Passenger Capacity Prediction Based on Least Squares Support Vector Regression with Continuous Ant Colony Optimization Algorithm

Abstract

In order to solve the shortcoming of support vector regression, passenger capacity prediction based on least squares support vector regression with ant colony optimization algorithm is proposed in this paper. Ant colony optimization algorithm is used to select the parameters of least squares support vector regression. Highway passenger capacity data of Anhui province from 2000 to 2011 are applied to testify the passenger capacity forecasting performance of ACO-LSSVR, among which the passenger capacity data from 2000 to 2009 are used to create the training samples and the passenger capacity from 2010 to 2011 are used as the testing samples. The testing results show that the forecasting ability for highway passenger capacity of ACO-LSSVR is better than those of LSSVR and SVR.