Incomplete Phase-Space Method to Reveal Time Delay From Scalar Time-series

TL;DR

This paper introduces a fast, simple method using incomplete phase-space reconstruction and permutation analysis to accurately recover the time delay in chaotic systems from scalar time series, even with noise and limited data.

Contribution

It presents a novel incomplete phase-space approach with the segmented mean-variance (SMV) technique for efficient time delay estimation in chaotic systems.

Findings

SMV shows clear maximum at true time delay

Method is robust to noise and small data sets

Low computational complexity

Abstract

A computationally quick and conceptually simple method to recover time delay of the chaotic system from scalar time series is developed in this paper. We show that the orbits in the incomplete two-dimensional reconstructed phase-space will show local clustering phenomenon after the component permutation procedure proposed in this work. We find that information captured by the incomplete two-dimensional reconstructed phase-space, is related to the time delay ${\tau _0}$ present in the system, and will be transferred to the permutation component by the procedure of component permutation. We then propose the segmented mean-variance (SMV) from the permutation component to identify the time delay ${\tau _0}$ of the system. The proposed SMV shows clear maximum when the embedding delay $\tau $ of the incomplete reconstruction matches the time delay ${\tau _0}$ of the chaotic system. Numerical data generated by a time-delay system based on the Mackey-Glass equation operating in the chaotic regime are used to illustrate the effectiveness of the proposed SMV. Experimental results show that the proposed SMV is robust to additive observational noise and is able to recover the time delay of the chaotic system even though the amount of data is relatively small and the feedback strength is weak. Moreover, the time complexity of the proposed method is quite low.