Association between Crash Attributes and Drivers’ Crash Involvement: A Study Based on Police-Reported Crash Data

Abstract

Understanding the association between crash attributes and drivers’ crash involvement in different types of crashes can help figure out the causation of crashes. The aim of this study was to examine the involvement in different types of crashes for drivers from different age groups, by using the police-reported crash data from 2014 to 2016 in Shenzhen, China. A synthetic minority oversampling technique (SMOTE) together with edited nearest neighbors (ENN) were used to solve the data imbalance problem caused by the lack of crash records of older drivers. Logistic regression was utilized to estimate the probability of a certain type of crashes, and odds ratios that were calculated based on the logistic regression results were used to quantify the association between crash attributes and drivers’ crash involvement in different types of crashes. Results showed that drivers’ involvement patterns in different crash types were affected by different factors, and the involvement patterns differed among the examined age groups. Knowledge generated from the present study could help improve the development of countermeasures for driving safety enhancement.

Road Traffic Injuries among Women Brought to the Largest Tertiary Hospital in the Philippines

“…This may be due to the rush-hour that often occurs as individuals rush back home as work ends at around 5 or 6 in the evening. This was similar to the results of the study by 23 where they observed a higher association of road crashes during the latter half of the day among young and middle-aged drivers. Younger drivers, in particular, were also more likely to be involved in a car crash during the first few hours' past midnight.…”

“…36 Driver behavior also has an effect on pedestrian safety as multiple studies have reported drivers colliding with pedestrians due to poorer experience and risky behaviors on the road. 7,19,23,37 These studies show that pedestrians remain as one of the most vulnerable, yet most neglected road user in terms of road infrastructure design that should promote their safety.…”

“…Younger drivers, in particular, were also more likely to be involved in a car crash during the first few hours' past midnight. 23 Crashes occurring at the latter hours of the night may also be likely to involve the use of alcohol or other intoxicating substances, which can affect a driver's judgement and predispose them to road crashes. 24 It is important to note this as the study also observed that some women road crash admissions involved alcohol.…”

Insights into Factors Affecting Traffic Accident Severity of Novice and Experienced Drivers: A Machine Learning Approach

“…To integrate the advantages of over-sampling and over-sampling, the SMOTE-ENN method firstly uses SMOTE method to achieve over-sampling on the minority class samples and then finishes under-sampling on the majority class samples by using ENN method. This method preserves the features of majority samples and increases the characteristics of minority samples, has good classification performance for unbalanced datasets [ 38 ], and it is widely used in traffic safety analysis [ 39 , 40 , 41 ].…”

Individual Driver Crash Risk Classification Based on IoV Data and Offline Consumer Behavior Data

“…Lombardi et al [18] analyzed 120,809 fatal accidents in the US during the period 2011-2014 and found that most drivers in fatal intersection crashes were either teenage drivers or older drivers. Li et al [19] found that different crash types were affected by different factors. For instance, the drivers in crashes that took place on rainy days were in many cases young drivers or old drivers.…”