{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T02:55:47Z","timestamp":1775184947483,"version":"3.50.1"},"reference-count":32,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T00:00:00Z","timestamp":1731542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T00:00:00Z","timestamp":1731542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001804","name":"Canada Research Chairs","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001804","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":[[2024,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>New scientific experiments and instruments generate vast amounts of data that need to be transferred for storage or further processing, often overwhelming traditional systems. Edge machine learning (EdgeML) addresses this challenge by integrating machine learning (ML) algorithms with edge computing, enabling real-time data processing directly at the point of data generation. EdgeML is particularly beneficial for environments where immediate decisions are required, or where bandwidth and storage are limited. In this paper, we demonstrate a high-speed configurable ML model in a fully customizable EdgeML system using a field programmable gate array (FPGA). Our demonstration focuses on an angular array of electron spectrometers, referred to as the \u2018CookieBox,\u2019 developed for the Linac Coherent Light Source II project. The EdgeML system captures 51.2 Gbps from a 6.4 GS\u2009s<jats:sup>\u22121<\/jats:sup> analog to digital converter and is designed to integrate data pre-processing and ML inside an FPGA. Our implementation achieves an inference latency of 0.2 <jats:italic>\u00b5<\/jats:italic>s for the ML model, and a total latency of 0.4 <jats:italic>\u00b5<\/jats:italic>s for the complete EdgeML system, which includes pre-processing, data transmission, digitization, and ML inference. The modular design of the system allows it to be adapted for other instrumentation applications requiring low-latency data processing.<\/jats:p>","DOI":"10.1088\/2632-2153\/ad8ea8","type":"journal-article","created":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T22:55:55Z","timestamp":1730760955000},"page":"045041","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Accelerating data acquisition with FPGA-based edge machine learning: a case study with LCLS-II"],"prefix":"10.1088","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6582-8322","authenticated-orcid":true,"given":"Mohammad","family":"Mehdi Rahimifar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6301-8450","authenticated-orcid":true,"given":"Quentin","family":"Wingering","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Berthi\u00e9","family":"Gouin-Ferland","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryan","family":"Coffee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6698-8400","authenticated-orcid":true,"given":"Audrey C","family":"Therrien","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2024,11,14]]},"reference":[{"key":"mlstad8ea8bib1","doi-asserted-by":"publisher","first-page":"316","DOI":"10.3390\/jcm8030316","article-title":"The challenges of diagnostic imaging in the era of big data","volume":"8","author":"Aiello","year":"2019","journal-title":"J. Clin. Med."},{"key":"mlstad8ea8bib2","first-page":"pp 48","article-title":"Addressing big data issues in scientific data infrastructure","author":"Demchenko","year":"2013"},{"key":"mlstad8ea8bib3","first-page":"pp 1","article-title":"Building a data system for lcls-ii","author":"Thayer","year":"2017"},{"key":"mlstad8ea8bib4","article-title":"The atlas trigger and data acquisition upgrades for the high luminosity lhc (hl-lhc)","author":"Valente","year":"2019"},{"key":"mlstad8ea8bib5","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1364\/AO.445798","article-title":"Potential of edge machine learning for instrumentation","volume":"61","author":"Therrien","year":"2022","journal-title":"Appl. Opt."},{"key":"mlstad8ea8bib6","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1016\/j.future.2019.02.050","article-title":"Edge computing: a survey","volume":"97","author":"Zada Khan","year":"2019","journal-title":"Future Gener. Comput. Syst."},{"key":"mlstad8ea8bib7","doi-asserted-by":"publisher","first-page":"895","DOI":"10.3390\/electronics10080895","article-title":"Embedded intelligence on FPGA: survey, applications and challenges","volume":"10","author":"Phooi Seng","year":"2021","journal-title":"Electronics"},{"key":"mlstad8ea8bib8","doi-asserted-by":"publisher","first-page":"3897","DOI":"10.1109\/TCSI.2018.2852260","article-title":"Real-time embedded machine learning for tensorial tactile data processing","volume":"65","author":"Ibrahim","year":"2018","journal-title":"Proc. IEEE"},{"key":"mlstad8ea8bib9","first-page":"pp 100","article-title":"A survey on convolutional neural network accelerators: GPU, FPGA and ASIC","author":"Yunxiang","year":"2022"},{"key":"mlstad8ea8bib10","first-page":"pp 1","article-title":"A systematic literature review of hardware neural networks","author":"Parra","year":"2018"},{"key":"mlstad8ea8bib11","first-page":"pp 409","article-title":"Hardware accelerators for edge enabled machine learning","author":"Suresh","year":"2020"},{"key":"mlstad8ea8bib12","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/17\/06\/C06009","article-title":"Machine learning on FPGA for event selection","volume":"17","author":"Furletov","year":"2022","journal-title":"J. Instrum."},{"key":"mlstad8ea8bib13","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/15\/05\/P05026","article-title":"Fast inference of boosted decision trees in FPGAS for particle physics","volume":"15","author":"Summers","year":"2020","journal-title":"J. Instrum."