Method for Identifying Factors Contributing to Driver-Injury Severity in Traffic Crashes

2000 ◽  
Vol 1717 (1) ◽  
pp. 1-9 ◽  
Author(s):  
Wan-Hui Chen ◽  
Paul P. Jovanis
Keyword(s):  
Injury Severity ◽  
Statistical Tests ◽  
Selection Procedure ◽  
Weather Conditions ◽  
Early Morning ◽  
Influential Factors ◽  
Complex Nature ◽  
Crash Data ◽  
Late Night ◽  
Log Linear

Numerous driver, vehicle, roadway, and environmental factors contribute to crash-injury severity. In addition to main effects, interactions between factors are very likely to be significant. The large number of potentially important factors, combined with the complex nature of crash etiology and injury outcome, present significant challenges to the safety analyst, who must select from a large number of factors and specify a comprehensive but feasible set of main factors and interactions for testing in statistical models. In addition, some factors contain a relatively large number of categories (e.g., weather conditions), and the selection of cut-off points for categorization of continuous factors may not be readily obvious (e.g., driver age). It is also important that statistical tests underlying these analyses accurately address the frequent problem of data sparseness. The development and testing of a variable-selection procedure to address each of these problems is the stated objective. Bus-involved crash data for Freeway 1 in Taiwan from 1985 through 1993 were used to screen a set of 39 possible influential factors, along with interactions. The final log-linear model shows that late-night or early-morning driving increases the risk for bus drivers of being severely injured, particularly when the drivers caused the accident or when the drivers were involved in rear-end accidents. Bus accidents involving large trucks or tractor-trailers also increase the risk. An assessment of the importance of considering interactions in crash models is presented as a conclusion.

scholarly journals Walking against or with traffic? Evaluating pedestrian fatalities and head injuries in Taiwan

2019 ◽  
Vol 19 (1) ◽  
Author(s):  
Chih-Wei Pai ◽  
Ping-Ling Chen ◽  
Shiao-Tzu Ma ◽  
Shan-Hong Wu ◽  
Václav Linkov ◽  
...  
Keyword(s):  
Head Injuries ◽  
Weather Conditions ◽  
Influential Factors ◽  
Traffic Crashes ◽  
Logistic Regression Models ◽  
Crash Data ◽  
The United Kingdom ◽  
Sight Distance ◽  
Adverse Weather ◽  
Negative Effect

Abstract Background Allowing contraflow cycling on one-way streets has been reported to reduce crash risks in Belgium and the United Kingdom. Similarly, walking against traffic on roadways without sidewalks substantially improves pedestrian safety. This study examined fatalities and head injuries sustained by pedestrians in against-traffic and with-traffic crashes. Methods Using police-reported crash data in Taiwan between 2011 and 2016, fatalities and head injuries were compared for pedestrians involved in against-traffic and with-traffic crashes. Results Of the 14,382 pedestrians involved in crashes, 10,749 and 3633 pedestrians in with-traffic and against-traffic crashes, respectively, were reported. Compared with pedestrians involved in against-traffic crashes, those in with-traffic crashes were more likely to sustain fatalities and head injuries. Results of logistic regression models revealed several influential factors on pedestrian fatalities and head injuries, including elderly pedestrians, male drivers, intoxicated drivers, rural roadways, unlit streets in darkness, limited sight distance, adverse weather conditions, midnight hours, and a heavy vehicle as the crash partner. Conclusions Pedestrians in with-traffic crashes were more likely to sustain fatalities and head injuries compared with those in against-traffic crashes. Furthermore, the negative effect of walking with traffic on injuries was more pronounced in reduced-visibility conditions.

scholarly journals Investigating the Risk Factors Associated with the Severity of the Pedestrians Injured on Spanish Crosstown Roads

2019 ◽  
Vol 11 (19) ◽  
pp. 5194 ◽  
Author(s):  
Natalia Casado-Sanz ◽  
Begoña Guirao ◽  
Antonio Lara Galera ◽  
Maria Attard
Keyword(s):  
Risk Factors ◽  
Injury Severity ◽  
Motor Vehicle ◽  
Weather Conditions ◽  
Crash Data ◽  
Factors Associated ◽  
The Road ◽  
Pedestrian Injury ◽  
On The Road ◽  
Pedestrian Crashes

