WANG Qingrong1， LI Tongwei1， ZHU Changfeng2
（1. School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China；2. School of Traffic and Transportation, Lanzhou Jiaotong University, Lanzhou 730070, China）
Abstract： Aiming at the problem that some existing traffic flow prediction models are only for a single road segment and the model input data are not pre-processed, a heuristic threshold algorithm is used to de-noise the original traffic flow data after wavelet decomposition.The correlation coefficients of road traffic flow data are calculated and the data compression matrix of road traffic flow is constructed. Data de-noising minimizes the interference of data to the model, while the correlation analysis of road network data realizes the prediction at the road network level.Utilizing the advantages of long short term memory (LSTM) network in time series data processing, the compression matrix is input into the constructed LSTM model for short-term traffic flow prediction.The LSTM-1 and LSTM-2 models were respectively trained by de-noising processed data and original data.Through simulation experiments, different prediction times were set, and the prediction results of the prediction model proposed in this paper were compared with those of other methods. It is found that the accuracy of the LSTM-2 model proposed in this paper increases by 10.278% on average compared with other prediction methods, and the prediction accuracy reaches 95.58%, which proves that the short-term traffic flow prediction method proposed in this paper is efficient.
Key words： short-term traffic flow prediction； deep learning； wavelet denoising； network matrix compression； long short term memory (LSTM) network
References
［1］Kumar K, Panda M, Katiyar V K. Short term traffic flow prediction for a nonurban highway using artificial neural network. Procedia-Scxiial and Behavioral Sciences, 2014, 104(4)： 755-764.
［2］Okutani I, Stephanedes Y J. Dynamic prediction of traffic volume through Kalman filtering theory. Transportation Research, 1984, 18(1)： 1-11.
［3］Guo J, Huang W, William B M. Adaptive Kalman filter approach for stochastic short-term traffic flow rate prediction and uncertainty quantification. Transportation Research Part C： Emerging Technologies, 2014, 43(3)： 50-64.
［4］Ahmed M S, Cook A R. Analysis of freeway traffic time-series data by using Box-Jenkins techniques. Transportation Research Record, 1979, 722(5)： 1-9.
［5］Nair A S, Liu J C, Rilett L, et al. Non-linear analysis of traffic flow. In: Proceedings of 4th International IEEE Conference on Intelligent Transportation Systems, Oakland, 2001： 681-685.
［6］Shen G J, Wang X H. Short-time traffic flow intelligent combination prediction model and its application. System Engineering Theory and Practice, 2011, 31(3)： 561-568.
［7］Wang J, Deng W, Guo Y T, et al. New Bayesian combination method for short-term traffic flow forecasting. Transportation Research Part C： Emerging Technologies, 2014, 43(3)： 79-94.
［8］Huang W, Song G, Hong H, et al. Deep architecture for traffic flow prediction：deep belief networks with multitask learning. IEEE Transactions on Intelligent Transportation Systems, 2014, 15(5)： 2191-2201.
［9］Ma X, Tao Z, Wang Y, et al. Long short-term memory neural network for traffic speed prediction using remote microwave sensor data. Transportation Research Part C: 2015, 54(3)： 187-197.
［10］Polson N G, Sokolov V O. Deep learning for short-term traffic flow prediction. Transportation Research Part C: Emerging Technologies, 2017, 79(4)： 1-17.
［11］Karlaftis M G, Vlahogianni E I. Statistical methods versus neural networks in transportation research：differences, similarities and some insights. Transportation Research Part C, 2011, 19(3)： 387-399.
［12］Park J, Li D, Murphey Y L. Real time vehicle speed prediction using a neural network traffic model. In: Proceedings of International Joint Conference on Neural Networks, IEEE, 2011： 2991-2996.
［13］Ma X. Learning traffic as images： a deep convolutional neural network for large-scale transportation network speed prediction. Sensors, 2017, 17(4)： 12-15.
［14］Wang J, Gu Q, Wu J. Traffic speed prediction and congestion source exploration： a deep learning method. In: Proceedings of IEEE International Conference on Data Mining, 2017： 499-508.
［15］Lü Y S, Duan Y J, Kang W, et al. Traffic flow prediction with big data： a deep learning approach. IEEE Transactions on Intelligent Transportation Systems, 2014, 16(2)： 865-873.
［16］Luo W H, Dong B T, Wang Z S. Short-term traffic flow prediction based on CNN-SVR hybrid deep learning model. Transportation System Engineering and Information, 2017, 17(5): 68-74.
［17］Luo X L, Li D, Yang Y, et al. Short-term traffic flow prediction based on KNN-LSTM. Journal of Beijing University of Technology, 2018, 44(12)： 55-61.
［18］Wang X X, Xu L H. Short-term traffic flow prediction based on deep learning. Transportation System Engineering and Information, 2018, 18(1): 85-92.
［19］Wang J, Hu F, Li L. Deep bi-directional long short-term memory model for short-term traffic flow prediction. In: Proceedings of the International Conference on Neural Information Processing, Springer, 2017： 306-316.
［20］Castro-Neto M, Jeong Y S, Jeong M K. Onlinesvr for short-term traffic flow prediction under typical and atypical traffic conditions. Expert Systems with Applications, 2009, 36(3)： 6164-6173.
［21］Karlaftis M, Vlahogianni E. Statistical methods versus neural networks in transportation research： differences, similarities and some insights. Transportation Research Part C： Emerging Technologies, 2011, 19(3)： 387-399.
［22］Vlahogianni E I, Karlaftis M G, Golias J C. Optimized and meta-optimized neural networks for short-term traffic flow prediction： a genetic approach. Transportation Research Part C： Emerging Technologies, 2005, 13(3)： 211-234.
［23］Hochreiter S, Schmdhuber J. Long short-term memory. Neural Computation, 1997, 9(8)： 1735-1780.
基于小波去噪和LSTM模型的短时交通流预测
王庆荣1， 李彤伟1， 朱昌锋2
（1. 兰州交通大学 电子与信息工程学院， 甘肃 兰州 730070；2. 兰州交通大学 交通运输学院， 甘肃 兰州 730070）
摘 要： 针对现有的部分交通流预测模型仅面向单一路段进行， 模型输入数据未预处理的问题， 采用启发式阈值算法对小波分解后的原始交通流数据进行去噪处理， 通过对路网内各路段交通流数据相关性系数计算， 构造出路网交通流数据压缩矩阵。 数据去噪将数据对模型的干扰降到最低， 同时路网数据相关性分析又使预测在路网层面上进行了考量。 利用长短时记忆（LSTM）网络在时序数据处理方面的优势， 将压缩矩阵输入构造好的LSTM模型进行短时交通流预测。 利用去噪处理数据和原始数据分别训练LSTM-1和LSTM-2模型， 通过仿真实验， 设置不同预测时间将本文提出的预测方法和其他4种模型对比， 验证了相较于其他4种模型预测的准确率平均可提升10.278%， 预测的准确率达到了95.58%， 说明这是一种高效率的短时交通流预测方法。
关键词： 短时交通流预测； 深度学习； 小波去噪； 路网矩阵压缩； 长短时记忆(LSTM)网络
引用格式： WANG Qingrong， LI Tongwei， ZHU Changfeng. Short-time prediction for traffic flow based on wavelet de-noising and LSTM model.
Journal of Measurement Science and Instrumentation, 2021, 12（2）： 195-207. DOI： 10.3969／j.issn.1674-8042.2021.02.009
[full text view]