},{"key":"mlstad8ea8bib14","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1038\/s42256-022-00441-3","article-title":"Autoencoders on field-programmable gate arrays for real-time, unsupervised new physics detection at 40 MHz at the large hadron collider","volume":"4","author":"Govorkova","year":"2022","journal-title":"Nat. Mach. Intell."},{"key":"mlstad8ea8bib15","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/16\/08\/P08016","article-title":"Nanosecond machine learning event classification with boosted decision trees in FPGA for high energy physics","volume":"16","author":"Tae Min Hong","year":"2021","journal-title":"J. Instrum."},{"key":"mlstad8ea8bib16","doi-asserted-by":"publisher","DOI":"10.1016\/j.nima.2022.167546","article-title":"Fast muon tracking with machine learning implemented in FPGA","volume":"1045","author":"Sun","year":"2023","journal-title":"Nucl. Instrum. Methods Phys. Res. A"},{"key":"mlstad8ea8bib17","doi-asserted-by":"publisher","first-page":"969","DOI":"10.1140\/epjc\/s10052-021-09770-w","article-title":"Model compression and simplification pipelines for fast deep neural network inference in FPGAS in hep","volume":"81","author":"Francescato","year":"2021","journal-title":"Eur. Phys. J. C"},{"key":"mlstad8ea8bib18","article-title":"Neural network-based algorithm for the identification of bottom quarks in the cms phase-2 level-1 trigger","author":"CMS Collaboration","year":"2022"},{"key":"mlstad8ea8bib19","article-title":"Hadronic tau reconstruction in the cms phase-2 level-1 trigger using nns with calorimetric information","author":"CMS Collaboration","year":"2023"},{"key":"mlstad8ea8bib20","article-title":"Level-1 Trigger Calorimeter Image Convolutional Anomaly Detection Algorithm","year":"2023"},{"key":"mlstad8ea8bib21","first-page":"pp 1","article-title":"Combining optimized quantization and machine learning for real-time data reduction at the edge","author":"Gouin-Ferland","year":"2022"},{"key":"mlstad8ea8bib22","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1038\/s41566-018-0107-6","article-title":"Attosecond time\u2013energy structure of x-ray free-electron laser pulses","volume":"12","author":"Hartmann","year":"2018","journal-title":"Nat. Photon."},{"key":"mlstad8ea8bib23","first-page":"pp 1","article-title":"Machine learning at the edge for ultra high rate detectors","author":"Corbeil Therrien","year":"2019"},{"key":"mlstad8ea8bib24","author":"Vivado","year":"2024"},{"key":"mlstad8ea8bib25","doi-asserted-by":"publisher","first-page":"887","DOI":"10.3389\/fphy.2022.957128","article-title":"Data reduction through optimized scalar quantization for more compact neural networks","volume":"25","author":"Gouin-Ferland","year":"2022","journal-title":"Front. Phys."},{"key":"mlstad8ea8bib26","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ad0d12","article-title":"Exploring machine learning to hardware implementations for large data rate x-ray instrumentation","volume":"4","author":"Mehdi Rahimifar","year":"2023","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstad8ea8bib27","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ac0ea1","article-title":"Fast convolutional neural networks on FPGAS with hls4ml","volume":"2","author":"Duarte","year":"2021","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstad8ea8bib28","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/13\/07\/P07027","article-title":"Fast inference of deep neural networks in fpgas for particle physics","volume":"13","author":"Duarte","year":"2018","journal-title":"J. Instrum."},{"key":"mlstad8ea8bib29","first-page":"pp 1","article-title":"A versatile edge machine learning test bench for high bandwidth instrumentation","author":"Wingering","year":"2023"},{"key":"mlstad8ea8bib30","article-title":"Time-of-flight computed tomography a proof of principle study","author":"Rossignol","year":"2019"},{"key":"mlstad8ea8bib31","article-title":"The cms trigger system","author":"CMS collaboration","year":"2016"},{"key":"mlstad8ea8bib32","article-title":"The atlas experiment at the cern large hadron collider: a description of the detector configuration for run 3.","author":"Atlas Collaboration","year":"2023"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad8ea8","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad8ea8\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad8ea8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad8ea8\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad8ea8\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad8ea8\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad8ea8\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad8ea8\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T11:38:17Z","timestamp":1731584297000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad8ea8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,14]]},"references-count":32,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,11,14]]},"published-print":{"date-parts":[[2024,12,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad8ea8","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,14]]},"assertion":[{"value":"Accelerating data acquisition with FPGA-based edge machine learning: a case study with LCLS-II","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":"2024-03-15","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-11-04","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-11-14","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}