Combination Prediction of Railway Freight Volume Based on Support Vector Machine and NARX Neural Network

被引：0

作者：

Li, Xuefei ^{[1
]}

Lang, Maoxiang ^{[1
]}

机构：

[1] Beijing Jiaotong Univ, Sch Traff & Transportat, Beijing 100044, Peoples R China

来源：

LISS 2013 | 2015年

关键词：

Railway freight volume; Support vector machine; NARX neural network; Combination prediction;

D O I：

10.1007/978-3-642-40660-7_129

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

The support vector machine, NARX neural network and combination prediction method are used to predict the railway freight volume in this paper. The impact factors of the railway freight volume are analyzed. Two single prediction models: support vector machine model and NARX neural network model are built to predict railway freight volume. Based on it, the linear combination prediction method is adopted to predict the railway freight volume and get better predicted results compared to the single prediction method. The linear combination prediction method is able to adapt to the railway freight volume prediction problem better, and could provide some references for the railway planning and the decision-making departments.

引用

页码：865 / 870

页数：6