{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:31:58Z","timestamp":1772137918487,"version":"3.50.1"},"reference-count":63,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2024,8,5]],"date-time":"2024-08-05T00:00:00Z","timestamp":1722816000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2024,8,5]],"date-time":"2024-08-05T00:00:00Z","timestamp":1722816000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100006151","name":"Basic Energy Sciences","doi-asserted-by":"crossref","award":["E-AC02- 76SF00515"],"award-info":[{"award-number":["E-AC02- 76SF00515"]}],"id":[{"id":"10.13039\/100006151","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2024,9,1]]},"abstract":"Abstract<\/jats:title>\n \n Anomaly detection is an important task for complex scientific experiments and other complex systems (e.g. industrial facilities, manufacturing), where failures in a sub-system can lead to lost data, poor performance, or even damage to components. While scientific facilities generate a wealth of data, labeled anomalies may be rare (or even nonexistent), and expensive to acquire. Unsupervised approaches are therefore common and typically search for anomalies either by distance or density of examples in the input feature space (or some associated low-dimensional representation). This paper presents a novel approach called coincident learning for anomaly detection (CoAD), which is specifically designed for multi-modal tasks and identifies anomalies based on\n coincident<\/jats:italic>\n behavior across two different slices of the feature space. We define an\n unsupervised<\/jats:italic>\n metric,\n \n \n \n <\/jats:tex-math>\n \n \n \n \n \n F<\/mml:mi>\n ^<\/mml:mo>\n <\/mml:mover>\n <\/mml:mrow>\n \u03b2<\/mml:mi>\n <\/mml:msub>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n , out of analogy to the supervised classification\n F<\/jats:italic>\n \n \u03b2<\/jats:italic>\n <\/jats:sub>\n statistic. CoAD uses\n \n \n \n <\/jats:tex-math>\n \n \n \n \n \n F<\/mml:mi>\n ^<\/mml:mo>\n <\/mml:mover>\n <\/mml:mrow>\n \u03b2<\/mml:mi>\n <\/mml:msub>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n to train an anomaly detection algorithm on\n unlabeled data<\/jats:italic>\n , based on the expectation that anomalous behavior in one feature slice is coincident with anomalous behavior in the other. The method is illustrated using a synthetic outlier data set and a MNIST-based image data set, and is compared to prior state-of-the-art on two real-world tasks: a metal milling data set and our motivating task of identifying RF station anomalies in a particle accelerator.\n <\/jats:p>","DOI":"10.1088\/2632-2153\/ad64a6","type":"journal-article","created":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T18:58:50Z","timestamp":1721242730000},"page":"035036","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Coincident learning for unsupervised anomaly detection of scientific instruments"],"prefix":"10.1088","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5854-9117","authenticated-orcid":true,"given":"Ryan","family":"Humble","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8143-0381","authenticated-orcid":true,"given":"Zhe","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2398-7381","authenticated-orcid":true,"given":"Finn","family":"O\u2019Shea","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1938-3836","authenticated-orcid":false,"given":"Eric","family":"Darve","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5747-7323","authenticated-orcid":false,"given":"Daniel","family":"Ratner","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2024,8,5]]},"reference":[{"key":"mlstad64a6bib1","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1016\/j.measurement.2016.04.007","article-title":"A sparse auto-encoder-based deep neural network approach for induction motor faults classification","volume":"89","author":"Sun","year":"2016","journal-title":"Measurement"},{"key":"mlstad64a6bib2","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1016\/j.ymssp.2018.05.050","article-title":"Deep learning and its applications to machine health monitoring","volume":"115","author":"Zhao","year":"2019","journal-title":"Mech. Syst. Signal Process."},{"key":"mlstad64a6bib3","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.3390\/en13051063","article-title":"Evaluation of anomaly detection of an autoencoder based on maintenace information and scada-data","volume":"13","author":"Lutz","year":"2020","journal-title":"Energies"},{"key":"mlstad64a6bib4","article-title":"Anomaly detection in particle accelerators using autoencoders","author":"Edelen","year":"2021"},{"key":"mlstad64a6bib5","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2021.103498","article-title":"A survey on anomaly detection for technical systems using LSTM networks","volume":"131","author":"Lindemann","year":"2021","journal-title":"Comput. Ind."