Investigation of Effects of Underreporting Crash Data on Three Commonly Used Traffic Crash Severity Models

2011 ◽  
Vol 2241 (1) ◽  
pp. 51-58 ◽  
Author(s):  
Fan Ye ◽  
Dominique Lord
Keyword(s):  
Crash Severity ◽  
Traffic Crash ◽  
Crash Data

Integrating Crime and Traffic Crash Data in Nashville

2010 ◽  
Author(s):  
Jason Wyatt ◽  
Michael Alexander
Keyword(s):  
Traffic Crash ◽  
Crash Data

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.

scholarly journals Comparison of Factors Affecting Crash Severities in Hit-and-Run and Non-Hit-and-Run Crashes

2018 ◽  
Vol 2018 ◽  
pp. 1-11 ◽  
Author(s):  
Bei Zhou ◽  
Zongzhi Li ◽  
Shengrui Zhang
Keyword(s):  
Comparison Group ◽  
Reference Group ◽  
Multinomial Logistic Regression ◽  
Crash Severity ◽  
Property Damage ◽  
Average Percentage ◽  
Crash Data ◽  
Hit And Run ◽  
The Impact ◽  
Average Percentage Deviation

A hit-and-run (HR) crash occurs when the driver of the offending vehicle flees the crash scene without reporting it or aiding the victims. The current study aimed at contributing to existing literatures by comparing factors which might affect the crash severity in HR and non-hit-and-run (NHR) crashes. The data was extracted from the police-reported crash data from September 2017 to August 2018 within the City of Chicago. Two multinomial logistic regression models were established for the HR and NHR crash data, respectively. The odds ratio (OR) of each variable was used to quantify the impact of this variable on the crash severity. In both models, the property damage only (PDO) crash was selected as the reference group, and the injury and fatal crash were chosen as the comparison group. When the injury crash was taken as the comparison group, it was found that 12 variables contributed to the crash severities in both HR and NHR model. The average percentage deviation of OR for these 12 variables was 34%, indicating that compared with property damage, HR crashes were 34% more likely to result in injuries than NHR crashes on average. When fatal crashes were chosen as the comparison group, 2 variables were found to be statistically significant in both the HR and the NHR model. The average percentage deviation of OR for these 2 variables was 127%, indicating that compared with property damage, HR crashes were 127% more likely to result in fatalities than NHR crashes on average.

scholarly journals Collective Risk Ranking of Highway Segments on the Basis of Severity-Weighted Crash Rates

2020 ◽  
Vol 2020 ◽  
pp. 1-9
Author(s):  
Dawei Li ◽  
Mustafa F. M. Al-Mahamda
Keyword(s):  
Empirical Bayes ◽  
Safety Information ◽  
Crash Severity ◽  
Regression To The Mean ◽  
Factors Affecting ◽  
Crash Data ◽  
Crash Rates ◽  
Risk Ranking ◽  
Collective Risk ◽  
Major Factors

This study is intended to focus on the major factors affecting traffic crash rates and severity levels, in addition to identifying crash-prone locations (i.e., black spots) based on the two indicators. The available crash data for different road segments used for the analysis were obtained from the Washington state database provided by the Highway Safety Information System (HSIS) for the years 2006 to 2011. A Random Forest (RF) classifier was used to predict the outcome level of crash severity, while crash rates were predicted by applying RF regressor. Certain features were selected for each model besides the abstraction of new features to check if there are unobserved correlations affecting the independent variables, such as accounting for the number and weight of crashes within 1 km2 area by implementing the Getis-Ord Gi∗ index. Moreover, to calculate the collective risk (CR) score, crash rates were adjusted to incorporate crash severity weights (cost per severity type) and regression-to-the-mean (RTM) bias via Empirical Bayes (EB) method. Finally, segments were ranked according to their CR score.

scholarly journals Analyzing Traffic Crash Severity With Combination of Information Entropy and Bayesian Network

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 63288-63302 ◽  
Author(s):  
Fang Zong ◽  
Xiangru Chen ◽  
Jinjun Tang ◽  
Ping Yu ◽  
Ting Wu
Keyword(s):  
Bayesian Network ◽  
Information Entropy ◽  
Crash Severity ◽  
Traffic Crash

Effects of Rural Highway Median Treatments and Access

2005 ◽  
Vol 1931 (1) ◽  
pp. 99-107 ◽  
Author(s):  
J. L. Gattis ◽  
Ramasubramaniyan Balakumar ◽  
Lynette K. Duncan
Keyword(s):  
Land Use ◽  
Crash Severity ◽  
Crash Frequency ◽  
Crash Data ◽  
Crash Rates ◽  
Access Frequency ◽  
Stop Sign ◽  
Median Volume ◽  
Rural Highway ◽  
Median Width

The safety records of rural and suburban four-lane highways in Arkansas as a function of median treatment and access density were examined. The study excluded roadways with posted speeds lower than 64 km/h (40 mph) and excluded fully controlled access roadways. When entering an urban area, the segments were normally terminated when the first traffic signal or stop sign was encountered. By using 3 years of crash data, the analyses revealed a number of relationships relating crash frequency to median, volume, and access frequency attributes. Crash severity and crash type were also examined. As median width increased, there was a weak but statistically significant decline in the crash rate. There was a weak but statistically significant increase in the crash rate as access density increased. The roadways with shoulders and depressed medians had the lowest crash rates, and the roadways with no median (i.e., painted centerline) and curbs had the worst safety record. An inspection of these data suggests that there may be a correlation between median type and land use type: certain types of median are more likely to be present in certain land use environments. This raises the possibility that in this and in other studies of the safety effects of median treatments, the findings may be influenced or skewed by correlations between median type and land use or surroundings or by other factors.

Safety of Freeway Service Patrol Operations: Case Study of Florida Road Rangers

2018 ◽  
Vol 2672 (33) ◽  
pp. 31-41 ◽  
Author(s):  
Grady Carrick ◽  
Sivaramakrishnan Srinivasan ◽  
Khajonsak Jermprapai
Keyword(s):  
Drug Use ◽  
Incident Management ◽  
Work Zones ◽  
Traffic Crashes ◽  
Traffic Incidents ◽  
Traffic Crash ◽  
Crash Data ◽  
Time Period ◽  
Suitable Case

Safety service patrols are a proven strategy to mitigate the effects of traffic incidents through quick clearance, incident management, and assistance to other incident responders like police, fire, emergency medical services, and towing. As encountered by other responders, working on or near roadways presents unique hazards for safety service patrol vehicles and operators. Road Rangers are Florida’s branded safety service patrols and, as a mature program with over 100 beats, a suitable case study for safety. This research combined an analysis of Road Ranger traffic crash data for 3 years with a comprehensive safety survey of more than 200 operators to determine safety characteristics related to service patrols. Comparing 200 Road Ranger traffic crashes from 2014 through 2016 with all Florida freeway crashes for the same time period revealed that Road Ranger crashes are five times more likely to involve a parked vehicle, and involve two or more vehicles 95% of the time. Pedestrian involvement, nighttime, shoulder locations, and work zones have higher representation for Road Ranger crashes, but weather is not a factor. Alcohol is three times more likely, drug use five times more likely, and distraction slightly higher when Road Ranger vehicles are struck. A survey of 217 Road Ranger drivers revealed that they are keenly aware of important safety topics like high-visibility safety apparel, non-traffic side vehicle approaches, and the dangers of working where there is limited lateral buffer space. Drivers overwhelmingly believe that they have the training and equipment necessary to do their jobs safely.

Sign in / Sign up

Export Citation Format

Share Document