Coping With Class Imbalance in Classification of Traffic Crash Severity Based on Sensor and Road Data: A Feature Selection and Data Augmentation Approach

Abstract

This paper presents machine learning-based approaches to classification of historical traffic crashes in Kansas by severity, applied to a data set consisting of highway geometry, weather, and road sensor data. The goal of this work is to identify relevant features using a variety of loss measures and algorithms for feature selection. This is shown to facilitate the discovery of the most relevant sensors for the task of learning to predict severe crashes (those involving bodily injury). The key technical challenges are to cope with class imbalance (as a 75% majority of crashes are non-severe) and a highly correlated and redundant set of features from multiple coalesced sources. The major novel contributions of this work are the development of a random oversampling strategy for data augmentation, combined with the systematic application of multiple feature selection measures over a range of supervised inductive learning models and algorithms. Positive results from this approach, on a data set of 277 initial ground features and 20,000 vehicle crashes collected over 9 years (2007-2015) by the Kansas Department of Transportation (KDOT), included models trained using 30 features (out of 277) that achieve cross-validation precision and recall comparable to those obtained using the full set of features. These and other results point towards potential use of feature selection findings and the resultant models in planning future road construction.

A data-mining study on the prediction of head injury in traffic accidents among vulnerable road users with varying body sizes and head anatomical characteristics

“…In addition, the binary classification problem has a comparatively low prediction complexity in terms of classification prediction. For example, Delen et al (2017) and Lamba et al (2019) built the human injury prediction models with high/low injury degree classification based on the SVM algorithm, and the accuracies were 0.904 and 0.966, respectively. The prediction category in this study is five, which makes it more difficult to predict than a binary classification problem.…”

Analysis of Fatal Truck-Involved Work Zone Crashes in Florida: Application of Tree-Based Models

“…Considering the importance of data imbalance and its prevalence in the real world, modelers have been looking for appropriate strategies to tackle this challenge. In particular, successful applications of data balancing techniques and consequent model improvements have been recently reported in safety analysis literature (73)(74)(75)(76). Ahmadi et al showed that a SVM model slightly outperformed multinomial and mixed logit models, provided that model parameters are efficiently tuned.…”

“…They addressed data imbalance by tuning separate cost parameters in their SVM model structure (73). Lamba et al (74) used a variety of over-and undersampling techniques and showed that a combination of algorithmic feature selection with random over-sampling provides the best model performance for precision and recall. Yahaya et al used a variety of variable selection techniques and combined them with SMOTE oversampling strategy.…”