relative distance over 5 s emerged as the most influential positive determinant of the crash severity. Conclusions Certain dynamic characteristics of vehicles involved in a crash in the five seconds before a crash significantly impact the crash severity. The study’s findings can serve as a reference for preventing severe crashes and advancing the development of autonomous vehicles.

Comparison of supervised ML algorithms for road traffic crash prediction models in Rwanda

The development of Rwanda was accompanied by rapid growth of various modes of transport and the occurrence of road traffic crashes (RTCs). RTC severity has also increased in Rwanda, with the number of fatalities increasing progressively every year. The aim of this study was to compare the classification performance of eight supervised machine learning (ML) algorithms in order to determine the best one to predict crash severity and identify potential RTC-influencing factors in Rwanda. Quantitative data sets of RTCs, numbers of registered vehicles and annual average daily traffic (AADT) from 2010 to 2022 were used. The ML algorithms examined were logistic regression (LR), support vector machine (SVM), naive Bayes (NB), K-nearest neighbour (KNN), random forest (RF), decision table (DT), lazy Bayesian rules (LBR) and J48. Five algorithms (RF, DT, J48, LBR and KNN classifiers) were found to have an accuracy of more than 80%. The RF classifier was found to have the best performance for predicting crash severity in Rwanda, with an accuracy of more than 97%. The most influential factors were identified as AADT, number of registered vehicles, causes of crashes and the type of vehicles involved. The model results can be used to provide useful information to road safety decision makers during the planning and design of road infrastructure.

Multilevel Discrete Outcome Modeling for Crash Severity: A Novel Approach for Crash Severity Models

Combining a total crash count model and a crash severity probability model simultaneously to predict crashes by severity is challenging because crash count models are implemented at an aggregate scale, that is, by sites (segments or intersections), while crash severity probability models are at a disaggregate scale, that is, by crashes or persons (drivers or occupants). This study develops a multilevel discrete outcome modeling framework to estimate crash counts by severity for California, U.S., rural four-lane divided highways by estimating and combining three models: a univariate count model for total crashes at the site level predicts total crash counts; an ordered logit discrete outcome crash severity prediction model at the crash-level predicts proportion of crashes by severity; and a proportional regression connection model that predicts proportion of groups of drivers and vehicles to connect the other two models. The combination of all three models provides crash counts by severity at the site level considering both aggregate and disaggregate factors. The prediction from the multilevel discrete outcome model is compared with predictions made by traditional univariate count models by severity for accuracy and transferability using estimation and validation data. Based on the estimation data, the multilevel discrete outcome model predicts injury and fatal crashes more accurately than the univariate count model. For validation data, the multilevel model has slightly better prediction accuracy for minor and possible injuries. Finally, the calibration factor indicates the multilevel discrete outcome model is more transferable than the univariate count model.

An optimisation model to locate level crossings in railway lines at mines to minimise the total weighted-walked distance

The location of level crossings for pedestrian circulation is a safety issue due to potential human losses and material damage. This problem has become a concern in urban and industrial environments due to the characteristics of rail systems and unsafe pedestrian behaviour. Research reveals that psychological and infrastructural factors influence pedestrians' decision-making when crossing railroad lines. One of these is the convenience that leads pedestrians to cross at the nearest point. However, investigations to date only study the impact of location on the risk and severity of crashes and pedestrian rule violations. The current research is quasi-experimental, i.e., no optimisation tool has been developed to determine which crossing points pedestrians should follow. Therefore, this research develops a mathematical model for locating level crossings at railways to minimise the total weighted-walked distance. A genetic algorithm was proposed for solving the model, especially for large-size problems. The algorithm parameters were calibrated using the design of experiments and ten instances based on the characteristics of the area under study. The obtained results provide (1) the location of the level crossings and (2) the route pedestrians should follow for each origin-destination pair based on the facilities adjacent to the rail lines. A sensitivity analysis was performed using the ten instances to determine how the location of the level crossings changes with modifications in the facilities' location. Results showed that the model provides alternative solutions according to the problem's size. This study delivers a methodology for practitioners and stakeholders of transportation systems.

