scholarly journals Determinants and Prediction of Injury Severities in Multi-Vehicle-Involved Crashes

2021 ◽  
Vol 18 (10) ◽  
pp. 5271
Author(s):  
Xiuguang Song ◽  
Rendong Pi ◽  
Yu Zhang ◽  
Jianqing Wu ◽  
Yuhuan Dong ◽  
...  
Keyword(s):  
Machine Learning ◽  
Traffic Safety ◽  
Statistical Models ◽  
Injury Severity ◽  
Safety Information ◽  
Temporal Stability ◽  
Prediction Performance ◽  
Transportation Safety ◽  
Contributing Factors ◽  
Injury Severities

Multi-vehicle (MV) crashes, which can lead to great damages to society, have always been a serious issue for traffic safety. A further understanding of crash severity can help transportation engineers identify the critical reasons and find effective countermeasures to improve transportation safety. However, studies involving methods of machine learning to predict the possibility of injury-severity of MV crashes are rarely seen. Besides that, previous studies have rarely taken temporal stability into consideration in MV crashes. To bridge these knowledge gaps, two kinds of models: random parameters logit model (RPL), with heterogeneities in the means and variances, and Random Forest (RF) were employed in this research to identify the critical contributing factors and to predict the possibility of MV injury-severity. Three-year (2016–2018) MV data from Washington, United States, extracted from the Highway Safety Information System (HSIS), were applied for crash injury-severity analysis. In addition, a series of likelihood ratio tests were conducted for temporal stability between different years. Four indicators were employed to measure the prediction performance of the selected models, and four categories of crash-related characteristics were specifically investigated based on the RPL model. The results showed that the machine learning-based models performed better than the statistical models did when taking the overall accuracy as an evaluation indicator. However, the statistical models had a better prediction performance than the machine learning models had considering crash costs. Temporal instabilities were present between 2016 and 2017 MV data. The effect of significant factors was elaborated based on the RPL model with heterogeneities in the means and variances.

scholarly journals Analyzing Factors Associated with Fatal Road Crashes: A Machine Learning Approach

2020 ◽  
Vol 17 (11) ◽  
pp. 4111
Author(s):  
Ali J. Ghandour ◽  
Huda Hammoud ◽  
Samar Al-Hajj
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Injury Severity ◽  
Road Traffic ◽  
Road Traffic Injury ◽  
Outcome Variable ◽  
Contributing Factors ◽  
Road Crashes ◽  
Factors Associated ◽  
Ensemble Machine Learning

Road traffic injury accounts for a substantial human and economic burden globally. Understanding risk factors contributing to fatal injuries is of paramount importance. In this study, we proposed a model that adopts a hybrid ensemble machine learning classifier structured from sequential minimal optimization and decision trees to identify risk factors contributing to fatal road injuries. The model was constructed, trained, tested, and validated using the Lebanese Road Accidents Platform (LRAP) database of 8482 road crash incidents, with fatality occurrence as the outcome variable. A sensitivity analysis was conducted to examine the influence of multiple factors on fatality occurrence. Seven out of the nine selected independent variables were significantly associated with fatality occurrence, namely, crash type, injury severity, spatial cluster-ID, and crash time (hour). Evidence gained from the model data analysis will be adopted by policymakers and key stakeholders to gain insights into major contributing factors associated with fatal road crashes and to translate knowledge into safety programs and enhanced road policies.

scholarly journals Short-Term Speed Prediction Using Remote Microwave Sensor Data: Machine Learning versus Statistical Model

2016 ◽  
Vol 2016 ◽  
pp. 1-13 ◽  
Author(s):  
Han Jiang ◽  
Yajie Zou ◽  
Shen Zhang ◽  
Jinjun Tang ◽  
Yinhai Wang
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Support Vector Machine ◽  
Statistical Models ◽  
Prediction Performance ◽  
Support Vector ◽  
Beijing City ◽  
Short Term ◽  
Time Step ◽  
Speed Prediction

Recently, a number of short-term speed prediction approaches have been developed, in which most algorithms are based on machine learning and statistical theory. This paper examined the multistep ahead prediction performance of eight different models using the 2-minute travel speed data collected from three Remote Traffic Microwave Sensors located on a southbound segment of 4th ring road in Beijing City. Specifically, we consider five machine learning methods: Back Propagation Neural Network (BPNN), nonlinear autoregressive model with exogenous inputs neural network (NARXNN), support vector machine with radial basis function as kernel function (SVM-RBF), Support Vector Machine with Linear Function (SVM-LIN), and Multilinear Regression (MLR) as candidate. Three statistical models are also selected: Autoregressive Integrated Moving Average (ARIMA), Vector Autoregression (VAR), and Space-Time (ST) model. From the prediction results, we find the following meaningful results: (1) the prediction accuracy of speed deteriorates as the prediction time steps increase for all models; (2) the BPNN, NARXNN, and SVM-RBF can clearly outperform two traditional statistical models: ARIMA and VAR; (3) the prediction performance of ANN is superior to that of SVM and MLR; (4) as time step increases, the ST model can consistently provide the lowest MAE comparing with ARIMA and VAR.

