关键词: 支持向量机, 公路旅游客流量, 神经网络, 预测

Abstract: The regression principle of Support Vector Machines（SVM） based on the statistic learning theory is introduced.To solve the problem of few training samples in modeling the prediction for highway traveling passenger volume，the method of modeling the highway traveling passenger volume based on the Support Vector machine Regression（SVR） model is presented.This algorithm is investigated to select the parameters of SVR model.A simulation example is taken to demonstrate correctness and effectiveness of the proposed approach.The result shows that the model and algorithm proposed possess convenience，objectivity and can get higher prediction precision than that of BP neural network.

Key words: Support Vector Machines（SVM）, highway traveling passenger volume, neural network, prediction