Promoting Emergency Medical Service Infrastructure Equality to Reduce Road Crash Fatalities

Timely emergency medical service (EMS) is critical to mitigate outcomes of severe traffic crashes, especially in rural areas. The urban–rural inequality of the EMS infrastructure has been one of the factors contributing to a higher death rate for patients in rural road crashes. To address the spatial imbalance of EMS infrastructure, this study aimed to provide a methodological framework for evaluating the existing EMS infrastructure by taking South Korea’s EMS infrastructure expansion plans as the case study. Specifically, this study developed a road crash data-driven methodology to promote spatial balance and economical expansion of EMS infrastructure of all types, including EMS stations, hospitals, the helicopter fleet, and landing spots. Geographically weighted binary logit regression and spatial analysis identified strategic locations for prioritizing the EMS infrastructure expansion using crash victim data and road networks to close the gap between urban and rural areas. The analysis of access to existing EMS infrastructure showed that the 16 to 20 min EMS response time, including on-scene time and transport time ranging from 11 to 15 min, are significantly associated with higher crash fatalities. The results also suggested that EMS stations and heliports are inadequate to meet the EMS time thresholds in the central province of Korea. The findings of this research could inform policymakers as they are working toward expanding the EMS infrastructure and creating a more equitable EMS response when it comes to transporting rural road crash patients.

Qualitatively and quantitatively explore injury severity of light motor vehicle drivers involved in heavy goods vehicle crashes

ABSTRACT Crashes involving heavy goods trucks (HGVs) are of significant concern as it poses a higher risk of fatality to light motor vehicles (LMVs). The study constructs three Deep Forest models with different Cascade structures to explore the relationship between HGV-LMV crash severity and risk factors. Based on the HGV-LMV crash data in Shandong province, China, motorcycles, electric vehicles, and sedans are defined as the LMV. According to the comparison results, the Deep Forest with Cascade LightGBM is significantly better. Through model interpretability tools, the study found that motorcycle and electric vehicle drivers aged 58 to 86, and LMV drivers with 1 to 3 years of driving experience are more likely suffering severity and fatal injury (SFI) in HGV-LMV crashes. And, disobey traffic sign, illegal turning, overtaking, changing lane, and crashes happened on non-motorway, national and provincial roads have an positive effect on SFI.

Predicting pedestrian-involved crash severity using inception-v3 deep learning model

This research leverages a novel deep learning model, Inception-v3, to predict pedestrian crash severity using data collected over five years (2016–2021) from Louisiana. The final dataset incorporates forty different variables related to pedestrian attributes, environmental conditions, and vehicular specifics. Crash severity was classified into three categories: fatal, injury, and no injury. The Boruta algorithm was applied to determine the importance of variables and investigate contributing factors to pedestrian crash severity, revealing several associated aspects, including pedestrian gender, pedestrian and driver impairment, posted speed limits, alcohol involvement, pedestrian age, visibility obstruction, roadway lighting conditions, and both pedestrian and driver conditions, including distraction and inattentiveness. To address data imbalance, the study employed Random Under Sampling (RUS) and the Synthetic Minority Oversampling Technique (SMOTE). The DeepInsight technique transformed numeric data into images. Subsequently, five crash severity prediction models were developed with Inception-v3, considering various scenarios, including original, under-sampled, over-sampled, a combination of under and over-sampled data, and the top twenty-five important variables. Results indicated that the model applying both over and under sampling outperforms models based on other data balancing techniques in terms of several performance metrics, including accuracy, sensitivity, precision, specificity, false negative ratio (FNR), false positive ratio (FPR), and F1-score. This model achieved prediction accuracies of 93.5%, 77.5%, and 85.9% for fatal, injury, and no injury categories, respectively. Additionally, comparative analysis based on several performance metrics and McNemar’s tests demonstrated that the predictive performance of the Inception-v3 deep learning model is statistically superior compared to traditional machine learning and statistical models. The insights from this research can be effectively harnessed by safety professionals, emergency service providers, traffic management centers, and vehicle manufacturers to enhance their safety measures and applications.

Modeling of single-vehicle and multi-vehicle truck-involved crashes injury severities: A comparative and temporal analysis in a developing country

Truck-involved crashes persist as a significant concern, yielding noteworthy human casualties and causing economic ramifications, particularly in developing countries. This paper aims to undertake a comprehensive analysis of the associated factors influencing injury severity in truck-involved crashes, with a particular emphasis on discerning variations between single-vehicle and multi-vehicle incidents, as well as accounting for heterogeneity and temporal stability. The data analysis involves a meticulous examination of crash data spanning the entirety of Thailand from 2017 to 2020. Employing three distinct levels of injury severities, namely PDO injury, moderate injury, and severe injury, the study employs a series of mixed logit models that account for unobserved heterogeneity in both means and variances. Results revealed significant instability in injury risk determinants over time among both single and multi-vehicle events. Aligning predictive assessments further spotlighted fluctuations in projected burdens across models and years – collectively underscoring the imperative to integrate temporal considerations into modeling and prevention. Several crash-type distinctions and priorities emerged. For single-truck events, key risks included roadway alignments and geometry, speeding, fatigue, and lighting conditions. However multi-truck collisions concentrated around exposure factors like highway traits, sightline limitations, and vulnerable road users. Ultimately, the technique permitted responsive countermeasure targeting and recalibration opportunities keyed to each crash form’s evolving landscapes. While it is indeed noteworthy that several variables have exhibited instability in their effects, it is equally important to acknowledge the existence of certain variables that maintain a relative degree of temporal stability. This underscores their pivotal role in shaping the foundation of enduring strategies aimed at enhancing traffic safety in the long run. The multifaceted investigation constitutes an invaluable reference for diverse transportation stakeholders seeking to curb rising truck fatalities through evidence-based improvements in policy, engineering, usage protocols, and technologies. It provides a blueprint for nimble safety planning within complex modernizing road systems.

