Comptes Rendus
no. 5
Statistics
A novel signal extraction approach for filtering and forecasting noisy exponential series
[Une nouvelle approche dans l'extraction de signal pour le filtrage et la prévision par des séries exponentielles avec bruit]

Présenté par : Paul Deheuvels

Hossein Hassani1 ; Mahdi Kalantari2
1 Research Institute for Energy Management and Planning, University of Tehran, Tehran, Iran
2 Department of Statistics, Payame Noor University, 19395-4697, Tehran, Iran
Comptes Rendus. Mathématique, Volume 356 (2018) no. 5, pp. 563-570.

Les coefficients des relations récurrentes linéaires (RRL) jouent un rôle central dans beaucoup de techniques de prévision. Une formule exacte et close des coefficients d'une RRL permet d'obtenir des prévisions plus précises. Prenant en compte le fait que, dans la réalité, une suite temporelle de données est contaminée par du bruit, il est très important de pouvoir en extraire la série sans bruit. Ce texte vise à obtenir une forme close, avec un niveau de bruit moindre, des coefficients d'une RRL, pour les suites en temps exponentiel avec bruit. Une autre nouveauté de notre approche est l'amélioration de l'efficacité du filtrage par l'utilisation de vecteurs propres sans bruit de la matrice de covariance. Les résultats des simulations confirment que l'approche proposée améliore le filtrage et les prévisions.

The coefficients of Linear Recurrent Relations (LRR) play a pivotal role in many forecasting techniques. Precise and closed form of the LRR coefficients enables one to achieve more accurate forecasts. On account to the fact that, in real-world situations, a time series data is contaminated with noise, extracting the noiseless series is of great importance. This paper seeks to obtain a closed form, with less noise level, of LRR coefficients for noisy exponential time series. Improving the filtering performance through employing noiseless eigenvectors of the covariance matrix is another novelty of this study. Our simulation results confirm that the proposed approach enhances filtering and forecasting results.

Reçu le :
Accepté le :
Publié le :
DOI : 10.1016/j.crma.2018.03.006
Hossein Hassani 1 ; Mahdi Kalantari 2

1 Research Institute for Energy Management and Planning, University of Tehran, Tehran, Iran
2 Department of Statistics, Payame Noor University, 19395-4697, Tehran, Iran 
@article{CRMATH_2018__356_5_563_0,
     author = {Hossein Hassani and Mahdi Kalantari},
     title = {A novel signal extraction approach for filtering and forecasting noisy exponential series},
     journal = {Comptes Rendus. Math\'ematique},
     pages = {563--570},
     publisher = {Elsevier},
     volume = {356},
     number = {5},
     year = {2018},
     doi = {10.1016/j.crma.2018.03.006},
     language = {en},
}
TY  - JOUR
AU  - Hossein Hassani
AU  - Mahdi Kalantari
TI  - A novel signal extraction approach for filtering and forecasting noisy exponential series
JO  - Comptes Rendus. Mathématique
PY  - 2018
SP  - 563
EP  - 570
VL  - 356
IS  - 5
PB  - Elsevier
DO  - 10.1016/j.crma.2018.03.006
LA  - en
ID  - CRMATH_2018__356_5_563_0
ER  - 
%0 Journal Article
%A Hossein Hassani
%A Mahdi Kalantari
%T A novel signal extraction approach for filtering and forecasting noisy exponential series
%J Comptes Rendus. Mathématique
%D 2018
%P 563-570
%V 356
%N 5
%I Elsevier
%R 10.1016/j.crma.2018.03.006
%G en
%F CRMATH_2018__356_5_563_0
Hossein Hassani; Mahdi Kalantari. A novel signal extraction approach for filtering and forecasting noisy exponential series. Comptes Rendus. Mathématique, Volume 356 (2018) no. 5, pp. 563-570. doi : 10.1016/j.crma.2018.03.006. https://comptes-rendus.academie-sciences.fr/mathematique/articles/10.1016/j.crma.2018.03.006/

[1] N. Alharbi; H. Hassani A new approach for selecting the number of the eigen values in singular spectrum analysis, J. Franklin Inst., Volume 353 (2016), pp. 1-16

[2] M. Carvalho; A. Rua Real-time nowcasting the US output gap: singular spectrum analysis at work, Int. J. Forecast., Volume 33 (2017) no. 1, pp. 185-198

