Severity Prediction of Highway Crashes in Saudi Arabia Using Machine Learning Techniques

Abstract

Kingdom of Among the G20 countries, Saudi Arabia (KSA) is facing alarming traffic safety issues compared to other G-20 countries. Mitigating the burden of traffic accidents has been identified as a primary focus as part of vision 20230 goals. Driver distraction is the primary cause of increased severity traffic accidents in KSA. In this study, three different machine learning-based severity prediction models were developed and implemented for accident data from the Qassim Province, KSA. Traffic accident data for January 2017 to December 2019 assessment period were obtained from the Ministry of Transport and Logistics Services. Three classifiers, two of which are ensemble machine learning methods, namely random forest, XGBoost, and logistic regression, were used for crash injury severity classification. A resampling technique was used to deal with the problem of bias due to data imbalance issue. SHapley Additive exPlanations (SHAP) analysis interpreted and ranked the factors contributing to crash injury. Two forms of modeling were adopted: multi and binary classification. Among the three models, XGBoost achieved the highest classification accuracy (71%), precision (70%), recall (71%), F1-scores (70%), and area curve (AUC) (0.87) of receiver operating characteristic (ROC) curve when used for multi-category classifications. While adopting the target as a binary classification, XGBoost again outperformed the other classifiers with an accuracy of 94% and an AUC of 0.98. The SHAP results from both global and local interpretations illustrated that the accidents classified under property damage only were primarily categorized by their consequences and the number of vehicles involved. The type of road and lighting conditions were among the other influential factors affecting injury s severity outcome. The death class was classified with respect to temporal parameters, including month and day of the week, as well as road type. Assessing the factors associated with the severe injuries caused by road traffic accidents will assist policymakers in developing safety mitigation strategies in the Qassim Region and other regions of Saudi Arabia.

Improving traffic accident severity prediction using MobileNet transfer learning model and SHAP XAI technique

“…In Saudi Arabia, Aldhari et al [ 36 ] proposed a machine learning-based approach for predicting the severity of road accidents. The system used three machine learning models, RF, LR, and XG-Boost, and used SHAP to solve bias concerns.…”

Multi-category driving maneuver recognition based on smartphone sensors and XGBoost

“…Aldhari et al used machine learning algorithms to predict the severity of highway accidents [8] , and XGBoost achieved the best classification performance on this type of imbalanced dataset, with an accuracy of 0.94 and F1 score of 0.94. Liang et al applied the XGBoost algorithm to steam turbine fault diagnosis [9] , with a ratio of approximately 67:1 between normal and fault data in the total dataset, and the overall accuracy on this imbalanced dataset was 0.97.…”

“…It is considered as an ensemble algorithm with ultra-high performance in classification problems and performs better than other algorithms in imbalanced datasets. The XGBoost algorithm builds weak learners one by one and accumulates multiple weak learners through continuous iteration, its objective function is [8] :…”

“…where L is the loss function, i y is actual value, ˆi y is predicted value, Ω is a regularization term, K is the total number of decision trees, k f is the structure of the kth decision tree, and n is the sample size. The regularization term is [8] :…”

Road Crash Injury Severity Prediction Using a Graph Neural Network Framework

“…These methods prove to be particularly advantageous in cases where the connection between predictor attributes and the targeted levels of injury severity remains poorly understood or exhibits a highly nonlinear relationship [18] [19]. RF, a commonly employed tree-based ensemble ML technique, has been found to be popular in different crash injury severity studies [20] [21]. In addition to RF, other techniques that are prominently used to predict crash injury severity include decision trees [19] [21], support vector machines (SVMs) [22], and XGBoost [19] [23].…”