{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/105266"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/105266","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Missing channel reconstruction for sloan digital sky survey images using linear models and generative adversarial networks","abstract":"The Sloan Digital Sky Survey (SDSS) dataset, one of the largest astronomical surveys, suffers from noise and missing information in some of the image channels. This thesis implements two methods—the linear model and the deep learning model—on 12,730 SDSS images for missing channel re- construction. Specifically, for the linear model, linear regression and patch- based regression are examined. For the deep learning model, the generative adversarial networks (GANs) with U-Net are deployed in the experiment. Several preprocessing techniques including normalization and cropping are done before feeding the images into the model. The results indicate that both methods can generate satisfactory results. In addition, there is a trade- off between training speed and the accuracy. Specifically, the training of the linear model is much faster than that of the GAN model, while the L1 loss of the GAN model can achieve average 15.29 per image, which is much smaller than the L1 loss of the linear model.","abstract_html":"The Sloan Digital Sky Survey (SDSS) dataset, one of the largest astronomical surveys, suffers from noise and missing information in some of the image channels. This thesis implements two methods—the linear model and the deep learning model—on 12,730 SDSS images for missing channel re- construction. Specifically, for the linear model, linear regression and patch- based regression are examined. For the deep learning model, the generative adversarial networks (GANs) with U-Net are deployed in the experiment. Several preprocessing techniques including normalization and cropping are done before feeding the images into the model. The results indicate that both methods can generate satisfactory results. In addition, there is a trade- off between training speed and the accuracy. Specifically, the training of the linear model is much faster than that of the GAN model, while the L1 loss of the GAN model can achieve average 15.29 per image, which is much smaller than the L1 loss of the linear model.","abstract_has_math":false,"creators":["Cheng, Yuan"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Zhao, Zhizhen"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2019,"date_issued":"2019-08-23T20:48:27Z","date_published":"2019-08-23T20:48:27Z","updated_at":"2026-07-22T22:24:44Z","subjects":["Image Reconstruction, Deep Learning, Sloan Digital Sky Survey, Generative Adversarial Networks, Linear Regression"],"languages":["en"],"rights":["Copyright 2019 Yuan Cheng"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/105266","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Zhao, Zhizhen"]},{"key":"dc:creator","label":"Author","values":["Cheng, Yuan"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2019-08-23T20:48:27Z","2021-08-24T09:15:38Z","2019-04-25","2019-05"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"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":["Image Reconstruction, Deep Learning, Sloan Digital Sky Survey, Generative Adversarial Networks, Linear Regression"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2019 Yuan Cheng"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/105266"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The Sloan Digital Sky Survey (SDSS) dataset, one of the largest astronomical surveys, suffers from noise and missing information in some of the image channels. This thesis implements two methods—the linear model and the deep learning model—on 12,730 SDSS images for missing channel re- construction. Specifically, for the linear model, linear regression and patch- based regression are examined. For the deep learning model, the generative adversarial networks (GANs) with U-Net are deployed in the experiment. Several preprocessing techniques including normalization and cropping are done before feeding the images into the model. The results indicate that both methods can generate satisfactory results. In addition, there is a trade- off between training speed and the accuracy. Specifically, the training of the linear model is much faster than that of the GAN model, while the L1 loss of the GAN model can achieve average 15.29 per image, which is much smaller than the L1 loss of the linear model.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2021-05-01","The student, Yuan Cheng, accepted the attached license on 2019-04-25 at 12:23.","The student, Yuan Cheng, submitted this Thesis for approval on 2019-04-25 at 12:34.","This Thesis was approved for publication on 2019-04-25 at 14:32.","DSpace SAF Submission Ingestion Package generated from Vireo submission #13915 on 2019-08-22 at 16:23:57","Made available in DSpace on 2019-08-23T20:48:27Z (GMT). No. of bitstreams: 2 CHENG-THESIS-2019.pdf: 8299692 bytes, checksum: 4c8898a72648ba87ff90490ab5fa1479 (MD5) LICENSE.txt: 4207 bytes, checksum: 0dc95fd3311f18c844d79c61c044f6ef (MD5) Previous issue date: 2019-04-25","Embargo set by: Seth Robbins for item 112388 Lift date: 2021-08-23T20:48:32Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited Restriction Lifted for Item 112388 on 2021-08-24T09:15:38Z."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Missing channel reconstruction for sloan digital sky survey images using linear models and generative adversarial networks"]}]}],"canonical_facts":{"dc:contributor":["Zhao, Zhizhen"],"dc:creator":["Cheng, Yuan"],"dc:date":["2019-08-23T20:48:27Z","2021-08-24T09:15:38Z","2019-04-25","2019-05"],"dc:description":["The Sloan Digital Sky Survey (SDSS) dataset, one of the largest astronomical surveys, suffers from noise and missing information in some of the image channels. This thesis implements two methods—the linear model and the deep learning model—on 12,730 SDSS images for missing channel re- construction. Specifically, for the linear model, linear regression and patch- based regression are examined. For the deep learning model, the generative adversarial networks (GANs) with U-Net are deployed in the experiment. Several preprocessing techniques including normalization and cropping are done before feeding the images into the model. The results indicate that both methods can generate satisfactory results. In addition, there is a trade- off between training speed and the accuracy. Specifically, the training of the linear model is much faster than that of the GAN model, while the L1 loss of the GAN model can achieve average 15.29 per image, which is much smaller than the L1 loss of the linear model.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2021-05-01","The student, Yuan Cheng, accepted the attached license on 2019-04-25 at 12:23.","The student, Yuan Cheng, submitted this Thesis for approval on 2019-04-25 at 12:34.","This Thesis was approved for publication on 2019-04-25 at 14:32.","DSpace SAF Submission Ingestion Package generated from Vireo submission #13915 on 2019-08-22 at 16:23:57","Made available in DSpace on 2019-08-23T20:48:27Z (GMT). No. of bitstreams: 2 CHENG-THESIS-2019.pdf: 8299692 bytes, checksum: 4c8898a72648ba87ff90490ab5fa1479 (MD5) LICENSE.txt: 4207 bytes, checksum: 0dc95fd3311f18c844d79c61c044f6ef (MD5) Previous issue date: 2019-04-25","Embargo set by: Seth Robbins for item 112388 Lift date: 2021-08-23T20:48:32Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited Restriction Lifted for Item 112388 on 2021-08-24T09:15:38Z."],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/105266"],"dc:language":["en"],"dc:rights":["Copyright 2019 Yuan Cheng"],"dc:subject":["Image Reconstruction, Deep Learning, Sloan Digital Sky Survey, Generative Adversarial Networks, Linear Regression"],"dc:title":["Missing channel reconstruction for sloan digital sky survey images using linear models and generative adversarial networks"],"dc:type":["text"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:44Z"}