scholarly journals Evaluation of Short-Term Freeway Speed Prediction Based on Periodic Analysis Using Statistical Models and Machine Learning Models

2020 ◽  
Vol 2020 ◽  
pp. 1-16 ◽  
Author(s):  
Xiaoxue Yang ◽  
Yajie Zou ◽  
Jinjun Tang ◽  
Jian Liang ◽  
Muhammad Ijaz
Keyword(s):  
Machine Learning ◽  
Statistical Models ◽  
Prediction Performance ◽  
Periodic Component ◽  
Learning Approaches ◽  
Learning Models ◽  
Short Term ◽  
Speed Prediction ◽  
The Impact ◽  
Machine Learning Models

Accurate prediction of traffic information (i.e., traffic flow, travel time, traffic speed, etc.) is a key component of Intelligent Transportation System (ITS). Traffic speed is an important indicator to evaluate traffic efficiency. Up to date, although a few studies have considered the periodic feature in traffic prediction, very few studies comprehensively evaluate the impact of periodic component on statistical and machine learning prediction models. This paper selects several representative statistical models and machine learning models to analyze the influence of periodic component on short-term speed prediction under different scenarios: (1) multi-horizon ahead prediction (5, 15, 30, 60 minutes ahead predictions), (2) with and without periodic component, (3) two data aggregation levels (5-minute and 15-minute), (4) peak hours and off-peak hours. Specifically, three statistical models (i.e., space time (ST) model, vector autoregressive (VAR) model, autoregressive integrated moving average (ARIMA) model) and three machine learning approaches (i.e., support vector machines (SVM) model, multi-layer perceptron (MLP) model, recurrent neural network (RNN) model) are developed and examined. Furthermore, the periodic features of the speed data are considered via a hybrid prediction method, which assumes that the data consist of two components: a periodic component and a residual component. The periodic component is described by a trigonometric regression function, and the residual component is modeled by the statistical models or the machine learning approaches. The important conclusions can be summarized as follows: (1) the multi-step ahead prediction accuracy improves when considering the periodic component of speed data for both three statistical models and three machine learning models, especially in the peak hours; (2) considering the impact of periodic component for all models, the prediction performance improvement gradually becomes larger as the time step increases; (3) under the same prediction horizon, the prediction performance of all models for 15-minute speed data is generally better than that for 5-minute speed data. Overall, the findings in this paper suggest that the proposed hybrid prediction approach is effective for both statistical and machine learning models in short-term speed prediction.

scholarly journals Formulating alcohol-influenced driver’s injury severities in intersection-related crashes

Transport ◽  
2016 ◽  
Vol 33 (1) ◽  
pp. 165-176 ◽  
Author(s):  
Qiong Wu ◽  
Guohui Zhang
Keyword(s):  
New Mexico ◽  
Traffic Safety ◽  
Practical Importance ◽  
Safety Performance ◽  
Highway Traffic ◽  
Contributing Factors ◽  
Severe Injuries ◽  
National Highway Traffic Safety ◽  
Causal Factors ◽  
Injury Severities

Approximately one third of all traffic fatal crashes are alcohol-related in the US according to the National Highway Traffic Safety Administration (NHTSA), alcohol-related crashes cost more than $37 billion annually. Considerable research efforts are needed to understand better significant causal factors for alcohol-related crash risks and driver’s injury severities in order to develop effective countermeasures and proper policies for system-wide traffic safety performance improvements. Furthermore, since two thirds of urban Vehicle Miles Traveled (VMT) is on signal-controlled roadways, it is of practical importance to investigate injury severities of all drivers who are involved in intersection-related crashes and their corresponding significant causal factors due to control and geometric impacts on flow progression interruptions. This study aims to identify and quantify the impacts of alcohol/non-alcohol-influenced driver’s behavior and demographic features as well as geometric and environmental characteristics on driver’s injury severities around intersections in New Mexico. The econometric models, multinomial Logit models, were developed to analyze injury severities for regular sober drivers and alcohol-influenced drivers, respectively, using the crash data collected in New Mexico from 2010 to 2011. Elasticity analyzes were conducted in order to understand better the quantitative impacts of these contributing factors on driver’s injury outcomes. The research findings provide a better understanding of contributing factors and their impacts on driver injury severities in crashes around intersections. For example, the probability of having severe injuries is higher for non-alcohol-influenced drivers when the drivers are 65 years old or older. Drivers’ left-turning action will increase non-alcohol-influenced driver injury severities in crash occurring around intersections. However, different characteristics are captured for alcohol-influenced drivers involved in intersection-related crashes. For example, more severe injuries of alcohol-influenced drivers can be observed around intersections with three or more lanes on each approach. The model specifications and estimation results are also helpful for transportation agencies and decision makers to develop cost-effective solutions to reduce alcohol-involved crash severities and improve traffic system safety performance.