According to the Spanish General Traffic Accident Directorate, in 2017 a total of 351 pedestrians were killed, and 14,322 pedestrians were injured in motor vehicle crashes in Spain. However, very few studies have been conducted in order to analyse the main factors that contribute to pedestrian injury severity. This study analyses the accidents that involve a single vehicle and a single pedestrian on Spanish crosstown roads from 2006 to 2016 (1535 crashes). The factors that explain these accidents include infractions committed by the pedestrian and the driver, crash profiles, and infrastructure characteristics. As a preliminary tool for the segmentation of 1535 pedestrian crashes, a k-means cluster analysis was applied. In addition, multinomial logit (MNL) models were used for analysing crash data, where possible outcomes were fatalities and severe and minor injured pedestrians. According to the results of these models, the risk factors associated with pedestrian injury severity are as follows: visibility restricted by weather conditions or glare, infractions committed by the pedestrian (such as not using crossings, crossing unlawfully, or walking on the road), infractions committed by the driver (such as distracted driving and not respecting a light or a crossing), and finally, speed infractions committed by drivers (such as inadequate speed). This study proposes the specific safety countermeasures that in turn will improve overall road safety in this particular type of road.

scholarly journals Analysis of Traffic Crashes Caused by Motorcyclists Running Red Lights in Guangdong Province of China

2021 ◽  
Vol 18 (2) ◽  
pp. 553
Author(s):  
Guangnan Zhang ◽  
Ying Tan ◽  
Qiaoting Zhong ◽  
Ruwei Hu
Keyword(s):  
Injury Severity ◽  
Negative Impact ◽  
Red Light ◽  
Guangdong Province ◽  
Random Parameter ◽  
Early Morning ◽  
Crash Data ◽  
Primary Means ◽  
Dark Conditions ◽  
Motorcycle Rider

Motorcycles are among the primary means of transport in China, and the phenomenon of motorcyclists running red lights is becoming increasingly prevalent. Based on the traffic crash data for 2006–2010 in Guangdong Province, China, fixed- and random-parameter logit models are used to study the characteristics of motorcyclists, vehicles, roads, and environments involved in red light violations and injury severity resulting from motorcyclists’ running red lights in China. Certain factors that affect the probability of motorcyclists running red lights are identified. For instance, while the likelihood of violating red light signals during dark conditions is lower than during light conditions for both car drivers and pedestrians, motorcyclists have significantly increased probability of a red light violation during dark conditions. For the resulting severe casualties in red-light-running crashes, poor visibility is a common risk factor for motorcyclists and car drivers experiencing severe injury. Regarding the relationship between red light violations and the severity of injuries in crashes caused by motorcyclists running red lights, this study indicated that driving direction and time period have inconsistent effects on the probability of red light violations and the severity of injuries. On the one hand, the likelihood of red light violations when a motorcycle rider is turning left/right is higher than when going straight, but this turning factor has a nonsignificant impact on the severity of injuries; on the other hand, reversing, making a U-turn and changing lanes have nonsignificant effects on the probability of motorcyclists’ red light violations in contrast to going straight, but have a very significant impact on the severity of injuries. Moreover, the likelihood of red light violations during the early morning is higher than off-peak hours, but this time factor has a negative impact on the severity of injuries. Measures including road safety educational programs for targeted groups and focused enforcement of traffic policy and regulations are suggested to reduce the number of crashes and the severity of injuries resulting from motorcyclists running red lights.

scholarly journals Analysis of Severe Injuries in Crashes Involving Large Trucks Using K-Prototypes Clustering-Based GBDT Model

Safety ◽  
2021 ◽  
Vol 7 (2) ◽  
pp. 32
Author(s):  
Syed As-Sadeq Tahfim ◽  
Chen Yan
Keyword(s):  
Injury Severity ◽  
Unobserved Heterogeneity ◽  
The United States ◽  
Clustering Methods ◽  
Severe Injuries ◽  
Traffic Crash ◽  
Crash Data ◽  
Boosted Decision Trees ◽  
The Individual ◽  
Crash Characteristics

