Occurrence Of Traffic Crashes Research Articles

Implementation of a realistic artificial data generator for crash data generation

In this paper, a framework is outlined to generate realistic artificial data (RAD) as a tool for comparing different models developed for safety analysis. The primary focus of transportation safety analysis is on identifying and quantifying the influence of factors contributing to traffic crash occurrence and its consequences. The current framework of comparing model structures using only observed data has limitations. With observed data, it is not possible to know how well the models mimic the true relationship between the dependent and independent variables. Further, real datasets do not allow researchers to evaluate the model performance for different levels of complexity of the dataset. RAD offers an innovative framework to address these limitations. Hence, we propose a RAD generation framework embedded with heterogeneous causal structures that generates crash data by considering crash occurrence as a trip level event impacted by trip level factors, demographics, roadway and vehicle attributes. Within our RAD generator we employ three specific modules: (a) disaggregate trip information generation, (b) crash data generation and (c) crash data aggregation. For disaggregate trip information generation, we employ a daily activity-travel realization for an urban region generated from an established activity-based model for the Chicago region. We use this data of more than 2 million daily trips to generate a subset of trips with crash data. For trips with crashes crash location, crash type, driver/vehicle characteristics, and crash severity. The daily RAD generation process is repeated for generating crash records at yearly or multi-year resolution. The crash databases generated can be employed to compare frequency models, severity models, crash type and various other dimensions by facility type – possibly establishing a universal benchmarking system for alternative model frameworks in safety literature.

Impacts of on-demand ride services on the number of traffic crashes – A case study of RideAustin in Austin, TX

On-demand ridesharing services are rapidly growing and are predicted to continue to do so, as they offer millions of trips to potential riders every day. Empirical research have extensively investigated the effects of ridesharing services on travel behaviour, traffic congestion, and environmental factors. However, the potential influence of these services on the occurrence of traffic crashes has been largely overlooked. Previous research examining the safety implications of ridesharing services has primarily focused on the existence of such services. Nevertheless, we contend that the mere presence of a ridesharing service does not inherently ensure either a favorable or unfavorable influence on traffic safety. It is the frequency of service consumption that is more likely to have an influence. The objective of this study is to examine the effects of ridesharing services on the incidence of traffic crashes and injuries. The analysis will focus on RideAustin, a locally based ridesharing service operating in Austin, TX, as a specific case study. The difference-in-difference methodology is employed in this study to examine the impact of RideAustin on traffic accidents at the U.S. census block group level. This analysis considers sociodemographic characteristics and built environment variables as control factors. The dataset utilised in this study comprises over 1.4 million trips from 2016 to 2017, sourced from RideAustin. Additionally, the traffic crash and injury data included in this study spans the period from 2012 to 2020 and encompasses approximately 373,000 traffic crashes, as obtained from the Texas Department of Transportation. The use of difference-in-difference models revealed that a statistically significant reduction in the occurrence of traffic crashes was observed solely when the number of trips within a certain block group above a specific threshold. The study determined that the mere presence of services and their infrequent utilization (less than one ride per block group) did not have a statistically significant effect on traffic safety. The results obtained from this study will contribute to a more comprehensive comprehension of the safety advantages associated with ridesharing services, consequently assisting transportation and policy planners in mitigating the occurrence of traffic accidents in metropolitan regions.

Deep hybrid learning framework for spatiotemporal crash prediction using big traffic data

The rapid growth in data collection, storage, and transformation technologies offered new approaches that can be effectively utilized to improve traffic crash prediction. Considering the probability of traffic crash occurrence vary due to the spatiotemporal heterogeneity, this study proposes a state-of-the-art deep learning-based model that incorporates spatiotemporal information for the short-term crash prediction, named as Deep Spatiotemporal Hybrid Network (DSHN). The model integrates Convolutional Neural Network (CNN), Long Short-term Memory (LSTM), and Artificial Neural Network (ANN) to incorporate the synergistic power of individual models. The study utilizes different data sources such as big traffic data collected from Paris road network sensors, weather conditions, infrastructure, holidays, and crash data. The results indicated that the proposed DSHN model outperforms the baseline models with an Area Under Curve (AUC) of about 0.800, an accuracy of 0.757, and a false alarm rate of 0.217. In addition, the importance of each data type is evaluated to investigate their impacts on the prediction performance of models. The sensitivity analysis results indicate that the road sensor data that includes average speed, vehicle kilometer traveled (VKT), and weighted average occupancy has the highest impact on the prediction accuracy.