scholarly journals Analysis of Intersection Traffic Safety in the City of San Antonio, 2013–2017

2021 ◽  
Vol 13 (9) ◽  
pp. 5296
Author(s):  
Khondoker Billah ◽  
Qasim Adegbite ◽  
Hatim O. Sharif ◽  
Samer Dessouky ◽  
Lauren Simcic
Keyword(s):  
High Risk ◽  
Traffic Safety ◽  
Traffic Control ◽  
Injury Severity ◽  
San Antonio ◽  
Binary Logistic Regression ◽  
Bivariate Analysis ◽  
Crash Severity ◽  
Contributing Factors ◽  
Late Night

An understanding of the contributing factors to severe intersection crashes is crucial for developing countermeasures to reduce crash numbers and severity at high-risk crash locations. This study examined the variables affecting crash incidence and crash severity at intersections in San Antonio over a five-year period (2013–2017) and identified high-risk locations based on crash frequency and injury severity using data from the Texas Crash Record and Information System database. Bivariate analysis and binary logistic regression, along with respective odds ratios, were used to identify the most significant variables contributing to severe intersection crashes by quantifying their association with crash severity. Intersection crashes were predominantly clustered in the downtown area with relatively less severe crashes. Males and older drivers, weekend driving, nighttime driving, dark lighting conditions, grade and hillcrest road alignment, and crosswalk, divider and marked lanes used as traffic control significantly increased crash severity risk at intersections. Prioritizing resource allocation to high-risk intersections, separating bicycle lanes and sidewalks from the roadway, improving lighting facilities, increasing law enforcement activity during the late night hours of weekend, and introducing roundabouts at intersections with stops and signals as traffic controls are recommended countermeasures.

Integrated Modeling Approach for Non-Motorized Mode Trips and Fatal Crashes in the Framework of Transportation Safety Planning

2018 ◽  
Vol 2672 (32) ◽  
pp. 49-60 ◽  
Author(s):  
Jaeyoung Lee ◽  
Mohamed Abdel-Aty ◽  
Qing Cai ◽  
Ling Wang ◽  
Helai Huang
Keyword(s):  
Traffic Safety ◽  
Prediction Models ◽  
Census Bureau ◽  
Integrated Modeling ◽  
Transportation Safety ◽  
Safety Planning ◽  
Contributing Factors ◽  
Modeling Approach ◽  
Exposure Variable ◽  
Safety Models

In recent decades, considerable efforts have been made to incorporate traffic safety into long-term transportation plans (LTTPs), a process which is often termed transportation safety planning (TSP). Although some researchers have attempted to integrate transportation plans and safety by adopting transportation planning data (e.g., trip generation) for estimating traffic crash frequency at the macroscopic level, no studies have attempted to develop trip and safety models in one structure simultaneously. A Bayesian integrated multivariate modeling approach is suggested for estimating trips and crashes of non-motorized modes (i.e., walking and cycling). American Housing Survey (AHS) data were collected from the U.S. Census Bureau and were used for the proposed approach. In the first part of the proposed model, the probabilities of choosing walking and cycling modes were estimated, and the estimated probabilities were converted to trips by multiplying the number of sampled households. In the second part, the estimated trips were fed into crash prediction models (or safety performance functions) as an exposure variable. The modeling result revealed many contributing factors for pedestrian/bicycle trips and crashes. Possible shared unobserved features between pedestrian and bicycle trips, and between pedestrian and bicycle crashes, were accounted for by adopting a multivariate structure. In addition, it was found that the crash models with the estimated exposures outperform those with the observed exposures. It is expected that the integrated modeling approach for trips and crashes in this study will provide great insights into the future directions of TSP.

