{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/110543"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/110543","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Generalized flow-based variational autoencoder networks for anomaly detection in multivariate time series","abstract":"Time series are widely used in applications such as finance, robotics, telecommunications, astronomy, and many more. Detecting anomalies like robotic arm failures or server attacks is a valuable and important task. Recent research in anomaly detection in multivariate temporal data formulates the problem as one of variational inference. To solve this problem, such approaches have used variational autoencoders to try to learn the probability distribution of multiple time series. Variational autoencoders are used as a way to approximate intractable distributions, and methods to improve these approximations are explored through the use of normalizing flows. By applying normalizing flow transforms to the latent variables of a variational autoencoder, the true latent distribution can be more richly modeled and learned, thus enabling better metrics for anomaly detection. This thesis explores five different types of normalizing flow in the context of three multivariate datasets, and demonstrates the effectiveness, compared to prior research, of flows and convolutional networks for anomaly detection by improving popular metrics like the F1-score.","abstract_html":"Time series are widely used in applications such as finance, robotics, telecommunications, astronomy, and many more. Detecting anomalies like robotic arm failures or server attacks is a valuable and important task. Recent research in anomaly detection in multivariate temporal data formulates the problem as one of variational inference. To solve this problem, such approaches have used variational autoencoders to try to learn the probability distribution of multiple time series. Variational autoencoders are used as a way to approximate intractable distributions, and methods to improve these approximations are explored through the use of normalizing flows. By applying normalizing flow transforms to the latent variables of a variational autoencoder, the true latent distribution can be more richly modeled and learned, thus enabling better metrics for anomaly detection. This thesis explores five different types of normalizing flow in the context of three multivariate datasets, and demonstrates the effectiveness, compared to prior research, of flows and convolutional networks for anomaly detection by improving popular metrics like the F1-score.","abstract_has_math":false,"creators":["Shah, Raimi"],"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":2021,"date_issued":"2021-09-17T01:11:13Z","date_published":"2021-09-17T01:11:13Z","updated_at":"2026-07-22T22:24:52Z","subjects":["anomaly detection","deep learning","normalizing flow","variational autoencoder","convolutional neural network"],"languages":["en"],"rights":["Copyright 2021 Raimi Shah"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/110543","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":["Shah, Raimi"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2021-09-17T01:11:13Z","2021-04-26","2021-05"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"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":["anomaly detection","deep learning","normalizing flow","variational autoencoder","convolutional neural network"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2021 Raimi Shah"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/110543"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Time series are widely used in applications such as finance, robotics, telecommunications, astronomy, and many more. Detecting anomalies like robotic arm failures or server attacks is a valuable and important task. Recent research in anomaly detection in multivariate temporal data formulates the problem as one of variational inference. To solve this problem, such approaches have used variational autoencoders to try to learn the probability distribution of multiple time series. Variational autoencoders are used as a way to approximate intractable distributions, and methods to improve these approximations are explored through the use of normalizing flows. By applying normalizing flow transforms to the latent variables of a variational autoencoder, the true latent distribution can be more richly modeled and learned, thus enabling better metrics for anomaly detection. This thesis explores five different types of normalizing flow in the context of three multivariate datasets, and demonstrates the effectiveness, compared to prior research, of flows and convolutional networks for anomaly detection by improving popular metrics like the F1-score.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2021-09-16 without embargo terms","The student, Raimi Shah, accepted the attached license on 2021-04-22 at 09:57.","The student, Raimi Shah, submitted this Thesis for approval on 2021-04-22 at 10:02.","This Thesis was approved for publication on 2021-04-26 at 09:58.","DSpace SAF Submission Ingestion Package generated from Vireo submission #16496 on 2021-09-16 at 16:47:01","Made available in DSpace on 2021-09-17T01:11:13Z (GMT). No. of bitstreams: 2 SHAH-THESIS-2021.pdf: 1312766 bytes, checksum: 19c6801e1ce1716ec2f974791e790ad0 (MD5) LICENSE.txt: 4207 bytes, checksum: 204af1c1b504d461c0393507ac5d9407 (MD5) Previous issue date: 2021-04-26"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Generalized flow-based variational autoencoder networks for anomaly detection in multivariate time series"]}]}],"canonical_facts":{"dc:contributor":["Zhao, Zhizhen"],"dc:creator":["Shah, Raimi"],"dc:date":["2021-09-17T01:11:13Z","2021-04-26","2021-05"],"dc:description":["Time series are widely used in applications such as finance, robotics, telecommunications, astronomy, and many more. Detecting anomalies like robotic arm failures or server attacks is a valuable and important task. Recent research in anomaly detection in multivariate temporal data formulates the problem as one of variational inference. To solve this problem, such approaches have used variational autoencoders to try to learn the probability distribution of multiple time series. Variational autoencoders are used as a way to approximate intractable distributions, and methods to improve these approximations are explored through the use of normalizing flows. By applying normalizing flow transforms to the latent variables of a variational autoencoder, the true latent distribution can be more richly modeled and learned, thus enabling better metrics for anomaly detection. This thesis explores five different types of normalizing flow in the context of three multivariate datasets, and demonstrates the effectiveness, compared to prior research, of flows and convolutional networks for anomaly detection by improving popular metrics like the F1-score.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2021-09-16 without embargo terms","The student, Raimi Shah, accepted the attached license on 2021-04-22 at 09:57.","The student, Raimi Shah, submitted this Thesis for approval on 2021-04-22 at 10:02.","This Thesis was approved for publication on 2021-04-26 at 09:58.","DSpace SAF Submission Ingestion Package generated from Vireo submission #16496 on 2021-09-16 at 16:47:01","Made available in DSpace on 2021-09-17T01:11:13Z (GMT). No. of bitstreams: 2 SHAH-THESIS-2021.pdf: 1312766 bytes, checksum: 19c6801e1ce1716ec2f974791e790ad0 (MD5) LICENSE.txt: 4207 bytes, checksum: 204af1c1b504d461c0393507ac5d9407 (MD5) Previous issue date: 2021-04-26"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/110543"],"dc:language":["en"],"dc:rights":["Copyright 2021 Raimi Shah"],"dc:subject":["anomaly detection","deep learning","normalizing flow","variational autoencoder","convolutional neural network"],"dc:title":["Generalized flow-based variational autoencoder networks for anomaly detection in multivariate time series"],"dc:type":["text","Thesis"],"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":"2026-07-22T22:24:52Z"}