Injury severity of police officers involved in traffic crashes: A spatial analysis of Alabama

Traffic crashes are the leading cause of injuries and deaths for police officers in the US. There has been limited research to investigate the characteristics of traffic crashes that involve police officers. This study aims to investigate the relationships between different independent variables and police officer injury severity in traffic crashes. Considering the inherent spatial correlation between traffic crashes and the geographical environment, this study employs the ordered logit regression and the Geographically Weighted Ordered Logistic Regression (GWOLR) approach to identify the contributing factors of police officers’ injuries in traffic crashes and to quantify the correlates of police injury severity in crashes. This study explored traffic crashes of five years (Number of observations = 4,231) that involved police officers in the State of Alabama. The results of the global ordered logit model illustrated that some independent variables, such as pre-crash behaviors, holiday, and road type, are statistically significantly related to police officer crash injury severity. Also, some variables, such as pre-crash behaviors and seatbelt usage, passed the non-stationarity tests. This suggests significant spatial variations in their relationships with the severity of injuries sustained by police officers in traffic crashes. The local correlates of police injury severity are valuable information for law enforcement agencies to localize strategies for improving officer safety on the road. For example, Move-over laws may need to be enhanced in the southeast Alabama area, where failing to yield (to police officers) seems to lead to increased traffic injury severities of police officers compared to other areas in Alabama.

Impact of real-time weather conditions on crash injury severity in Kentucky using the correlated random parameters logit model with heterogeneity in means

The present study investigated the impact of real-time weather (air temperature, relative humidity, precipitation, wind speed, and solar radiation) on crash injury severity. Recent crash data (January 2016 to April 2021) on Interstate-75 in the state of Kentucky were merged with real-time weather information (retrieved from Kentucky Mesonet stations) at the 1-hour level. The severity index “SI” (i.e., the ratio of percent severe crashes to percent exposure of a specific weather state during the crash period) was introduced to evaluate the impact of different real-time weather states on fatal and severe injury crashes. Furthermore, the standard mixed logit (MXL), correlated mixed logit (CMXL), and correlated mixed logit with heterogeneity in means (CMXLHM) models were fitted and compared to identify the risk factors contributing to crash injury severity while accounting for unobserved heterogeneity. The results showed that the CMXLHM model was statistically superior to the CMXL and MXL models based on various goodness-of-fit measures (e.g., Akaike information criterion “AIC” and McFadden pseudo R-squared). Results from the SI analysis and CMXLHM model showed that real-time weather-related factors (e.g., air temperature ≥ 70 0F and relative humidity ≥ 90 %) were significantly associated with higher severe injury likelihood. Further, driving under the influence (DUI), young drivers, and vehicle travel speed were associated with greater injury severities. On the other hand, presence of horizontal curve, passenger cars, and hourly traffic volume were associated with lower injury severity likelihood. The study outcomes can help in incident management by suggesting specific real-time weather-related states to feed to dynamic message signs (DMS) to enhance travelers’ safety along the interstates.

Factors affecting injury severity in motorcycle crashes: Different age groups analysis using Catboost and SHAP techniques

