Analysis of Factors Affecting Hit-and-Run and Non-Hit-and-Run in Vehicle-Bicycle Crashes: A Non-Parametric Approach Incorporating Data Imbalance Treatment

Abstract

Hit-and-run (HR) crashes refer to crashes involving drivers of the offending vehicle fleeing incident scenes without aiding the possible victims or informing authorities for emergency medical services. This paper aims at identifying significant predictors of HR and non-hit-and-run (NHR) in vehicle-bicycle crashes based on the classification and regression tree (CART) method. An oversampling technique is applied to deal with the data imbalance problem, where the number of minority instances (HR crash) is much lower than that of the majority instances (NHR crash). The police-reported data within City of Chicago from September 2017 to August 2018 is collected. The G-mean (geometric mean) is used to evaluate the classification performance. Results indicate that, compared with original CART model, the G-mean of CART model incorporating data imbalance treatment is increased from 23% to 61% by 171%. The decision tree reveals that the following five variables play the most important roles in classifying HR and NHR in vehicle-bicycle crashes: Driver age, bicyclist safety equipment, driver action, trafficway type, and gender of drivers. Several countermeasures are recommended accordingly. The current study demonstrates that, by incorporating data imbalance treatment, the CART method could provide much more robust classification results.

Comparing the Performance of Deep Learning Methods to Predict Companies’ Financial Failure

“…Then, for the instances far away from the borderline, an extrapolation technique is used to generate minority class instances. On the other hand, for the instances closer to the borderline an interpolation technique similar to SMOTE is used to generate the minority instances [26].…”

“…To handle the data inconsistent distribution problem, eight advanced balancing techniques from the literature have been applied in the preprocessing stage, namely, SMOTE (Synthetic Minority Oversampling TEchnique) [22], BL-SMOTE (Borderline SMOTE) [23], SMOTE-ENN [24], K-means SMOTE [25], SMOTE-NC (SMOTE Nominal-Continuous) [22], SMOTE-Tomek (SMOTE with Tomek links) [24], SVM-SMOTE (Support Vector Machine with SMOTE) [26] and ADASYN (ADaptive SYNthetic sampling approach) [27]. These resampling techniques significantly enhance the behavior of the classifiers, i.e., they dramatically decrease the classifiers' minority class misclassification.…”

Development of a Model for Predicting Probabilistic Life-Cycle Cost for the Early Stage of Public-Office Construction

“…To validate Model I and II, k-fold cross-validation was conducted, which is a popular procedure for estimating the performance of a classification algorithm on a data set [46,47]. In this study, k was set up as ten; thus, the validation was tenfold.…”

“…The error rates for the comparison of prediction performance of the models were calculated using Equation (8). The average error rate in the four cases was used to analyze the accuracy of each fold; then, the total average [47] and the standard deviation of the ten folds were used as model-validation criteria.…”

Analysis of Factors Affecting Real-Time Ridesharing Vehicle Crash Severity

“…This would induce a bias toward the majority instances. The trained model would classify the majority instances much more accurately while misclassifying the minority instances, making the model fail to be informative [24,25]. When the identification of minority instances is of interest, this misclassification could result in substantial costs.…”