Factors affecting the injury severity of out-of-control single-vehicle crashes in Singapore

doi:10.1016/j.aap.2019.01.009

Accident Analysis & Prevention

Volume 124, March 2019, Pages 104-112

https://doi.org/10.1016/j.aap.2019.01.009 Get rights and content

Highlights

•
Out-of-control single-vehicle crashes are investigated with three-year crash data.
•
Motorized two-wheelers and other motorized vehicles are studied separately.
•
Factors influential to injury severity are identified for vehicle operators.
•
Three hazardous situations are concluded collectively for both vehicle types.
•
Targeted countermeasures are suggested for each type of vehicle operator.

Abstract

Single-vehicle (SV) crashes are of major concerns because of their high fatality rates. To understand the proneness of high injury severity for vehicle operators brought about by SV crashes without the confounding influence of other road users, this study focuses on those SV crashes without colliding with pedestrians, which are defined as out-of-control SV crashes given the general consequence of involved vehicles. Moreover, to compare the influence of contributory factors (including driver-vehicle/rider-vehicle, roadway, and environmental characteristics) by vehicle types, the injury severity for riders of motorized two-wheelers and drivers of other motorized vehicles are investigated separately using two disaggregated ordered probit models. The results show that for both riders and drivers, variables such as age (65 and above), drink driving, error type of failing to have proper control, driving maneuvers of left and right turns as well as driving after midnight are associated with more severe injuries whereas factors such as wet, oily or sandy surfaces are related to less severe injury. Four other variables, i.e., foreign vehicle registration, probation or expired license, high speed-limit roads, and type of median lane, have different influences on riders and drivers on injury severity. Additionally, factors such as road traffic type and nationality are only found to significantly influence only riders and drivers respectively. The results shed light on both the similar and different causes of high injury severity for riders and drivers involved in out-of-control SV crashes. Based on the findings, targeted countermeasures may be introduced from multiple perspectives such as driver education and policy development to improve non-traffic-interactive safety.

Introduction

Single-vehicle (SV) crashes are of major concerns especially when they result in injuries. A number of studies have indicated that SV crashes account for a large proportion of all fatal crashes and the fatality rate of the vehicle operators are also higher compared to other types of crashes (Kim et al., 2013; Lang et al., 1996; Renski et al., 1999; Wu et al., 2016a). In Singapore, the odds of fatal injuries for vehicle operators during SV crashes is 1.7 times that during two-vehicle crashes (Rifaat and Chin, 2005). Thus, it is imperative to further investigate SV crashes and identify the factors contributing to the injury severity.

SV crashes can be classified into two categories based on the consequences: those that collide with pedestrians and those that do not collide with other road users. Different from the former type of crashes, the primary causation of the latter type, e.g. self-skidding or hitting-stationary-object crashes, is simply contributed to the riders/drivers themselves and the influence from roadway and environmental characteristics. To observe those relationships without potential confounding effects brought by pedestrians, we only focus on the latter type of SV crashes. Given the general consequence of involved vehicles, these crashes are defined as out-of-control SV crashes in this study. According to empirical datasets (Quddus et al., 2002; Huang et al., 2008) and the current dataset, out-of-control SV crashes constitute nearly 80% of the total SV crashes in Singapore. Although certain specific types of SV crashes have been studied such as rollover, run-off-road, and collisions with fixed objects, few have analyzed them generally. Moreover, in spite of the possible influence of vehicle types on injury severity of the operators, a limited number of studies have been conducted with this type of crashes in a disaggregated manner.

The objective of this study is to obtain a clearer understanding regarding the high injury severity of vehicle operators brought about by out-of-control SV crashes. Contributory factors including driver-vehicle/rider-vehicle, roadway, and environmental characteristics are investigated and discussed. Moreover, their influence on the injury severity of riders of motorized two-wheelers (denoted as “riders” thereafter) and drivers of other motorized vehicles (denoted as “drivers” thereafter) are analyzed and compared by formulating two disaggregated ordered probit models. This can be particularly insightful given the considerable number of motorized two-wheelers involved in this type of crashes.

