LEARNING REPRESENTATIONS OF EEG SIGNALS WITH SELF-SUPERVISED LEARNING

Self-supervised learning (SSL) is used to leverage structure in unlabeled data, to learn representations of EEG signals. Two tasks based on temporal context prediction as well as contrastive predictive coding are applied to two clinically-relevant problems: EEG-based sleep staging and pathology dete...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: AIMONE, Christopher Allen, WOOD, Sean Ulrich Niethe, JACOB BANVILLE, Hubert
Format: Patent
Sprache:eng ; fre
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator AIMONE, Christopher Allen
WOOD, Sean Ulrich Niethe
JACOB BANVILLE, Hubert
description Self-supervised learning (SSL) is used to leverage structure in unlabeled data, to learn representations of EEG signals. Two tasks based on temporal context prediction as well as contrastive predictive coding are applied to two clinically-relevant problems: EEG-based sleep staging and pathology detection. Experiments are performed on two large public datasets with thousands of recordings and perform baseline comparisons with purely supervised and hand-engineered paradigms. Selon l'invention, un apprentissage autosupervisé (SSL) est utilisé pour tirer parti de la structure dans des données non étiquetées, pour apprendre des représentations de signaux d'EEG. Deux tâches basées sur une prédiction de contexte temporel et un codage prédictif contrastif sont appliquées à deux problèmes pertinents d'un point de vue clinique : L'invention concerne également la stadification du sommeil et la détection de pathologies basées sur l'EEG. Des expériences sont effectuées sur deux grands ensembles de données publics avec des milliers d'enregistrements et réalisent des comparaisons de niveau de référence avec des paradigmes purement supervisés et empiriques.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_WO2022020968A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>WO2022020968A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_WO2022020968A13</originalsourceid><addsrcrecordid>eNrjZHD1cXUM8vP0c1cIcg0Icg129QtxDPH09wtW8HdTcHV1Vwj2dPdz9AlWCPcM8VAIdvVx0w0ODXANCvMMdnVRgGnmYWBNS8wpTuWF0twMym6uIc4euqkF-fGpxQWJyal5qSXx4f5GBkZAZGBpZuFoaEycKgBUDS00</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>LEARNING REPRESENTATIONS OF EEG SIGNALS WITH SELF-SUPERVISED LEARNING</title><source>esp@cenet</source><creator>AIMONE, Christopher Allen ; WOOD, Sean Ulrich Niethe ; JACOB BANVILLE, Hubert</creator><creatorcontrib>AIMONE, Christopher Allen ; WOOD, Sean Ulrich Niethe ; JACOB BANVILLE, Hubert</creatorcontrib><description>Self-supervised learning (SSL) is used to leverage structure in unlabeled data, to learn representations of EEG signals. Two tasks based on temporal context prediction as well as contrastive predictive coding are applied to two clinically-relevant problems: EEG-based sleep staging and pathology detection. Experiments are performed on two large public datasets with thousands of recordings and perform baseline comparisons with purely supervised and hand-engineered paradigms. Selon l'invention, un apprentissage autosupervisé (SSL) est utilisé pour tirer parti de la structure dans des données non étiquetées, pour apprendre des représentations de signaux d'EEG. Deux tâches basées sur une prédiction de contexte temporel et un codage prédictif contrastif sont appliquées à deux problèmes pertinents d'un point de vue clinique : L'invention concerne également la stadification du sommeil et la détection de pathologies basées sur l'EEG. Des expériences sont effectuées sur deux grands ensembles de données publics avec des milliers d'enregistrements et réalisent des comparaisons de niveau de référence avec des paradigmes purement supervisés et empiriques.</description><language>eng ; fre</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; DIAGNOSIS ; HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA ; HUMAN NECESSITIES ; HYGIENE ; IDENTIFICATION ; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS ; MEDICAL OR VETERINARY SCIENCE ; PHYSICS ; SURGERY</subject><creationdate>2022</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20220203&amp;DB=EPODOC&amp;CC=WO&amp;NR=2022020968A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76516</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20220203&amp;DB=EPODOC&amp;CC=WO&amp;NR=2022020968A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>AIMONE, Christopher Allen</creatorcontrib><creatorcontrib>WOOD, Sean Ulrich Niethe</creatorcontrib><creatorcontrib>JACOB BANVILLE, Hubert</creatorcontrib><title>LEARNING REPRESENTATIONS OF EEG SIGNALS WITH SELF-SUPERVISED LEARNING</title><description>Self-supervised learning (SSL) is used to leverage structure in unlabeled data, to learn representations of EEG signals. Two tasks based on temporal context prediction as well as contrastive predictive