Nonlinear Time Series Analysis using Recurrence Plots

1-day workshop offered by Hauke Krämer and Bedartha Goswami, PIK Potsdam

Date: Wednesday 7 November 2018
Time: 09.00 AM – 05.00 PM
Location: Room F 1.14, FG Building, University of Waikato, Hamilton

Recurrence plots are a powerful nonlinear data analysis tool that has its roots in the theory of nonlinear dynamical systems and deterministic chaos. In the last three to four decades the theory of recurrence plot analysis has been developed extensively and applied to investigate data sets a wide range of complex systems such as  climate, physiology, brain dynamics, finance, social interactions, and signal processing. Recurrence can be used to address a wide range of time series problems: such as identifying interactions between different systems using phase synchronisation, classifying the level of determinism or randomness in a measured signal, identifying transitions in the dynamics of a system, and looking for optimal lags between two data sets that maximize correlation between the two. Founded in nonlinear dynamical theory, the power of recurrence plots lies in the fact that it identifies characteristics that go beyond the standard linear properties such as Pearson’s cross-correlation, Fourier transform-based power spectral analysis, linear autocorrelations, and linear partial correlations.

In this one day workshop, Hauke Kramer and Bedartha Goswami, both experts in recurrence plot analysis, will discuss the basics of this approach and present a broad overview of its potentials. In addition to the introductory lectures, the workshop will also involve a hands-on component where the instructors will present a Matlab based toolbox that allows users to construct a recurrence plot from their data sets via an intuitive graphical user interface. No prior knowledge of Matlab or nonlinear dynamics is necessary.

NOTE: There is no registration fee. But we encourage interested people to register their interest by sending an email to Bedartha Goswami at goswami@pik-potsdam.de.

Please note that there are only a limited number of places available so please register your interest only if you are sure to attend!

We will send around a detailed schedule and discuss the logistics of laptop/computer arrangements to registered participants on Monday 5 Nov.

Schedule

09.00 AM - 09:45 AM - Lecture 1 Part 1
09.45 AM - 10.00 AM - BREAK
10.00 AM - 10.45 AM - Lecture 1 Part 2
10.45 AM - 11.00 AM - BREAK
11.00 AM - 11:45 AM - Lecture 2 Part 1
11.45 AM - 12.00 PM - BREAK
12.00 PM - 12.30 PM - Lecture 2 Part 2
12.30 PM - 01.30 PM - LUNCH BREAK
01.30 PM - 02.00 PM - Lecture 2 Part 3
02.00 PM - 02.45 PM - QUESTIONS & TOOLBOX INSTALLATION + CHECK
02.45 PM - 03.00 PM - BREAK
03.00 PM - 03.45 PM - Hands-on Session 1
03.45 PM - 04.00 PM - BREAK
04.00 PM - 04.45 PM - Hands-on Session 2

Detailed Session Titles

Lecture 1: Introduction to nonlinear time series analysis
Lecture 2: Recurrence plots as a data analysis tool
Hands-on 1: Recurrence plot toolbox in Matlab (CRP)
Hands-on 2: Specific data questions: transitions, synchronization, etc.