Objective Motorcycle crashes often result in severe injuries on roads that affect people’s lives physically, financially, and psychologically. These injuries could be notably harmful to drivers of all age groups. The main objective of this study is to investigate the risk factors contributing to the severity of crash injuries in different age groups. Methods This Objective is achieved by developing accurate machine learning (ML) based prediction models. This research examines the relationship between potential risk factors of motorcycle-associated crashes using (ML) and Shapley Additive explanations (SHAP) technique. The SHAP technique further helped interpreting ML methods for traffic injury severity prediction. It indicates the significant non-linear interactions between dependent and independent variables. The data for this study was collected from the Provincial Emergency Response Service RESCUE 1122 for the Rawalpindi region (Pakistan) over three years (from 2017 to 2020). The Synthetic Minority Oversampling Technique (SMOTE) is employed to balance injury severity classes in the pre-processing phase. Results The results demonstrate that age, gender, posted speed limit, the number of lanes, and month of the year are positively associated with severe and fatal injuries. This research also assesses how the modeling framework varies between the ML and classical statistical methods. The predictive performance of proposed ML models was assessed using several evaluation metrics, and it is found that Catboost outperformed the XGBoost, Random Forest (RF) and Multinomial Logit (MNL) model. Conclusion The findings of this study will assist road users, road safety authorities, stakeholders, policymakers, and decision-makers in obtaining substantial and essential guidance for reducing the severity of crash injuries in Pakistan and other countries with prevailing conditions.

Assessing crash severity of urban roads with data mining techniques using big data from in-vehicle dashcam

<abstract> <p>The factors that affect the severity of crashes must be identified for pedestrian and traffic safety in urban roads. Specifically, in the case of urban road crashes, these crashes occur due to the complex interaction of various factors. Therefore, it is necessary to collect high-quality data that can derive these various factors. Accordingly, this study collected crash data, which included detailed crash factor data on the huge urban and mid-level roads. Using this, various crash factors including driver, vehicle, road, environment, and crash characteristics are constructed to develop a crash severity prediction model. Through this, this study identified more detailed factors affecting the severity of urban road crashes. The crash severity model was developed using both machine learning and statistical models because the insights that can be obtained from the latest technology and traditional methods are different. Therefore, the binary logit model, a support vector machine, and extreme gradient boosting were developed using key variables derived from the multiple correspondence analysis and Boruta-SHapley Additive exPlanations. The main result of this study shows that the crash severity decreased at four-street intersections and when traffic segregation facilities were installed. The findings of this study can be used to establish a traffic safety management strategy to reduce the severity of crashes on urban roads.</p> </abstract>

Examination of factors associated with the temporal stability assessment of crash severity by using generalised linear model-A case study.

Road crashes are a major public safety concern in Pakistan. Prior studies in Pakistan investigated the impact of different factors on road crashes but did not consider the temporal stability of crash data. This means that the recommendations based on these studies are not fully effective, as the impact of certain factors may change over time. To address this gap in the literature, this study aims to identify the factors contributing to crash severity in road crashes and examine how their impact varies over time. In this comprehensive study, we utilized Generalised Linear Model (GLM) on the crash data between the years 2013 to 2017, encompassing a total sample of 802 road crashes occurred on the N-5 road section in Pakistan, a 429-kilometer stretch connecting two big cities of Pakistan, i.e., Peshawar and Lahore. The purpose of the GLM was to quantify the temporal stability of the factors contributing crash severity in each year from 2013 to 2017. Within this dataset, 60% (n = 471) were fatal crashes, while the remaining 40% (n = 321) were non-fatal. The results revealed that the factors including the day of the week, the location of the crashes, weather conditions, causes of the crashes, and the types of vehicles involved, exhibited the temporal instability over time. In summary, our study provides in-depth insights aimed at reducing crash severity and potentially aiding in the development of effective crash mitigation policies in Pakistan and other nations having similar road safety problems. This research holds great promise in exploring the dynamic safety implications of emerging transportation technologies, particularly in the context of the widespread adoption of connected and autonomous vehicles.

Lane numbers and their impact on commercial motor vehicle crash safety: An econometric perspective

This research investigates the intricate relationship between the number of lanes on highways and injury severities sustained by commercial motor vehicle (CMV) drivers. Many studies have addressed crash determinants, but the safety implications of differing numbers of lanes remain insufficiently examined, especially during the highway planning stages. Our study fills this knowledge gap by analyzing injury severity crash factors for a varied number of lane scenarios. Employing a random parameters logit modeling framework, we differentiated injury levels for 2–4 lanes and 6–10 lanes. Key factors were identified for each number of lanes, with older, loss of vehicle control, non-collision crashes, and crashes on locations where grade or hill existed being more perilous and increasing the risk of sustaining severe injuries on 2-lane highways. For 4-lane highways, factors such as non-Oregonian drivers, older drivers, crashes that occurred during the spring season, and crashes that occurred beyond shoulders were associated with an elevated probability of being involved in severe injury crashes. Regarding highways with 6 lanes and higher, driving too fast for conditions and driver error (drowsy, fatigued, inattentive, or reckless) increases the odds of being involved in higher levels of injury crashes. To enhance truck driver safety, we recommend the implementation of electronic stability control in CMVs, moderated speeds on graded sections, improved curve markers, and robust public safety campaigns.

