Prediction of accident severity based on BP neural networks

Traffic safety has been of great concern in recent years. The prediction of the severity of traffic accidents is an important part of it. The occurrence of traffic accidents shows the characteristics of uncertainty and non-linearity because of the influence of random factors. However, most of the existing models are single machine learning (ML) models, which have limitations in accuracy and generalization. This study proposes a traffic accident severity prediction model based on a combination of classification and regression trees (CART) and back -propagation neural network (BPNN). CART captures the significant features while BPNN builds the predictive model. Meanwhile, grid search finds the best combination of parameters for the model. Finally, the precision, recall and area under the curve (AUC) are used to evaluate the prediction results of the model. Due to the natural imbalance of the traffic accident dataset, cost-sensitive learning minimizes the total cost. The results show that CART-BPNN model outperforms logistic regression (LR), AdaBoost and naive bayes (NB) classifier in terms of precision and F-1-score. Therefore, CART-BPNN model performs better on predicting the severity of traffic accidents.