ZHAO Shu-xu， ZHANG Bao-hua
（School of Electronic and Information Engineering， Lanzhou Jiaotong University， Lanzhou 730070, China）
Abstract： Traffic flow prediction, as the basis of signal coordination and travel time prediction, has become a research point in the field of transportation. For traffic flow prediction, researchers have proposed a variety of methods, but most of these methods only use the time domain information of traffic flow data to predict the traffic flow, ignoring the impact of spatial correlation on the prediction of target road segment flow, which leads to poor prediction accuracy. In this paper, a traffic flow prediction model called as long short time memory and random forest (LSTM-RF) was proposed based on the combination model. In the process of traffic flow prediction, the long short time memory (LSTM) model was used to extract the time sequence features of the predicted target road segment. Then, the predicted value of LSTM and the collected information of adjacent upstream and downstream sections were simultaneously used as the input features of the random forest model to analyze the spatial-temporal correlation of traffic flow, so as to obtain the final prediction results. The traffic flow data of 132 urban road sections collected by the license plate recognition system in Guiyang City were tested and verified. The results show that the method is better than the single model in prediction accuracy, and the prediction error is obviously reduced compared with the single model.
Key words： traffic flow prediction; long short time memory and random forest (LSTM-RF) model; random forest; combination model; spatial-temporal correlation
CLD number： TP391 doi： 10.3969/j.issn.1674-8042.2020.02.005
References
［1］Stephanedes Y J, Michalopoulos P G. Improve destimation of traffic flow for real-time control. Transportation Research Record, 1981, 7(9): 28-39.
［2］Chen Y F, Shu L, Wang L. Traffic flow prediction with big data: a deep learning based time series model. In: Proceedings of IEEE Conference on Computer Communications Workshops, Atlanta, 2017, 150(1): 1010-1011.
［3］Okutani I, Stephanedes Y J. Dynamic prediction of traffic volume through kalman filtering theory. Transportation Research Part B Methodological, 1984, 18(1): 1-11.
［4］Davis G A, Nihan N L. Nonparametric regression and short-term freeway traffic forecasting. Journal of Transportation Engineering, 1991, 117(2): 178-188.
［5］Lan L W, Lin F Y, Kuo A Y. Three novel methods to predict traffic time series in reconstructed state spaces. International Journal of Applied Evolutionary Computation, 2010, 1(1): 16-35.
［6］Dougherty M S, Cobbett M R. Short-term inter-urban traffic forecasts using neural networks. International Journal of Forecasting, 1997, 13(1): 21-31.
［7］Ledoux C. An urban traffic flow model integrating neural networks. Transportation Research Part C Emerging Technologies, 1997, 5(5): 287-300.
［8］Yuan J, Fan B Q. VHSSA model for predicting short-term traffic flow of urban road. Journal of Highway & Transportation Research & Development, 2014, 8(4): 90-96.
［9］Zhang Y, Zhang Y, Haghani A. A hybrid short-term traffic flow forecasting method based on spectral analysis and statistical volatility model. Transportation Research Part C Emerging Technologies, 2014, 43(1): 65-78.
［10］Luan X C, Yang B S, Zhang Y F. Structural hierarchy analysis of streets based on complex network theory. Geomatics and Information Science of Wuhan University, 2012, 37(6): 728-732.
［11］Chang G, Zhang Y, Yao D. Short-term traffic flow forecasting model for regional road network based on spatial-temporal dependency. Journal of Tsinghua University, 2013, 53(2): 215-221.
［12］Yang G, Wang Y P, Yu H Y, et al. Short-term traffic state prediction based on the spatiotemporal features of critical road sections. Sensors, 2018, 18(7): 2287-2313.
［13］Fang K N, Wu J B, Zhu J P, et al. Review of stochastic forest methodology. Statistics & Information Forum, 2011, 26(3): 32-38.
［14］Yao D J, Yang J, Zhan X J. Feature selection algorithm based on random forest. Journal of Jilin University, 2014, 44(1): 137-141.
［15］Luo X L, Jiao Q Q, Niu L Y, et al. Short-term traffic flow prediction based on deep learning. Application Research of Computers, 2017, 18(1): 91-93.
［16］Qian W, Yang K L, Yang H H, et al. Short-term traffic flow prediction based on combined models. Computer Simulation, 2015, 32(2): 175-178.
［17］Li Y H, Liu L M, Wang Y Q. Short-term traffic flow prediction based on combination of predictive models. Journal of Transportation Systems Engineering and Information Technology, 2013, 13(2): 32-41.
［18］Wang X X, Xu L H. Short-term traffic flow prediction based on deep learning. Journal of Transportation Systems Engineering and Information Technology, 2018, 18(1): 81-88.
［19］Min W, Wynter L. Real-time road traffic prediction with spatio-temporal correlations. Transportation Research Part C Emerging Technologies, 2011, 19(4): 606-616.
基于LSTM-RF模型的城市道路交通流预测
赵庶旭， 张宝花
（兰州交通大学 电子与信息工程学院， 甘肃 兰州 730070）
摘 要： 交通流预测作为信号协调和出行时间预测等任务的基础， 成为了交通领域的研究点。对于交通流预测问题， 研究人员提出了多种方法， 但这些方法大多只使用交通流数据的时域信息进行交通流预测， 忽略了空间相关性对于预测目标路段流的影响， 导致预测精度不理想。基于组合模型的思想提出了一种称为LSTM-RF的交通流预测模型。 在交通流预测过程中， 首先使用LSTM模型提取预测目标路段的时序特征， 再将其预测值与采集的相邻上下游路段信息同时作为随机森林模型的输入特征， 进行交通流时空相关性分析， 获得最终的预测结果。 并通过贵阳市车牌识别系统采集的城区132条路段的交通流数据进行实验验证。 结果表明： 该方法在预测精度上优于单一模型， 并且预测误差相比单一模型有明显减少。
关键词: 交通流预测； LSTM-RF模型； 随机森林； 组合模型； 时空相关性
引用格式： ZHAO Shu-xu, ZHANG Bao-hua. Traffic flow prediction of urban road network based on LSTM-RF model. Journal of Measurement Science and Instrumentation, 2020, 11（2）： 135-142. ［doi： 10.3969／j.issn.1674-8042.2020.02.005］
[full text view]
