基于最大信息挖掘广域学习系统的混沌时间序列预测

CHAOTIC TIME SERIES PREDICTION BASED ONMAXIMUM INFORMATION MINING BROAD LEARNING SYSTEM

为了进一步挖掘混沌系统的演化信息,提升预测精度,减少训练时间,提出一种基于最大信息挖掘广域学习系统的混沌时间序列预测模型。为了有效地捕捉混沌系统的线性信息,引入一种改进的漏积分器动态储层,不仅可以获取系统当前状态的信息,而且可以兼顾历史状态信息。通过非线性随机映射将特征映射到增强层从而充分挖掘非线性信息。引入层叠机制促进了动态建模中信息的传播,实现了特征的再激活。在四个大规模数据集上的实验结果表明,提出的方法具有更好的预测精度和更少的计算代价,验证了该方法可以在大规模动态系统建模中获得更好的预测结果。

In order to further mine the evolution information of chaotic system,improve the prediction accuracy and reduce the training time,a chaotic time series prediction model based on maximum information mining broad learning system is proposed.In order to effectively capture the linear information of chaotic system,an improved leakage integrator dynamic reservoir was introduced,which could not only obtain the current state information of the system,but also take into account the historical state information.The feature was mapped to the enhancement layer by nonlinear random mapping to fully mine the nonlinear information.In addition,the cascade mechanism was introduced to promote the dissemination of information in dynamic modeling and realize the reactivation of features.The experimental results on four large-scale data sets show that the proposed method has better prediction accuracy and time cost,which verifies that the method can obtain better prediction results in large-scale dynamic system modeling.