分析SVM的非线性回归预测基本原理,分别选用不同的核函数进行拟合训练预测。然后利用LIBSVM软件求解,利用Python和Gnuplot对核函数的参数寻优。把1975年到2006年全国的客运量数据和其他相关指标作为学习样本,验证寻优参数得到训练模型预测结果的可靠性。
Non-linear predictive theory, is analyzed, different kinds of kernel functions are chosen to do fit training and extrapolation forecast analysis. Then LIBSVM is used to solve the model, Python and Gnuplot are used to find the optimal parameters. The 1975 -2006 National passenger traffic data and other related indicators are taten as a learning sample, then the validity of the training model after parameter optimization is verified.