},{"key":"mlstad64a6bib6","article-title":"Application of convolutional and feedforward neural networks for fault detection in particle accelerator power systems","volume":"vol 14","author":"Radaideh","year":"2022"},{"key":"mlstad64a6bib7","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1007\/978-1-4899-7488-4_196","article-title":"Gaussian mixture models","volume":"741","author":"Reynolds","year":"2009","journal-title":"Encyclopedia Biometrics"},{"key":"mlstad64a6bib8","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1198\/004017001316975899","article-title":"Multivariate outlier detection and robust covariance matrix estimation","volume":"43","author":"Pe\u00f1a","year":"2001","journal-title":"Technometrics"},{"key":"mlstad64a6bib9","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1002\/wics.61","article-title":"Minimum covariance determinant","volume":"2","author":"Hubert","year":"2010","journal-title":"Wiley Interdiscip. Rev. Comput. Stat."},{"key":"mlstad64a6bib10","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1007\/978-3-642-38652-7","article-title":"K-nearest neighbors","author":"Kramer","year":"2013"},{"key":"mlstad64a6bib11","first-page":"pp 444","article-title":"Angle-based outlier detection in high-dimensional data","author":"Kriegel","year":"2008"},{"key":"mlstad64a6bib12","first-page":"pp 3077","article-title":"Improving one-class svm for anomaly detection","volume":"vol 5","author":"Li","year":"2003"},{"key":"mlstad64a6bib13","doi-asserted-by":"crossref","DOI":"10.1109\/ICDM.2008.17","article-title":"Isolation forest","author":"Liu","year":"2008"},{"key":"mlstad64a6bib14","doi-asserted-by":"publisher","first-page":"1443","DOI":"10.1162\/089976601750264965","article-title":"Estimating the support of a high-dimensional distribution","volume":"13","author":"Sch\u00f6lkopf","year":"2001","journal-title":"Neural Comput."},{"key":"mlstad64a6bib15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/bdcc5010001","article-title":"A review of local outlier factor algorithms for outlier detection in big data streams","volume":"5","author":"Alghushairy","year":"2020","journal-title":"Big data Cogn. Comput."},{"key":"mlstad64a6bib16","doi-asserted-by":"publisher","first-page":"1641","DOI":"10.1016\/S0167-8655(03)00003-5","article-title":"Discovering cluster-based local outliers","volume":"24","author":"He","year":"2003","journal-title":"Pattern Recognit. Lett."},{"key":"mlstad64a6bib17","first-page":"pp 315","article-title":"LOCI: fast outlier detection using the local correlation integral","author":"Papadimitriou","year":"2003"},{"key":"mlstad64a6bib18","first-page":"2012","article-title":"Stochastic outlier selection","volume":"1","author":"Janssens","year":"2012"},{"key":"mlstad64a6bib19","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1145\/335191.335388","article-title":"LOF","volume":"29","author":"Breunig","year":"2000","journal-title":"ACM SIGMOD Record"},{"key":"mlstad64a6bib20","doi-asserted-by":"publisher","first-page":"1065","DOI":"10.1214\/aoms\/1177704472","article-title":"On estimation of a probability density function and mode","volume":"33","author":"Parzen","year":"1962","journal-title":"Ann. Math. Stat."},{"key":"mlstad64a6bib21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TNNLS.2023.3344118","article-title":"MSFLOW: multiscale flow-based framework for unsupervised anomaly detection","author":"Zhou","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"mlstad64a6bib22","article-title":"Graph-augmented normalizing flows for anomaly detection of multiple time series","author":"Dai","year":"2022"},{"key":"mlstad64a6bib23","first-page":"pp 98","article-title":"CFLOW-AD: real-time unsupervised anomaly detection with localization via conditional normalizing flows","author":"Gudovskiy","year":"2022"},{"key":"mlstad64a6bib24","article-title":"FastFlow: unsupervised anomaly detection and localization via 2D normalizing flows","author":"Yu","year":"2021"},{"key":"mlstad64a6bib25","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1016\/j.patcog.2006.07.009","article-title":"Kernel pca for novelty detection","volume":"40","author":"Hoffmann","year":"2007","journal-title":"Pattern Recognit."