Construction of complex networks from time series based on the cross correlation interval

Feng, Chen

doi:10.1515/phys-2017-0028

Cited by 7 publications

(4 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors used the degree distribution to decide the best parameters for the algorithm. In contrast, Feng and He (Feng and He, 2017), used the cross-correlation as a measure of similarity between two points in phase space, and used the clustering coefficient and efficiency to decide the best parameters for the model. They analyzed the Lorenz system, white Gaussian noise and sea clutter time series.…”

Section: Correlation Networkmentioning

confidence: 99%

Time series analysis via network science: Concepts and algorithms

Silva

Ribeiro

et al. 2021

WIREs Data Min & Knowl

View full text Add to dashboard Cite

There is nowadays a constant flux of data being generated and collected in all types of real world systems. These data sets are often indexed by time, space, or both requiring appropriate approaches to analyze the data. In univariate settings, time series analysis is a mature field. However, in multivariate contexts, time series analysis still presents many limitations. In order to address these issues, the last decade has brought approaches based on network science. These methods involve transforming an initial time series data set into one or more networks, which can be analyzed in depth to provide insight into the original time series. This review provides a comprehensive overview of existing mapping methods for transforming time series into networks for a wide audience of researchers and practitioners in machine learning, data mining, and time series. Our main contribution is a structured review of existing methodologies, identifying their main characteristics, and their differences. We describe the main conceptual approaches, provide authoritative references and give insight into their advantages and limitations in a unified way and language. We first describe the case of univariate time series, which can be mapped to single layer networks, and we divide the current mappings based on the underlying concept: visibility, transition, and proximity. We then proceed with multivariate time series discussing both single layer and multiple layer approaches. Although still very recent, this research area has much potential and with this survey we intend to pave the way for future research on the topic. This article is categorized under: Fundamental Concepts of Data and Knowledge > Data Concepts Fundamental Concepts of Data and Knowledge > Knowledge Representation

show abstract

Section: Correlation Networkmentioning

confidence: 99%

Time series analysis via network science: Concepts and algorithms

Silva

Ribeiro

et al. 2021

WIREs Data Min & Knowl

View full text Add to dashboard Cite

show abstract

“…In many cases, the correlation networks are extremely complex and network structures are continuously evolving through various heterogeneous interactions in time [9,15]. In [16], authors reviewed their systematic works on autocorrelations in financial time series data, from the perspective of complex networks.…”

Section: Introductionmentioning

confidence: 99%

A KST framework for correlation network construction from time series signals

Zhu

et al. 2018

Ninth International Conference on Graphic and Image Processing (ICGIP 2017)

View full text Add to dashboard Cite

A KST (Kolmogorov-Smirnov test and T statistic) method is proposed for construction of a correlation network based on the fluctuation of each time series within the multivariate time signals. In this method, each time series is divided equally into the multiple segments, and the maximal data fluctuation in each segment is calculated by our KST change detection procedure. Connections between each time series are derived from the data fluctuation matrix, and are used for constructing the fluctuation correlation network (FCN). The method was tested with synthetic simulations and the result was compared with those from using KS or T only for detection of data fluctuation. The novelty of this study is that the correlation analyses was based on the data fluctuation in each segment of each time series rather than on the original time signals. It would be more meaningful for many real world applications and for analysis of large-scale time signals where prior knowledge is uncertain.

show abstract

“…A multi-scale mapping of time-series onto a network and the transmission of ordinal regression patterns between two time-series in the local trends of non-stationary time-series give useful results, too [21]. With respect to the cross-correlation networks [22], the network properties such as the clustering coefficient, the efficiency, the cross-correlation degree of cross-correlation interval and also the modularity of dynamic states, have all been investigated [23]. An example of another real-world application provides from the mapping of time-series onto a network in tourism management [24].…”

mentioning

confidence: 99%

“…Hence, in our work without the need for necessarily linear relations, the couplings are defined. This procedure can be explored by both temporal intervals [23] and amplitude intervals [9]. We generate discrete intervals to evaluate the amplitude of the markets and we then map those amplitudes (nodes) and their relations (links) onto a network.…”

mentioning

confidence: 99%

Mapping coupled time-series onto a complex network

Ardalankia¹,

Askari²,

Sheykhali³

et al. 2020

EPL

View full text Add to dashboard Cite

In order to extract hidden joint information from two possibly uncorrelated time-series, we explored the measures of network science. Alongside common methods in time-series analysis of the economic markets, the mapping joint structure of two time-series onto a network provides insight into hidden aspects embedded in the couplings. We quantise the amplitude of two time-series and investigate relative simultaneous locations of those amplitudes. Each segment of a quantised amplitude is considered as a node. The simultaneity of the amplitudes of the two time-series is considered as the links in the network. The frequency of occurrences forms the weighted links. In order to extract information, we need to measure to what extent the coupling deviates from the coupling of two uncoupled series. Also, we need to measure to what extent the couplings inherit their charachteristics from a Gaussian distribution or a non-Gaussian distribution. We mapped the network from two surrogate time-series. The results show that the couplings of markets possess some features which diverge from the same features of the network mapped from white noise, and from the network mapped from two surrogate time-series. These deviations prove that there exist joint information and cross-correlation therein. By applying network's topological and statistical measures and the deformation ratio in joint probability distribution, we distinguished basic structures of cross-correlation and coupling of cross-markets. It was discovered that even two possibly known uncorrelated markets may possess some joint patterns with each other. Thereby, those markets should be examined as coupled and weakly coupled markets.

show abstract

Construction of complex networks from time series based on the cross correlation interval

Cited by 7 publications

References 31 publications

Time series analysis via network science: Concepts and algorithms

Time series analysis via network science: Concepts and algorithms

A KST framework for correlation network construction from time series signals

Mapping coupled time-series onto a complex network

Contact Info

Product

Resources

About