Abstract:

Short-term traffic flow prediction is not only related to historical data， but also affected by the traffic of adjacent areas. Since the trend and spatial correlation of traffic flow are ignored by traditional Time Series Decomposition （TSD） models， a time series processing model based on the combination of Time Series Decomposition and Spatio-Temporal features （TSD-ST） was proposed. Firstly， the trend component and periodic component were obtained by using Empirical Mode Decomposition （EMD） and Discrete Fourier Transform （DFT）， the Spatio-Temporal （ST） correlation of the fluctuation component was mined by Mutual Information algorithm （MI）， and the state vector was reconstructed on the basis of the above. Then， the fluctuation component was predicted by using the state vector through Long Short-Term Memory （LSTM） network. Finally， the final predicted value was obtained by reconstructing the prediction results of the three parts of the sequence. The validity of the model was verified on the real data of Interstate I090 in Washington State， USA. Experimental results show that the Root Mean Square Error （RMSE） of the proposed model TSD-ST-LSTM is reduced by 16.5%， 34.0%， and 36.6% compared with that of Support Vector Regression （SVR）， Gradient Boosting Regression Tree （GBRT） and LSTM， respectively. It can be seen that the proposed model is very effective in improving prediction accuracy.

Key words: short-term traffic flow prediction, Time Series Decomposition (TSD), Spatio-Temporal (ST) feature, Discrete Fourier Transform (DFT), Mutual Information (MI), supervised learning

摘要：

短时交通流预测不仅与历史数据相关，而且也受相邻区域交通情况影响。针对传统时间序列分解（TSD）模型忽略交通流的趋势性和空间相关性的问题，提出了基于时间序列分解与时空特征（TSD-ST）结合的时间序列处理模型。首先，利用经验模态分解（EMD）和离散傅里叶变换（DFT）得到趋势分量和周期分量，利用互信息（MI）算法挖掘波动分量的时空（ST）相关性，并以此为根据重构状态向量；随后，通过长短期记忆（LSTM）网络利用状态向量对波动分量进行预测；最后，将序列的3部分的预测结果重构，得到最终预测值。利用美国华盛顿州I090号州际公路的真实数据验证模型的有效性。实验结果表明，与支持向量回归（SVR）、梯度提升回归树（GBRT）、LSTM相比，所提模型的均方根误差（RMSE）分别降低了16.5%、34.0%和36.6%。由此可见，所提模型在提升预测精度方面十分有效。

关键词: 短时交通流预测, 时间序列分解, 时空特征, 离散傅里叶变换, 互信息, 监督学习