Predicting duration of traffic accidents based on cost-sensitive Bayesian network and weighted K-nearest neighbor

With the development of urbanization, road congestion has become increasingly serious, and an important cause is the traffic accidents. In this article, we aim to predict the duration of traffic accidents given a set of historical records and the feature of the new accident, which can be collected from the vehicle sensors, in order to help guide the congestion and restore the road. Existing work on predicting the duration of accidents seldom consider the imbalance of samples, the interaction of attributes, and the cost-sensitive problem sufficiently. Therefore, in this article, we propose a two-level model, which consists of a cost-sensitive Bayesian network and a weighted K-nearest neighbor model, to predict the duration of accidents. After data preprocessing and variance analysis on the traffic accident data of Xiamen City in 2015, the model uses some important discrete attributes for classification, and then utilizes the remaining attributes for K-nearest neighbor regression prediction. The experiment results show that our proposed approach to predicting the duration of accidents achieves higher accuracy compared with classical models.