{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/106234"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/106234","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Automated isotope identification and quantification using artificial neural networks","abstract":"Current radioisotope identification devices struggle to identify and quantify isotopes in low-resolution gamma-ray spectra in a wide range of realistic conditions. Trained gamma-ray spectroscopists typically rely on intuition when identifying isotopes in spectra. A trained gamma-ray spectroscopist can inject their intuition into pattern recognition algorithms by creating training datasets and intelligently choosing a machine learning model for a task. 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. To investigate this, we simulated datasets and used them to train artificial neural networks (ANNs) for identification and quantification tasks using gamma-ray spectra. Because the datasets were simulated, this method can be extended to a variety of gamma-ray spectroscopy tasks. Models we investigated include dense, convolutional, and autoencoder ANNs. In this work we introduce annsa, an open source Python package capable of creating gamma-ray spectroscopy training datasets and applying machine learning models to solve spectroscopic tasks. Using annsa, we found that identification performance in simulated spectra was sensitive to the source-to-background ratio, detector gain setting, and shielding. Performance was less sensitive to the source-detector height and detector resolution. We demonstrate annsa's capabilities on a source interdiction classification problem, outperforming a peak-based Bayesian classifier for source identification. We also demonstrate annsa on a uranium enrichment quantification problem which shows an accuracy useful for homeland security applications.","abstract_html":"Current radioisotope identification devices struggle to identify and quantify isotopes in low-resolution gamma-ray spectra in a wide range of realistic conditions. Trained gamma-ray spectroscopists typically rely on intuition when identifying isotopes in spectra. A trained gamma-ray spectroscopist can inject their intuition into pattern recognition algorithms by creating training datasets and intelligently choosing a machine learning model for a task. 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. To investigate this, we simulated datasets and used them to train artificial neural networks (ANNs) for identification and quantification tasks using gamma-ray spectra. Because the datasets were simulated, this method can be extended to a variety of gamma-ray spectroscopy tasks. Models we investigated include dense, convolutional, and autoencoder ANNs. In this work we introduce annsa, an open source Python package capable of creating gamma-ray spectroscopy training datasets and applying machine learning models to solve spectroscopic tasks. Using annsa, we found that identification performance in simulated spectra was sensitive to the source-to-background ratio, detector gain setting, and shielding. Performance was less sensitive to the source-detector height and detector resolution. We demonstrate annsa's capabilities on a source interdiction classification problem, outperforming a peak-based Bayesian classifier for source identification. We also demonstrate annsa on a uranium enrichment quantification problem which shows an accuracy useful for homeland security applications.","abstract_has_math":false,"creators":["Kamuda, Mark M."],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Nuclear, Plasma, Radiolgc Engr","degree_department":null,"school":null,"contributors":["Huff, Kathryn","Hasagawa-Johnson, Mark","Kozlowski, Tomasz","Sullivan, Clair","Uddin, Rizwan"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-03-02T21:58:20Z","date_published":"2020-03-02T21:58:20Z","updated_at":"2026-07-22T22:24:45Z","subjects":["gamma-ray spectroscopy","neural networks","machine learning"],"languages":["en"],"rights":["Copyright 2019 Mark Kamuda"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/106234","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Huff, Kathryn","Hasagawa-Johnson, Mark","Kozlowski, Tomasz","Sullivan, Clair","Uddin, Rizwan"]},{"key":"dc:creator","label":"Author","values":["Kamuda, Mark M."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2020-03-02T21:58:20Z","2019-12-04","2019-12"]},{"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":["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":["gamma-ray spectroscopy","neural networks","machine learning"]}]},{"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 Mark Kamuda"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/106234"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Current radioisotope identification devices struggle to identify and quantify isotopes in low-resolution gamma-ray spectra in a wide range of realistic conditions. Trained gamma-ray spectroscopists typically rely on intuition when identifying isotopes in spectra. A trained gamma-ray spectroscopist can inject their intuition into pattern recognition algorithms by creating training datasets and intelligently choosing a machine learning model for a task. 