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

Investigating built environment and traffic flow impact on crash frequency in urban road networks

While numerous studies have examined the factors that influence crash occurrence, there remains a gap in understanding the intricate relationship between built environment, traffic flow, and crash occurrences across different spatial units. This study explores how built environment attributes, and dynamic traffic flow characteristics affect crash frequency by focusing on proposed traffic density-based zones (TDZs). Utilizing a comprehensive dataset from Greater Melbourne, Australia, this research emphasizes on the dynamic traffic flow variables and insights from the Macroscopic Fundamental Diagram model, considering parameters such as shockwave velocity and congestion index. The association between the potential influencing factors and crash frequency is examined using a random parameter negative binomial regression model. Results indicate that the data segmentation based on TDZs is instrumental in establishing a more refined crash model compared to traditional planning-based zones, as demonstrated by improved goodness-of-fit measures. Factors including density (e.g., employment density), network design (e.g., road density and highway density), land use diversity (e.g., job-housing balance and land use mixture), and public transit accessibility (e.g., bus route density) are significantly associated with crash occurrence. Furthermore, the unobserved heterogeneity effects of the shockwave velocity and congestion index on crashes are revealed. The study highlights the significance of incorporating dynamic traffic flow variables in understanding crash frequency variations across different spatial units. These findings can inform optimal real-time traffic monitoring, environmental design, and road safety management strategies to mitigate crash risks.

From unstructured accident reports to a hybrid decision support system for occupational risk management: The consensus converging approach

INTRODUCTION

Workplace accidents in the petroleum industry can cause catastrophic damage to people, property, and the environment. Earlier studies in this domain indicate that the majority of the accident report information is available in unstructured text format. Conventional techniques for the analysis of accident data are time-consuming and heavily dependent on experts' subject knowledge, experience, and judgment. There is a need to develop a machine learning-based decision support system to analyze the vast amounts of unstructured text data that are frequently overlooked due to a lack of appropriate methodology.

METHOD

To address this gap in the literature, we propose a hybrid methodology that uses improved text-mining techniques combined with an un-bias group decision-making framework to combine the output of objective weights (based on text mining) and subjective weights (based on expert opinion) of risk factors to prioritize them. Based on the contextual word embedding models and term frequencies, we extracted five important clusters of risk factors comprising more than 32 risk sub-factors. A heterogeneous group of experts and employees in the petroleum industry were contacted to obtain their opinions on the extracted risk factors, and the best-worst method was used to convert their opinions to weights.

CONCLUSIONS AND PRACTICAL APPLICATIONS

The applicability of our proposed framework was tested on the data compiled from the accident data released by the petroleum industries in India. Our framework can be extended to accident data from any industry, to reduce analysis time and improve the accuracy in classifying and prioritizing risk factors.

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.

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.

A systematic approach to macro-level safety assessment and contributing factors analysis considering traffic crashes and violations

During rapid urbanization and increase in motorization, it becomes particularly important to understand the relationships between traffic safety and risk factors in order to provide targeted improvements and policy recommendations. Violations and police enforcement are key variables, but the endogenous relationship between crashes and violations has made these variables unreliable and has limited their use. To manage this problem, this study developed a systematic approach for the joint modeling of crashes and violations to identify crash and violation hotspots and examine the mechanisms underlying macro-level contributing factors. Socio-economic, road network, public facility, traffic enforcement, and land use intensity data from 115 towns in Suzhou, China, were collected as independent variables. A bivariate negative binomial spatial conditional autoregressive model (BNB-CAR) and the potential for safety improvement (PSI) method were adopted to identify crash-prone and violation-prone areas, and an interpretable machine learning framework was applied to explore the factors' effects by area. Results showed that the proposed framework was able to accurately identify problem areas and quantify the impact of key factors, which, in Suzhou, were the number of traffic police and their daily patrol time. Considering such enforcement-related information provided important insights into reducing crash and violation frequency; for example, keeping the number of traffic police and daily patrol time under certain thresholds (number of police lower than 11 and patrol time lower than 2.3 h in this sample) was as effective as increasing these numbers for reducing the probability of high-crash and high-violation areas. The proposed approach can help traffic administrators identify the key contributing factors, especially enforcement factors, in crash-prone and violation-prone areas and provide guidelines for improvement.

The influence of traffic-infrastructure factors on pedestrian accidents at the macro-level: The geographically weighted regression approach

INTRODUCTION

Walking is an active way of moving the population, but in recent years there have been more pedestrian casualties in traffic, especially in developing countries such as Serbia. Macro-level road safety studies enable the identification of influential factors that play an important role in creating pedestrian safety policies.

METHOD

This study analyzes the impact of traffic and infrastructure characteristics on pedestrian accidents at the level of traffic analysis zones. The study applied a geographically weighted regression approach to identify and localize all factors that contribute to the occurrence of pedestrian accidents. Taking into account the spatial correlations between the zones and the frequency distribution of accidents, the geographically Poisson weighted model showed the best predictive performance.

RESULTS

This model showed 10 statistically significant factors influencing pedestrian accidents. In addition to exposure measures, a positive relationship with pedestrian accidents was identified in the length of state roads (class I), the length of unclassified streets, as well as the number of bus stops, parking spaces, and object units. However, a negative relationship was recorded with the total length of the street network and the total length of state roads passing through the analyzed area.

CONCLUSION

These results indicate the importance of determining the categorization and function of roads in places where pedestrian flows are pronounced, as well as the perception of pedestrian safety near bus stops and parking spaces.

PRACTICAL APPLICATIONS

The results of this study can help traffic safety engineers and managers plan infrastructure measures for future pedestrian safety planning and management in order to reduce pedestrian casualties and increase their physical activity.

Rule-based classifier based on accident frequency and three-stage dimensionality reduction for exploring the factors of road accident injuries

Road accidents are one of the primary causes of death worldwide; hence, they constitute an important research field. Taiwan is a small country with a high-density population. It particularly has a considerable number of locomotives. Furthermore, Taiwan’s traffic accident fatality rate increased by 23.84% in 2019 compared with 2018, primarily because of human factors. Road safety has long been a challenging problem in Taiwanese cities. This study collected public data pertaining to traffic accidents from the Taoyuan city government in Taiwan and generated six datasets based on the various accident frequencies at the same location. To find key attributes, this study proposes a three-stage dimension reduction to filter attributes, which includes removing multicollinear attributes, the integrated attribute selection method, and statistical factor analysis. We applied five rule-based classifiers to classify six different frequency datasets and generate the rules of accident severity. The order of top ten key attributes was hit vehicle > certificate type > vehicle > action type > drive quality > escape > accident type > gender > job > trip purposes in the maximum accident frequency CF ≥ 10 dataset. When locomotives, bicycles, and people collide with other locomotives or trucks, injury or death can easily occur, and the motorcycle riders are at the highest risk. The findings of this study provide a reference for governments and stakeholders to reduce the road accident risk factors.

Application of Extremely Randomised Trees for exploring influential factors on variant crash severity data

Crash severity models play a crucial role in evaluating the influencing factors in the severity of traffic crashes. In this study, Extremely Randomised Tree (ERT) is used as a machine learning technique to analyse the severity of crashes. The crash data in the province of Khorasan Razavi, Iran, for a period of 5 years from 2013 to 2017, is used for crash severity model development. The dataset includes traffic-related variables, vehicle specifications, vehicle movement, land use characteristics, temporal characteristics, and environmental variables. In this paper, Feature Importance Analysis (FIA), Partial Dependence Plots (PDP), and Individual Conditional Expectation (ICE) plots are utilised to analyse and interpret the results. According to the results, the involvement of vulnerable road users such as motorcyclists and pedestrians alongside traffic-related variables are among the most significant variables in crash severity. Results show that the presence of motorcycles can increase the probability of injury crashes by around 30% and almost double the probability of fatal crashes. Analysing the interaction of PDPs shows that driving speeds above 60 km/h in residential areas raises the probability of injury crashes by about 10%. In addition, at speeds higher than 70 km/h, the presence of pedestrians approximately increases the probability of fatal crashes by 6%.

Unveiling the relevance of traffic enforcement cameras on the severity of vehicle-pedestrian collisions in an urban environment with machine learning models

PURPOSE

One of the leading causes of violent fatalities around the world is road traffic collisions, and pedestrians are among the most vulnerable road users with respect to such incidents. Since walking is highly promoted in urban areas to alleviate motor-vehicle externalities, it is paramount to understand the causes associated with vehicle-pedestrian collisions and their severity to provide safe environments. Although traffic enforcement cameras can address vehicle-vehicle collisions, little is known about their effectiveness with respect to vehicle-pedestrian incidents.