Prevalence and Risk Factors Associated with Road Traffic Crash among Bus Drivers in the Southern Region of Cameroon: A Cross Sectional Study

Background: Annually, road traffic crash account for more than 1.2 million deaths and up to 50 million injuries worldwide, making it a leading cause of death globally. Given the low rate of vehicle ownership in developing countries, most of the population depends on buses for public transport. In Cameroon, buses are frequently involved in road traffic crashes. The aim of this study was to determine the prevalence of road traffic crashes and risk factors associated with road traffic crash among bus drivers in the South West Region-Cameroon. Methods: This was a cross-sectional study involving bus drivers with at least 3 years driving experience in passenger transportation. Multi-stage sampling was employed with random selection of six parks from three divisions in the South West Region of Cameroon. Proportionate sampling was done to select the bus drivers at the selected parks. Data was collected using a structured questionnaire. It was inputted and analyzed using EPI info version 3.5.4. Bivariate and multivariate analysis were used to identify risk factors associated road traffic crash history within 3 years prior to the survey with statistical significance set at p<0.05. Results: Out of the total 422 participants recruited, 98 bus drivers reported, giving an overall crash prevalence of 23.2%. Among the crashed group, 72 drivers (12.1%) were involved in more than one crash within the past 3 years (2014-2017). Multivariate analysis showed excessive speed [AOR 6.98 95% CI; 3.7-12.8], drinking alcohol during driving hours [AOR 10.15, 95% CI; 4.7-21.8], phone distraction (AOR=6.48, 95% CI; 3.8-10.8], passenger distraction [AOR 8.77, 95% CI; 4.6-16.2], violating road traffic rules [AOR=2.13, 95% CI; 1.2-3.5] and fatigue [AOR 0.17, 95 & CI; 0.05-.053] as factors that are significantly associated with road traffic crash among bus drivers within the past 3 years (2014-2017). Conclusion: Almost a quarter (23.2%) of bus drivers have a history of road traffic crash within the past 3 years. Many factors have been found to be associated with road traffic crash occurrence among these drivers and these calls for urgent sensitization campaigns, amelioration of road conditions and proper law enforcement on road safety issues.

Short-Duration Crash Modeling to Understand the Impact of Operating Speed on Freeway Crashes During COVID-19

Gaining an understanding of speed–crash relationships is a critical issue in highway safety research. Because of the ongoing pandemic (COVID-19) there has been a reduction in traffic volume, and some early studies explain that speeding in an environment with less traffic is associated with a high number of crashes, especially fatal and serious injury crashes. This study aims to quantify the impact of operating speed on traffic crash occurrences. The study conflated several databases (speed data, roadway inventory data, and crash data) that contain data from Dallas, Texas, spanning from 2018 to 2020, to examine the speed–crash association. Using the negative binomial Lindley regression model, this study showed that the trends of crash prediction models vary over the years (2018, 2019, and 2020) by different injury severity levels (i.e., fatal crashes, fatal and incapacitating injury crashes). The 2020 models show that operating speed measures (i.e., average operating speed) have a significant impact on crash frequencies. The magnitudes of the speed measures show variations across the models at different injury severity levels.

