Searcharxiv⌕ Search

arXiv subjects

Nina Golyandina

Publications and source records attributed to Nina Golyandina.

15 recordsLinked to original sources
arXiv2025

Filling the gap in the IERS C01 polar motion series in 1858.9-1860.9

The C01 Earth orientation parameters (EOP) series provided by the International Earth Rotation and Reference Systems Service (IERS) is the longest reliable record of the Earth's rotation. In particular, the polar motion (PM) series beginning from 1846 provides a basis for investigation of the long-term PM variations. However, the pole coordinate $Y_p$ in the IERS C01 PM series has a 2-year gap, which makes this series not completely evenly spaced. This paper presents the results of the first attempt to overcome this problem and discusses some ways to fill this gap. Two novel approaches were considered for this purpose: parametric astronomical model consisting of the bias and the Chandler and annual wobbles with linearly changing amplitudes, and data-driven model based on Singular Spectrum Analysis (SSA). Both methods were tested with various options to ensure robust and reliable results. The results obtained by the two methods generally agree within the $Y_p$ errors in the IERS C01 series, but the results obtained by the SSA approach can be considered preferable because it is based on a more complete PM model.

physics.geo-ph↗
arXiv2021

Detection of signals by Monte Carlo singular spectrum analysis: Multiple testing

Detection of a signal in a noisy time series using Monte Carlo singular spectrum analysis (MC-SSA) is studied from the statistical viewpoint. The MC-SSA test consists of simultaneous testing of several hypotheses related to the presence of different frequencies. The multiple MC-SSA test procedure is constructed to control the family-wise error rate. The technique to control both the type I and the type II errors and also to compare criteria is proposed to study several versions of MC-SSA.

stat.ME↗
arXiv2021

Fast and stable modification of the Gauss-Newton method for low-rank signal estimation

The weighted nonlinear least-squares problem for low-rank signal estimation is considered. The problem of constructing a numerical solution that is stable and fast for long time series is addressed. A modified weighted Gauss-Newton method, which can be implemented through the direct variable projection onto a space of low-rank signals, is proposed. For a weight matrix which provides the maximum likelihood estimator of the signal in the presence of autoregressive noise of order $p$ the computational cost of iterations is $O(N r^2 + N p^2 + r N \log N)$ as $N$ tends to infinity, where $N$ is the time-series length, $r$ is the rank of the approximating time series. Moreover, the proposed method can be applied to data with missing values, without increasing the computational cost. The method is compared with state-of-the-art methods based on the variable projection approach in terms of floating-point numerical stability and computational cost.

math.NA↗
arXiv2021

Particularities and commonalities of singular spectrum analysis as a method of time series analysis and signal processing

Singular spectrum analysis (SSA), starting from the second half of the XX century, has been a rapidly developing method of time series analysis. Since it can be called principal component analysis for time series, SSA will definitely be a standard method in time series analysis and signal processing in the future. Moreover, the problems solved by SSA are considerably wider than that for principal component analysis. In particular, the problems of frequency estimation, forecasting and missing values imputation can be solved within the framework of SSA. The idea of SSA came from different scientific communities, such as that of researchers in time series analysis (Karhunen-Loeve decomposition), signal processing (low-rank approximation and frequency estimation) and multivariate data analysis (principal component analysis). Also, depending on the area of applications, different viewpoints on the same algorithms, choice of parameters, and methodology as a whole are considered. Thus, the aim of the paper is to describe and compare different viewpoints on SSA and its modifications and extensions to give people from different scientific communities the possibility to be aware of potentially new aspects of the method.

stat.ME↗
arXiv2021

Low-rank signal subspace: parameterization, projection and signal estimation

The paper contains several theoretical results related to the weighted nonlinear least-squares problem for low-rank signal estimation, which can be considered as a Hankel structured low-rank approximation problem. A parameterization of the subspace of low-rank time series connected with generalized linear recurrence relations (GLRRs) is described and its features are investigated. It is shown how the obtained results help to describe the tangent plane, prove optimization problem features and construct stable algorithms for solving low-rank approximation problems. For the latter, a stable algorithm for constructing the projection onto a subspace of time series that satisfy a given GLRR is proposed and justified. This algorithm is used for a new implementation of the known Gauss-Newton method using the variable projection approach. The comparison by stability and computational cost is performed theoretically and with the help of an example.

math.NA↗
arXiv2020

Blind deconvolution of covariance matrix inverses for autoregressive processes

Matrix $\mathbf{C}$ can be blindly deconvoluted if there exist matrices $\mathbf{A}$ and $\mathbf{B}$ such that $\mathbf{C}= \mathbf{A} \ast \mathbf{B}$, where $\ast$ denotes the operation of matrix convolution. We study the problem of matrix deconvolution in the case where matrix $\mathbf{C}$ is proportional to the inverse of the autocovariance matrix of an autoregressive process. We show that the deconvolution of such matrices is important in problems of Hankel structured low-rank approximation (HSLRA). In the cases of autoregressive models of orders one and two, we fully characterize the range of parameters where such deconvolution can be performed and provide construction schemes for performing deconvolutions. We also consider general autoregressive models of order $p$, where we prove that the deconvolution $\mathbf{C}= \mathbf{A} \ast \mathbf{B}$ does not exist if the matrix $\mathbf{B}$ is diagonal and its size is larger than $p$.

