基于涡流搜索算法的过程支持向量回归机模型

针对传统支持向量回归机在机制上难以直接对时变信号进行处理的问题, 提出了一种用于时间序列预测 的过程支持向量回归模型, 采用涡流搜索算法优化选择模型参数, 采用 UCI(University of California Irvine)数据 库的空气质量数据集和比利时 SIDC(Solar Influences Data Analysis Center)的太阳黑子数据进行仿真实验。 实验 结果表明, 该模型预测结果均优于粒子群过程支持向量回归机和支持向量回归机的预测结果, 具有较好的预测 能力。

Model of Process Support Vector Regression MachineBase on Vortex Search Algorithm

Aiming at the traditional support vector regression machine on t he mechanism can't solute dynamic time-varying signal pattern classificatio n, proposes a process support vector regression time series prediction model, an d the vortex search algorithm for support vector machine parameter optimization.Using air quality data set of UCI(University of California Irvine)machine learni ng repository and belgium solar influences data analysis center sunspot activities data for simulation.The simulation results show that the prediction results of the prediction model are better than the particle swarm optimization process su pport vector regression and support vector regression, the time series predictio n model has well predictive ability.