基于EMD-GRU的高速公路行程时间组合预测模型

彭勇; 周欣; 宋乾坤; 向中华

doi:10.21656/1000-0887.410165

基于EMD-GRU的高速公路行程时间组合预测模型

doi: 10.21656/1000-0887.410165

¹重庆交通大学交通运输学院, 重庆 400074
²重庆交通大学数学与统计学院, 重庆 400074

基金项目: 教育部人文社会科学规划基金项目（17YJA630079）；重庆市社会科学规划项目（2019YBGL049）

详细信息

作者简介:
彭勇（1973—），男，教授，博士(通讯作者. E-mail: pengyong@cqjtu.edu.cn).

中图分类号: U491
计量
- 文章访问数: 912
- HTML全文浏览量: 173
- PDF下载量: 512
- 被引次数: 0
出版历程
- 收稿日期: 2020-06-08
- 修回日期: 2020-06-15
- 刊出日期: 2021-04-01

A Combined Predicting Model for Expressway Travel Time Based on EMD-GRU

¹College of Traffic & Transportation, Chongqing Jiaotong University, Chongqing 400074, P.R.China
²College of Mathematics and Statistics, Chongqing Jiaotong University, Chongqing 400074, P.R.China

摘要

摘要: 考虑到高速公路行程时间影响因素繁多且行程时间序列非线性、非平稳特征显著，设计了基于经验模态分解和GRU神经网络的高速公路行程时间组合预测模型.首先，利用高速公路收费数据中车辆进出高速公路的时间信息获取路段行程时间序列；然后，利用经验模态分解算法，将复杂的行程时间序列分解为若干时间尺度不同、相对平稳的本征模态函数分量和残差分量；接着，使用GRU神经网络对各本征模态函数分量和残差分量进行预测与集成操作.实例分析表明：经验模态分解可有效提高LSTM、GRU神经网络的预测精度；在相同参数设置的情况下，GRU神经网络的预测精度优于LSTM神经网络.
- 智能交通 /
- 组合预测 /
- 行程时间 /
- 经验模态分解 /
- GRU神经网络
Abstract: In view of the variety of influential factors on the expressway travel time and the significance of nonlinear and non-stationary characteristics of the travel time series, a combined expressway travel time predicting model was designed based on the empirical mode decomposition and the GRU neural network. First, the time information of vehicles entering and exiting the expressway in toll data was used to obtain the travel time series of the road segments; then, the empirical mode decomposition algorithm was applied to decompose the complex travel time series into a number of relatively stable and different-time-scale eigen modal function components as well as residual components; then, the GRU neural network was used to predict and integrate the intrinsic modal function components and residual components. The example analysis shows that, the empirical mode decomposition can effectively improve the prediction accuracy of the LSTM and the GRU neural networks; under the same parameter settings, the prediction accuracy of the GRU neural network is better than that of the LSTM neural network.
- intelligent transportation /
- combined prediction /
- travel time /
- empirical mode decomposition /
- GRU neural network

HTML全文

参考文献(17)

