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.

中文翻译：

---

交通速度序列预测的时间回溯和多步延迟

作为典型的时间序列，数据序列的长度对于交通状态预测的准确性至关重要。为了充分探讨交通数据之间的因果关系，本研究建立了基于递归神经网络（RNN）的时间回溯和多步延迟模型，以学习和提取交通状态数据的长期和短期依赖性。对于真实的交通数据集，采用协调下降算法搜索并确定交通序列的最佳回溯长度，并进行多步时延预测，以证明时延步骤与预测精度之间的关系。此外，还比较了RNN的三个变体（LSTM，GRU和BiLSTM）和6个常用模型（决策树（DT），支持向量机（SVM），k近邻（KNN），随机森林（RF），梯度提升决策树（GBDT）和堆叠式自动编码器（SAE）。10个连续延迟步骤的预测结果表明，RNN的精度远优于其他模型，这是因为时间序列中的模式表示能力更强大，更准确。还证明了RNN可以学习和挖掘更长的时间依赖性。