Promoted Short-term Traffic Flow Prediction Model Based on Deep Learning and Support Vector Regression

被引：0
|
作者：
Fu C.-H. [1 ]
Yang S.-M. [1 ]
Zhang Y. [1 ]
机构：
[1] Department of Transport, Fujian University of Technology, Fuzhou
来源：
Jiaotong Yunshu Xitong Gongcheng Yu Xinxi/Journal of Transportation Systems Engineering and Information Technology | 2019年 / 19卷 / 04期
关键词：
Deep learning; Intelligent transportation; Particle; Short- time traffic flow; Support vector regression; swarm optimization;
D O I：
10.16097/j.cnki.1009-6744.2019.04.019
中图分类号：
学科分类号：
摘要：
Short-term traffic flow prediction is the basis of an Intelligent Transport Systems (ITS) project. However, in current practice, the methods for short-term traffic flow prediction have encountered many challenges in fitting the traffic flow data, one is it depends too much on historical data. Therefore, a novel short-term traffic flow forecasting method based on Deep Learning and Support Vector Regression (DL-SVR) is proposed in this paper. Firstly, the DL-SVR model is composed by a Restricted Boltzmann Machine (RBM) visible inputting layer with some RBM intermediate layers and a radial SVR output layer. Furthermore, in order to enhance the generalization of the model, an improved Particle Swarm Optimization (PSO) algorithm is designed to optimize the number of nodes in the inputting layer. Finally, the DL-SVR method is compared with other typical short-term traffic flow prediction algorithms on the same computing platform. The experimental results show that the proposed DL-SVR method gets a higher accuracy in its real-time prediction. Copyright © 2019 by Science Press.
引用
收藏
页码：130 / 134and148
相关论文
共 12 条
  • [1] Sun H.Y., Liu H., Xiao H., Et al., Use of local linear regression model for short-term traffic forecasting, Transportation Research Record: Journal of the Transportation Research Board, 1836, 1, pp. 143-150, (2003)
  • [2] Gong B.W., Lin C.Y., Li J., Et al., Short-time traffic flow prediction based on KSOM_BP neural network, Journal of Jilin University (Engineering and Technology Edition), 41, 4, pp. 938-943, (2011)
  • [3] Garg N., Mangal S.K., Saini P.K., Et al., Comparison of ANN and analytical models in traffic noise modeling and predictions, Acoustics Australia, 43, 2, pp. 1-11, (2015)
  • [4] Zhu J.Z., Cao J.X., Zhu Y., Traffic volume forecasting based on radial basis function neuralnetwork with the consideration of traffic flows at the adjacent intersections, Transportation Research Part C, 47, 2, pp. 139-154, (2014)
  • [5] Yu B., Wang Y.T., Yao J.B., Et al., A Comparison of the performance of ANN and SVM for the prediction of traffic accident duration, Neural Network World, 26, 3, pp. 271-287, (2016)
  • [6] Sun Z.Q., Fox G., Traffic flow forecasting based on combination of multidimensional scaling and SVM, International Journal of Intelligent Transportation Systems Research, 12, 1, pp. 20-25, (2014)
  • [7] Wang J., Shi Q.X., Short-term traffic speed forecasting hybrid model based on chaos-wavelet analysis-support vector machine theory, Transportation Research Part C, 27, 2, pp. 219-232, (2013)
  • [8] Fu C.H., Zhang Y., An improved SVR algorithm based on the nuclear parameter optimization for traffic demand forecasting of urban agglomeration, System Engineering, 2, pp. 114-120, (2016)
  • [9] Chen B., Gungor P., Guillermo S., Deep learning with hierarchical convolutional factor analysis, IEEE Transactions on Pattern Analysis and Machine Intelligence, 35, 8, pp. 1887-1901, (2013)
  • [10] Vapnik V., Golowich S.E., Smola A., Support vector method for function approximation, regression estimation, and signal processing, Advances in Neural Information Processing Systems, 9, pp. 281-287, (1970)
12