Road Adhesion Coefficient Estimation Based on Vehicle-Road Coordination and Deep Learning

Accurate estimation of the road adhesion coefficient can help drivers and vehicles perceive changes in road state effectively, reducing the occurrence of traffic crashes accordingly. Therefore, this paper proposes a road adhesion coefficient estimation method based on vehicle-road coordination and deep learning. Firstly, a vehicle-based data feedback system combined with a vehicle-road network cloud is introduced, and CarSim simulation is used to expand the data set and train the model effectively. Then, the dynamic analysis of the whole vehicle is carried out, and the vehicle operation data related to the adhesion coefficient are obtained as the input of the estimation model. Then a combined model of road adhesion coefficient estimation based on self-attention (SA), convolutional neural network (CNN), and long short-term memory (LSTM) is established, to reduce the instability of the prediction, Q-learning is used to optimize the weight of the model. Finally, the model is verified by the simulation data and the actual vehicle-based data. The results show that the vehicle-based data feedback system combined with the vehicle-road network Ccloud is effective, and compared with other commonly used model, the estimation model proposed in this paper can effectively predict the road adhesion coefficient.

Influence of Risky Driving Behavior and Road Section Type on Urban Expressway Driving Safety

The causes of traffic crashes are complex and uncertain, among which the risky driving behaviors of drivers and the types of road sections in high-crash areas are all critical influencing factors. We used ArcGIS software to draw traffic heat maps under different thresholds to prevent the occurrence of traffic crashes accurately and effectively according to the vehicle GPS data of urban expressways in Jinan City, Shandong Province. This paper studied the relationship between risky driving behaviors (rapid acceleration, rapid deceleration, and overspeed) and road types with traffic crashes. The traffic safety evaluation model of urban expressways based on ordered logistic was established to predict the safety level of the urban expressway. The model’s accuracy was 85.71%, and the applicability was good. The research results showed that rapid deceleration was the most significant influencing factor of crashes on urban expressways. When the vehicle deceleration was less than or equal to −4 m/s2, the probability of a crash was 22.737 times greater than when the vehicle deceleration was at −2 to −2.5 m/s2; when the vehicle acceleration was greater than or equal to 3 m/s2, the probability of a crash was 19.453 times greater than when the vehicle acceleration was at 1 to 1.5 m/s2. The likelihood of a crash at a road section with a ramp opening was 8.723 times greater than that of a crash at a non-ramp opening; the crash probability of a speeding vehicle was 7.925 times greater than that of a non-speeding vehicle; the likelihood of a crash on a curve was 6.147 times greater than that on a straight. The research results can provide adequate technical support for identifying high-risk sections of expressways and active early warning of traffic crashes.

Exploring Traffic Crash Occurrence Mechanism toward Cross-Area Freeways via an Improved Data Mining Approach

Exploring Traffic Crash Occurrence Mechanism toward Cross-Area Freeways via an Improved Data Mining Approach

An evaluation of highway crash-prone areas: A case study on Pan Borneo Highway in the state of Sarawak

Road traffic crashes is one of the major causes of death that needs to be addressed globally. Many studies have been conducted to identify the contributing factors to traffic crashes and to determine the required preventive measures. This study evaluates the causes of 164 traffic crashes along a 10 kilometres section of Pan Borneo Highway Sarawak. The study investigated the main causes of traffic crashes within this section of road through multiple sources: based on expert on site evaluation, analysis of site incident report and police accident record. The finding reveals that most of the accidents (93%) occurs during the daytime, weather contributes a combined 69% and private car owners (80%) cause most of the traffic crashes. The study also indicates that the road condition is a significant factor to the occurrence of traffic crashes in that area contributing 64% of the total crashes.