Addressing imbalanced data in predicting injury severity after traffic crashes: A comparative analysis of machine learning models

Road traffic crashes are a significant public health concern, leading to substantial human and financial losses. Accurately predicting injury severity is crucial for optimizing rescue efforts and saving lives. This study utilizes various Machine Learning (ML) algorithms, such as Random Forest, Logistic Regression, XGBoost, and Support Vector Machine (SVM), to predict crash severity. The dataset spans from 2015 to 2023, comprising crash data from the City of Chicago, featuring a highly imbalanced ratio of non-severe to severe incidents (1000 to 1). To address class imbalance challenges, the study evaluates various data sampling methods, including Oversampling, Undersampling, and Hybridsampling. Model performance is assessed using AUC-ROC and recall to account for accuracy limitations in imbalanced datasets. Results reveal the inefficacy of conventional data sampling methods where data is highly imbalanced. Consequently, a novel approach was adopted, involving the random removal of observations before applying data sampling methods, leading to a significant improvement in model performance. SVM-SMOTE and ClusterCentroid emerge as the most effective resampling methods. Notably, among all ML models, SVM demonstrates the best overall performance. The final findings of this study aim to assist emergency responders in quickly evaluating the severity of an incident upon receiving a report.

Effect of emergency medical service response time on fatality risk of freeway crashes: Bayesian random parameters spatial logistic approach.

Emergency medical service (EMS) serves as a pivotal role in linking injured road users to hospitals via offering first aid measures and transportation. This paper aims to investigate the effect of emergency medical service (EMS) response time on the fatality risk of freeway crashes. Crash injury severity data from Kaiyang Freeway, China in 2014 and 2015 are employed for the empirical investigation. A Bayesian random parameters spatial logistic model is developed for analyzing crash severity. Bayesian inference of the random parameters spatial logistic model demonstrates the importance of reducing EMS response time on minimizing the fatality risk of freeway crashes. Fatality odds would increase by 2.6% for 1 min increase in EMS response time. Additionally, vehicle type, crash type, time of day, horizontal curvature, vertical grade, and precipitation are also found to have significant effects on the fatality probability of freeway crashes. It is crucial to reduce EMS response time to decrease the fatality likelihood of freeway crashes. Some countermeasures have been proposed to shorten EMS response time.

Road Traffic Crash Severity Analysis: A Bayesian-Optimized Dynamic Ensemble Selection Guided by Instance Hardness and Region of Competence Strategy

Road Traffic Crash Severity Analysis: A Bayesian-Optimized Dynamic Ensemble Selection Guided by Instance Hardness and Region of Competence Strategy

Assessment of Large Trucks Crash Severity on a Rural Interstate Road in Wyoming Using Decision Trees and Structural Equation Model

Assessment of Large Trucks Crash Severity on a Rural Interstate Road in Wyoming Using Decision Trees and Structural Equation Model

Modeling Crashes Severity Using Ensemble Techniques

Traffic crashes are modelled using different techniques and contributing factors. In this work, several ensemble machine learning algorithms were used to model crash severity at urban roundabouts using data from 15 roundabouts in Jordan. The original dataset covers four years, from 2017 to 2021. A total of 15 variables were collected and used in this work. Results indicated that ten variables are important. The various models show their ability to classify traffic crash severity with a high overall accuracy range from 96% to 98%. Results indicated that driver fault and age are the most significant contributing factors for crash severity.

Investigating effective factors on rural crash severity at marginal areas around cities in Iran: a partial proportional odds modelling approach

Over the past decade, rural crashes have been responsible for an average of 65% of crash-induced casualties in Iran. Evidence from prior studies reveals that a significant number of these rural crashes occur at marginal areas around cities. Thus, Exclusive crash severity models should be developed to identify the factors associated with higher injury and fatality probabilities in these areas. In this study, a partial proportional odds (PPO) model was formulated using the rural crash data collected from roads leading to the city of Isfahan. The PPO model holds the ordinal nature of crash observations and allows for different influences of independent variables on various crash severity levels. Insights derived from the results reveal that factors such as vehicle traffic maintaining an average speed exceeding 95 km/h, the occurrence of multi-vehicle crashes, the incidence of overturn-type crashes, the at-fault vehicle being a truck/trailer and at-fault or not-at-fault vehicle being a motorcycle, increase the likelihood of more severe rural crashes. Conversely, a foreign vehicle being at-fault, and the driver of the at-fault vehicle aged between 30 and 40 years, tend to diminish the occurrence of severe crashes at marginal areas around cities.