基于免疫进化的支撑矢量回归的参数优化

在对支撑矢量回归的参数性能进行分析的基础上，引入了免疫进化算法对支撑矢量回归的模型参数和核参数进行优化。免疫进化算法是一种集免疫机制和进化机制于一体的一种新的全局并行算法，它可以通过对进化环境的自适应和自学习，有针对性地抑制由原进化算子操作的盲目性而引起的退化现象。仿真实验结果表明，免疫进化算法优化支撑矢量回归的参数不仅是可行的，也是十分有效的。

Parameter optimization of support vector regression based on immune Evolution

Based on the analysis of the parameter principle of support vector regression (SVR),this paper introduces the immune evolutionary algorithm (IEA) to optimize model parameter and kernel parameter of SVR. The IEA is a global parallel algorithm integrating immunity with evolutionary mechanisms. It is conducive to alleviating the undulating phenomenon produced by the blindfold behaviors of the original operators in the existent evolutionary algorithm through adaptive learning from the evolutionary environment. Simulation experiments indicate that the IEA optimizing parameter of SVR is not only feasible but also effective.