Spatio-Temporal Crash Prediction: Effects of Negative Sampling on Understanding Network-Level Crash Occurrence

In projects centered around rare event case data, the challenge of data comprehension is greatly increased because of insufficient data for deriving insight and analysis. This is particularly the case with traffic crash occurrence, where positive events (crashes) are rare and, in most cases, no data set exists for negative events (non-crashes). One method to increase available data is negative sampling, which is the process of creating a negative event based on the absence of a positive event. In this work, four negative sampling techniques are presented with varying ratios of negative to positive data. These types of techniques are based on spatial data, temporal data, and a mixture of the two, with the data ratios acting as class balancing tools. The best performing model found was with a negative sampling technique that shifted temporal information and had an even 50/50 data split, with an F-1 score, a formulaic combination of precision and recall, of 93.68. These results are promising for Inteligent Transportation Systems (ITS) applications to inform of potential crash locations in an entire area for proactive measures to be put in place.

Multiple correspondence analysis applied to the study of the relationship between traffic crashes and precipitation on a highway in Brazil

A incorporação de dados meteorológicos em pesquisas envolvendo o estudo de acidentes é considerada como essencial quando se objetiva analisar o comportamento de acidentes rodoviários. Neste contexto, o presente trabalho pretendeu explorar a existência de correlação entre ocorrência de acidentes rodoviários e condições climáticas, em específico a precipitação diária, num trecho selecionado da Rodovia BR- 376 (Paraná, Brasil). Uma análise de correspondência múltipla (ACM) foi aplicada (software Statigraphics) para determinar a relação existente entre as características dos acidentes e a precipitação. A ACM permitiu a criação de um mapa perceptual, agrupando as variáveis consideradas semelhantes de acordo com o método, o qual evidenciou que a intensidade da chuva não foi um fator significativo para alterar as características dos acidentes. Entretanto, a ocorrência de precipitação mostrou-se como uma circunstância condicionante. Com respeito à segurança da rodovia, a pesquisa indica aplicações práticas que podem ser aplicadas pelas agências de tráfego, como a implementação de sinalização de tráfego e educacional em pontos específicos da rodovia.

Evaluating the Nonlinear Correlation between Vertical Curve Features and Crash Frequency on Highways Using Random Forests

AbstractVertical curve features on interstate highways greatly affect traffic operations and vehicle performance and, thus, could have an impact on the occurrence of traffic crashes. Most studies t...

Impact of Pavement Roughness on Traffic Safety under Heterogeneous Traffic Conditions

H ighway safety is a major priority for public use and for transportation agencies. Pavement roughness indirectly influence drivers' concentration, vehicle operation, and road traffic accidents, and it directly affect ride quality. This study focuses on analyzing the influence of pavement roughness on traffic safety using traffic, pavement and accident data on dual and single carriageway operated under heterogeneous traffic conditions in South-west, Nigeria. Traffic crash data between 2012 and 2015 was obtained from the Federal Road Safety Commission (FRSC) and International Roughness Index (IRI) data from the Pavement Evaluation Unit of the Federal Ministry of Works, Kaduna. Crash road segments represented 63 percent of the total length of roads. IRI values for crash and non-crash segments was a close difference of 0.3,This indicates that roughness is not the only factors affecting occurrence of traffic crashes but a combination with other factors such as human error, geometric characteristics and vehicle conditions. Crash severity was categorized into Fatal, serious and minor injury crashes. In all cases, the total crash rate increases with increase in IRI value up to a critical IRI value of 4.4 and 6.15 for Sagamu-Ore road and Ilesha-Akure-Owo road respectively, wherein the crash rate dropped. The conclusion is key in improving safety concerns, if transportation agencies keep their road network below these critical pavement conditions, the crash rate would largely decrease. The study concluded that ride quality does not directly affect traffic crash rate.
 Keywords: Pavement conditions, traffic safety, International Roughness Index, crash rate, carriageway.

