Research on the Combination Forecast Model based on the BP Neural Network

DOI

10.2991/iccse-15.2015.10How to use a DOI?

Keywords

Neural Network; Back Propagation; Combination Forecast; Adaptive Linear Element

Abstract

According to the combined forecasting theory and BP neural network for nonlinear data good approximation properties, is proposed based on Bayesian combination, GM (1, 1) model and regression model of BP neural network combination forecast model. In this paper, the short-term number of railway passenger forecasting is used as the special case to illustrate the combined forecasting theory and BP neural network. Then to railway passenger traffic and railway mileage to between 2003 and 2011 as the basic data for prediction of railway passenger traffic from 2012 to 2016.Prediction results show that this model can objectively reflect the development trend of railway passenger traffic, can obtain more accurate prediction results, offer the decision basis for related departments.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Shengwang Zong
PY  - 2015/07
DA  - 2015/07
TI  - Research on the Combination Forecast Model based on the BP Neural Network
BT  - Proceedings of the 2015 International Conference on Computational Science and Engineering
PB  - Atlantis Press
SP  - 49
EP  - 53
SN  - 2352-538X
UR  - https://doi.org/10.2991/iccse-15.2015.10
DO  - 10.2991/iccse-15.2015.10
ID  - Zong2015/07
ER  -