math.NA↗
arXiv2017

Two-exponential models of gene expression patterns for noisy experimental data

Motivation: Spatial pattern formation of the primary anterior-posterior morphogenetic gradient of the transcription factor Bicoid (Bcd) has been studied experimentally and computationally for many years. Bcd specifies positional information for the downstream segmentation genes, affecting the fly body plan. More recently, a number of researchers have focused on the patterning dynamics of the underlying bcd mRNA gradient, which is translated into Bcd protein. New, more accurate techniques for visualizing bcd mRNA need to be combined with quantitative signal extraction techniques to reconstruct the bcd mRNA distribution. Results: Here, we present a robust technique for quantifying gradients with a two-exponential model. This approach: 1) has natural, biologically relevant parameters; and 2) is invariant to linear transformations of the data which can arise due to variation in experimental conditions (e.g. microscope settings, non-specific background signal). This allows us to quantify bcd mRNA gradient variability from embryo to embryo (important for studying the robustness of developmental regulatory networks); sort out atypical gradients; and classify embryos to developmental stage by quantitative gradient parameters.

q-bio.QM↗
arXiv2015

Semi-nonparametric singular spectrum analysis with projection

Singular spectrum analysis (SSA) is considered for decomposition of time series into identifiable components. The Basic SSA method is nonparametric and constructs an adaptive expansion based on singular value decomposition. The investigated modification is able to take into consideration a structure given in advance and therefore can be called semi-nonparametric. The approach called SSA with projection includes preliminary projections of rows and columns of the series trajectory matrix to given subspaces. One application of SSA with projection is the extraction of polynomial trends, e.g., a linear trend. It is shown that SSA with projection can extract polynomial trends much better than Basic SSA, especially for linear trends. Numerical examples including comparison with the least-square approach to polynomial regression are presented.

stat.ME↗
arXiv2015

Iterative algorithms for weighted and unweighted finite-rank time-series approximations

The problem of time series approximation by series of finite rank is considered from the viewpoint of signal extraction. For signal estimation, a weighted least-squares method is applied to the trajectory matrix of the considered time series. Matrix weights are chosen to obtain equal or approximately equal weights in the equivalent problem of time-series least-squares approximation. Several new methods are suggested and examined together with the Cadzow's iterative method. The questions of convergence, computational complexity, and accuracy are considered for the proposed methods. The methods are compared on numeric examples.

stat.ME↗
arXiv2014

Multivariate and 2D Extensions of Singular Spectrum Analysis with the Rssa Package

Implementation of multivariate and 2D extensions of Singular Spectrum Analysis (SSA) by means of the R-package Rssa is considered. The extensions include MSSA for simultaneous analysis and forecasting of several time series and 2D-SSA for analysis of digital images. A new extension of 2D-SSA analysis called Shaped 2D-SSA is introduced for analysis of images of arbitrary shape, not necessary rectangular. It is shown that implementation of Shaped 2D-SSA can serve as a base for implementation of MSSA and other generalizations. Efficient implementation of operations with Hankel and Hankel-block-Hankel matrices through FFT is suggested. Examples with code fragments in R, which explain the methodology and demonstrate the proper use of Rssa, are presented.

stat.ME↗
arXiv2014

Shaped extensions of singular spectrum analysis

Extensions of singular spectrum analysis (SSA) for processing of non-rectangular images and time series with gaps are considered. A circular version is suggested, which allows application of the method to the data given on a circle or on a cylinder, e.g. cylindrical projection of a 3D ellipsoid. The constructed Shaped SSA method with planar or circular topology is able to produce low-rank approximations for images of complex shapes. Together with Shaped SSA, a shaped version of the subspace-based ESPRIT method for frequency estimation is developed. Examples of 2D circular SSA and 2D Shaped ESPRIT are presented.

stat.ME↗
arXiv2014

Variations of singular spectrum analysis for separability improvement: non-orthogonal decompositions of time series

Singular spectrum analysis (SSA) as a nonparametric tool for decomposition of an observed time series into sum of interpretable components such as trend, oscillations and noise is considered. The separability of these series components by SSA means the possibility of such decomposition. Two variations of SSA, which weaken the separability conditions, are proposed. Both proposed approaches consider inner products corresponding to oblique coordinate systems instead of the conventional Euclidean inner product. One of the approaches performs iterations to obtain separating inner products. The other method changes contributions of the components by involving the series derivative to avoid component mixing. Performance of the suggested methods is demonstrated on simulated and real-life data.

stat.ME↗
arXiv2013

Basic Singular Spectrum Analysis and Forecasting with R

Singular Spectrum Analysis (SSA) as a tool for analysis and forecasting of time series is considered. The main features of the Rssa package, which implements the SSA algorithms and methodology in R, are described and examples of its use are presented. Analysis, forecasting and parameter estimation are demonstrated by means of case study with an accompanying code in R.

stat.ME↗
arXiv2011

On the choice of parameters in Singular Spectrum Analysis and related subspace-based methods

In the present paper we investigate methods related to both the Singular Spectrum Analysis (SSA) and subspace-based methods in signal processing. We describe common and specific features of these methods and consider different kinds of problems solved by them such as signal reconstruction, forecasting and parameter estimation. General recommendations on the choice of parameters to obtain minimal errors are provided. We demonstrate that the optimal choice depends on the particular problem. For the basic model `signal + residual' we show that the error behavior depends on the type of residuals, deterministic or stochastic, and whether the noise is white or red. The structure of errors and the convergence rate are also discussed. The analysis is based on known theoretical results and extensive computer simulations.

stat.ME↗