},{"key":"mlstad64a6bib26","first-page":"pp 727","article-title":"Adversarially learned anomaly detection","author":"Zenati","year":"2018"},{"key":"mlstad64a6bib27","first-page":"pp 1618","article-title":"Regularized cycle consistent generative adversarial network for anomaly detection","author":"Yang","year":"2020"},{"key":"mlstad64a6bib28","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/j.media.2019.01.010","article-title":"f-AnoGAN: Fast unsupervised anomaly detection with generative adversarial networks","volume":"54","author":"Schlegl","year":"2019","journal-title":"Med. Image Anal."},{"key":"mlstad64a6bib29","doi-asserted-by":"publisher","first-page":"1517","DOI":"10.1109\/TKDE.2019.2905606","article-title":"Generative adversarial active learning for unsupervised outlier detection","volume":"32","author":"Liu","year":"2019","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"mlstad64a6bib30","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/j.neucom.2021.04.089","article-title":"Vae-based deep svdd for anomaly detection","volume":"453","author":"Zhou","year":"2021","journal-title":"Neurocomputing"},{"key":"mlstad64a6bib31","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1038\/nphoton.2010.176","article-title":"First lasing and operation of an \u00e5ngstrom-wavelength free-electron laser","volume":"4","author":"Emma","year":"2010","journal-title":"Nat. Photon."},{"key":"mlstad64a6bib32","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevAccelBeams.25.122804","article-title":"Beam-based rf station fault identification at the SLAC Linac Coherent Light Source","volume":"25","author":"Humble","year":"2022","journal-title":"Phys. Rev. Accel. Beams"},{"key":"mlstad64a6bib33","first-page":"pp 90","article-title":"Outlier detection with autoencoder ensembles","author":"Chen","year":"2017"},{"key":"mlstad64a6bib34","first-page":"pp 2828","article-title":"Robust anomaly detection for multivariate time series through stochastic recurrent neural network","author":"Su","year":"2019"},{"key":"mlstad64a6bib35","first-page":"pp 146","article-title":"Unsupervised anomaly detection with generative adversarial networks to guide marker discovery","author":"Schlegl","year":"2017"},{"key":"mlstad64a6bib36","first-page":"pp 1643","article-title":"Deep generative model with hierarchical latent factors for time series anomaly detection","author":"Challu","year":"2022"},{"key":"mlstad64a6bib37","article-title":"Anomaly detection with conditioned denoising diffusion models","author":"Mousakhan","year":"2023"},{"key":"mlstad64a6bib38","first-page":"pp 650","article-title":"AnoDDPM: anomaly detection with denoising diffusion probabilistic models using simplex noise","author":"Wyatt","year":"2022"},{"key":"mlstad64a6bib39","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2023.103983","article-title":"Unsupervised industrial anomaly detection with diffusion models","volume":"97","author":"Xu","year":"2023","journal-title":"J. Vis. Commun. Image Represent."},{"key":"mlstad64a6bib40","first-page":"pp 4393","article-title":"Deep one-class classification","author":"Ruff","year":"2018"},{"key":"mlstad64a6bib41","first-page":"pp 13016","article-title":"Timeseries anomaly detection using temporal hierarchical one-class network","volume":"vol 33","author":"Shen","year":"2020"},{"key":"mlstad64a6bib42","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1093\/biomet\/28.3-4.321","article-title":"Relations between two sets of variates","volume":"28","author":"Hotelling","year":"1936","journal-title":"Biometrika"},{"key":"mlstad64a6bib43","article-title":"A kernel method for canonical correlation analysis","author":"Akaho","year":"2001","journal-title":"Int. Meet. of Psychometric Soc."},{"key":"mlstad64a6bib44","doi-asserted-by":"publisher","first-page":"2639","DOI":"10.1162\/0899766042321814","article-title":"Canonical correlation analysis: an overview with application to learning methods","volume":"16","author":"Hardoon","year":"2004","journal-title":"Neural Comput."},{"key":"mlstad64a6bib45","first-page":"pp 1083","article-title":"On deep multi-view representation learning","author":"Wang","year":"2015"},{"key":"mlstad64a6bib46","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1162\/NECO_a_00801","article-title":"Correlational neural networks","volume":"28","author":"Chandar","year":"2016","journal-title":"Neural Comput."},{"key":"mlstad64a6bib47","first-page":"pp 1247","article-title":"Deep canonical correlation analysis","author":"Andrew","year":"2013"},{"key":"mlstad64a6bib48","author":"Storch","year":"1999"},{"key":"mlstad64a6bib49","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1175\/1520-0442(1992)0052.0.CO;2","article-title":"An intercomparison of methods for finding coupled patterns in climate data","volume":"5","author":"Bretherton","year":"1992","journal-title":"J. Clim."