COMING SOON! PQDT Open is getting a new home!

ProQuest Open Access Dissertations & Theses will remain freely available as part of a new and enhanced search experience at

Questions? Please refer to this FAQ.

Dissertation/Thesis Abstract

Ensemble supervised and unsupervised learning with Kepler variable stars
by Bass, Gideon, Ph.D., George Mason University, 2015, 120; 10027479
Abstract (Summary)

Variable star analysis and classification is an important task in the understanding of stellar features and processes. While historically classifications have been done manually by highly skilled experts, the recent and rapid expansion in the quantity and quality of data has demanded new techniques, most notably automatic classification through supervised machine learning. I present a study on variable stars in the Kepler field using these techniques, and the novel work of unsupervised learning. I use new methods of characterization and multiple independent classifiers to produce an ensemble classifier that equals or matches existing classification abilities. I also explore the possibilities of unsupervised learning in making novel feature discovery in stars.

Indexing (document details)
Advisor: Borne, Kirk
Commitee: Summers, Michael, Weingartner, Joe, Yang, Ruixin
School: George Mason University
Department: Physics
School Location: United States -- Virginia
Source: DAI-B 77/07(E), Dissertation Abstracts International
Subjects: Astrophysics
Keywords: Astronomy, Data mining, Machine learning, Variable stars
Publication Number: 10027479
ISBN: 978-1-339-52692-8
Copyright © 2021 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy