Using our tools backwards, AF detection by confusing time and frequency

Title

Using our tools backwards, AF detection by confusing time and frequency

 Author

Kraaijeveld, Michael (TU Delft Electrical Engineering, Mathematics and Computer Science; TU Delft Signal Processing Systems)

Contributor

Hendriks, R.C. (mentor) ORCID 0000-0001-8297-0251
Varon, Carolina (mentor)
Martinez, Jorge (graduation committee) ORCID 0000-0001-9360-461X

 Degree granting institution

Delft University of Technology

 Programme

Electrical Engineering | Signals and Systems

 Date

2024-01-09

 Abstract

Atrial Fibrillation or AF is the most common heart rhythm anomaly affecting millions of people. This work explores the possibilities of reinterpreting speech processing techniques for use in atrial fibrillation detection. An existing method of modelling single heartbeat, single lead ECG signals by means of an ARMA model's amplitude response as a time domain signal is implemented. The parameters of the models are then used for AF detection by means of detecting P wave absence. For this detection, the distribution of the P wave associated parameters is compared to a GMM model of normal sinus rhythm beats obtained from a large number of recordings from different sources.

 Subject

heart
Atrial Fibrillation
Electrocardiogram (ECG)
Modelling
Detection
ARMA models
Gaussian Mixture Modeling (GMM)

 To reference this document use:

http://resolver.tudelft.nl/uuid:fc37f3d2-2cd6-4068-ad79-893ffd9cdc1d

 Part of collection

Student theses

 Document type

master thesis

 Rights

© 2024 Michael Kraaijeveld
Files
PDF Thesis_Michael_Kraaijeveld.pdf 4.59 MB
Close viewer