由于分解是基于信号时域局部特征的，因此它特别适合用来分析非线性非平稳过程。
Since the decomposition is based on the local characteristic time scale of the data, it is applicable to nonlinear and non-stationary processes.
这种方法将一个复杂的非线性非平稳信号逐级分解成若干平稳的数据层与剩余的最终趋势项的叠加。
This method will gradually decompose a complex nonlinear and non-stationary signal into some stable data layers and the remaining final trend.
由于股票预测是不确定、非线性、非平稳的时间序列问题，传统的方法往往难以取得满意的预测效果。
Because stock forecasting is a uncertain, nonlinear and nonstationary time series problem, it is difficult to achieve a satisfying prediction effect by traditional methods.
应用推荐