coding are applied to two clinically-relevant problems: EEG-based sleep staging and pathology detection. Experiments are performed on two large public datasets with thousands of recordings and perform baseline comparisons with purely supervised and hand-engineered paradigms. Selon l'invention, un apprentissage autosupervisé (SSL) est utilisé pour tirer parti de la structure dans des données non étiquetées, pour apprendre des représentations de signaux d'EEG. Deux tâches basées sur une prédiction de contexte temporel et un codage prédictif contrastif sont appliquées à deux problèmes pertinents d'un point de vue clinique : L'invention concerne également la stadification du sommeil et la détection de pathologies basées sur l'EEG. Des expériences sont effectuées sur deux grands ensembles de données publics avec des milliers d'enregistrements et réalisent des comparaisons de niveau de référence avec des paradigmes purement supervisés et empiriques.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>DIAGNOSIS</subject><subject>HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA</subject><subject>HUMAN NECESSITIES</subject><subject>HYGIENE</subject><subject>IDENTIFICATION</subject><subject>INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS</subject><subject>MEDICAL OR VETERINARY SCIENCE</subject><subject>PHYSICS</subject><subject>SURGERY</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZHD1cXUM8vP0c1cIcg0Icg129QtxDPH09wtW8HdTcHV1Vwj2dPdz9AlWCPcM8VAIdvVx0w0ODXANCvMMdnVRgGnmYWBNS8wpTuWF0twMym6uIc4euqkF-fGpxQWJyal5qSXx4f5GBkZAZGBpZuFoaEycKgBUDS00</recordid><startdate>20220203</startdate><enddate>20220203</enddate><creator>AIMONE, Christopher Allen</creator><creator>WOOD, Sean Ulrich Niethe</creator><creator>JACOB BANVILLE, Hubert</creator><scope>EVB</scope></search><sort><creationdate>20220203</creationdate><title>LEARNING REPRESENTATIONS OF EEG SIGNALS WITH SELF-SUPERVISED LEARNING</title><author>AIMONE, Christopher Allen ; WOOD, Sean Ulrich Niethe ; JACOB BANVILLE, Hubert</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_WO2022020968A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>DIAGNOSIS</topic><topic>HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA</topic><topic>HUMAN NECESSITIES</topic><topic>HYGIENE</topic><topic>IDENTIFICATION</topic><topic>INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS</topic><topic>MEDICAL OR VETERINARY SCIENCE</topic><topic>PHYSICS</topic><topic>SURGERY</topic><toplevel>online_resources</toplevel><creatorcontrib>AIMONE, Christopher Allen</creatorcontrib><creatorcontrib>WOOD, Sean Ulrich Niethe</creatorcontrib><creatorcontrib>JACOB BANVILLE, Hubert</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>AIMONE, Christopher Allen</au><au>WOOD, Sean Ulrich Niethe</au><au>JACOB BANVILLE, Hubert</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>LEARNING REPRESENTATIONS OF EEG SIGNALS WITH SELF-SUPERVISED LEARNING</title><date>2022-02-03</date><risdate>2022</risdate><abstract>Self-supervised learning (SSL) is used to leverage structure in unlabeled data, to learn representations of EEG signals. Two tasks based on temporal context prediction as well as contrastive predictive coding are applied to two clinically-relevant problems: EEG-based sleep staging and pathology detection. Experiments are performed on two large public datasets with thousands of recordings and perform baseline comparisons with purely supervised and hand-engineered paradigms. Selon l'invention, un apprentissage autosupervisé (SSL) est utilisé pour tirer parti de la structure dans des données non étiquetées, pour apprendre des représentations de signaux d'EEG. Deux tâches basées sur une prédiction de contexte temporel et un codage prédictif contrastif sont appliquées à deux problèmes pertinents d'un point de vue clinique : L'invention concerne également la stadification du sommeil et la détection de pathologies basées sur l'EEG. Des expériences sont effectuées sur deux grands ensembles de données publics avec des milliers d'enregistrements et réalisent des comparaisons de niveau de référence avec des paradigmes purement supervisés et empiriques.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng ; fre
recordid cdi_epo_espacenet_WO2022020968A1
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
DIAGNOSIS
HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA
HUMAN NECESSITIES
HYGIENE
IDENTIFICATION
INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS
MEDICAL OR VETERINARY SCIENCE
PHYSICS
SURGERY
title LEARNING REPRESENTATIONS OF EEG SIGNALS WITH SELF-SUPERVISED LEARNING
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-14T12%3A59%3A48IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=AIMONE,%20Christopher%20Allen&rft.date=2022-02-03&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EWO2022020968A1%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true