METHODOLOGY

In this study, we trained a set of machine learning models to forecast if a vehicle-pedestrian collision will turn into an injury or fatality, and the most suitable model was used to investigate the contributing features associated with such events with emphasis on the impact of traffic enforcement cameras. In addition to traffic enforcement camera proximity, features associated with the collision, weather, vehicle, victim, and infrastructure are included in the model to reduce unobserved heterogeneity.

RESULTS

Results show that a Linear Discriminant Analysis model surpasses other machine learning models considering the evaluation metrics. Results reveal that the age and gender of the victim, the involvement of larger vehicles in the collision, and the quality of the illumination are the causes associated with pedestrian fatalities. On the other hand, involvement of motorcycles and collisions that occurred in densely populated locations are the causes associated with pedestrian injuries.

CONCLUSIONS

This investigation demonstrates how to articulate machine learning into a vehicle-pedestrian crash analysis to understand the direction and magnitude of covariates in the corresponding severity outcome. Furthermore, it highlights the remarkable effect that traffic enforcement cameras and other features have on vehicle-pedestrian crash severity. These results provide actionable guidance for educational campaigns, enhanced traffic engineering, and infrastructure improvements that could be implemented in the analyzed region to provide safer transportation.

Comparing and Contrasting the Impacts of Macro-Level Factors on Crash Duration and Frequency

Road traffic crashes cause social, economic, physical and emotional losses. They also reduce operating speed and road capacity and increase delays, unreliability, and productivity losses. Previous crash duration research has concentrated on individual crashes, with the contributing elements extracted directly from the incident description and records. As a result, the explanatory variables were more regional, and the effects of broader macro-level factors were not investigated. This is in contrast to crash frequency studies, which normally collect explanatory factors at a macro-level. This study explores the impact of various factors and the consistency of their effects on vehicle crash duration and frequency at a macro-level. Along with the demographic, vehicle utilisation, environmental, and responder variables, street network features such as connectedness, density, and hierarchy were added as covariates. The dataset contains over 95,000 vehicle crash records over 4.5 years in Greater Sydney, Australia. Following a dimension reduction of independent variables, a hazard-based model was estimated for crash duration, and a Negative Binomial model was estimated for frequency. Unobserved heterogeneity was accounted for by latent class models for both duration and frequency. Income, driver experience and exposure are considered to have both positive and negative impacts on duration. Crash duration is shorter in regions with a dense road network, but crash frequency is higher. Highly connected networks, on the other hand, are associated with longer length but lower frequency.

Predicting effects of built environment on fatal pedestrian accidents at location-specific level: Application of XGBoost and SHAP

Understanding locally heterogeneous physical contexts in built environment is of great importance in developing preemptive countermeasures to mitigate pedestrian fatality risks. In this study, we aim to investigate the non-linear relationship between physical factors and pedestrian fatality at a location-specific level using a machine learning approach. The state-of-art machine learning algorithm, eXtreme Gradient Boosting (XGBoost), is employed for a binary classification problem, in which nationwide locations where fatal pedestrian accidents occurred for the years from 2012 to 2019 in Korea serve as positive samples (n_p = 13,366). For negative samples, locations with no pedestrian accidents are selected randomly to the size that is 10 times larger (n_n = 133,660) than positive samples. Fifteen features under the categories of road conditions, road facilities, road networks, and land uses are assigned to both the positive and negative sample locations using Geographic Information System (GIS). A method is proposed to avoid the class imbalance problem, and a final unbiased model is utilized to predict fatal pedestrian risks at the negative sample locations. In addition, Shapley Additive Explanations (SHAP) is introduced to provide a robust interpretation of the XGBoos prediction results. It is shown that 21.6% of the negative sample locations have a probability of fatal pedestrian accidents greater than 0.5 (or 78.4% accuracy). Generally, a road segment that lies in many of the shortest routes in a dense residential area with many lively activities from aligned buildings is a potential spot for fatal pedestrian accidents. However, based on the SHAP interpretation, the relationships between the features and pedestrian fatality are found nonlinear and locally heterogeneous. We discuss the implications of this result has for drafting policy recommendations to reduce pedestrian fatalities.

