Adaptive predict-filter of chaotic time series constructed Based on the neighbou rhood in the reconstructed phase space(Ⅱ)nonlinear adaptive filter
Gan Jian-Chao, Xiao Xian-Ci, (1)电子科技大学电子工程学院，成都 610054; (2)电子科技大学电子工程学院，成都 610054;电子对抗国防科技重点实验室，成都 610036 · Acta Physica Sinica · 2003
A kind of adaptive nonlinear predict-filter of chaotic time series using the neighbourhood in the reconstructed phase space,the minimum square-root-error criterion and the steepest descent principle is proposed.It can convert the time domain into the multi-dimensional vector domain, and predict chaotic time series by nonlinear filter. The result of computer simulation illustrates that the algorithm is available to predict some chaotic series and anti-noise.