Statistical inference and time-frequency estimation for non-stationary signal classification

Rachele Anderson

Statistical inference and time-frequency estimation for non-stationary signal classification

Rachele Anderson

Research output: Thesis › Doctoral Thesis (compilation)

25 Downloads (Pure)

Abstract

This thesis focuses on statistical methods for non-stationary signals. The methods considered or developed address problems of stochastic modeling, inference, spectral analysis, time-frequency analysis, and deep learning for classification. In all the contributions, an example of a biomedical application of the proposed method is provided, either to electroencephalography (EEG) data or to Heart Rate Variability (HRV) data. Four manuscripts are included in this Ph.D. thesis.

Original language	English
Qualification	Doctor
Awarding Institution	Mathematical Statistics
Supervisors/Advisors	Sandsten, Maria, Supervisor
Award date	2019 Oct 4
Place of Publication	Lund, Sweden
Publisher	Media-Tryck, Lund University, Sweden
ISBN (Print)	978-91-7895-274-8
ISBN (electronic)	978-91-7895-275-5
Publication status	Published - 2019 Sept 9

Bibliographical note

Defence details
Date: 2019-10-04
Time: 09:15
Place: Lecture hall MH:R, Matematikcentrum, Sölvegatan 18A, Lund
External reviewer(s)
Name: Baxevani, Anastassia
Title: Docent
Affiliation: University of Cyprus, Nicosia, Cyprus
---

Subject classification (UKÄ)

Signal Processing
Probability Theory and Statistics

Free keywords

Non-stationary processes
stochastic modeling
inference
spectral analysis
time-frequency analysis
classification
biomedical applications
deep learning

3 Article
1 Paper in conference proceeding

Time-frequency feature extraction for classification of episodic memory
Anderson, R. & Sandsten, M., 2020 May 1, In: Eurasip Journal on Advances in Signal Processing. 19.
Research output: Contribution to journal › Article › peer-review

Open Access
Multitaper Spectral Granger Causality with Application to Ssvep
Anderson, R. & Sandsten, M., 2020 May, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing. IEEE - Institute of Electrical and Electronics Engineers Inc., p. 1284-1288
Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review
Stochastic Modeling and Optimal Time-Frequency Estimation of Task-Related HRV
Anderson, R., Jönsson, P. & Sandsten, M., 2019 Nov 28, In: Applied Sciences (Switzerland). 9, 23, 5154.
Research output: Contribution to journal › Article › peer-review

Open Access

Cite this

@phdthesis{c70ed88efb954aa59476c5e791a83a68,

title = "Statistical inference and time-frequency estimation for non-stationary signal classification",

abstract = "This thesis focuses on statistical methods for non-stationary signals. The methods considered or developed address problems of stochastic modeling, inference, spectral analysis, time-frequency analysis, and deep learning for classification. In all the contributions, an example of a biomedical application of the proposed method is provided, either to electroencephalography (EEG) data or to Heart Rate Variability (HRV) data. Four manuscripts are included in this Ph.D. thesis.",

keywords = "Non-stationary processes, stochastic modeling, inference, spectral analysis, time-frequency analysis, classification, biomedical applications, deep learning",

author = "Rachele Anderson",

note = "Defence details Date: 2019-10-04 Time: 09:15 Place: Lecture hall MH:R, Matematikcentrum, S{\"o}lvegatan 18A, Lund External reviewer(s) Name: Baxevani, Anastassia Title: Docent Affiliation: University of Cyprus, Nicosia, Cyprus ---",

year = "2019",

month = sep,

day = "9",

language = "English",

isbn = "978-91-7895-274-8",

series = "Doctoral Theses in Mathematical Sciences",

publisher = "Media-Tryck, Lund University, Sweden",

number = "5",

type = "Doctoral Thesis (compilation)",

school = "Mathematical Statistics",

}

TY - THES

T1 - Statistical inference and time-frequency estimation for non-stationary signal classification

AU - Anderson, Rachele

N1 - Defence details Date: 2019-10-04 Time: 09:15 Place: Lecture hall MH:R, Matematikcentrum, Sölvegatan 18A, Lund External reviewer(s) Name: Baxevani, Anastassia Title: Docent Affiliation: University of Cyprus, Nicosia, Cyprus ---

PY - 2019/9/9

Y1 - 2019/9/9

N2 - This thesis focuses on statistical methods for non-stationary signals. The methods considered or developed address problems of stochastic modeling, inference, spectral analysis, time-frequency analysis, and deep learning for classification. In all the contributions, an example of a biomedical application of the proposed method is provided, either to electroencephalography (EEG) data or to Heart Rate Variability (HRV) data. Four manuscripts are included in this Ph.D. thesis.

AB - This thesis focuses on statistical methods for non-stationary signals. The methods considered or developed address problems of stochastic modeling, inference, spectral analysis, time-frequency analysis, and deep learning for classification. In all the contributions, an example of a biomedical application of the proposed method is provided, either to electroencephalography (EEG) data or to Heart Rate Variability (HRV) data. Four manuscripts are included in this Ph.D. thesis.

KW - Non-stationary processes

KW - stochastic modeling

KW - inference

KW - spectral analysis

KW - time-frequency analysis

KW - classification

KW - biomedical applications

KW - deep learning

M3 - Doctoral Thesis (compilation)

SN - 978-91-7895-274-8

T3 - Doctoral Theses in Mathematical Sciences

PB - Media-Tryck, Lund University, Sweden

CY - Lund, Sweden

ER -

Statistical inference and time-frequency estimation for non-stationary signal classification

Abstract

Bibliographical note

Subject classification (UKÄ)

Free keywords

Fingerprint

Research output

Time-frequency feature extraction for classification of episodic memory

Multitaper Spectral Granger Causality with Application to Ssvep

Stochastic Modeling and Optimal Time-Frequency Estimation of Task-Related HRV

Cite this