Complex Network Construction of Multivariate Time Series Using Information Geometry

Sun, Jiancheng; Yang, Yong; Xiong, Naixue; Dai, Liyun; Peng, Xiangdong; Luo, Jian

doi:10.1109/tsmc.2017.2751504

Cited by 31 publications

(9 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, to evaluate the proposed method, three other metrics (geodesic distance, DTW and correlation coefficient) are also used to construct the network for comparison. By estimating the covariance matrix of MTS in phase space, the geodesic distance can be obtained and then a network formed [ 5 ]. For DTW and correlation coefficient, the metrics can be calculated directly between UTS.…”

Section: Experiments and Resultsmentioning

confidence: 99%

“…In recent years, the application of complex network theory to time series analysis is increasing rapidly. Firstly, the time series was transformed into a network, and then, various complex network tools were used for analysis [ 3 , 4 , 5 , 6 , 7 ]. There are three kinds of network reconstruction methods: recurrence network based on phase space and visibility graphs and transition network based on Markov chain [ 6 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Complex Network Construction of Univariate Chaotic Time Series Based on Maximum Mean Discrepancy

Sun

2020

Entropy

Self Cite

View full text Add to dashboard Cite

The analysis of chaotic time series is usually a challenging task due to its complexity. In this communication, a method of complex network construction is proposed for univariate chaotic time series, which provides a novel way to analyze time series. In the process of complex network construction, how to measure the similarity between the time series is a key problem to be solved. Due to the complexity of chaotic systems, the common metrics is hard to measure the similarity. Consequently, the proposed method first transforms univariate time series into high-dimensional phase space to increase its information, then uses Gaussian mixture model (GMM) to represent time series, and finally introduces maximum mean discrepancy (MMD) to measure the similarity between GMMs. The Lorenz system is used to validate the correctness and effectiveness of the proposed method for measuring the similarity.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Complex Network Construction of Univariate Chaotic Time Series Based on Maximum Mean Discrepancy

Sun

2020

Entropy

Self Cite

View full text Add to dashboard Cite

show abstract

“…In recent years, the machine learning has been used to extract statistical or dynamical characteristics for prediction. Several artificial neural networks (ANNs) [22], [23], multi-input-multi-output network [24], [25], and deep learning method [26] have been used to extract the hidden information in time series data. Wang proposed a doublelayer recurrent neural network to predict the PM2.5 value [27].…”

Section: Related Workmentioning

confidence: 99%

The System Identification and Prediction of the Social Earthquakes Burst in Human Society

et al. 2020

Self Cite

View full text Add to dashboard Cite

The internal mechanism of the social "earthquakes"-the wars burst in human society, is investigated by nonlinear theory. We explore the scaling behavior in the human activity and the historical evolution of ancient China. Based on the war chronology and history chronology from B.C.2000 to A.D.1840, using statistical analysis together with the detrended fluctuation analysis, we find that the social evolution system shows self-organized critical behavior and there exists self-similar scaling behavior during the evolution system. Based on time-delay reconstructed phase space, a modified radial basis function neural network (modified RBF-NN) is used to predict the number of wars and the transformation of the historical stage. It shows that the prediction result matches quite well with the real value for the following two historical stages. Furthermore, by singular value decomposition and the sparse identification algorithm in time-delay coordinates, the coefficients of the candidate functions in identified system can be solved from a sparse regression problem. We extracted the governing equations of big events burst in social system. The identified system fits well with the real data, and it can capture the same topology with the original system of wars. In this paper, we investigated the wars burst in social system by statistic analysis, neural network as well as sparse identification. It sheds light on the study of wars or conflicts from perspective of data science and dynamical theory. INDEX TERMS Scaling behavior, Self-organized criticality, Neural networks, System identification.

show abstract

“…19 The use of CNs as a tool of analysis was motivated by their ability to synthetically and effectively characterize the structure and function of complex physical systems such as four-dimensional (4D) cardiovascular flows, as in the case object of the study. In fact, in the context of graph theory, CNs were used to model pairwise connections between highly interacting dynamical objects, 20,21 through a set of nodes and links. Recently, correlation-based CNs have been successfully applied to complex fluid mechanics phenomena.…”

Section: Introductionmentioning

confidence: 99%

Exploring wall shear stress spatiotemporal heterogeneity in coronary arteries combining correlation-based analysis and complex networks with computational hemodynamics

Calò

Nisco

Gallo

et al. 2020

Proc Inst Mech Eng H

View full text Add to dashboard Cite

Atherosclerosis at the early stage in coronary arteries has been associated with low cycle-average wall shear stress magnitude. However, parallel to the identification of an established active role for low wall shear stress in the onset/progression of the atherosclerotic disease, a weak association between lesions localization and low/oscillatory wall shear stress has been observed. In the attempt to fully identify the wall shear stress phenotype triggering early atherosclerosis in coronary arteries, this exploratory study aims at enriching the characterization of wall shear stress emerging features combining correlation-based analysis and complex networks theory with computational hemodynamics. The final goal is the characterization of the spatiotemporal and topological heterogeneity of wall shear stress waveforms along the cardiac cycle. In detail, here time-histories of wall shear stress magnitude and wall shear stress projection along the main flow direction and orthogonal to it (a measure of wall shear stress multidirectionality) are analyzed in a representative dataset of 10 left anterior descending pig coronary artery computational hemodynamics models. Among the main findings, we report that the proposed analysis quantitatively demonstrates that the model-specific inlet flow-rate shapes wall shear stress time-histories. Moreover, it emerges that a combined effect of low wall shear stress magnitude and of the shape of the wall shear stress–based descriptors time-histories could trigger atherosclerosis at its earliest stage. The findings of this work suggest for new experiments to provide a clearer determination of the wall shear stress phenotype which is at the basis of the so-called arterial hemodynamic risk hypothesis in coronary arteries.

show abstract

Complex Network Construction of Multivariate Time Series Using Information Geometry

Cited by 31 publications

References 56 publications

Complex Network Construction of Univariate Chaotic Time Series Based on Maximum Mean Discrepancy

Complex Network Construction of Univariate Chaotic Time Series Based on Maximum Mean Discrepancy

The System Identification and Prediction of the Social Earthquakes Burst in Human Society

Exploring wall shear stress spatiotemporal heterogeneity in coronary arteries combining correlation-based analysis and complex networks with computational hemodynamics

Contact Info

Product

Resources

About