Adaptive G–G clustering for fuzzy segmentation of multivariate time series

In this paper, Gath–Geva (G–G) fuzzy clustering is extended to adaptively segment hydrometeorological multivariate time series. First, KPCA is used to extract principle components of multivariate time series to remove the impacts of redundant and irrelevant variables. Then, taking the time information into account, the segmentation of principle components of multivariate time series is derived with the modified Davies–Bouldin Index and adaptive G–G fuzzy clustering. In the experiment, our proposed algorithm is applied on the real-world hydrometeorological multivariate time series collected every 6 min with length $$N=720$$ N = 720 . Comparison with the existing segmentation algorithms, our proposed algorithm proves the applicability and usefulness in hydrometeorological multivariate time series analysis.

[1]  V. K. Jayaraman,et al.  Feature extraction and denoising using kernel PCA , 2003 .

[2]  Ath. Kehagias,et al.  A hidden Markov model segmentation procedure for hydrological and environmental time series , 2004 .

[3]  János Abonyi,et al.  Modified Gath-Geva clustering for fuzzy segmentation of multivariate time-series , 2005, Fuzzy Sets Syst..

[4]  A. Kehagias,et al.  A dynamic programming segmentation procedure for hydrological and environmental time series , 2006 .

[5]  A. Kehagias,et al.  Time series segmentation with shifting means hidden markov models , 2006 .

[6]  Lingfeng Shi,et al.  Adaptive learning of dynamic Bayesian networks with changing structures by detecting geometric structures of time series , 2008, Knowledge and Information Systems.

[7]  Abdullah Gedikli,et al.  Segmentation algorithm for long time series analysis , 2008 .

[8]  Lingfeng Shi,et al.  Adaptive learning of dynamic Bayesian networks with changing structures by detecting geometric structures of time series , 2008, Knowledge and Information Systems.

[9]  Athanasios Kehagias,et al.  Modified dynamic programming approach for offline segmentation of long hydrometeorological time series , 2010 .

[10]  Li Ke-wu.  Research on pattern matching method for multivariate time series , 2011 .

[11]  János Abonyi,et al.  Dynamic Principal Component Analysis in Multivariate Time-Series Segmentation , 2011 .

[12]  Borut Zalik,et al.  Validity index for clusters of different sizes and densities , 2011, Pattern Recognit. Lett..

[13]  Tak-Chung Fu,et al.  A review on time series data mining , 2011, Eng. Appl. Artif. Intell..

[14]  K. alik,et al.  Validity index for clusters of different sizes and densities , 2011 .

[15]  Xiaodong Liu,et al.  Improved Gath–Geva clustering for fuzzy segmentation of hydrometeorological time series , 2011, Stochastic Environmental Research and Risk Assessment.

[16]  I. Simon,et al.  Studying and modelling dynamic biological processes using time-series gene expression data , 2012, Nature Reviews Genetics.

[17]  Carlos Agón,et al.  Time-series data mining , 2012, CSUR.

[18]  Dong Zhou,et al.  Translation techniques in cross-language information retrieval , 2012, CSUR.

[19]  János Abonyi,et al.  On-line detection of homogeneous operation ranges by dynamic principal component analysis based time-series segmentation , 2012 .

[20]  Faicel Chamroukhi,et al.  Joint segmentation of multivariate time series with hidden process regression for human activity recognition , 2013, Neurocomputing.

[21]  Piotr Fryzlewicz,et al.  Multiple‐change‐point detection for high dimensional time series via sparsified binary segmentation , 2015, 1611.08639.

[22]  Xiaodong Liu,et al.  Dynamic programming approach for segmentation of multivariate time series , 2014, Stochastic Environmental Research and Risk Assessment.

[23]  Xiaodong Liu,et al.  Dynamic programming-based optimization for segmentation and clustering of hydrometeorological time series , 2016, Stochastic Environmental Research and Risk Assessment.

[24]  Azuraliza Abu Bakar,et al.  Adaptive sliding window algorithm for weather data segmentation , 2015 .

[25]  Jinfeng Yi,et al.  Stochastic Optimization for Kernel PCA , 2016, AAAI.

[26]  H. Madsen,et al.  Dynamic Allocation or Diversification: A Regime-Based Approach to Multiple Assets , 2017 .