Modeling and Sampling of Spectrally Structured Signals
(2020) In Doctoral Theses in Mathematical Sciences 2020(2). Abstract
 This thesis consists of five papers concerned with the modeling of stochastic signals, as well as deterministic signals in stochastic noise, exhibiting different kinds of structure. This structure is manifested as the existence of finitedimensional parameterizations, and/or in the geometry of the signals' spectral representations.
The two first papers of the thesis, Papers A and B, consider the modeling of differences, or distances, between stochastic processes based on their secondorder statistics, i.e., covariances. By relating the covariance structure of a stochastic process to spectral representations, it is proposed to quantify the dissimilarity between two processes in terms of the cost associated with morphing one... (More)  This thesis consists of five papers concerned with the modeling of stochastic signals, as well as deterministic signals in stochastic noise, exhibiting different kinds of structure. This structure is manifested as the existence of finitedimensional parameterizations, and/or in the geometry of the signals' spectral representations.
The two first papers of the thesis, Papers A and B, consider the modeling of differences, or distances, between stochastic processes based on their secondorder statistics, i.e., covariances. By relating the covariance structure of a stochastic process to spectral representations, it is proposed to quantify the dissimilarity between two processes in terms of the cost associated with morphing one spectral representation to the other, with the cost of morphing being defined in terms of the solutions to optimal mass transport problems. The proposed framework allows for modeling smooth changes in the frequency characteristics of stochastic processes, which is shown to yield interpretable and physically sensible predictions when used in applications of temporal and spatial spectral estimation. Also presented are efficient computational tools, allowing for the framework to be used in highdimensional problems.
Paper C considers the modeling of socalled inharmonic signals, i.e., signals that are almost, but not quite, harmonic. Such signals appear in many fields of signal processing, not least in audio. Inharmonicity may be interpreted as a deviation from a parametric structure, as well as from a particular spectral structure. Based on these views, as well as on a third, stochastic interpretation, Paper C proposes three different definitions of the concept of fundamental frequency for inharmonic signals, and studies the estimation theoretical implications of utilizing either of these definitions. Paper D then considers deliberate deviations from a parametric signal structure arising in spectroscopy applications. With the motivation of decreasing the computational complexity of parameter estimation, the paper studies the implications of estimating the parameters of the signal in a sequential fashion, starting out with a simplified model that is then refined step by step.
Lastly, Paper E studies how parametric descriptions of signals can be leveraged as to design optimal, in an estimation theoretical sense, schemes for sampling or collecting measurements from the signal. By means of a convex program, samples are selected as to minimize bounds on estimator variance, allowing for efficiently measuring parametric signals, even when the parametrization is only partially known. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/record/ca35ac5bad2e4e44b01f9232dd74664f
 author
 Elvander, Filip ^{LU}
 supervisor

 Andreas Jakobsson ^{LU}
 opponent

 Ass. Prof. Ollila, Esa, Aalto University, Finland.
 organization
 publishing date
 2020
 type
 Thesis
 publication status
 published
 subject
 keywords
 spectral estimation, parameter estimation, optimal mass transport, covariance interpolation, misspecified models, inharmonicity
 in
 Doctoral Theses in Mathematical Sciences
 volume
 2020
 issue
 2
 pages
 256 pages
 publisher
 Centre for the Mathematical sciences, Lund University
 defense location
 Lecture hall MH:Riesz, Centre for Mathematics, SÃ¶lvegatan 18, Faculty of Engineering LTH, Lund University, Lund. Join via Zoom: https://luse.zoom.us/j/64224180684
 defense date
 20200612 9:00:00
 ISSN
 14040034
 ISBN
 9789178954889
 9789178954896
 language
 English
 LU publication?
 yes
 id
 ca35ac5bad2e4e44b01f9232dd74664f
 date added to LUP
 20200429 15:51:26
 date last changed
 20200728 11:35:13
@phdthesis{ca35ac5bad2e4e44b01f9232dd74664f, abstract = {This thesis consists of five papers concerned with the modeling of stochastic signals, as well as deterministic signals in stochastic noise, exhibiting different kinds of structure. This structure is manifested as the existence of finitedimensional parameterizations, and/or in the geometry of the signals' spectral representations. <br/><br/>The two first papers of the thesis, Papers A and B, consider the modeling of differences, or distances, between stochastic processes based on their secondorder statistics, i.e., covariances. By relating the covariance structure of a stochastic process to spectral representations, it is proposed to quantify the dissimilarity between two processes in terms of the cost associated with morphing one spectral representation to the other, with the cost of morphing being defined in terms of the solutions to optimal mass transport problems. The proposed framework allows for modeling smooth changes in the frequency characteristics of stochastic processes, which is shown to yield interpretable and physically sensible predictions when used in applications of temporal and spatial spectral estimation. Also presented are efficient computational tools, allowing for the framework to be used in highdimensional problems.<br/><br/>Paper C considers the modeling of socalled inharmonic signals, i.e., signals that are almost, but not quite, harmonic. Such signals appear in many fields of signal processing, not least in audio. Inharmonicity may be interpreted as a deviation from a parametric structure, as well as from a particular spectral structure. Based on these views, as well as on a third, stochastic interpretation, Paper C proposes three different definitions of the concept of fundamental frequency for inharmonic signals, and studies the estimation theoretical implications of utilizing either of these definitions. Paper D then considers deliberate deviations from a parametric signal structure arising in spectroscopy applications. With the motivation of decreasing the computational complexity of parameter estimation, the paper studies the implications of estimating the parameters of the signal in a sequential fashion, starting out with a simplified model that is then refined step by step.<br/><br/>Lastly, Paper E studies how parametric descriptions of signals can be leveraged as to design optimal, in an estimation theoretical sense, schemes for sampling or collecting measurements from the signal. By means of a convex program, samples are selected as to minimize bounds on estimator variance, allowing for efficiently measuring parametric signals, even when the parametrization is only partially known.}, author = {Elvander, Filip}, isbn = {9789178954889}, issn = {14040034}, language = {eng}, number = {2}, publisher = {Centre for the Mathematical sciences, Lund University}, school = {Lund University}, series = {Doctoral Theses in Mathematical Sciences}, title = {Modeling and Sampling of Spectrally Structured Signals}, url = {https://lup.lub.lu.se/search/ws/files/79002346/Filip_Elvander_komplett.pdf}, volume = {2020}, year = {2020}, }