|本期目录/Table of Contents|

[1]张海静,姚博彬*,武奇生.基于差分数据图和深度学习的短时交通流预测[J].工业仪表与自动化装置,2020,(02):3-7.
 ZHANG Haijing,YAO Bobin,WU Qisheng.Short-term traffic flow prediction based on the differential data graph and deep learning[J].Industrial Instrumentation & Automation,2020,(02):3-7.
点击复制

基于差分数据图和深度学习的短时交通流预测

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:
期数:
2020年02期
页码:
3-7
栏目:
出版日期:
2020-04-15

文章信息/Info

Title:
Short-term traffic flow prediction based on the differential data graph and deep learning
文章编号:
1000-0682(2020)02-0000-00
作者:
张海静姚博彬*武奇生
长安大学 电子与控制工程学院,西安 710064
Author(s):
ZHANG Haijing YAO Bobin* WU Qisheng
School of Electronic and Control Engineering, Chang’an University, Xi’an 710064, China
关键词:
交通流量预测卷积神经网络支持向量回归数据差分交通数据图
Keywords:
traffic flow prediction convolutional neural network support vector regression data differential traffic data graph
分类号:
TP181
DOI:
-
文献标志码:
A
摘要:
交通流量预测(TFP)是提高交通出行效率,减少智能交通系统(ITS)交通拥堵的重要问题。为了从交通流特征提取的角度提高TFP精度,该文提出了一种新的方法DG-CNN-SVR。这种方法的基本思想依赖于2个方面:交通流数据趋势和不同工作日的细微差别。因此,引入差分运算来消除趋势分量,然后构建交通数据图以帮助解释复杂特征。通过卷积神经网络(CNN)进行特征学习,并使用支持向量回归(SVR)进行交通流量预测。通过测试数据集的实验结果表明,所提出的TFP方法比单独使用CNN和SVR的情况更有效。
Abstract:
Traffic flow prediction(TFP) is an very important issue for successfully promoting traffic efficiency and reducing traffic congestion in intelligent transportation system(ITS).In order to improve the TFP accuracy from the perspective of traffic flow features extraction,this paper propose a new method named DG-CNN-SVR.The basic thought behind relies on two aspects:the inherit trend in traffic flow data and the some subtle difference at different weekdays.Therefore,introduce differential operation to eliminate the trend component and then construct a traffic data graph to help interpret the complex features.Uses convolutional neural network(CNN) for features learning and support vector regression(SVR) for traffic flow predicting.The experimental results by the test data set show that the proposed TFP method performs more effective than the cases when CNN and SVR are used individually.

参考文献/References:

[1]Voort M V D,Dougherty M,Watson S.Combining kohonen maps with arima time series models to forecast traffic flow [J].Transportation Research Part C(Emerging Techno- logies),1996,4(5):307-318.

[2] Gong Y S, Zhang Y. Research of Short-Term Traffic Volume Prediction Based on Kalman Filtering[C]//Inter- national Conference on Intelligent Networks & Intelligent Systems. IEEE, 2014.
[3] Zhang C,Sun S,Yu G.A Bayesian network approach to time series forecasting of short-term traffic flows[C]// Intelligent Transportation Systems, The 7th International IEEE Conference on, IEEE, 2004.
[4] Chan K Y, Dillon T S, Singh J, et al. Neural-Network- Based Models for Short-Term Traffic Flow Forecasting Using a Hybrid Exponential Smoothing and Levenberg- Marquardt Algorithm[J]. IEEE Transactions on Intelligent Transportation Systems, 2012,13(2):644-654.
[5] Park B, Messer C, Urbanik Ii T. Short-Term Freeway Traffic Volume Forecasting Using Radial Basis Function Neural Network[J].Transportation Research Record: Journal of the Transportation Research Board,1998,1651: 39-47.
[6] Castro-Neto M, Jeong Y S, Jeong M K, et al. Online-SVR for short-term traffic flow prediction under typical and atypical traffic conditions[J].Expert Systems with Applica- tions, 2009, 36(3-part-P2):6164-6173.
[7] Li R, Lu H. Combined Neural Network Approach for Short-Term Urban Freeway Traffic Flow Prediction[C]// Wuhan,China:Advances in Neural Networks-ISNN 2009, 6th International Symposium on Neural Networks, Procee- dings, Part III. Springer Berlin Heidelberg,2009.
[8] 郑为中,史其信.基于贝叶斯组合模型的短期交通量预测研究[J].中国公路学报,2005(01):89-93.
[9] Zulong D, Dafang Z, Xin W, et al. A Hybrid Model For Short-Term Traffic Volume Prediction In Massive Trans- portation Systems[J].IEEE Transactions on Intelligent Transportation Systems, 2018:1-12.
[10] Huang W, Song G, Hong H, et al. Deep Architecture for Traffic Flow Prediction:Deep Belief Networks With Multitask Learning[J].IEEE Transactions on Intelligent Transportation Systems,2014,15(5):2191-2201.
[11] Lü Y,Duan Y,Kang W,et al.Traffic Flow Prediction With Big Data:A Deep Learning Approach[J].IEEE TRAN- SACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2015,16(2):865-873.
[12] Koesdwiady A,Soua R,Karray F.Improving Traffic Flow Prediction With Weather Information in Connected Cars: A Deep Learning Approach[J].IEEE Transactions on Vehicular Technology, 2016, 65(12):1-1.
[13] 罗向龙,焦琴琴,牛力瑶,等.基于深度学习的短时交通流 预测[J].计算机应用研究,2017,34(01):91-93+97.
[14] Yang H F, Dillon T S, Chen Y P P. Optimized Structure of the Traffic Flow Forecasting Model With a Deep Learning Approach[J].IEEE Transactions on Neural Networks and Learning Systems,2017,28(10):2371-2381.
[15] Zhao Z, Chen W, Wu X, et al. LSTM network: a deep learning approach for short-term traffic forecast[J].IET Intelligent Transport Systems, 2017, 11(2):68-75.
[16] Jain R K,Smith K M,Culligan P J,et al.Forecasting energy consumption of multi-family residential buildings using support vector regression: Investigating the impact of temporal and spatial monitoring granularity on perfor- mance accuracy[J].Applied Energy, 2014,123:168-178.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期:2019-07-05
基金项目:国家自然科学基金项目(61601058);河南省交通运输厅科技计划项目(2019G-2-5);中央高校基本科研业务费专项基金(300102329106)
作者简介:张海静(1995),长安大学电子与控制工程学院硕士研究生,研究方向为大数据处理等。
更新日期/Last Update: 1900-01-01