Semi-supervised learning for electrocardiography signal classification.

dc.contributor.advisorDong, Liang, 1974-
dc.creatorZhang, Dedong, 1991-
dc.creator.orcid0000-0002-1697-5430
dc.date.accessioned2018-05-30T13:51:08Z
dc.date.available2018-05-30T13:51:08Z
dc.date.created2018-05
dc.date.issued2018-04-24
dc.date.submittedMay 2018
dc.date.updated2018-05-30T13:51:08Z
dc.description.abstractAn electrocardiogram (ECG) is a cardiology test that provides information about the structure and function of the heart. The size of the ECG data collected from patients can be very large, and the data analysis is tedious. Inspired by human learning, in this thesis we propose a new semi-supervised training framework for deep neural network to classify ECG data. The idea is to reward the valid associations that belong to the same class after a round trip during cross-matching of supervised and unsupervised learning, while penalizing the incorrect associations. The implementation of our framework can be easily integrated with any existing training setup. With data preprocessing, the detection of heart disease is improved.
dc.format.mimetypeapplication/pdf
dc.identifier.urihttp://hdl.handle.net/2104/10391
dc.language.isoen
dc.rights.accessrightsWorldwide access.
dc.rights.accessrightsAccess changed 7/31/20.
dc.subjectSemi-supervised learning, Electrocardiography, pattern recognition
dc.titleSemi-supervised learning for electrocardiography signal classification.
dc.typeThesis
dc.type.materialtext
local.embargo.lift2020-05-01
local.embargo.terms2020-05-01
thesis.degree.departmentBaylor University. Dept. of Electrical & Computer Engineering.
thesis.degree.grantorBaylor University
thesis.degree.levelMasters
thesis.degree.nameM.S.E.C.E.

Files

Original bundle

Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
ZHANG-THESIS-2018.pdf
Size:
1.75 MB
Format:
Adobe Portable Document Format
No Thumbnail Available
Name:
Dedong_Zhang_Copyrightavailabilityform.pdf
Size:
801.15 KB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
LICENSE.txt
Size:
1.95 KB
Format:
Plain Text
Description: