Prediction of railway passenger traffic volume by means of LS-SVM

Authors:
Zhen-Rui Peng;Fu Wu;Zhao-Yuan Jiang
Affiliations:
School of Mechatronics, Lanzhou Jiaotong University, Lanzhou, China;Key Laboratory of Opto-Electronic Technology and Intelligent Control of Ministry of Education, Lanzhou Jiaotong University, Lanzhou, China;School of Mechatronics, Lanzhou Jiaotong University, Lanzhou, China
Venue:
ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part III
Year:
2006

Citing 3
Cited 1

Least Squares Support Vector Machine Classifiers

Neural Processing Letters
Travel-time prediction with support vector regression

IEEE Transactions on Intelligent Transportation Systems
Combination of artificial neural-network forecasters for prediction of natural gas consumption

IEEE Transactions on Neural Networks

Using real-time weather information for traveler information: a statistical learning application under alternative experimental conditions

Proceedings of the Second International Workshop on Computational Transportation Science

Quantified Score

Hi-index	0.00

Visualization

Abstract

Based on Least Squares Support Vector Machine (LS-SVM), a method for the prediction of railway passenger traffic volume is proposed. The railway passenger traffic volume from 1985 to 2002, provided by National Bureau of Statistics of China, is employed as total data set. The normalized passenger volume from 1985 to1999 is used as training data set to establish LS-SVM model, while the normalized volume from 1999 to 2002 is utilized as testing data set to carry out prediction. LS-SVM is applied to establish prediction model. The prediction results by LS-SVM model are compared with those by BP neural network method. The results show that LS-SVM outperforms BP neural network in the prediction of railway passenger traffic volume.