},{"key":"mlstad64a6bib50","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1175\/1520-0442(1992)0052.0.CO;2","article-title":"Singular value decomposition of wintertime sea surface temperature and 500-mb height anomalies","volume":"5","author":"Wallace","year":"1992","journal-title":"J. Clim."},{"key":"mlstad64a6bib51","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA.2018.8460494","article-title":"ViTac: feature sharing between vision and tactile sensing for cloth texture recognition","author":"Luo","year":"2018"},{"key":"mlstad64a6bib52","first-page":"pp 776","article-title":"Contrastive multiview coding","author":"Tian","year":"2020"},{"key":"mlstad64a6bib53","article-title":"Learning representations by maximizing mutual information across views","volume":"vol 32","author":"Bachman","year":"2019"},{"key":"mlstad64a6bib54","first-page":"pp 1597","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"mlstad64a6bib55","first-page":"pp 4182","article-title":"Data-efficient image recognition with contrastive predictive coding","author":"Henaff","year":"2020"},{"key":"mlstad64a6bib56","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/j.patcog.2017.09.015","article-title":"Learning by coincidence: Siamese networks and common variable learning","volume":"74","author":"Shaham","year":"2018","journal-title":"Pattern Recognit."},{"key":"mlstad64a6bib57","article-title":"Pytorch: an imperative style, high-performance deep learning library","volume":"vol 32","author":"Paszke","year":"2019"},{"key":"mlstad64a6bib58","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2015"},{"key":"mlstad64a6bib59","article-title":"Milling data set","author":"Agogino","year":"2007"},{"key":"mlstad64a6bib60","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1504\/IJHM.2021.114174","article-title":"Self-supervised learning for tool wear monitoring with a disentangled-variational-autoencoder","volume":"4","author":"Hahn","year":"2021","journal-title":"Int. J. Hydromechatron."},{"key":"mlstad64a6bib61","doi-asserted-by":"publisher","DOI":"10.11578\/1869296","article-title":"LCLS RF Station Anomaly Candidates, SLAC, Nov 2020 to Dec 2020, Version 1","author":"Ratner","year":"2022"},{"key":"mlstad64a6bib62","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"mlstad64a6bib63","first-page":"1","article-title":"PyOD: a python toolbox for scalable outlier detection","volume":"20","author":"Zhao","year":"2019","journal-title":"J. Mach. Learn. Res."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad64a6","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad64a6\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad64a6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad64a6\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad64a6\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad64a6\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad64a6\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad64a6\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,5]],"date-time":"2024-08-05T09:09:12Z","timestamp":1722848952000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad64a6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,5]]},"references-count":63,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,8,5]]},"published-print":{"date-parts":[[2024,9,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad64a6","relation":{"has-review":[{"id-type":"doi","id":"10.1088\/2632-2153\/AD64A6\/v2\/response1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/AD64A6\/v2\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/AD64A6\/v3\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/AD64A6\/v3\/response1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/AD64A6\/v1\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/AD64A6\/v2\/review1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/AD64A6\/v2\/review2","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/AD64A6\/v1\/review1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/AD64A6\/v1\/review2","asserted-by":"object"}]},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,5]]},"assertion":[{"value":"Coincident learning for unsupervised anomaly detection of scientific instruments","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2024 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2023-10-08","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-07-17","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-08-05","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}