Visual Recurrence Analysis (VRA)

By Eugene Kononov
Print

Visual Recurrence Analysis (VRA) for Windows 95/98/ME/2000/NT/XP is a software package for topological analysis, qualitative and quantitative assessment, and nonparametric prediction of nonlinear and chaotic time series.

Main features:

  • Pattern and determinism recognition in the time series using the recurrence plot, which is essentially a graphical representation of the correlation integral in such a way so that the temporal dependence in the system under study is preserved.
  • Dynamic recurrence quantification analysis (RQA) for recurrence plots classification and characterization: analyze stationarity, periodicity, determinism, and complexity of the dynamical system as it evolves over time.
  • Recurrence plots animation: see the dynamical system trajectories recovered from the time series stretch and unfold in real time.
  • Average Mutual Information, False Nearest Neighbors, Recurrence Histogram and spatio-temporal entropy methods to determine the optimal values of embedding dimension and time delay for delayed coordinate embedding.
  • Nonparametric modeling for nonlinear time series prediction. A wide variety of models and options is available, including nearest neighbor, locally constant, locally linear, locally weighted linear, kernel regression, and radial basis functions models.
  • Nonparametric noise reduction
  • State space graph
  • Importing time series stored in different file formats, including ASCII text, MS Excel, and sound (WAVE) formats.
  • Sample data sets (periodic, chaotic, and random), comprehensive context-sensitive help, and references are included.
KeywordsDynamics (phase diagrams), Visualization
Model
  • Time Series
Software Type
  • Package
Language
  • C++
Platform
  • Windows
Availability
Free download for academic purposes (commercial users must pay fee) at website: http://www.myjavaserver.com/~nonlinear/vra/download.html
Contact Person
Eugene Kononov (nonlinear5 AT yahoo DOT com)
Categories: Software
Tags:

Please login or register to post comments.

Name:
Email:
Subject:
Message:
x

More from DSWeb