[3] Q. Chen; T.V. Dam; N. Sneeuw; X. Collilieux; M. Weigelt; P. Rebischung Singular spectrum analysis for modeling seasonal signals from GPS time series, J. Geodyn., Volume 72 (2013), pp. 25-35

[4] P.H. Franses; D.V. Dijk Nonlinear Time Series Models in Empirical Finance, Cambridge University Press, 2013

[5] Z. Ghodsi; E.S. Silva; H. Hassani Bicoid signal extraction with a selection of parametric and nonparametric signal processing techniques, Genomics Proteomics Bioinform., Volume 13 (2015) no. 3, pp. 183-191

[6] N. Golyandina; A. Zhigljavsky Singular Spectrum Analysis for Time Series, Springer Briefs in Statistics, Springer, 2013

[7] H. Hassani Singular spectrum analysis based on the minimum variance estimator, Nonlinear Anal., Real World Appl., Volume 11 (2010), pp. 2065-2077

[8] H. Hassani; Z. Xu; A. Zhigljavsky Singular spectrum analysis based on the perturbation theory, Nonlinear Anal., Real World Appl., Volume 12 (2011) no. 5, pp. 2752-2766

[9] H. Hassani; A. Webster; E.S. Silva; S. Heravi; U.S. Forecasting Tourist arrivals using optimal singular spectrum analysis, Tour. Manag., Volume 46 (2015), pp. 322-335

[10] H. Hassani; E.S. Silva; Z. Ghodsi Optimizing bicoid signal extraction, Math. Biosci., Volume 294 (2017), pp. 46-56

[11] Z. Hou; G. Wen; P. Tang; G. Cheng Periodicity of carbon element distribution along casting direction in continuous-casting billet by using singular spectrum analysis, Metall. Mater. Trans. B, Volume 45 (2014) no. 5, pp. 1817-1826

[12] M. Kalantari; M. Yarmohammadi; H. Hassani Singular spectrum analysis based on L1-norm, Fluct. Noise Lett., Volume 15 (2016) no. 1

[13] K. Liu; S.S. Law; Y. Xia; X.Q. Zhu Singular spectrum analysis for enhancing the sensitivity in structural damage detection, J. Sound Vib., Volume 333 (2014) no. 2, pp. 392-417

[14] R. Mahmoudvand; P.C. Rodrigues Missing value imputation in time series using singular spectrum analysis, Int. J. Energy Stat., Volume 4 (2016) no. 1

[15] F. Papailias; D. Thomakos EXSSA: SSA-based reconstruction of time series via exponential smoothing of covariance eigenvalues, Int. J. Forecast., Volume 33 (2017) no. 1, pp. 214-229

[16] L. Rodriguez-Aragon; A. Zhigljavsky Singular spectrum analysis for image processing, Stat. Interface, Volume 3 (2010), pp. 419-426

[17] S. Sanei; H. Hassani Singular Spectrum Analysis of Biomedical Signals, Taylor & Francis, CRC Press, Boca Raton, FL, USA, 2016

[18] E.S. Silva; H. Hassani On the use of singular spectrum analysis for forecasting U.S. trade before, during and after the 2008 recession, Int. Econ., Volume 141 (2015), pp. 34-49

[19] M. Small Applied Nonlinear Time Series Analysis, Applications in Physics, Physiology and Finance, World Scientific, 2005

[20] R.S. Tsay Analysis of Financial Time Series, John Wiley & Sons, 2010

[21] M. Verbeek A Guide to Modern Econometrics, John Wiley & Sons, 2004

[22] R. Wang; H.G. Ma; G.Q. Liu; D.G. Zuo Selection of window length for singular spectrum analysis, J. Franklin Inst., Volume 352 (2015), pp. 1541-1560

[23] J. Zhang; H. Hassani; H. Xie; X. Zhang Estimating multi-country prosperity index: a two-dimensional singular spectrum analysis approach, J. Syst. Sci. Complex., Volume 27 (2014), pp. 56-74

Cité par Sources :

Commentaires - Politique

Ces articles pourraient vous intéresser

An improved SSA forecasting result based on a filtered recurrent forecasting algorithm

Hossein Hassani; Mahdi Kalantari; Masoud Yarmohammadi

C. R. Math (2017)

Forecasting for flood warning

Robert J. Moore; Victoria A. Bell; David A. Jones

C. R. Géos (2005)

Improving the performance of precipitation outputs from Global Climate Models to predict monthly and seasonal rainfall over the Indian subcontinent

Archana Nair; Uma C. Mohanty; Tarini C. Panda

C. R. Géos (2015)