[1]	ABDOLLAHI M, KHALEGHI T, YANG K. An integrated feature learning approach using deep learning for travel time prediction[J]. Expert Systems With Applications,2020,139: 112864.
[2]	赵建东, 王浩, 刘文辉. 高速公路旅行时间的自适应插值卡尔曼滤波预测[J]. 华南理工大学学报(自然科学版), 2014,42(2): 109-115.(ZHAO Jiandong, WANG Hao, LIU Wenhui. Adaptive interpolation Kalman filter prediction of highway travel time[J]. Journal of South China University of Technology (Natural Science Edition),2014,42(2): 109-115.(in Chinese))
[3]	孙健, 张纯, 陈书恺, 等. 基于季节模型及Kalman滤波的道路行程时间[J]. 长安大学学报(自然科学版), 2014,34(6): 145-151.(SUN Jian, ZHANG Chun, CHEN Shukai, et al. Road travel time based on seasonal model and Kalman filtering[J]. Journal of Chang’an University (Natural Science Edition),2014,34(6): 145-151.(in Chinese))
[4]	张娟, 孙剑. 基于SVM的城市快速路行程时间预测研究[J]. 交通运输系统工程与信息, 2011,11(2): 174-179.(ZHANG Juan, SUN Jian. Prediction of urban expressway travel time based on SVM[J]. Transportation System Engineering and Information,2011,11(2): 174-179.(in Chinese))
[5]	李松江, 宋军芬, 杨华民, 等. 基于聚类分析的高速公路行程时间预测[J]. 计算机仿真, 2019,36(2): 384-389.(LI Songjiang, SONG Junfen, YANG Huamin, et al. Travel time prediction of freeway based on clustering analysis[J]. Computer Simulation,2019,36(2): 384-389.(in Chinese))
[6]	王翔, 陈小鸿, 杨祥妹. 基于K最近邻算法的高速公路短时行程时间预测[J]. 中国公路学报, 2015,28(1): 102-111.(WANG Xiang, CHEN Xiaohong, YANG Xiangmei. Prediction of expressway short-term travel time based on K nearest neighbor algorithm[J]. Chinese Journal of Highway and Transport,2015,28(1): 102-111.(in Chinese))
[7]	WANG J, TSAPAKIS I, ZHONG C. A space-time delay neural network model for travel time prediction[J]. Engineering Applications of Artificial Intelligence,2016,52(6): 145-160.
[8]	GOODFELLOW I, BENGIO Y, COURVILLE A. Deep Learning [M]. Cambridge, MA: MIT Press, 2016.
[9]	HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation,1997,9(8): 1735-1780.
[10]	张威威, 李瑞敏, 谢中教. 基于深度学习的城市道路旅行时间预测[J]. 系统仿真学报, 2017,29(10): 2309-2315, 2322.(ZHANG Weiwei, LI Ruimin, XIE Zhongjiao. Travel time prediction of urban road based on deep learning[J]. Journal of System Simulation,2017,29(10): 2309-2315, 2322.(in Chinese))
[11]	RAN X, SHAN Z, FANG Y, et al. An LSTM-based method with attention mechanism for travel time prediction[J]. Sensors,2019,19(4): 861.
[12]	王志建, 李达标, 崔夏. 基于LSTM神经网络的降雨天旅行时间预测研究[J]. 交通运输系统工程与信息, 2020,20(1): 137-144.(WANG Zhijian, LI Dabiao, CUI Xia. Research on rainy day travel time forecast based on LSTM neural network[J]. Transportation System Engineering and Information,2020,20(1): 137-144.(in Chinese))
[13]	CHO K, VAN MERRIENBOER B, BAHDANAU D, et al. On the properties of neural machine translation: encoder-decoder approaches[Z/OL].(2014-10-07)[2021-03-08]. https://arxiv.org/abs/1409.1259.
[14]	刘松, 彭勇, 邵毅明, 等. 基于门控递归单元神经网络的高速公路行程时间预测[J]. 应用数学和力学, 2019,40(11): 1289-1298.(LIU Song, PENG Yong, SHAO Yiming, et al. Highway travel time prediction based on gated recursive unit neural network[J]. Applied Mathematics and Mechanics,2019,40(11): 1289-1298.(in Chinese))
[15]	汤霞, 匡海波, 孟斌, 等. 基于EMD的中国出口集装箱运价指数波动特性[J]. 科研管理, 2017,38(12): 144-154.(TANG Xia, KUANG Haibo, MENG Bin, et al. Fluctuation characteristics of China’s export container freight index based on EMD[J]. Research Management,2017,38(12): 144-154.(in Chinese))
[16]	李合龙, 杨能, 林楚汉, 等. 我国股票市场行业间波动溢出效应研究: 基于改进的EMD去噪方法[J]. 系统工程理论与实践, 2019,39(9): 2179-2188.(LI Helong, YANG Neng, LIN Chuhan, et al. Research on the volatility spillover effect in my country’s stock market: based on improved EMD denoising method[J]. Systems Engineering Theory and Practice,2019,39(9): 2179-2188.(in Chinese))
[17]	WU Z, HUANG N E. Ensemble empirical mode decomposition: a noise-assisted data analysis method[J]. Advances in Adaptive Data Analysis,2009,1(1): 1-41.