Remark on the Accuracy of Recurrent Forecasting in Singular Spectrum Analysis

Standard

Remark on the Accuracy of Recurrent Forecasting in Singular Spectrum Analysis. / Nekrutkin, V. V. .

In: Vestnik St. Petersburg University: Mathematics, Vol. 56, No. 1, 04.2023, p. 35-45.

Research output: Contribution to journal › Article › peer-review

Author

Nekrutkin, V. V. . / Remark on the Accuracy of Recurrent Forecasting in Singular Spectrum Analysis. In: Vestnik St. Petersburg University: Mathematics. 2023 ; Vol. 56, No. 1. pp. 35-45.

BibTeX

@article{c2b198862453460f859995ff63d11624,

title = "Remark on the Accuracy of Recurrent Forecasting in Singular Spectrum Analysis",

abstract = "Within the series of singular spectrum analysis (SSA) methods, there exist several versionsof forecasting algorithms for signals corrupted by additive noise. In this paper, a technique is proposedto estimate the asymptotic accuracy of the recurrent version of such forecasting when the length of aseries tends to infinity. Most elements of this construction can be reduced to already studied and published results, although some of them are hard to implement in specific situations. The article bringstogether all these elements and augments and comments on them. Several examples of determiningestimates of accuracy for a recurrent forecast are given for specific signals and noises. The computational experiments carried out confirm the theoretical results.",

keywords = "signal processing, singular spectrum analysis, recurrent forecast, asymptotic analysis",

author = "Nekrutkin, {V. V.}",

year = "2023",

month = apr,

language = "English",

volume = "56",

pages = "35--45",

journal = "Vestnik St. Petersburg University: Mathematics",

issn = "1063-4541",

publisher = "Pleiades Publishing",

number = "1",

}

RIS

TY - JOUR

T1 - Remark on the Accuracy of Recurrent Forecasting in Singular Spectrum Analysis

AU - Nekrutkin, V. V.

PY - 2023/4

Y1 - 2023/4

N2 - Within the series of singular spectrum analysis (SSA) methods, there exist several versionsof forecasting algorithms for signals corrupted by additive noise. In this paper, a technique is proposedto estimate the asymptotic accuracy of the recurrent version of such forecasting when the length of aseries tends to infinity. Most elements of this construction can be reduced to already studied and published results, although some of them are hard to implement in specific situations. The article bringstogether all these elements and augments and comments on them. Several examples of determiningestimates of accuracy for a recurrent forecast are given for specific signals and noises. The computational experiments carried out confirm the theoretical results.

AB - Within the series of singular spectrum analysis (SSA) methods, there exist several versionsof forecasting algorithms for signals corrupted by additive noise. In this paper, a technique is proposedto estimate the asymptotic accuracy of the recurrent version of such forecasting when the length of aseries tends to infinity. Most elements of this construction can be reduced to already studied and published results, although some of them are hard to implement in specific situations. The article bringstogether all these elements and augments and comments on them. Several examples of determiningestimates of accuracy for a recurrent forecast are given for specific signals and noises. The computational experiments carried out confirm the theoretical results.

KW - signal processing

KW - singular spectrum analysis

KW - recurrent forecast

KW - asymptotic analysis

M3 - Article

VL - 56

SP - 35

EP - 45

JO - Vestnik St. Petersburg University: Mathematics

JF - Vestnik St. Petersburg University: Mathematics

SN - 1063-4541

IS - 1

ER -

ID: 104023468