Investigating exposure of the population to crash injury using a spatiotemporal analysis: A case study in Florida

Over the years, as the roadway networks have been developing gradually to improve transportation accessibility to various facilities, the probability of traffic crash occurrences has also increased consequently. With an increasing transportation demand, the traffic safety needs to be improved in order to reduce the crash rates and the exposure of the population to crash-prone regions. This paper aims to conduct a spatiotemporal analysis to quantify the exposure of population to crash-prone locations focusing on different age groups, and to statistically analyze the decision-making process for possible improvement. For this purpose, first, the crash-prone locations for different population age groups and various time intervals of a day were identified by using a geographic information system (GIS) hotspot analysis. This was followed by an Origin-Destination (OD) analysis applied on a case study in Tampa Bay region (Florida, District 7) to calculate the roadway network-based travel times between census blocks centroids (origins) and crash hotspot locations (destinations) along the least-cost roadways. Later, the results were utilized in an exceedance probability analysis to simplify the decision-making process for improvement. The results showed that the time-based analysis provides more accurate and detailed information than the distance-based analysis. The Weighted Hotspot Exposure Measure parameter introduced for statistical analysis showed that the senior age group (over 65 years old) are more exposed to the risk of being injured in a crash compared to other age groups.

Rules Based Intersection Collision Avoidance System for V2X Safety

The biggest problem associated with the increased use of private and public transport is the increasing number of accidents on the roads. Most of the intersection collision avoidance systems use vehicle-to-infrastructure communication to avoid accidents at urban intersections. However, they are costly because additional roadside infrastructure must be installed, and they suffer from problem-related to real-time information delivery. The proposed system namely, Rules-based Intersection Collision Avoidance System (RICA) is a novel application using GPS technology for vehicle-to-everything (V2X) safety. The distance to the intersection is calculated and a time-to-intersection index is computed to establish the risk of a collision. The proposed system was achieved through simulations. It is potential as a new intersection collision avoidance system for V2X safety based on vehicular ad hoc network (VANET) communication. The result reveals that the proposed system can effectively prevent the occurrence of traffic crashes at an intersection.

Impact of data aggregation approaches on the relationships between operating speed and traffic safety

The impact of operating speed on traffic crash occurrence has been a controversial topic in the traffic safety discipline as some studies reported a positive association whereas others indicated a negative relationship between speed and crashes. Two major issues thought to be accountable for such conflicting findings are the application of inappropriate statistical methods and the use of sample datasets with varying levels of aggregation. The main objective of this study is therefore to investigate the impacts of data aggregation schemes on the relationships between operating speed and traffic safety. A total of three aggregation approaches were examined: (1) a segment-based dataset in which crashes are grouped by roadway segment, (2) a scenario-based dataset where crashes are aggregated by traffic operating scenarios, and (3) a disaggregated crash-level dataset consisting of information from individual crashes. The first two aggregation approaches were used in examining the relationships between operating speed and crash frequency using Bayesian random-effects negative binomial models. The third disaggregated crash risk analysis was conducted utilizing Bayesian random-effects logistic regression models. From the modeling results, it has been concluded that the scenario-based approach shared similar findings with those of the disaggregated crash risk analysis approach in which a U-shaped relationship between operating speed and crash occurrence was identified. However, the commonly adopted segment-based aggregation approach revealed a monotonous negative relationship between speed and crash frequency. The implications of the different analyses results and the potential applications of the results on speed management systems have therefore been discussed.

A Multi-level Analysis of the Relationship Between Urban Built Environment and Severe Injury Traffic Crashes

This study investigates the relationship between urban built environment and traffic crash occurrences in San Diego County by employing a multi-level Poisson regression model. This model is intended to address the so-called ‘Modifiable Areal Unit Problem’ by properly capturing the spatial correlations that might exist among crash occurrences within or across zones specified for data aggregation. A preliminary inspection based on a geographic information system reveals that the crash occurrences of Traffic Analysis Zones (TAZs) tend to show similar spatial pattern if they belong to the same city. This observation motivated us to incorporate hierarchical random components into a Poisson regression model to complement its systematic components (i.e. explanatory variables) related to socio-demographic characteristics, travel characteristics, or urban built environment. This approach turns out to improve the model’s explanatory power in assessing the relationship between urban built environment and traffic crash occurrences while controlling other variables. A key finding from this study is that crash occurrences of individual TAZs tend to decrease with the expansion of their urban portion.

