Identifying ECG Clusters in Congenital Heart Disease

Simple item page
dc.contributor.advisorRiviere, Beatrice M.
dc.contributor.committeeMemberRusin, Craig
dc.contributor.committeeMemberCox, Steven
dc.contributor.committeeMemberDabaghian, Yuri
dc.creatorHendryx, Emily
dc.date.accessioned2016-01-25T21:54:36Z
dc.date.available2016-01-25T21:54:36Z
dc.date.created2015-05
dc.date.issued2015-04-23
dc.date.submittedMay 2015
dc.date.updated2016-01-25T21:54:36Z
dc.description.abstractThis thesis presents a method of clustering ECG morphologies for the identification of individual ECG features in congenital heart disease. Clustering is performed on the computed heart dipole moment magnitude using k-medoids clustering with variants of dynamic time warping. The method is applied to both synthetic data and patient data with different parameter values for classic and derivative dynamic time warping. A deterministic k-medoids algorithm demonstrates poor clustering results on both data sets, but an iterative approach with random initialization shows marked improvement. The synthetic data clusters are generally well-defined with the expected number of clusters. Though the patient data derivative results are inconclusive, upon closer examination, the clustering results from classic dynamic time warping with a small warping window seem sensible. Through this project, the groundwork is laid for the future classification of ECG recordings and the development of predictive models in patients with congenital heart disease.
dc.format.mimetypeapplication/pdf
dc.identifier.citationHendryx, Emily. "Identifying ECG Clusters in Congenital Heart Disease." (2015) Master’s Thesis, Rice University. <a href="https://hdl.handle.net/1911/88126">https://hdl.handle.net/1911/88126</a>.
dc.identifier.urihttps://hdl.handle.net/1911/88126
dc.language.isoeng
dc.rightsCopyright is held by the author, unless otherwise indicated. Permission to reuse, publish, or reproduce the work beyond the bounds of fair use or other exemptions to copyright law must be obtained from the copyright holder.
dc.subjectTime series clustering
dc.subjectECG
dc.subjectdynamic time warping
dc.subjectk-medoids
dc.titleIdentifying ECG Clusters in Congenital Heart Disease
dc.typeThesis
dc.type.materialText
thesis.degree.departmentComputational and Applied Mathematics
thesis.degree.disciplineEngineering
thesis.degree.grantorRice University
thesis.degree.levelMasters
thesis.degree.nameMaster of Arts
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
HENDRYX-DOCUMENT-2015.pdf
Size:
2.06 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
PROQUEST_LICENSE.txt
Size:
5.84 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
LICENSE.txt
Size:
2.61 KB
Format:
Plain Text
Description:
Download
Collections
Rice University Electronic Theses and Dissertations