The Analysis of the Factors Influencing the Severity of Bicyclist Injury in Bicyclist-Vehicle Crashes

Transportation and technological development have for centuries strongly influenced the shaping of urbanized areas. On one hand, it undoubtedly brings many benefits to their residents. However, also has a negative impact on urban areas and their surroundings. Many transportation and technological solutions lead, for example, to increased levels of pollution, noise, excessive energy use, as well as to traffic accidents in cities. So, it is important to safe urban development and sustainability in all city aspects as well as in the area of road transport safety. Due to the long-term policy of sustainable transport development, cycling is promoted, which contributes to the increase in the number of this group of users of the transport network in road traffic for short-distance transport. On the one hand, cycling has a positive effect on bicyclists’ health and environmental conditions, however, a big problem is an increase in the number of serious injuries and fatalities among bicyclists involved in road incidents with motor vehicles. This study aims to identify factors that influence the occurrence and severity of bicyclist injury in bicyclist-vehicle crashes. It has been observed that the factors increasing the risk of serious injuries and deaths of bicyclists are: vehicle driver gender and age, driving under the influence of alcohol, exceeding the speed limit by the vehicle driver, bicyclist age, cycling under the influence of alcohol, speed of the bicyclist before the incident, vehicle type (truck), incident place (road), time of the day, incident type. The obtained results can be used for activities aimed at improving the bicyclists’ safety level in road traffic in the area of analysis.

Analysis and Prediction of Vehicle Kilometers Traveled: A Case Study in Spain

Knowledge of the kilometers traveled by vehicles is essential in transport and road safety studies as an indicator of exposure and mobility. Its application in the determination of user risk indices in a disaggregated manner is of great interest to the scientific community and the authorities in charge of ensuring road safety on highways. This study used a sample of the data recorded during passenger vehicle inspections at Vehicle Technical Inspection stations and housed in a data warehouse managed by the General Directorate for Traffic of Spain. This study has three notable characteristics: (1) a novel data source is explored, (2) the methodology developed applies to other types of vehicles, with the level of disaggregation the data allows, and (3) pattern extraction and the estimate of mobility contribute to the continuous and necessary improvement of road safety indicators and are aligned with goal 3 (Good Health and Well-Being: Target 3.6) of The United Nations Sustainable Development Goals of the 2030 Agenda. An Operational Data Warehouse was created from the sample received, which helped in obtaining inference values for the kilometers traveled by Spanish fleet vehicles with a level of disaggregation that, to the knowledge of the authors, was unreachable with advanced statistical models. Three machine learning methods, CART, random forest, and gradient boosting, were optimized and compared based on the performance metrics of the models. The three methods identified the age, engine size, and tare weight of passenger vehicles as the factors with greatest influence on their travel patterns.

Crash severity analysis of vulnerable road users using machine learning

Road crash fatality is a universal problem of the transportation system. A massive death toll caused annually due to road crash incidents, and among them, vulnerable road users (VRU) are endangered with high crash severity. This paper focuses on employing machine learning-based classification approaches for modelling injury severity of vulnerable road users-pedestrian, bicyclist, and motorcyclist. Specifically, this study aims to analyse critical features associated with different VRU groups-for pedestrian, bicyclist, motorcyclist and all VRU groups together. The critical factor of crash severity outcomes for these VRU groups is estimated in identifying the similarities and differences across different important features associated with different VRU groups. The crash data for the study is sourced from the state of Queensland in Australia for the years 2013 through 2019. The supervised machine learning algorithms considered for the empirical analysis includes the K-Nearest Neighbour (KNN), Support Vector Machine (SVM) and Random Forest (RF). In these models, 17 distinct road crash parameters are considered as input features to train models, which originate from road user characteristics, weather and environment, vehicle and driver condition, period, road characteristics and regions, traffic, and speed jurisdiction. These classification models are separately trained and tested for individual and unified VRU to assess crash severity levels. Afterwards, model performances are compared with each other to justify the best classifier where Random Forest classification models for all VRU modes are found to be comparatively robust in test accuracy: (motorcyclist: 72.30%, bicyclist: 64.45%, pedestrian: 67.23%, unified VRU: 68.57%). Based on the Random Forest model, the road crash features are ranked and compared according to their impact on crash severity classification. Furthermore, a model-based partial dependency of each road crash parameters on the severity levels is plotted and compared for each individual and unified VRU. This clarifies the tendency of road crash parameters to vary with different VRU crash severity. Based on the outcome of the comparative analysis, motorcyclists are found to be more likely exposed to higher crash severity, followed by pedestrians and bicyclists.

