Temporal Backtracking and Multistep Delay of Traffic Speed Series Prediction

Abstract

As a typical time series, the length of the data sequence is critical to the accuracy of traffic state prediction. In order to fully explore the causality between traffic data, this study established a temporal backtracking and multistep delay model based on recurrent neural networks (RNNs) to learn and extract the long- and short-term dependencies of the traffic state data. With a real traffic data set, the coordinate descent algorithm was employed to search and determine the optimal backtracking length of traffic sequence, and multistep delay predictions were performed to demonstrate the relationship between delay steps and prediction accuracies. Besides, the performances were compared between three variants of RNNs (LSTM, GRU, and BiLSTM) and 6 frequently used models, which are decision tree (DT), support vector machine (SVM), k-nearest neighbour (KNN), random forest (RF), gradient boosting decision tree (GBDT), and stacked autoencoder (SAE). The prediction results of 10 consecutive delay steps suggest that the accuracies of RNNs are far superior to those of other models because of the more powerful and accurate pattern representing ability in time series. It is also proved that RNNs can learn and mine longer time dependencies.