Stephan Weiss
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Stephan Weiss has a total of 189 co-authors. Here are the top co-authors by number of shared publications:
R.W. Stewart
Centre for White Space Communications, Department of Electronic & Electrical Engineering, University of Strathclyde, Glasgow G1 1XW, Scotland, UK
20 shared publications- Wei Liu
Hong Kong Polytechnic University
20 shared publications - Ian Keith Proudler
Department of EEE, University of Strathclyde, Glasgow, U.K.
15 shared publications John G. McWhirter
University of Cardiff, Cardiff, U.K.
13 shared publications- Jamie Corr
Department of Electronic & Electrical Engineering, University of Strathclyde, Glasgow, Scotland
12 shared publications - Lajos Hanzo
University of Southampton
12 shared publications
Latest Publications
- 23 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33 (10709908) , 1106-1110
Accuracy of the Wiener-Hopf Solution When Based on Sample Statistics
This paper addresses the problem of an adaptive linear combiner when using sample statistics. In this case, the Wiener-Hopf solution can be based on sample covariance matrices and cross-correlation vectors. Despite these estimates being inaccurate, the calculated, approximate solution can be very precise. We explore why this is so by interpreting the Wiener-Hopf solution as coming from a least squares problem. We compare this solution to the case where we exploit knowledge about some of the statistics. Surprisingly this has very limited benefits and often is detrimental. We also show why it is disadvantageous to separately estimate the two statistics.
- 23 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33 (10709908) , 1106-1110
Accuracy of the Wiener-Hopf Solution When Based on Sample Statistics
This paper addresses the problem of an adaptive linear combiner when using sample statistics. In this case, the Wiener-Hopf solution can be based on sample covariance matrices and cross-correlation vectors. Despite these estimates being inaccurate, the calculated, approximate solution can be very precise. We explore why this is so by interpreting the Wiener-Hopf solution as coming from a least squares problem. We compare this solution to the case where we exploit knowledge about some of the statistics. Surprisingly this has very limited benefits and often is detrimental. We also show why it is disadvantageous to separately estimate the two statistics.
- 11 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 74 (1053587X) , 904-919
Best Least Squares Paraunitary Approximation: Analytic Procrustes Problem
This paper addresses the analytic Procrustes problem, which aims to find the best least-squares paraunitary approximation of a square matrix of analytic transfer functions, or the best paraunitary transformation between two rectangular analytic matrices. This is accomplished by generalising the Procrustes solution from ordinary matrices to the case of matrices of analytic functions via their analytic singular value decomposition (SVD). Different from the ordinary matrix case, the analytic SVD is not restricted to singular values being nonnegative. In the case that singular values do not possess any zero crossings, we can find an analytic paraunitary matrix analogously to the standard Procrustes approach. In the case that singular values exhibit any zero crossings, the solution does not only depend on the left- and right-singular vectors, but also on a discontinuous and hence non-analytic switching function that forces those analytic singular values to become nonnegative real. We show that a close approximation of this switching function can be achieved via a complex-valued allpass filter, for which we suggest a new suitable design to minimise the overall least squares error of the fit. In addition, we propose a DFT domain algorithm to approximate this polynomial Procrustes solution, which avoids ambiguities in the analytic SVD, and possesses proven convergence. Generally, this solution requires a delay for causality, and this delay grows with the approximation order. Examples and simulations demonstrate our proposed method.
