State Space Reconstruction Parameters in the Analysis of Chaotic Time Series - the Role of the Time Window Length

Abstract

The most common state space reconstruction method in the analysis of chaotic time series is the Method of Delays (MOD). Many techniques have been suggested to estimate the parameters of MOD, i.e. the time delay $\tau$ and the embedding dimension $m$. We discuss the applicability of these techniques with a critical view as to their validity, and point out the necessity of determining the overall time window length, ${\tau }_w$, for successful embedding. Emphasis is put on the relation between ${\tau }_w$ and the dynamics of the underlying chaotic system, and we suggest to set ${\tau }_w\ge {\tau }_p$, the mean orbital period; ${\tau }_p$ is approximated from the oscillations of the time series. The procedure is assessed using the correlation dimension for both synthetic and real data. For clean synthetic data, values of ${\tau }_w$ larger than ${\tau }_p$ always give good results given enough data and thus ${\tau }_p$ can be considered as a lower limit (${\tau }_w\ge {\tau }_p$). For noisy synthetic data and real data, an upper limit is reached for ${\tau }_w$ which approaches ${\tau }_p$ for increasing noise amplitude.

20 pages including 23 Postscript figures, uses epsfig.sty and amssymb.sty, to be published in Physica D

Cited by in corpus (20)

• Non-uniform state space reconstruction and coupling detection
• Direct coupling information measure from non-uniform embedding
• A Unified Approach to Attractor Reconstruction
• Hybrid modeling and prediction of dynamical systems
• Evaluation of Granger causality measures for constructing networks from multivariate time series
• A unified and automated approach to attractor reconstruction
• Optimal reconstruction of dynamical systems: A noise amplification approach
• A new method for choosing parameters in delay reconstruction-based forecast strategies
• Prediction in Projection
• Equal heartbeat intervals and their effects on the nonlinearity of permutation-based time irreversibility in heart rate
• Stabilizing Embedology: Geometry-Preserving Delay-Coordinate Maps
• Time-series-analysis-based detection of critical transitions in real-world non-autonomous systems
• Using Curvature to Select the Time Lag for Delay Reconstruction
• Towards automated extraction and characterization of scaling regions in dynamical systems
• Local prediction of turning points of oscillating time series
• Comparative analysis of time irreversibility and amplitude irreversibility based on joint permutation
• Turning Point Prediction of Oscillating Time Series using Local Dynamic Regression Models
• Using nonlinear stochastic and deterministic (chaotic tools) to test the EMH of two Electricity Markets the case of Italy and Greece
• Parallelizing Convergent Cross Mapping Using Apache Spark
• Software Corrections of Vocal Disorders