{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/97440"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/97440","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Automated isotope identification algorithm using artificial neural networks","abstract":"There is a need to develop an algorithm that can determine the relative activities of a mixture of many isotopes in a low-resolution gamma-ray spectrum. While techniques for this task exist, they require a human operator and are too slow to use on very large datasets of spectra. Pattern recognition algorithms such as neural networks are prime candidates for automated isotope identification using low-resolution gamma-ray spectra. While algorithms based on feature extraction such as peak finding or ROI algorithms work well for well calibrated high resolution detectors, for low-resolution detectors it may be more beneficial to use algorithms that incorporate more abstract features of the spectrum. This is especially true when analyzing a mixture of isotopes where peak overlap and Compton continuum effects occlude features of interest. To solve this, an artificial neural network (ANN) was trained to predict the presence and relative activities of isotopes from a mixture of many isotopes. The ANN is trained with simulated gamma-ray spectra, allowing easy expansion of the library of target isotopes. In this thesis, an algorithm based on an ANN is presented and evaluated against a series of measured spectra.","abstract_html":"There is a need to develop an algorithm that can determine the relative activities of a mixture of many isotopes in a low-resolution gamma-ray spectrum. While techniques for this task exist, they require a human operator and are too slow to use on very large datasets of spectra. Pattern recognition algorithms such as neural networks are prime candidates for automated isotope identification using low-resolution gamma-ray spectra. While algorithms based on feature extraction such as peak finding or ROI algorithms work well for well calibrated high resolution detectors, for low-resolution detectors it may be more beneficial to use algorithms that incorporate more abstract features of the spectrum. This is especially true when analyzing a mixture of isotopes where peak overlap and Compton continuum effects occlude features of interest. To solve this, an artificial neural network (ANN) was trained to predict the presence and relative activities of isotopes from a mixture of many isotopes. The ANN is trained with simulated gamma-ray spectra, allowing easy expansion of the library of target isotopes. In this thesis, an algorithm based on an ANN is presented and evaluated against a series of measured spectra.","abstract_has_math":false,"creators":["Kamuda, Mark M."],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Nuclear, Plasma, Radiolgc Engr","degree_department":null,"school":null,"contributors":["Sullivan, Clair J.","Huff, Kathryn"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2017,"date_issued":"2017-08-10T19:15:56Z","date_published":"2017-08-10T19:15:56Z","updated_at":"2026-07-22T22:24:34Z","subjects":["Automated isotope identification","Artificial neural networks"],"languages":["en"],"rights":["Copyright 2017 Mark Kamuda"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/97440","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Sullivan, Clair J.","Huff, Kathryn"]},{"key":"dc:creator","label":"Author","values":["Kamuda, Mark M."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2017-08-10T19:15:56Z","2017-04-25","2017-05"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Nuclear, Plasma, Radiolgc 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":["Automated isotope identification","Artificial neural 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 2017 Mark Kamuda"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/97440"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["There is a need to develop an algorithm that can determine the relative activities of a mixture of many isotopes in a low-resolution gamma-ray spectrum. While techniques for this task exist, they require a human operator and are too slow to use on very large datasets of spectra. Pattern recognition algorithms such as neural networks are prime candidates for automated isotope identification using low-resolution gamma-ray spectra. While algorithms based on feature extraction such as peak finding or ROI algorithms work well for well calibrated high resolution detectors, for low-resolution detectors it may be more beneficial to use algorithms that incorporate more abstract features of the spectrum. This is especially true when analyzing a mixture of isotopes where peak overlap and Compton continuum effects occlude features of interest. To solve this, an artificial neural network (ANN) was trained to predict the presence and relative activities of isotopes from a mixture of many isotopes. The ANN is trained with simulated gamma-ray spectra, allowing easy expansion of the library of target isotopes. In this thesis, an algorithm based on an ANN is presented and evaluated against a series of measured spectra.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2017-08-10 without embargo terms","The student, Mark Kamuda, accepted the attached license on 2017-04-21 at 15:53.","The student, Mark Kamuda, submitted this Thesis for approval on 2017-04-21 at 16:00.","This Thesis was approved for publication on 2017-04-25 at 12:16.","DSpace SAF Submission Ingestion Package generated from Vireo submission #10986 on 2017-08-10 at 13:45:29","Made available in DSpace on 2017-08-10T19:15:56Z (GMT). No. of bitstreams: 2 KAMUDA-THESIS-2017.pdf: 930591 bytes, checksum: 9d194aaaa5d7e6539546459a651afb2f (MD5) LICENSE.txt: 4208 bytes, checksum: e114db01312dfbe53ba4c46f4036723b (MD5) Previous issue date: 2017-04-25"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Automated isotope identification algorithm using artificial neural networks"]}]}],"canonical_facts":{"dc:contributor":["Sullivan, Clair J.","Huff, Kathryn"],"dc:creator":["Kamuda, Mark M."],"dc:date":["2017-08-10T19:15:56Z","2017-04-25","2017-05"],"dc:description":["There is a need to develop an algorithm that can determine the relative activities of a mixture of many isotopes in a low-resolution gamma-ray spectrum. While techniques for this task exist, they require a human operator and are too slow to use on very large datasets of spectra. Pattern recognition algorithms such as neural networks are prime candidates for automated isotope identification using low-resolution gamma-ray spectra. While algorithms based on feature extraction such as peak finding or ROI algorithms work well for well calibrated high resolution detectors, for low-resolution detectors it may be more beneficial to use algorithms that incorporate more abstract features of the spectrum. This is especially true when analyzing a mixture of isotopes where peak overlap and Compton continuum effects occlude features of interest. To solve this, an artificial neural network (ANN) was trained to predict the presence and relative activities of isotopes from a mixture of many isotopes. The ANN is trained with simulated gamma-ray spectra, allowing easy expansion of the library of target isotopes. In this thesis, an algorithm based on an ANN is presented and evaluated against a series of measured spectra.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2017-08-10 without embargo terms","The student, Mark Kamuda, accepted the attached license on 2017-04-21 at 15:53.","The student, Mark Kamuda, submitted this Thesis for approval on 2017-04-21 at 16:00.","This Thesis was approved for publication on 2017-04-25 at 12:16.","DSpace SAF Submission Ingestion Package generated from Vireo submission #10986 on 2017-08-10 at 13:45:29","Made available in DSpace on 2017-08-10T19:15:56Z (GMT). No. of bitstreams: 2 KAMUDA-THESIS-2017.pdf: 930591 bytes, checksum: 9d194aaaa5d7e6539546459a651afb2f (MD5) LICENSE.txt: 4208 bytes, checksum: e114db01312dfbe53ba4c46f4036723b (MD5) Previous issue date: 2017-04-25"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/97440"],"dc:language":["en"],"dc:rights":["Copyright 2017 Mark Kamuda"],"dc:subject":["Automated isotope identification","Artificial neural networks"],"dc:title":["Automated isotope identification algorithm using artificial neural networks"],"dc:type":["text"],"thesis:degree_discipline":["Nuclear, Plasma, Radiolgc Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:34Z"}