- 11 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 74 (1053587X) , 904-919
Best Least Squares Paraunitary Approximation: Analytic Procrustes Problem
This paper addresses the analytic Procrustes problem, which aims to find the best least-squares paraunitary approximation of a square matrix of analytic transfer functions, or the best paraunitary transformation between two rectangular analytic matrices. This is accomplished by generalising the Procrustes solution from ordinary matrices to the case of matrices of analytic functions via their analytic singular value decomposition (SVD). Different from the ordinary matrix case, the analytic SVD is not restricted to singular values being nonnegative. In the case that singular values do not possess any zero crossings, we can find an analytic paraunitary matrix analogously to the standard Procrustes approach. In the case that singular values exhibit any zero crossings, the solution does not only depend on the left- and right-singular vectors, but also on a discontinuous and hence non-analytic switching function that forces those analytic singular values to become nonnegative real. We show that a close approximation of this switching function can be achieved via a complex-valued allpass filter, for which we suggest a new suitable design to minimise the overall least squares error of the fit. In addition, we propose a DFT domain algorithm to approximate this polynomial Procrustes solution, which avoids ambiguities in the analytic SVD, and possesses proven convergence. Generally, this solution requires a delay for causality, and this delay grows with the approximation order. Examples and simulations demonstrate our proposed method.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 74, 3597-3611
Analytic Gram-Schmidt Orthogonalization and QR Decomposition for Polynomial Matrices
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 74, 3597-3611
Analytic Gram-Schmidt Orthogonalization and QR Decomposition for Polynomial Matrices
- Open Access
Least-Squares Khatri-Rao Factorization of a Polynomial Matrix
The Khatri-Rao product is extensively used in array processing, tensor decomposition, and multi-way data analysis. Many applications require a least-squares (LS) Khatri-Rao factorization. In broadband sensor array problems, polynomial matrices effectively model frequency-dependent behaviors, necessitating extensions of conventional linear algebra techniques. This paper generalizes LS Khatri-Rao factorization from ordinary to polynomial matrices by applying it to the discrete Fourier transform (DFT) samples of polynomial matrices. Phase coherence across bin-wise Khatri-Rao factors is ensured via a phasesmoothing algorithm. The proposed method is validated through broadband angle-of-arrival (AoA) estimation for uniform planar arrays (UPAs), where the steering matrix is a polynomial matrix, which can be represented as a Khatri-Rao product between steering matrix in azimuth and elevation directions.
Open AccessLeast-Squares Khatri-Rao Factorization of a Polynomial Matrix
The Khatri-Rao product is extensively used in array processing, tensor decomposition, and multi-way data analysis. Many applications require a least-squares (LS) Khatri-Rao factorization. In broadband sensor array problems, polynomial matrices effectively model frequency-dependent behaviors, necessitating extensions of conventional linear algebra techniques. This paper generalizes LS Khatri-Rao factorization from ordinary to polynomial matrices by applying it to the discrete Fourier transform (DFT) samples of polynomial matrices. Phase coherence across bin-wise Khatri-Rao factors is ensured via a phasesmoothing algorithm. The proposed method is validated through broadband angle-of-arrival (AoA) estimation for uniform planar arrays (UPAs), where the steering matrix is a polynomial matrix, which can be represented as a Khatri-Rao product between steering matrix in azimuth and elevation directions.
- Open Access
- 19 February 2025
- Published by Elsevier in Signal Processing
- Vol. 233
Impact of space–time covariance matrix estimation on bin-wise eigenvalue and eigenspace perturbations
- 19 February 2025
- Published by Elsevier in Signal Processing
- Vol. 233
Open AccessImpact of space–time covariance matrix estimation on bin-wise eigenvalue and eigenspace perturbations
- Open Access
- 11 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 166652-166659
Scalable Analytic Eigenvalue Extraction Algorithm
Broadband sensor array problems can be formulated using parahermitian polynomial matrices, and the optimal solution to these problems can be based on the eigenvalue decomposition (EVD) of these matrices. An algorithm has been proposed in the past to extract analytic eigenvalues of parahermitian matrices, but it does not scale well with the temporal and spatial dimensions of the parahermitian matrix. This paper introduces a scalable analytical eigenvalue extraction algorithm for parahermitian polynomial matrices. The proposed algorithm operates in the discrete Fourier transform (DFT) domain, where an EVD is computed in each bin. Associations across bins are established based on properties of the analytic eigenvectors. The need to avoid problems with non-trivial algebraic multiplicities and control time-domain aliasing leads to an iterative algorithm that increases the DFT size until a suitable error criterion is satisfied. The algorithm can be shown to converge. Benchmarked against the existing algorithm, it performs accurately and with lower cost, and can successfully decompose matrices with dimensions much larger than previously had been feasible.