The unobserved heterogeneity in traffic crash data hides certain relationships between the contributory factors and injury severity. The literature has been limited in exploring different types of clustering methods for the analysis of the injury severity in crashes involving large trucks. Additionally, the variability of data type in traffic crash data has rarely been addressed. This study explored the application of the k-prototypes clustering method to countermeasure the unobserved heterogeneity in large truck-involved crashes that had occurred in the United States between the period of 2016 to 2019. The study segmented the entire dataset (EDS) into three homogeneous clusters. Four gradient boosted decision trees (GBDT) models were developed on the EDS and individual clusters to predict the injury severity in crashes involving large trucks. The list of input features included crash characteristics, truck characteristics, roadway attributes, time and location of the crash, and environmental factors. Each cluster-based GBDT model was compared with the EDS-based model. Two of the three cluster-based models showed significant improvement in their predicting performances. Additionally, feature analysis using the SHAP (Shapley additive explanations) method identified few new important features in each cluster and showed that some features have a different degree of effects on severe injuries in the individual clusters. The current study concluded that the k-prototypes clustering-based GBDT model is a promising approach to reveal hidden insights, which can be used to improve safety measures, roadway conditions and policies for the prevention of severe injuries in crashes involving large trucks.

Examining Driver Injury Severity in Single-Vehicle Road Departure Crashes Involving Large Trucks

2021 ◽  
pp. 036119812110101
Author(s):  
Mehdi Hosseinpour ◽  
Kirolos Haleem
Keyword(s):  
Rural Areas ◽  
Injury Severity ◽  
Factors Affecting ◽  
Crash Data ◽  
Natural Logarithm ◽  
Concrete Barriers ◽  
Local Roads ◽  
Single Vehicle ◽  
Safety Countermeasures ◽  
Injury Severities

Road departure (RD) crashes are among the most severe crashes that can result in fatal or serious injuries, especially when involving large trucks. Most previous studies neglected to incorporate both roadside and median hazards into large-truck RD crash severity analysis. The objective of this study was to identify the significant factors affecting driver injury severity in single-vehicle RD crashes involving large trucks. A random-parameters ordered probit (RPOP) model was developed using extensive crash data collected on roadways in the state of Kentucky between 2015 and 2019. The RPOP model results showed that the effect of local roadways, the natural logarithm of annual average daily traffic (AADT), the presence of median concrete barriers, cable barrier-involved collisions, and dry surfaces were found to be random across the crash observations. The results also showed that older drivers, ejected drivers, and drivers trapped in their truck were more likely to sustain severe single-vehicle RD crashes. Other variables increasing the probability of driver injury severity have included rural areas, dry road surfaces, higher speed limits, single-unit truck types, principal arterials, overturning-consequences, truck fire occurrence, segments with median concrete barriers, and roadside fixed object strikes. On the other hand, wearing seatbelt, local roads and minor collectors, higher AADT, and hitting median cable barriers were associated with lower injury severities. Potential safety countermeasures from the study findings include installing median cable barriers and flattening steep roadside embankments along those roadway stretches with high history of RD large-truck-related crashes.

scholarly journals Testing the Validity of a Link Function Assumption in Repeated Type-II Censored General Step-Stress Experiments

Sankhya B ◽  
2021 ◽  
Author(s):  
Stefan Bedbur ◽  
Thomas Seiche
Keyword(s):  
Null Hypothesis ◽  
Statistical Tests ◽  
Operating Conditions ◽  
Link Function ◽  
Asymptotic Results ◽  
Failure Data ◽  
Stress Levels ◽  
Log Linear ◽  
Multiple Samples ◽  
General Step

AbstractIn step-stress experiments, test units are successively exposed to higher usually increasing levels of stress to cause earlier failures and to shorten the duration of the experiment. When parameters are associated with the stress levels, one problem is to estimate the parameter corresponding to normal operating conditions based on failure data obtained under higher stress levels. For this purpose, a link function connecting parameters and stress levels is usually assumed, the validity of which is often at the discretion of the experimenter. In a general step-stress model based on multiple samples of sequential order statistics, we provide exact statistical tests to decide whether the assumption of some link function is adequate. The null hypothesis of a proportional, linear, power or log-linear link function is considered in detail, and associated inferential results are stated. In any case, except for the linear link function, the test statistics derived are shown to have only one distribution under the null hypothesis, which simplifies the computation of (exact) critical values. Asymptotic results are addressed, and a power study is performed for testing on a log-linear link function. Some improvements of the tests in terms of power are discussed.

