APPLICATION OF SUPPORT VECTOR MACHINES TO LONGITUDINAL FUNCTIONAL NEUROIMAGING DATA
dc.contributor.author | Rudiuk, Alexander | |
dc.contributor.copyright-release | Not Applicable | en_US |
dc.contributor.degree | Master of Applied Science | en_US |
dc.contributor.department | Department of Biomedical Engineering | en_US |
dc.contributor.ethics-approval | Received | en_US |
dc.contributor.external-examiner | Dr. Jeremy Brown | en_US |
dc.contributor.graduate-coordinator | Dr. Janie Wilson | en_US |
dc.contributor.manuscripts | Not Applicable | en_US |
dc.contributor.thesis-reader | Dr. Robert Adamson | en_US |
dc.contributor.thesis-reader | Dr. Thomas Trappenberg | en_US |
dc.contributor.thesis-supervisor | Dr. Steven Beyea | en_US |
dc.contributor.thesis-supervisor | Dr. Tim Bardouille | en_US |
dc.date.accessioned | 2016-12-15T15:39:12Z | |
dc.date.available | 2016-12-15T15:39:12Z | |
dc.date.defence | 2016-11-22 | |
dc.date.issued | 2016-12-15T15:39:12Z | |
dc.description.abstract | The principal objective of this thesis was to test a novel adaptation of the support vector machine (SVM), called a longitudinal support vector machine(LSVM), on longitudinal functional neuroimaging data. LSVM performance was compared to a traditional SVM and logistic regression (LR) using classification accuracy and interpretability of feature weights. Classification accuracy was measured as the percentage of subjects placed into their correct categories, and feature weights by how closely they matched the known signal. The first study involved purely simulated data, which found the LSVM had higher classification accuracy for data without heteroscedasticity, but performed worse when heteroscedasticity was introduced. The second study used real magnetoencephalography (MEG) resting state readings added to a simulated trend. The LSVM had similar classification accuracy, and only had more interpretable feature weights at the highest SNR dataset. Currently the LSVM is not recommended over the SVM/LR algorithms. | en_US |
dc.identifier.uri | http://hdl.handle.net/10222/72586 | |
dc.language.iso | en | en_US |
dc.subject | Machine Learning | en_US |
dc.subject | Functional Longitudinal Neuroimaging Data | en_US |
dc.subject | Magnetoencephalography | en_US |
dc.subject | Support Vector Machine | en_US |
dc.title | APPLICATION OF SUPPORT VECTOR MACHINES TO LONGITUDINAL FUNCTIONAL NEUROIMAGING DATA | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Rudiuk-Alexander-MASc-BME-Dec-2016.pdf
- Size:
- 4.11 MB
- Format:
- Adobe Portable Document Format
- Description:
- Master's Thesis
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 1.71 KB
- Format:
- Item-specific license agreed upon to submission
- Description: