基于改进粒子群算法的SVR参数优化选择的研究

支持向量回归机(SVR)模型的拟合精度和泛化能力取决于其相关参数的选取,由于在参数的选择范围内可选择的数量是无穷的,在多个参数中盲目搜索最优参数是需要极大的时间代价,并且很难逼近最优。因此提出了基于改进粒子群算法的SVR参数优化选择方法。仿真结果表明:该改进粒子群算法优化SVR参数方法可行、有效,由此得到的SVR模型具有更好的学习精度和推广能力。

To Study on Optimization of SVR Parameters Selection Based on IPSO

The regression accuracy and generalization performance of the support vector regression (SVR) models depend on a proper setting of its parameters. As the parameter choice is infinite, the parameter chioce needs enormous time, and is very difficult to approach superiorly. So An optimal selection approach of SVR parameters was put forward based on improved particle swarm optimization algorithm. Simulation results show that the optimal selection approach based on IPSO is available and the IPSO-SVR model has superior learning accuracy and generalization performance.