Singular Spectrum Analysis Based on L1-Norm

In recent years, the singular spectrum analysis (SSA) technique has been further developed and increasingly applied to solve many practical problems. The aim of this research is to introduce a new version of SSA based on L1-norm. The performance of the proposed approach is assessed by applying it to various real and simulated time series, especially with outliers. The results are compared with those obtained using the basic version of SSA which is based on the Frobenius norm or L2-norm. Different criteria are also examined including reconstruction errors and forecasting performances. The theoretical and empirical results confirm that SSA based on L1-norm can provide better reconstruction and forecasts in comparison to basic SSA when faced with time series which are polluted by outliers.

[1]  Zhengyuan Xu,et al.  Singular spectrum analysis based on the perturbation theory , 2011 .

[2]  Sadik Kara,et al.  Singular Spectrum Analysis of Sleep EEG in Insomnia , 2011, Journal of Medical Systems.

[3]  Hardi Nabe Omer,et al.  A Preliminary Investigation into the Effect of Outlier(s) on Singular Spectrum Analysis , 2014 .

[4]  Stuart Jay Deutsch,et al.  Effects of a single outlier on arma identification , 1990 .

[5]  David Birkes,et al.  Alternative Methods of Regression: Birkes/Alternative , 1993 .

[6]  Chin-Hsiung Loh,et al.  Application of singular spectrum analysis to structural monitoring and damage diagnosis of bridges , 2014 .

[7]  P. Tang,et al.  Periodicity of Carbon Element Distribution Along Casting Direction in Continuous-Casting Billet by Using Singular Spectrum Analysis , 2014, Metallurgical and Materials Transactions B.

[8]  Siu-Seong Law,et al.  Singular spectrum analysis for enhancing the sensitivity in structural damage detection , 2014 .

[9]  R. Rajkó.  Treatment of Model Error in Calibration by Robust and Fuzzy Procedures , 1994 .

[10]  Rahim Mahmoudvand,et al.  FILTERING AND DENOISING IN LINEAR REGRESSION ANALYSIS , 2010 .

[11]  S. P. Ellis,et al.  Leverage and Breakdown in L 1 Regression , 1992 .

[12]  R. Tsay.  Outliers, Level Shifts, and Variance Changes in Time Series , 1988 .

[13]  Nico Sneeuw,et al.  Singular spectrum analysis for modeling seasonal signals from GPS time series , 2013 .

[14]  Mansi Ghodsi,et al.  Exchange rate forecasting with optimum singular spectrum analysis , 2014, J. Syst. Sci. Complex..

[15]  Karine Le Bail,et al.  Quantifying the Correlation Between the MEI and LOD Variations by Decomposing LOD with Singular Spectrum Analysis , 2014 .

[16]  Rahim Mahmoudvand,et al.  On the separability between signal and noise in singular spectrum analysis , 2012 .

[17]  Emmanuel Sirimal Silva,et al.  Forecasting U.S. Tourist arrivals using optimal Singular Spectrum Analysis , 2015 .

[18]  Hossein Hassani,et al.  MULTIVARIATE SINGULAR SPECTRUM ANALYSIS: A GENERAL VIEW AND NEW VECTOR FORECASTING APPROACH , 2013 .

[19]  Melvin F. Janowitz,et al.  Ordinal and percentile clustering , 1989 .

[20]  N. Antonakakis,et al.  OIL PRICES AND STOCK MARKET CORRELATION: A TIME-VARYING APPROACH , 2013 .

[21]  S.A.V. Satya Murty,et al.  Roller element bearing fault diagnosis using singular spectrum analysis , 2013 .