2026-09-20T15:24:43Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/100895 2023-07-11 col_2142_5131 col_2142_8859 com_2142_5130 com_2142_8858 com_2142_234

Brunner, Robert J. Thaler, Jon J. Gollin, George D. Schwing, Alexander G. Kim, Junhyung 2018-09-04T20:26:31Z 2018-09-04T20:26:31Z 2018-01-31 2018-05 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 application/pdf http://hdl.handle.net/2142/100895 en Copyright 2018 Junhyung Kim data analysis image processing photometric surveys star-galaxy classification cosmology deep learning convolutional neural networks generative adversarial networks Machine learning approaches to star-galaxy classification text text Physics Physics University of Illinois at Urbana-Champaign Dissertation Ph.D.