Multi-Vehicle Crashes Involving Large Trucks: A Random Parameter Discrete Outcome Modeling Approach

2015 ◽  
Author(s):  
Mouyid Islam
Keyword(s):  
Injury Severity ◽  
Economic Impacts ◽  
Mixed Logit ◽  
Random Parameter ◽  
Ordered Probit ◽  
Vehicle Crashes ◽  
Contributing Factors ◽  
Modeling Approach ◽  
Complex Interactions ◽  
Injury Severities

A growing concern on large-truck crashes increased over the years due to the potential economic impacts and level of injury severity. This study aims to analyze the injury severities of multi-vehicle large-trucks crashes on national highways. To capture and understand the complexities of contributing factors, two random parameter discrete outcome models – random parameter ordered probit and mixed logit – were estimated to predict the likelihood of five injury severity outcomes: fatal, incapacitating, non-incapacitating, possible injury, and no-injury. Estimation findings indicate that the level of injury severity is highly influenced by a number of complex interactions of factors, namely, human, vehicular, road-environmental, and crash dynamics that can vary across the observations.

Factors Affecting Driver Injury Severity in the Wrong-Way Crash: Accounting for Potential Heterogeneity in Means and Variances of Random Parameters

2021 ◽  
pp. 036119812110098
Author(s):  
Miao Yu ◽  
Jinxing Shen ◽  
Changxi Ma
Keyword(s):  
High Speed ◽  
Injury Severity ◽  
Unobserved Heterogeneity ◽  
Research Effort ◽  
Random Parameter ◽  
Policy Implications ◽  
Contributing Factors ◽  
Severe Injuries ◽  
Data Set ◽  
Severity Levels

Because of the high percentage of fatalities and severe injuries in wrong-way driving (WWD) crashes, numerous studies have focused on identifying contributing factors to the occurrence of WWD crashes. However, a limited number of research effort has investigated the factors associated with driver injury-severity in WWD crashes. This study intends to bridge the gap using a random parameter logit model with heterogeneity in means and variances approach that can account for the unobserved heterogeneity in the data set. Police-reported crash data collected from 2014 to 2017 in North Carolina are used. Four injury-severity levels are defined: fatal injury, severe injury, possible injury, and no injury. Explanatory variables, including driver characteristics, roadway characteristics, environmental characteristics, and crash characteristics, are used. Estimation results demonstrate that factors, including the involvement of alcohol, rural area, principal arterial, high speed limit (>60 mph), dark-lighted conditions, run-off-road collision, and head-on collision, significantly increase the severity levels in WWD crashes. Several policy implications are designed and recommended based on findings.

scholarly journals Prediction of Healing Performance of Autogenous Healing Concrete Using Machine Learning

Materials ◽  
2021 ◽  
Vol 14 (15) ◽  
pp. 4068
Author(s):  
Xu Huang ◽  
Mirna Wasouf ◽  
Jessada Sresakoolchai ◽  
Sakdirat Kaewunruen
Keyword(s):  
Machine Learning ◽  
Search Algorithm ◽  
Weather Conditions ◽  
Prediction Performance ◽  
Machine Learning Algorithms ◽  
Coefficient Of Determination ◽  
Gradient Boosting ◽  
Support Vector ◽  
Self Healing ◽  
Artificial Neural Network Ann

Cracks typically develop in concrete due to shrinkage, loading actions, and weather conditions; and may occur anytime in its life span. Autogenous healing concrete is a type of self-healing concrete that can automatically heal cracks based on physical or chemical reactions in concrete matrix. It is imperative to investigate the healing performance that autogenous healing concrete possesses, to assess the extent of the cracking and to predict the extent of healing. In the research of self-healing concrete, testing the healing performance of concrete in a laboratory is costly, and a mass of instances may be needed to explore reliable concrete design. This study is thus the world’s first to establish six types of machine learning algorithms, which are capable of predicting the healing performance (HP) of self-healing concrete. These algorithms involve an artificial neural network (ANN), a k-nearest neighbours (kNN), a gradient boosting regression (GBR), a decision tree regression (DTR), a support vector regression (SVR) and a random forest (RF). Parameters of these algorithms are tuned utilising grid search algorithm (GSA) and genetic algorithm (GA). The prediction performance indicated by coefficient of determination (R2) and root mean square error (RMSE) measures of these algorithms are evaluated on the basis of 1417 data sets from the open literature. The results show that GSA-GBR performs higher prediction performance (R2GSA-GBR = 0.958) and stronger robustness (RMSEGSA-GBR = 0.202) than the other five types of algorithms employed to predict the healing performance of autogenous healing concrete. Therefore, reliable prediction accuracy of the healing performance and efficient assistance on the design of autogenous healing concrete can be achieved.

Sign in / Sign up

Export Citation Format

Share Document