- 11 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 166652-166659
Open AccessScalable Analytic Eigenvalue Extraction Algorithm
Broadband sensor array problems can be formulated using parahermitian polynomial matrices, and the optimal solution to these problems can be based on the eigenvalue decomposition (EVD) of these matrices. An algorithm has been proposed in the past to extract analytic eigenvalues of parahermitian matrices, but it does not scale well with the temporal and spatial dimensions of the parahermitian matrix. This paper introduces a scalable analytical eigenvalue extraction algorithm for parahermitian polynomial matrices. The proposed algorithm operates in the discrete Fourier transform (DFT) domain, where an EVD is computed in each bin. Associations across bins are established based on properties of the analytic eigenvectors. The need to avoid problems with non-trivial algebraic multiplicities and control time-domain aliasing leads to an iterative algorithm that increases the DFT size until a suitable error criterion is satisfied. The algorithm can be shown to converge. Benchmarked against the existing algorithm, it performs accurately and with lower cost, and can successfully decompose matrices with dimensions much larger than previously had been feasible.
- Open Access
Impact of Estimation Errors of a Matrix of Transfer Functions onto Its Analytic Singular Values and Their Potential Algorithmic Extraction
A matrix of analytic functions A(z), such as the matrix of transfer functions in a multiple-input multiple-output (MIMO) system, generally admits an analytic singular value decomposition (SVD), where the singular values themselves are functions. When evaluated on the unit circle, for the sake of analyticity, these singular values must be permitted of become negative. In this paper, we address how the estimation of such a matrix, causing a stochastic perturbation of A}(z), results in fundamental changes to the analytic singular values: for the perturbed system, we show that their analytic singular values lose any algebraic multiplicities and are strictly non-negative with probability one. We present examples and highlight the impact that this has on algorithmic solutions to extracting an analytic or approximate analytic SVD.
Open AccessImpact of Estimation Errors of a Matrix of Transfer Functions onto Its Analytic Singular Values and Their Potential Algorithmic Extraction
A matrix of analytic functions A(z), such as the matrix of transfer functions in a multiple-input multiple-output (MIMO) system, generally admits an analytic singular value decomposition (SVD), where the singular values themselves are functions. When evaluated on the unit circle, for the sake of analyticity, these singular values must be permitted of become negative. In this paper, we address how the estimation of such a matrix, causing a stochastic perturbation of A}(z), results in fundamental changes to the analytic singular values: for the perturbed system, we show that their analytic singular values lose any algebraic multiplicities and are strictly non-negative with probability one. We present examples and highlight the impact that this has on algorithmic solutions to extracting an analytic or approximate analytic SVD.
- Open Access
Computational and Numerical Properties of a Broadband Subspace-Based Likelihood Ratio Test
This paper investigates the performance of a likelihood ratio test in combination with a polynomial subspace projection approach to detect weak transient signals in broadband array data. Based on previous empirical evidence that a likelihood ratio test is advantageously applied in a lower-dimensional subspace, we present analysis that highlights how the polynomial subspace projection whitens a crucial part of the signals, enabling a detector to operate with a shortened temporal window. This reduction in temporal correlation, together with a spatial compaction of the data, also leads to both computational and numerical advantages over a likelihood ratio test that is directly applied to the array data. The results of our analysis are illustrated by examples and simulations.
Open AccessComputational and Numerical Properties of a Broadband Subspace-Based Likelihood Ratio Test
This paper investigates the performance of a likelihood ratio test in combination with a polynomial subspace projection approach to detect weak transient signals in broadband array data. Based on previous empirical evidence that a likelihood ratio test is advantageously applied in a lower-dimensional subspace, we present analysis that highlights how the polynomial subspace projection whitens a crucial part of the signals, enabling a detector to operate with a shortened temporal window. This reduction in temporal correlation, together with a spatial compaction of the data, also leads to both computational and numerical advantages over a likelihood ratio test that is directly applied to the array data. The results of our analysis are illustrated by examples and simulations.
