Network structure of multivariate time series

Abstract

Our understanding of a variety of phenomena in physics, biology and economics crucially depends on the analysis of multivariate time series. While a wide range of tools and techniques for time series analysis already exist, the increasing availability of massive data structures calls for new approaches for multidimensional signal processing. We present here a non-parametric method to analyse multivariate time series, based on the mapping of a multidimensional time series into a multilayer network, which allows to extract information on a high dimensional dynamical system through the analysis of the structure of the associated multiplex network. The method is simple to implement, general, scalable, does not require ad hoc phase space partitioning, and is thus suitable for the analysis of large, heterogeneous and non-stationary time series. We show that simple structural descriptors of the associated multiplex networks allow to extract and quantify nontrivial properties of coupled chaotic maps, including the transition between different dynamical phases and the onset of various types of synchronization. As a concrete example we then study financial time series, showing that a multiplex network analysis can efficiently discriminate crises from periods of financial stability, where standard methods based on time-series symbolization often fail.

7 pages, 4 figures. Original title was "From multivariate time series to multiplex visibility graphs"

References in corpus (5)

• The structure and dynamics of multilayer networks
• From time series to complex networks: the visibility graph
• Time reversibility from visibility graphs of non-stationary processes
• On the degree distribution of horizontal visibility graphs associated to Markov processes and dynamical systems: diagrammatic and variational approaches
• Influence network in Chinese stock market

Cited by in corpus (30)

• Complex network approaches to nonlinear time series analysis
• The new challenges of multiplex networks: measures and models
• Unveiling the higher-order organization of multivariate time series
• Large-scale nonlinear Granger causality: A data-driven, multivariate approach to recovering directed networks from short time-series data
• Visibility graphs for image processing
• Multiplex Recurrence Networks
• Sequential visibility-graph motifs
• Time Series Analysis via Network Science: Concepts and Algorithms
• Visibility graphs and symbolic dynamics
• Visibility graph analysis of economy policy uncertainty indices
• Visibility graphs of random scalar fields and spatial data
• Visibility graphs of ground-level ozone time series: A multifractal analysis
• Can complex networks describe the urban and rural tropospheric O3 dynamics?
• Multiplex visibility graphs to investigate recurrent neural networks dynamics
• Background PM10 atmosphere: In the seek of a multifractal characterization using complex networks
• Multiplex Visibility Graphs as a complementary tool for describing the relation between ground level O3 and NO2
• Tetradic motif profiles of horizontal visibility graphs
• Wet scavenging process of particulate matter (PM10): A multivariate complex network approach
• Analytic degree distributions of horizontal visibility graphs mapped from unrelated random series and multifractal binomial measures
• Extracting correlations in earthquake time series using visibility graph analysis
• Connecting Network Science and Information Theory
• Efficient On-line Computation of Visibility Graphs
• Improving graph-based detection of singular events for photochemical smog agents
• Symbolic dynamics techniques for complex systems: Application to share price dynamics
• Mapping Coupled Time-series Onto Complex Network
• Nonparametrically estimating dynamic bivariate correlation using visibility graph algorithm
• Multiplex Recurrence Networks from multi-lead ECG data
• Assessing imbalance in signed brain networks
• Hierarchical deposition and scale-free networks: a visibility algorithm approach
• An egonet-based approach to effective weighted network comparison