Short-term Traffic Flow Prediction Based on Deep Learning

被引：0

作者：

Wang X.-X. ^{[1
]}

Xu L.-H. ^{[1
]}

机构：

[1] School of Civil Engineering and Transportation, South China University of Technology, Guangzhou

来源：

Jiaotong Yunshu Xitong Gongcheng Yu Xinxi/Journal of Transportation Systems Engineering and Information Technology | 2018年 / 18卷 / 01期

基金：

中国国家自然科学基金;

关键词：

Deep learning; LSTM-RNN; Time series; Traffic engineering; Traffic flow prediction;

D O I：

10.16097/j.cnki.1009-6744.2018.01.012

中图分类号：

学科分类号：

摘要：

This paper proposes a traffic flow time series prediction model for urban expressway based on LSTMRNN under deep learning framework. First, we refactor the traffic time series with integrated spatial and temporal correlation of traffic flow, making LSTM-RNN obtain and strengthen the ability of data mining. Next, network depth is determined by both precision and timeliness during model designing. And then, we take use of Keras based on TensorFlow to implement LSTM- RNN with building model layer by layer and regulating all the parameters subtly. We validate the model utilizing the measured data from real express way, and implement local model saving and updating regularly according to the prediction accuracy. It is proved that the proposed model performs an accurate prediction for short-term traffic flow which is not restricted by the training sample size to a large extent. Meanwhile, the extensibility and practicability of the model is improved significantly. Copyright © 2018 by Science Press.

引用

页码：81 / 88

页数：7

共 17 条

[1]

Williams B.M., Hoel L.A., Modeling and forecasting vehicular traffic flow as a seasonal ARIMA process: Theoretical basis and empirical results, Journal of Transportation Engineering, 129, 6, pp. 664-672, (2003)

[2]

Clark S., Traffic prediction using multivariate nonparametric regression, Journal of Transportation Engineering, 129, 2, pp. 161-168, (2003)

[3]

Zhang L., Ma Y., Shi L., A hybrid traffic flow model for real time freeway traffic simulation, KSCE Journal of Civil Engineering, 18, 4, pp. 1160-1164, (2014)

[4]

Quek C., Pasquier M., Lim B.B.S., POP-TRAFFIC: a novel fuzzy neural approach to road traffic analysis and prediction, IEEE Transactions on Intelligent Transportation Systems, 7, 2, pp. 133-146, (2006)

[5]

Li S., Liu L.J., Zhai M., Prediction for short- term traffic flow based on modified PSO optimized BP neural network, Systems Engineering-Theory & Practice, 32, 9, pp. 2045-2049, (2012)

[6]

Chan K.Y., Dillon T.S., Singh J., Et al., Neuralnetwork-based models for short- term traffic flow forecasting using a hybrid exponential smoothing and levenberg-marquardt algorithm, IEEE Transactions on Intelligent Transportation Systems, 13, 2, pp. 644-654, (2012)

[7]

Fusco G., Colombaroni C., Comelli L., Et al., Short-term traffic predictions on large urban traffic networks: Applications of network- based machine learning models and dynamic traffic assignment models, Models and Technologies for Intelligent Transportation Systems (MT-ITS), 2015 International Conference on, pp. 93-101, (2015)

[8]

Yin Y., Shang P., Forecasting traffic time series with multivariate predicting method, Applied Mathematics & Computation, 291, pp. 266-278, (2016)

[9]

Yang Z., Liu Y., Zhu X., Et al., Removing forecasting errors with white gaussian noise after square root transformation, Journal of Forecasting, 35, 8, pp. 741-750, (2016)

[10]

Yuan P.C., Lin X.X., How long will the traffic flow time series keep efficacious to forecast the future?, Physica A: Statistical Mechanics & Its Applications, 467, pp. 419-431, (2017)

← 1 2 →