Trends and Variability of North American Cool-Season Extratropical Cyclones: 1979–2019

2021 ◽  
Author(s):  
Robert Fritzen ◽  
Victoria Lang ◽  
Vittorio A. Gensini
Keyword(s):  
North American ◽  
Research Question ◽  
Weather Conditions ◽  
Extratropical Cyclones ◽  
Mountain Range ◽  
Cool Season ◽  
The North ◽  
Primary Driver ◽  
Regional Reanalysis ◽  
Log Linear

AbstractExtratropical cyclones are the primary driver of sensible weather conditions across the mid-latitudes of North America, often generating various types of precipitation, gusty non-convective winds, and severe convective storms throughout portions of the annual cycle. Given ongoing modifications of the zonal atmospheric thermal gradient due to anthropogenic forcing, analyzing the historical characteristics of these systems presents an important research question. Using the North American Regional Reanalysis, boreal cool-season (October–April) extratropical cyclones for the period 1979–2019 were identified, tracked, and classified based on their genesis location. Additionally, bomb cyclones—extratropical cyclones that recorded a latitude normalized pressure fall of 24 hPa in 24-hr—were identified and stratified for additional analysis. Cyclone lifespan across the domain exhibits a log-linear relationship, with 99% of all cyclones tracked lasting less than 8 days. On average, ≈ 270 cyclones were tracked across the analysis domain per year, with an average of ≈ 18 year−1 being classified as bomb cyclones. The average number of cyclones in the analysis domain has decreased in the last 20 years from 290 year−1 during the period 1979–1999 to 250 year−1 during the period 2000–2019. Spatially, decreasing trends in the frequency of cyclone track counts were noted across a majority of the analysis domain, with the most significant decreases found in Canada’s Northwest Territories, Colorado, and east of the Graah mountain range. No significant interannual or spatial trends were noted with bomb cyclone frequency.

Machine Learning Methods to Analyze Injury Severity of Drivers from Different Age and Gender Groups

2018 ◽  
Vol 2672 (38) ◽  
pp. 171-183 ◽  
Author(s):  
Somayeh Mafi ◽  
Yassir AbdelRazig ◽  
Ryan Doczy
Keyword(s):  
Machine Learning ◽  
Injury Severity ◽  
Road Traffic ◽  
Sensitive Data ◽  
Learning Methods ◽  
Safety Measures ◽  
Crash Data ◽  
Machine Learning Methods ◽  
And Gender ◽  
Gender Groups

Access to non-biased and accurate models capable of predicting driver injury severity of collision events is vital for determining what safety measures should be implemented at intersections. Inadequate models can underestimate the potential for collision events to result in driver fatalities or injuries, which can lead to improperly assessing the safety criteria of an intersection. This study investigates how injury severity differs between drivers of various ages and gender groups using cost-sensitive data-mining models. Previous research efforts have used machine learning methods for predicting injury severity; however, these studies did not consider the consequences (cost) of incorrect predictions. This paper addresses this shortfall by considering the monetary cost of incorrect injury severity predictions when developing C4.5, instance-based (IB), and random forest (RF) machine-learning models. One model of each method was developed for four distinct cohorts of drivers (i.e., younger males, younger females, older males, and older females). Each model considered a selection of driver, vehicular, road/traffic, environmental, and crash parameters for determining if they significantly influenced driver injury severity. A five-year period of two-vehicle crash data collected at signalized intersections in the metropolitan area of Miami, Florida was used in the models. Results indicated that cost-sensitive learning classifiers were superior to regular classifiers at accurately predicting injuries and fatalities of crashes. Among cost-sensitive models, RF outperformed C4.5 and IB models in predicting driver injury severity for four groups of drivers. The models displayed substantial differences in injury severity determinants across the age/gender cohorts.

Sign in / Sign up

Export Citation Format

Share Document