Appraisal of urban road safety factors in South Africa

Traffic safety in the suburban roads of South African cities is a major challenge. Although many studies have explored the contributing factors, the influence of urban factors such as land use, urban form, urban pattern, accessibility and density on the occurrence of traffic crashes have been least explored. This investigation examined the influence of the major urban factors that cause traffic crashes and how road safety can be improved in the suburban arterial roads. For this purpose, a case study was performed using the Bloemfontein city of South Africa. The findings have shown that the level of accessibility (number of accessible roads) from residential areas to arterial roads is the major variable, which causes traffic crashes. Road geometry variables such as the median width and road width influence the occurrence of traffic crashes to a certain extent. Reduction in the number of access roads from the suburban residential areas to the arterial roads, provision of adequate medians in roads with no divided facility along with urban planning interventions, such as appropriate urban pattern, and avoidance of location of urban functions in convoluted areas will enable reduction in the occurrence of traffic crashes and improve road safety in the cities of South Africa.

Predicting crash frequency using an optimised radial basis function neural network model

With the enormous losses to society that result from highway crashes, gaining a better understanding of the risk factors that affect traffic crash occurrence has long been a prominent focus of safety research. In this study, we develop an optimised radial basis function neural network (RBFNN) model to approximate the nonlinear relationships between crash frequency and the relevant risk factors. Our case study compares the performance of the RBFNN model with that of the traditional negative binomial (NB) and back-propagation neural network (BPNN) models for crash frequency prediction on road segments in Hong Kong. The results indicate that the RBFNN has better fitting and prediction performance than the NB and BPNN models. After the RBFNN is optimised, its approximation performance improves, although several factors are found to hardly influence the frequency of crash occurrence for the crash data that we use. Furthermore, we conduct a sensitivity analysis to determine the effects of the remaining input variables of the optimised RBFNN on the outcome. The results reveal that there are nonlinear relationships between most of the risk factors and crash frequency, and they provide a deeper insight into the risk factors’ effects than the NB model, supporting the use of the modified RBFNN models for road safety analysis.

기하구조의 비동질성을 고려한 교통사고와의 관계: 고속도로 본선구간을 중심으로

지금까지 교통사고발생과 기하구조와의 관계파악을 위한 모형정립에 관한 연구가 많이 이루어져 왔다. 이러한 연구들은 도로선형, 기하구조의 개선 혹은 위험구간 선정 등에 사용되어 교통사고 건수 및 사고심각도를 줄이는데 기여를 하여왔다. 하지만, 모형정립에 사용되었던 변수들은 자료수집 부족 등의 이유로 변수 혹은 대상구간이 가지고 있는 기하구조의 비동질성을 고려하지 못한 측면이 있었으며, 이는 모형 정립시 계수의 표준오차값이 과소 추정되어 모형전체의 신뢰성에 영향을 미쳐왔다. 따라서, 이번 연구에서는 사용되는 변수의 비동질성 고려가 모형의 결과에 미치는 영향을 알아봄으로써, 비동질성의 중요성을 파악하고자 하는데 목적이 있다. 그 결과, 모든 기하구조에 대한 비동질성을 고려하지는 못하였으나, 몇몇 사용된 기하구조 변수들의 경우, 의미 있는 결과가 도출되었다. Until now, several research on the relationship of traffic crash occurrences and geometric had been conducted and revealed that projects of road alignment, geometric improvement and hazardous segment selection reduced the number of accidents and accident severities. However, such variables did not consider the non-homogeneous characteristics of roadway segments due to the difficulty of data collection, which results in under-estimation of the standard error affecting the overall modeling goodness-of-fit. This study highlights the importance of non-homogeneity by looking at the effect of the non-homogeneous geometric variables through the modeling process. The model delivers meaningful results when using some geometric variables without relevant geometrics' variables.