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. To investigate this, we simulated datasets and used them to train artificial neural networks (ANNs) for identification and quantification tasks using gamma-ray spectra. Because the datasets were simulated, this method can be extended to a variety of gamma-ray spectroscopy tasks. Models we investigated include dense, convolutional, and autoencoder ANNs. In this work we introduce annsa, an open source Python package capable of creating gamma-ray spectroscopy training datasets and applying machine learning models to solve spectroscopic tasks. Using annsa, we found that identification performance in simulated spectra was sensitive to the source-to-background ratio, detector gain setting, and shielding. Performance was less sensitive to the source-detector height and detector resolution. We demonstrate annsa's capabilities on a source interdiction classification problem, outperforming a peak-based Bayesian classifier for source identification. We also demonstrate annsa on a uranium enrichment quantification problem which shows an accuracy useful for homeland security applications.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2020-02-28 without embargo terms","The student, Mark Kamuda, accepted the attached license on 2019-12-02 at 18:57.","The student, Mark Kamuda, submitted this Dissertation for approval on 2019-12-02 at 19:04.","This Dissertation was approved for publication on 2019-12-04 at 08:48.","DSpace SAF Submission Ingestion Package generated from Vireo submission #14653 on 2020-02-28 at 17:14:46","Made available in DSpace on 2020-03-02T21:58:20Z (GMT). No. of bitstreams: 2 KAMUDA-DISSERTATION-2019.pdf: 7892108 bytes, checksum: ee56750cb80ecb37a180b55a90685165 (MD5) LICENSE.txt: 4208 bytes, checksum: ff2789ff565213db1fe894838de8ad72 (MD5) Previous issue date: 2019-12-04"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Automated isotope identification and quantification using artificial neural networks"]}]}],"canonical_facts":{"dc:contributor":["Huff, Kathryn","Hasagawa-Johnson, Mark","Kozlowski, Tomasz","Sullivan, Clair","Uddin, Rizwan"],"dc:creator":["Kamuda, Mark M."],"dc:date":["2020-03-02T21:58:20Z","2019-12-04","2019-12"],"dc:description":["Current radioisotope identification devices struggle to identify and quantify isotopes in low-resolution gamma-ray spectra in a wide range of realistic conditions. Trained gamma-ray spectroscopists typically rely on intuition when identifying isotopes in spectra. A trained gamma-ray spectroscopist can inject their intuition into pattern recognition algorithms by creating training datasets and intelligently choosing a machine learning model for a task. 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. To investigate this, we simulated datasets and used them to train artificial neural networks (ANNs) for identification and quantification tasks using gamma-ray spectra. Because the datasets were simulated, this method can be extended to a variety of gamma-ray spectroscopy tasks. Models we investigated include dense, convolutional, and autoencoder ANNs. In this work we introduce annsa, an open source Python package capable of creating gamma-ray spectroscopy training datasets and applying machine learning models to solve spectroscopic tasks. Using annsa, we found that identification performance in simulated spectra was sensitive to the source-to-background ratio, detector gain setting, and shielding. Performance was less sensitive to the source-detector height and detector resolution. We demonstrate annsa's capabilities on a source interdiction classification problem, outperforming a peak-based Bayesian classifier for source identification. We also demonstrate annsa on a uranium enrichment quantification problem which shows an accuracy useful for homeland security applications.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2020-02-28 without embargo terms","The student, Mark Kamuda, accepted the attached license on 2019-12-02 at 18:57.","The student, Mark Kamuda, submitted this Dissertation for approval on 2019-12-02 at 19:04.","This Dissertation was approved for publication on 2019-12-04 at 08:48.","DSpace SAF Submission Ingestion Package generated from Vireo submission #14653 on 2020-02-28 at 17:14:46","Made available in DSpace on 2020-03-02T21:58:20Z (GMT). No. of bitstreams: 2 KAMUDA-DISSERTATION-2019.pdf: 7892108 bytes, checksum: ee56750cb80ecb37a180b55a90685165 (MD5) LICENSE.txt: 4208 bytes, checksum: ff2789ff565213db1fe894838de8ad72 (MD5) Previous issue date: 2019-12-04"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/106234"],"dc:language":["en"],"dc:rights":["Copyright 2019 Mark Kamuda"],"dc:subject":["gamma-ray spectroscopy","neural networks","machine learning"],"dc:title":["Automated isotope identification and quantification using artificial neural networks"],"dc:type":["text"],"thesis:degree_discipline":["Nuclear, Plasma, Radiolgc Engr"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:45Z"}