Mode decomposition based deep learning model for multi-section traffic prediction

Road traffic prediction plays a vital role in real-time traffic management of an intelligent transportation system (ITS). Many prediction models achieve fine results. However, most ignore the intrinsic characteristics of traffic parameter data and do not consider the spatiotemporal effects of road sections, which can reflect the situation of all road traffic. Therefore, multi-section traffic prediction is still an open problem. In this paper, empirical mode decomposition (EMD) is employed to decompose the information of traffic parameters into many intrinsic mode function (IMF) components, which represent the original road traffic information in periodic and random sequences. Then, by considering the superiority of deep learning in multi-dimensional data processing, which can handle the spatiotemporal effects, a prediction model based on a convolutional neural network (CNN) is proposed to achieve the prediction of periodic and random sequences, whose results are combined to obtain the final prediction. The dataset from the Caltrans Performance Measurement System is used to validate the model. The proposed prediction model is compared to several well-known models, such as PCA-BP, Lasso-BP, and standard CNN. Experiments show that the proposed prediction model achieves higher accuracy.