To improve the forecast ability of highway freight volume, standard support vector regression (SVR) based on structural risk minimization is applied to forecasting highway freight volume. By selecting polynomial kernel function and appropriate parameters, the proposed method is used for forecasting highway freight volume of Zhengzhou city. Compared with artificial neural network (ANN) and linear regression, experimental results show that the training relative error and testing relative error obtained by SVR are lower than those by ANN and linear regression.
Model of Highway Freight Volume Time Serial Forecast Based on Support Vector Regression
First International Conference on Transportation Engineering ; 2007 ; Southwest Jiaotong University, Chengdu, China
2007-07-09
Conference paper
Electronic Resource
English
Model of Highway Freight Volume Time Serial Forecast Based on Support Vector Regression
British Library Conference Proceedings | 2007
|Railway Freight Volume Prediction Based on Support Vector Regression (SVR)
Trans Tech Publications | 2014
|