| GENERAL |
|
|
|
|
Generalized Multivariate Singular Spectrum Analysis for Nonlinear Time Series De-Noising and Prediction |
| Yi Ji1, Hong-Bo Xie2** |
1School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013
2ARC Centre of Excellence for Mathematical and Statistical Frontiers, Queensland University of Technology, Brisbane, QLD 4000, Australia
|
|
| Cite this article: |
|
Yi Ji, Hong-Bo Xie 2017 Chin. Phys. Lett. 34 120501 |
|
|
|
|
Abstract Singular spectrum analysis and its multivariate or multichannel singular spectrum analysis (MSSA) variant are effective methods for time series representation, denoising and prediction, with broad application in many fields. However, a key element in MSSA is singular value decomposition of a high-dimensional matrix stack of component matrices, where the spatial (structural) information among multivariate time series is lost or distorted. This vector-space model also leads to difficulties including high dimensionality, small sample size, and numerical instability when applied to multi-dimensional time series. We present a generalized multivariate singular spectrum analysis (GMSSA) method to simultaneously decompose multivariate time series into constituent components, which can overcome the limitations of conventional multivariate singular spectrum analysis. In addition, we propose a SampEn-based method to determine the dominant components in GMSSA. We demonstrate the effectiveness and efficiency of GMSSA to simultaneously de-noise multivariate time series for attractor reconstruction, and to predict both simulated and real-world multivariate noisy time series.
|
|
|
Received: 01 August 2017
Published: 24 November 2017
|
|
| PACS: |
05.45.Tp
|
(Time series analysis)
|
| |
05.45.Ac
|
(Low-dimensional chaos)
|
| |
95.75.Wx
|
(Time series analysis, time variability)
|
|
|
| Fund: Supported by the Priority Academic Program Development of Jiangsu Higher Education Institutions (PAPD). |
|
|
|
| [1] | Xie H B, Guo T, Sivakumar B, Liew A W C and Dokos S 2014 Proc. R. Soc. A 470 20140409 | | [2] | Hassani H, Heravi S and Zhigljavsky A 2013 J. Forecasting 32 395 | | [3] | Hossein H 2013 Int. J. Energy Stat. 1 55 | | [4] | Song J J, Ren Y and Yan F L 2009 Comput. Biol. Chem. 33 408 | | [5] | Pilgram B and Schappacher W 1998 Int. J. Bifurcation Chaos Appl. Sci. Eng. 8 571 | | [6] | Xie H B, Guo J Y and Zheng Y P 2010 Phys. Lett. A 374 3926 | | [7] | Xie H B, He W X and Liu H 2008 Phys. Lett. A 372 7140 | | [8] | Xie H B, Chen W T, He W X and Liu H 2011 Appl. Soft Comput. 11 2871 | | [9] | Xie H B, Guo J Y and Zheng Y P 2010 Ann. Biomed. Eng. 38 1483 | | [10] | Kennel M B, Brown R and Abarbanel H D I 1992 Phys. Rev. A 45 3403 | | [11] | Jiang J and Xie H B 2016 Chin. Phys. Lett. 33 100501 | | [12] | Wu C L and Chau K W 2013 Eng. Appl. Artif. Intel. 26 997 | | [13] | Wang X Y and Han M 2015 Eng. Appl. Artif. Intel. 40 28 | | [14] | du Preez J and Witt S F 2003 Int. J. Forecasting 19 435 | | [15] | Xie H B, Sivakumar B, Boontra T W and Mengersen K 2017 IEEE Trans. Fuzzy Syst. (in press) |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
