Abstract

Road accidents is a global issue that cause deaths and injuries besides other direct and indirect losses. Countries and international organisations have designed technologies, systems, and policies to prevent accidents. The use of big traffic data and artificial intelligence may help develop a promising solution to predict or reduce the risk of road accidents. Most existing studies examine the impact of road geometry, environment, and weather parameters on road accidents. However, human factors such as alcohol, drug, age, and gender are often ignored when determining accident severity. In this work, we considered various contributing factors and their impact on the prediction of the severity of accidents. For this, we studied a set of single and ensemble mode machine learning (ML) methods and compared their performance in terms of prediction accuracy, precision, recall, F1 score, area under the receiver operator characteristic (AUROC). This research considered the road accident severity prediction as a classification problem that can classify the intensity of an accident in two categories: (i) binary classification (e.g. grievous and non-grievous), and (ii) multiclass classification (fatal, serious, minor, and non-injury). Our results show that Random Forest (RF) outperformed other methods' like logistic regression (LR), K-nearest neighbor (KNN), naive Bayes (NB), extreme gradient boosting (XGBoost), and adaptive boosting (AdaBoost) (e.g., 86.64% for binary and 67.67% for multiclass classification) in both single and ensemble ML methods in comparison to other methods considered in this research. LR, KNN, and NB are single mode ML methods that show similar performance to each other for both binary and multiclass classification. Compared to single mode, ensemble ML methods can predict the severity of accident more accurately with the order of RF, XGBoost, and Adaboost. The findings from this study can help to gain insights into the accident contributing factors and the severity of injuries as a result.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call