Local State-Space Reconstruction Using Averaged Scalar Products of the Dynamical-System Flow Vectors
R. Huerta; C. Santa Cruz; J. R. Dorronsoro; V. López; R. Huerta; Instituto de Ingeniería del Conocimiento (IIC), Universidad Autónoma de Madrid Cantoblanco, C-XVI, 28049 Madrid, Spain; C. Santa Cruz; Instituto de Ingeniería del Conocimiento (IIC), Universidad Autónoma de Madrid Cantoblanco, C-XVI, 28049 Madrid, Spain; J. R. Dorronsoro; Instituto de Ingeniería del Conocimiento (IIC), Universidad Autónoma de Madrid Cantoblanco, C-XVI, 28049 Madrid, Spain; V. López; Instituto de Ingeniería del Conocimiento (IIC), Universidad Autónoma de Madrid Cantoblanco, C-XVI, 28049 Madrid, Spain
Журнал:
EPL (Europhysics Letters)
Дата:
1995-01-01
Аннотация:
A technique for local state-space reconstruction is proposed. It is based on the local scalar product of flow vectors coming from a state-space reconstruction of a scalar time series. This technique leads to a set of dimensions in which the regions of the system are well embedded. It is particularly useful for detecting those regions of a high-dimensional system that can be modelled with a low-dimensional system. The simplicity and the effectiveness of the method is shown in the Lorentz attractor and the Mackey-Glass system.
402.3Кб