- 11 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 72 (1053587X) , 2260-2275
On Properties and Structure of the Analytic Singular Value Decomposition
We investigate the singular value decomposition (SVD) of a rectangular matrix $\boldsymbol{\mathit{A}}(z)$ of functions that are analytic on an annulus that includes at least the unit circle. Such matrices occur, e.g., as matrices of transfer functions representing broadband multiple-input multiple-output systems. Our analysis is based on findings for the analytic SVD applicable to continuous time systems, and on the analytic eigenvalue decomposition. Using these, we establish two potentially overlapping cases where analyticity of the SVD factors is denied. Firstly, from a structural point of view, multiplexed systems require oversampling by the multiplexing factor in order to admit an analytic solution. Secondly, from an algebraic perspective, we state under which condition spectral zeros of any singular value require additional oversampling by a factor of two if an analytic solution is to be found. In all other cases, an analytic matrix admits an analytic SVD, whereby the singular values are unique up to a permutation, and the left- and right-singular vectors are coupled through a joint ambiguity w.r.t. an arbitrary allpass function. We demonstrate how some state-of-the-art polynomial matrix decomposition algorithms approximate this solution, motivating the need for dedicated algorithms.
- 11 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 72 (1053587X) , 2260-2275
On Properties and Structure of the Analytic Singular Value Decomposition
We investigate the singular value decomposition (SVD) of a rectangular matrix $\boldsymbol{\mathit{A}}(z)$ of functions that are analytic on an annulus that includes at least the unit circle. Such matrices occur, e.g., as matrices of transfer functions representing broadband multiple-input multiple-output systems. Our analysis is based on findings for the analytic SVD applicable to continuous time systems, and on the analytic eigenvalue decomposition. Using these, we establish two potentially overlapping cases where analyticity of the SVD factors is denied. Firstly, from a structural point of view, multiplexed systems require oversampling by the multiplexing factor in order to admit an analytic solution. Secondly, from an algebraic perspective, we state under which condition spectral zeros of any singular value require additional oversampling by a factor of two if an analytic solution is to be found. In all other cases, an analytic matrix admits an analytic SVD, whereby the singular values are unique up to a permutation, and the left- and right-singular vectors are coupled through a joint ambiguity w.r.t. an arbitrary allpass function. We demonstrate how some state-of-the-art polynomial matrix decomposition algorithms approximate this solution, motivating the need for dedicated algorithms.
- Open Access
Siamese Residual Neural Network for Musical Shape Evaluation in Piano Performance Assessment
Understanding and identifying musical shape plays an important role in music education and performance assessment. To simplify the otherwise time- and cost-intensive musical shape evaluation, in this paper we explore how artificial intelligence (AI) driven models can be applied. Considering musical shape evaluation as a classification problem, a light-weight Siamese residual neural network (S-ResNN) is proposed to automatically identify musical shapes. To assess the proposed approach in the context of piano musical shape evaluation, we have generated a new dataset, containing 4116 music pieces derived by 147 piano preparatory exercises and performed in 28 categories of musical shapes. The experimental results show that the S-ResNN significantly outperforms a number of benchmark methods in terms of the precision, recall and F1 score.
Open AccessSiamese Residual Neural Network for Musical Shape Evaluation in Piano Performance Assessment
Understanding and identifying musical shape plays an important role in music education and performance assessment. To simplify the otherwise time- and cost-intensive musical shape evaluation, in this paper we explore how artificial intelligence (AI) driven models can be applied. Considering musical shape evaluation as a classification problem, a light-weight Siamese residual neural network (S-ResNN) is proposed to automatically identify musical shapes. To assess the proposed approach in the context of piano musical shape evaluation, we have generated a new dataset, containing 4116 music pieces derived by 147 piano preparatory exercises and performed in 28 categories of musical shapes. The experimental results show that the S-ResNN significantly outperforms a number of benchmark methods in terms of the precision, recall and F1 score.