Embedding of multidimensional time-dependent observations

被引：4

作者：

Barnard, J.P. ^{[1
]}

Aldrich, C. ^{[1
]}

Gerber, M. ^{[1
]}

机构：

[1] Department of Chemical Engineering, University of Stellenbosch, Private Bag XI, Matieland, Stellenbosch 7602, South Africa

来源：

Physical Review E - Statistical, Nonlinear, and Soft Matter Physics | 2001年 / 64卷 / 4 II期

关键词：

Algorithms - Chaos theory - Eigenvalues and eigenfunctions - Independent component analysis - Mathematical models - Ordinary differential equations - Phase space methods - Vectors;

D O I：

10.1103/PhysRevE.64.046201

中图分类号：

学科分类号：

摘要：

A method of embedding multidimensional observations that avoids both linear approximations in finding embedding dimensions and potentially suboptimal embedding lags was proposed. The Takens embedding theory was combined with independent component analysis to transform the embedding into a vector space of linearly independent vectors. The proposed method worked well with systems defined by ordinary differential equations for which noiseless data can be generated.

引用

页码：462011 / 462014