Independent component analysis for maternal-fetal electrocardiography

Simple item page
dc.contributor.authorMarcynuk, Kathryn L.
dc.contributor.examiningcommitteeMcNeill, Dean (Electrical and Computer Engineering) Domaratzki, Michael (Computer Science)en_US
dc.contributor.supervisorKinsner, Witold (Electrical and Computer Engineering)en_US
dc.date.accessioned2015-01-09T14:42:40Z
dc.date.available2015-01-09T14:42:40Z
dc.date.issued2015-01-09
dc.degree.disciplineElectrical and Computer Engineeringen_US
dc.degree.levelMaster of Science (M.Sc.)en_US
dc.description.abstractSeparating unknown signal mixtures into their constituent parts is a difficult problem in signal processing called blind source separation. One of the benchmark problems in this area is the extraction of the fetal heartbeat from an electrocardiogram in which it is overshadowed by a strong maternal heartbeat. This thesis presents a study of a signal separation technique called independent component analysis (ICA), in order to assess its suitability for the maternal-fetal ECG separation problem. This includes an analysis of ICA on deterministic, stochastic, simulated and recorded ECG signals. The experiments presented in this thesis demonstrate that ICA is effective on linear mixtures of known simulated or recorded ECGs. The performance of ICA was measured using visual comparison, heart rate extraction, and energy, information theoretic, and fractal-based measures. ICA extraction of clinically recorded maternal-fetal ECGs mixtures, in which the source signals were unknown, were successful at recovering the fetal heart rate.en_US
dc.description.noteFebruary 2015en_US
dc.identifier.urihttp://hdl.handle.net/1993/30181
dc.language.isoengen_US
dc.rightsopen accessen_US
dc.subjectblind signal separationen_US
dc.subjectindependent component analysis (ICA)en_US
dc.subjectcomplexity measuresen_US
dc.subjectECG signal modelling and analysisen_US
dc.subjectdigital signal processingen_US
dc.titleIndependent component analysis for maternal-fetal electrocardiographyen_US
dc.typemaster thesisen_US
Files
Original bundle
Now showing 1 - 2 of 2
Thumbnail Image
Name:
marcynuk_kathryn.pdf
Size:
4.64 MB
Format:
Adobe Portable Document Format
Description:
MSc Thesis
Download
Thumbnail Image
Name:
marcynuk_kathryn_code.zip
Size:
10.83 KB
Format:
Winzipped zip file
Description:
MSc Thesis Appendix B
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.25 KB
Format:
Item-specific license agreed to upon submission
Description:
Download
Collections
FGS - Electronic Theses and Practica