Evaluation of pedestrian critical gap and crossing speed at midblock crossing using image processing

Pedestrians confront risky situations at midblock sections due to the unyielding behavior of drivers. Thus, pedestrians have to wait for an appropriate gap to cross. This research investigates pedestrians' gap acceptance and crossing speed for midblock crossings by image processing methods in Izmir, Turkey. A total of 498 pedestrians have been tracked at two midblock crossings. The data were collected for one hour at each midblock crossing during the evening peak hour between 5.00-6.00 p.m. Three synchronized cameras were used to record pedestrian crossings. Then, by using image processing, vehicle and pedestrian trajectories have been obtained. Two cameras were mounted on telescopic tripods reaching up to 9 m, and the third camera was used to identify pedestrians' gender better. The parameters extracted from the recordings are; pedestrians' gender, group size, whether they carried items or not, and their accepted/rejected gaps. Pedestrian and item detection has been performed by YOLOv3 and YOLACT models. The accepted and rejected time gaps were extracted for pedestrians, excluding the pedestrians who crossed between stopped vehicles and crossed when an approaching vehicle did not exist within 100 m from the midblock crossing. Raff's method was used to estimate the critical gap using accepted/rejected gaps. The critical gaps ranged between 4.1 s and 6.2 s. The 15th percentile crossing speeds were found to be similar, ranging between 0.78 m/s and 0.80 m/s.

Identification of Road Traffic Injury Risk Prone Area Using Environmental Factors by Machine Learning Classification in Nonthaburi, Thailand

Road traffic injuries are a major cause of morbidity and mortality worldwide and currently rank ninth globally among the leading causes of disease burden regarding disability-adjusted life years lost. Nonthaburi and Pathum Thani are parts of the greater Bangkok metropolitan area, and the road traffic injury rate is very high in these areas. This study aimed to identify the environmental factors affecting road traffic injury risk prone areas and classify road traffic injuries from an environmental factor dataset using machine learning algorithms. Road traffic injury risk prone areas were set as the dependent variables for the analysis, with other factors that influence road traffic injury risk prone areas being set as independent variables. A total of 20 environmental factors were selected from the spatial datasets. Then, machine learning algorithms were applied using a grid search. The first experiment from 2017 in Nonthaburi and Pathum Thani was used for training the model, and then, 2018 data from Nonthaburi and Pathum Thani were used for validation. The second experiment used 2018 Nonthaburi data for the training, and 2018 Pathum Thani data were used for the validation. The important factors were grocery stores, convenience stores, electronics stores, drugstores, schools, gas stations, restaurants, supermarkets, and road geometrics, with length being the most critical factor that influenced the road traffic injury risk prone model. The first and second experiments in a random forest model provided the best model environmental factors affecting road traffic injury risk prone areas, and machine learning can classify such road traffic injuries.

Mid-term prediction of at-fault crash driver frequency using fusion deep learning with city-level traffic violation data

Traffic violations and improper driving are behaviors that primarily contribute to traffic crashes. This study aimed to develop effective approaches for predicting at-fault crash driver frequency using only city-level traffic enforcement predictors. A fusion deep learning approach combining a convolution neural network (CNN) and gated recurrent units (GRU) was developed to compare predictive performance with one econometric approach, two machine learning approaches, and another deep learning approach. The performance comparison was conducted for (1) at-fault crash driver frequency prediction tasks and (2) city-level crash risk prediction tasks. The proposed CNN-GRU achieved remarkable prediction accuracy and outperformed other approaches, while the other approaches also exhibited excellent performances. The results suggest that effective prediction approaches and appropriate traffic safety measures can be developed by considering both crash frequency and crash risk prediction tasks. In addition, the accumulated local effects (ALE) plot was utilized to investigate the contribution of each traffic enforcement activity on traffic safety in a scenario of multicollinearity among predictors. The ALE plot illustrated a complex nonlinear relationship between traffic enforcement predictors and the response variable. These findings can facilitate the development of traffic safety measures and serve as a good foundation for further investigations and utilization of traffic violation data.