{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/100895"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/100895","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Machine learning approaches to star-galaxy classification","abstract":"Accurate star-galaxy classification has many important applications in modern precision cosmology. However, a vast number of faint sources that are detected in the current and next-generation ground-based surveys may be challenged by poor star-galaxy classification. Thus, we explore a variety of machine learning approaches to improve star-galaxy classification in ground-based photometric surveys. In Chapter 2, we present a meta-classification framework that combines existing star-galaxy classifiers, and demonstrate that our Bayesian combination technique improves the overall performance over any individual classification method. In Chapter 3, we show that a deep learning algorithm called convolutional neural networks is able to produce accurate and well-calibrated classifications by learning directly from the pixel values of photometric images. In Chapter 4, we study another deep learning technique called generative adversarial networks in a semi-supervised setting, and demonstrate that our semi-supervised method produces competitive classifications using only a small amount of labeled examples.","abstract_html":"Accurate star-galaxy classification has many important applications in modern precision cosmology. However, a vast number of faint sources that are detected in the current and next-generation ground-based surveys may be challenged by poor star-galaxy classification. Thus, we explore a variety of machine learning approaches to improve star-galaxy classification in ground-based photometric surveys. In Chapter 2, we present a meta-classification framework that combines existing star-galaxy classifiers, and demonstrate that our Bayesian combination technique improves the overall performance over any individual classification method. In Chapter 3, we show that a deep learning algorithm called convolutional neural networks is able to produce accurate and well-calibrated classifications by learning directly from the pixel values of photometric images. In Chapter 4, we study another deep learning technique called generative adversarial networks in a semi-supervised setting, and demonstrate that our semi-supervised method produces competitive classifications using only a small amount of labeled examples.","abstract_has_math":false,"creators":["Kim, Junhyung"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Physics","degree_department":null,"school":null,"contributors":["Brunner, Robert J.","Thaler, Jon J.","Gollin, George D.","Schwing, Alexander G."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2018,"date_issued":"2018-09-04T20:26:31Z","date_published":"2018-09-04T20:26:31Z","updated_at":"2026-07-22T22:24:38Z","subjects":["data analysis","image processing","photometric surveys","star-galaxy classification","cosmology","deep learning","convolutional neural networks","generative adversarial networks"],"languages":["en"],"rights":["Copyright 2018 Junhyung Kim"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/100895","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Brunner, Robert J.","Thaler, Jon J.","Gollin, George D.","Schwing, Alexander G."]},{"key":"dc:creator","label":"Author","values":["Kim, Junhyung"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2018-09-04T20:26:31Z","2018-01-31","2018-05"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Physics"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["data analysis","image processing","photometric surveys","star-galaxy classification","cosmology","deep learning","convolutional neural networks","generative adversarial networks"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2018 Junhyung Kim"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/100895"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Accurate star-galaxy classification has many important applications in modern precision cosmology. However, a vast number of faint sources that are detected in the current and next-generation ground-based surveys may be challenged by poor star-galaxy classification. Thus, we explore a variety of machine learning approaches to improve star-galaxy classification in ground-based photometric surveys. In Chapter 2, we present a meta-classification framework that combines existing star-galaxy classifiers, and demonstrate that our Bayesian combination technique improves the overall performance over any individual classification method. In Chapter 3, we show that a deep learning algorithm called convolutional neural networks is able to produce accurate and well-calibrated classifications by learning directly from the pixel values of photometric images. In Chapter 4, we study another deep learning technique called generative adversarial networks in a semi-supervised setting, and demonstrate that our semi-supervised method produces competitive classifications using only a small amount of labeled examples.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2018-08-31 without embargo terms","The student, Junhyung Kim, accepted the attached license on 2018-01-30 at 12:11.","The student, Junhyung Kim, submitted this Dissertation for approval on 2018-01-30 at 12:43.","This Dissertation was approved for publication on 2018-01-31 at 13:38.","DSpace SAF Submission Ingestion Package generated from Vireo submission #12026 on 2018-08-31 at 17:08:13","Made available in DSpace on 2018-09-04T20:26:31Z (GMT). No. of bitstreams: 3 KIM-DISSERTATION-2018.pdf: 3504296 bytes, checksum: dafbe7ec35556558e53f0b7c7be07a6e (MD5) LICENSE.txt: 4207 bytes, checksum: e26fc923b4d6ebbd3fe7ec852b84c760 (MD5) PROQUEST_LICENSE.txt: 4553 bytes, checksum: 25d7339a234a993899a1b913f672dee5 (MD5) Previous issue date: 2018-01-31"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Machine learning approaches to star-galaxy classification"]}]}],"canonical_facts":{"dc:contributor":["Brunner, Robert J.","Thaler, Jon J.","Gollin, George D.","Schwing, Alexander G."],"dc:creator":["Kim, Junhyung"],"dc:date":["2018-09-04T20:26:31Z","2018-01-31","2018-05"],"dc:description":["Accurate star-galaxy classification has many important applications in modern precision cosmology. However, a vast number of faint sources that are detected in the current and next-generation ground-based surveys may be challenged by poor star-galaxy classification. Thus, we explore a variety of machine learning approaches to improve star-galaxy classification in ground-based photometric surveys. In Chapter 2, we present a meta-classification framework that combines existing star-galaxy classifiers, and demonstrate that our Bayesian combination technique improves the overall performance over any individual classification method. In Chapter 3, we show that a deep learning algorithm called convolutional neural networks is able to produce accurate and well-calibrated classifications by learning directly from the pixel values of photometric images. In Chapter 4, we study another deep learning technique called generative adversarial networks in a semi-supervised setting, and demonstrate that our semi-supervised method produces competitive classifications using only a small amount of labeled examples.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2018-08-31 without embargo terms","The student, Junhyung Kim, accepted the attached license on 2018-01-30 at 12:11.","The student, Junhyung Kim, submitted this Dissertation for approval on 2018-01-30 at 12:43.","This Dissertation was approved for publication on 2018-01-31 at 13:38.","DSpace SAF Submission Ingestion Package generated from Vireo submission #12026 on 2018-08-31 at 17:08:13","Made available in DSpace on 2018-09-04T20:26:31Z (GMT). No. of bitstreams: 3 KIM-DISSERTATION-2018.pdf: 3504296 bytes, checksum: dafbe7ec35556558e53f0b7c7be07a6e (MD5) LICENSE.txt: 4207 bytes, checksum: e26fc923b4d6ebbd3fe7ec852b84c760 (MD5) PROQUEST_LICENSE.txt: 4553 bytes, checksum: 25d7339a234a993899a1b913f672dee5 (MD5) Previous issue date: 2018-01-31"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/100895"],"dc:language":["en"],"dc:rights":["Copyright 2018 Junhyung Kim"],"dc:subject":["data analysis","image processing","photometric surveys","star-galaxy classification","cosmology","deep learning","convolutional neural networks","generative adversarial networks"],"dc:title":["Machine learning approaches to star-galaxy classification"],"dc:type":["text"],"thesis:degree_discipline":["Physics"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:38Z"}