Adapting archetypal analysis to scientific imaging applications

dc.contributor.advisorChairperson, Graduate Committee: Dominique Zossoen
dc.contributor.authorPotts, Catherine Gabrielen
dc.date.accessioned2022-06-10T18:58:47Z
dc.date.available2022-06-10T18:58:47Z
dc.date.issued2022en
dc.description.abstractScientific imaging applications create large sets of high-dimensional data, which may be difficult to process using traditional supervised machine learning representative models. First, many representative models generate computational elements that are difficult to interpret in terms of the scientific application and second, the high embedding dimension of the images often makes generating the models computationally inefficient. We propose using archetypal analysis (AA) as the representative model for these scientific imaging problems, since the computational elements, so called archetypes, resemble members of the original dataset. Specifically, the archetypes are generated as extreme points to an approximation of the convex hull of the data cloud, which means they maintain the structure of individual data points. To improve the computational task of generating the AA model, we propose a sketch-based AA method which projects the data to a lower embedding dimension before calculating the computational elements, lowering computation time for these high-dimensional problems, while at the same time retaining the geometric structure enough so that the computational elements closely match the results of AA. We also applied a primal-dual hybrid gradient (PDHG) solver to the AA algorithm structure attempting to speed up computation. To verify the significance of the interpretation of AA, we applied AA to transient fluorescent calcium images, recorded in the Kunze Neuroengineering lab as videos, in order to determine whether or not adding different nanoparticles changed the way the neurons in culture communicate. We also applied our sketch-based AA method to other sorts of imaging data sets, exploring the differences between our method and the standard AA method. Our experimentation shows the different ways that AA can be adapted to scientific imaging applications, providing a machine learning representation model that is interpretable in the context of the imaging problem and verifies the benefits of the sketch-based method in terms of computation time.en
dc.identifier.urihttps://scholarworks.montana.edu/handle/1/16648en
dc.language.isoenen
dc.publisherMontana State University - Bozeman, College of Letters & Scienceen
dc.rights.holderCopyright 2022 by Catherine Gabriel Pottsen
dc.subject.lcshMachine learningen
dc.subject.lcshAlgorithmsen
dc.subject.lcshImaging systemsen
dc.subject.lcshMicroscopyen
dc.subject.lcshCalciumen
dc.titleAdapting archetypal analysis to scientific imaging applicationsen
dc.typeDissertationen
mus.data.thumbpage173en
thesis.degree.committeemembersMembers, Graduate Committee: Lisa Davis; Lukas Geyer; Scott McCalla; Anja Kunzeen
thesis.degree.departmentMathematical Sciences.en
thesis.degree.genreDissertationen
thesis.degree.namePhDen
thesis.format.extentfirstpage1en
thesis.format.extentlastpage225en

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
potts-adapting-2021.pdf
Size:
18.62 MB
Format:
Adobe Portable Document Format
Description:
Adapting archetypal analysis to scientific imaging applications (PDF)

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
826 B
Format:
Plain Text
Description:
Copyright (c) 2002-2022, LYRASIS. All rights reserved.