Section snippets

Data

The data used in the study are based on the national crash records in Singapore from 2012 to 2014, which were established from both the onsite crash reports by either the traffic police or the driver (applied for property-damage-only crashes) and the post-crash validation by investigation officers. The crash records contain four categories of information in general: 1) vehicle-related information about vehicle itself and its operator (including vehicle type, demographics of the operator, degree

Results and discussions

According to the likelihood ratio test, the log-likelihood values at convergence for the rider model and driver model are −907.843 (54 df) and −976.452 (54 df) respectively, while the corresponding value for the aggregated model is −2040.177 (55 df). Apart from the difference in nature of the two groups, the $χ^{2}$ statistic of 311.764 (p-value<0.001) also suggests that separate analyses for riders and drivers is preferable.

Following the stepwise backward elimination (10% criterion) to minimize

Conclusions

This study focuses on out-of-control crashes, a prevailing type of SV crashes in Singapore that has rarely been studied specifically. 18 contributing factors from rider- /driver-vehicle, roadway and environmental characteristics to injury severity of this type of crash are investigated using ordered probit models. The results discussed in the paper are considered to be valid since the marginal effects of those variables are consistent with similar studies that have adopted the same approach in

Acknowledgments

This research is sponsored by the Safety Studies Initiative of the National University of Singapore and is grateful to the Singapore Traffic Police for making available the data for the analysis.

References (27)

A.J. Anarkooli et al.
Investigation of factors affecting the injury severity of single-vehicle rollover crashes: a random-effects generalized ordered probit model
Accid. Anal. Prev.
(2017)
F. Chen et al.
Injury severities of truck drivers in single- and multi-vehicle accidents on rural highways
Accid. Anal. Prev.
(2011)
C. Chen et al.
Driver injury severity outcome analysis in rural interstate highway crashes: a two-level Bayesian logistic regression interpretation
Accid. Anal. Prev.
(2016)
H.C. Chin et al.
A study of at-fault older drivers in light-vehicle crashes in Singapore
Accid. Anal. Prev.
(2018)
Z. Christoforou et al.
Vehicle occupant injury severity on highways: an empirical investigation
Accid. Anal. Prev.
(2010)
R. Garrido et al.
Prediction of road accident severity using the ordered probit model
Transp. Res. Procedia
(2014)
L. Gong et al.
Modeling single-vehicle run-off-road crash severity in rural areas: accounting for unobserved heterogeneity and age difference
Accid. Anal. Prev.
(2017)
M.M. Haque et al.
Modeling fault among motorcyclists involved in crashes
Accid. Anal. Prev.
(2009)
M.M. Haque et al.
An investigation on multi-vehicle motorcycle crashes using log-linear models
Saf. Sci.
(2012)
H. Huang et al.
Severity of driver injury and vehicle damage in traffic crashes at intersections: a Bayesian hierarchical analysis
Accid. Anal. Prev.
(2008)

X. Jiang et al.

Investigating the influence of curbs on single-vehicle crash injury severity utilizing zero-inflated ordered probit models

Accid. Anal. Prev.

(2013)

J.K. Kim et al.

Driver-injury severity in single-vehicle crashes in California: a mixed logit analysis of heterogeneity due to age and gender

Accid. Anal. Prev.

(2013)

S.W. Lang et al.

Adolescent driving: characteristics associated with single-vehicle and injury crashes

J. Saf. Res.

(1996)

Cited by (52)

Factors affecting injury severity in motorcycle crashes: Different age groups analysis using Catboost and SHAP techniques
2024, Traffic Injury Prevention
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.
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.
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.
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.
Modeling injury severity of crashes involving golf carts: A case study of The Villages, Florida
2024, Traffic Injury Prevention
Crashes involving golf carts (GCs) have been on an increasing trend in recent years, particularly in the United States. This study focuses on analyzing GC crashes in the Florida community known as The Villages, one of the largest GC-oriented communities in the nation and worldwide. The objective was to evaluate the injury severity of crashes involving GCs in a retirement community where GCs are a common mode of transportation.
The ordinal logistic regression (OLR) and Decision Tree Ensemble (DTE) models were used to analyze the injury severity of 616 GC-related crashes. Models’ accuracy parameters were used to check their reliability.
The analysis revealed that GC crash severity is influenced by various factors. Factors found to be significant by the OLR model in determining injury severity include ejection of one or more occupants from the GC, the extent of damage to the GC, GC speed prior to the crash, roadway characteristics (including divided roadways, traffic control devices, paved shoulders, and T-intersections), and roll-over incidents. The OLR model demonstrated an overall accuracy of approximately 71% in predicting injury severity. The DTE model performed better, with an overall accuracy of 78%. The OLR model’s findings were supported by the DTE model, which identified estimated GC speed, occupant(s) ejection from the GC, estimated GC vehicle damage, intersection type, and type of shoulder as the most important factors influencing GC crash severity.
Understanding these factors is vital for transportation agencies to develop effective strategies to reduce the severity of GC crashes, ensuring the safety of GC users. This study provides recommendations to transportation agencies on measures to improve the safety of GCs.
Improving model robustness of traffic crash risk evaluation via adversarial mix-up under traffic flow fundamental diagram
2024, Accident Analysis and Prevention
Recent state-of-art crash risk evaluation studies have exploited deep learning (DL) techniques to improve performance in identifying high-risk traffic operation statuses. However, it is doubtful if such DL-based models would remain robust to real-world traffic dynamics (e.g., random traffic fluctuations.) as DL models are sensitive to input changes, where small perturbations could lead to wrong predictions. This study raises the critical robustness issue for crash risk evaluation models and investigates countermeasures to enhance it. By mixing up crash and non-crash samples under the traffic flow fundamental diagram, traffic flow adversarial examples (TF-AEs) were generated to simulate real-world traffic fluctuations. With the developed TF-AEs, model accuracy decreased by 8% and sensitivity dropped by 18%, indicating weak robustness of the baseline model (a convolutional neural network, CNN-based crash risk evaluation model). Then, a coverage-oriented adversarial training method was proposed to improve model robustness in highly imbalanced crash and non-crash situations and various crash risk transition patterns. Experiments showed that the proposed method was effective to improve model robustness as it could prevent 76.5% accuracy drops and 98.9% sensitivity drops against TF-AEs. Finally, the evaluation model outputs’ stability and limitations of the current study are discussed.
A full Bayesian multilevel approach for modeling interaction effects in single-vehicle crashes
2023, Accident Analysis and Prevention
Interaction effects constitute crucial crash attributes that can be classified into two distinct categories: spatiotemporal interactions and factor interactions. These interactions are rarely addressed systematically in modeling the severity of single-vehicle (SV) crashes. This study focuses on uncovering these crash attributes by designing a full Bayesian spatiotemporal interaction multilevel logit (STIML-logit) approach with heterogeneity in means and variances (HMV). Meanwhile, a nested Gaussian conditional autoregressive (CAR) structure is proposed to fit the spatiotemporal interaction component and its effectiveness is verified by calibrating four different interaction patterns. A standard multilevel logit (with and without HMV), a multilevel logit with HMV, and a spatiotemporal multilevel logit with HMV are constructed for comparison. Risk factors are decomposed into traffic environment factors (group level) and individual crash factors (case level) to construct a multilevel structure and to capture possible interactions between risk factors from different levels (cross-level factor interactions). We perform regression modeling utilizing SV crash cases covering 96 major urban roads in Shandong, China. The modeling results underscore several significant findings: (1) the STIML-logit with HMV demonstrates the best regression performance, suggesting that systematically dealing with the interaction effects and the HMV is a trustworthy modeling perspective; (2) crash models with the nested CAR outperform those with the traditional CAR and the result is supported by all the spatiotemporal statistical functions, highlighting the potential advantages of the nested structure; (3) all the environment factors maintain significant interactions with the case factors, highlighting that the contribution of the environment factors to crash injuries is not constant but is rather influenced by the specific case-related crash factors. The study introduces a promising regression architecture for modeling crash injuries and revealing subtle crash attributes.
Effects of design consistency measures and roadside hazard types on run-off-road crash severity: Application of random parameters hierarchical ordered probit model
2023, Analytic Methods in Accident Research
Run-off-road crashes are one of the most significant causes of road deaths worldwide. Given such significant safety concerns, a number of earlier studies examined the critical factors contributing towards run-off-road crash severity outcomes, mostly by using the information compiled in the official crash database. However, the official crash databases are less likely to have detailed information on driver behavior (errors/expectations) and roadway environment (roadway geometry and roadside attributes). This study aims to investigate the effects of design consistency measures on run-off-road crash severity mechanisms by applying a random parameters hierarchical ordered Probit model. This study contributes towards existing safety literature by demonstrating a complementary approach to capturing the effects of driver behavior and heterogeneity in roadway environment on run-off-road crash severity outcome through the composite measures of design consistency indices and cosmopolite measures of roadside hazard type variables. Specifically, 17 different functional forms of design consistency indices are developed to capture the behavioral factors from the road-geometric changes in developing run-off-road crash severity models. Further, in examining the effect of different types of the roadside environment on run-off-road crash severity outcomes, seven roadside hazard type variables are generated as a composite function of roadside object type and clear zone (lateral distance to roadside object). The empirical analysis of this study involves a two-step modelling approach - in the first step, the decision tree algorithm is applied to identify the higher-order interaction among independent variables, and in the second step, crash severity models are developed by employing several econometric approaches. The hybrid models are estimated by employing four econometric frameworks, which include Ordered Probit, Hierarchical Ordered Probit, Random Parameters Ordered Probit, and Random parameters Hierarchical Ordered Probit models. The run-off-road crash severity models are estimated by using crash data collected from the State of Queensland, Australia, for the years 2015 through 2019. Overall, this study reveals the importance of considering the interaction of drivers' behavior, road geometry, and roadside attributes along with other independent variables in developing run-off-road crash severity models.
Modelling crash severity outcomes for low speed urban roads using back propagation – Artificial neural network (BP – ANN) – A case study in Indian context
2023, IATSS Research
This work analyses influence of road, weather and crash-specific factors on crash severity outcomes for low-speed urban midblock sections and intersections, for day and night time, using Backpropagation–Artificial Neural Network (BP–ANN). Five-year crash data (2015–2019) from 82Km urban road network of Patna, India was used for the study. The road factors include pavement width, distress condition, marking; shoulder type, condition; road section type as mid-block, intersection and intersection control. Weather factors include season of crash, fog or rain at crash time. Crash factor include collision partner, type and crash time. The most appropriate BP–ANN model architecture was estimated using Misclassification-Rate. It was observed that midblock segments witness higher severities during daytime, whereas intersections witness higher severities during night. Controlled intersections are safer compared to un-controlled intersections. Pavement distress greatly increase the chance of higher severities. Narrow roads record greater severities during day due to lack of surveillance.

View all citing articles on Scopus

View full text

Factors affecting the injury severity of out-of-control single-vehicle crashes in Singapore

Highlights

Abstract

Introduction

Section snippets

Data

Results and discussions

Conclusions

Acknowledgments

Accid. Anal. Prev.

Accid. Anal. Prev.

Accid. Anal. Prev.

Accid. Anal. Prev.

Accid. Anal. Prev.

Transp. Res. Procedia

Accid. Anal. Prev.

Accid. Anal. Prev.

Saf. Sci.

Accid. Anal. Prev.

Accid. Anal. Prev.

Accid. Anal. Prev.

J. Saf. Res.