Extraction of features from sleep EEG for Bayesian assessment of brain development

2.50
Hdl Handle:
http://hdl.handle.net/10547/622072
Title:
Extraction of features from sleep EEG for Bayesian assessment of brain development
Authors:
Schetinin, Vitaly ( 0000-0003-1826-0153 ) ; Jakaite, Livija
Abstract:
Brain development can be evaluated by experts analysing age-related patterns in sleep electroencephalograms (EEG). Natural variations in the patterns, noise, and artefacts affect the evaluation accuracy as well as experts' agreement. The knowledge of predictive posterior distribution allows experts to estimate confidence intervals within which decisions are distributed. Bayesian approach to probabilistic inference has provided accurate estimates of intervals of interest. In this paper we propose a new feature extraction technique for Bayesian assessment and estimation of predictive distribution in a case of newborn brain development assessment. The new EEG features are verified within the Bayesian framework on a large EEG data set including 1,100 recordings made from newborns in 10 age groups. The proposed features are highly correlated with brain maturation and their use increases the assessment accuracy.
Citation:
Schetinin V, Jakaite L (2017) 'Extraction of features from sleep EEG for Bayesian assessment of brain development', PLoS ONE, 12 (3).
Publisher:
Public Library of Science
Journal:
PLoS ONE
Issue Date:
21-Mar-2017
URI:
http://hdl.handle.net/10547/622072
DOI:
10.1371/journal.pone.0174027
PubMed ID:
28323852
Additional Links:
http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0174027
Type:
Article
Language:
en
ISSN:
1932-6203
Sponsors:
Leverhulme Trust
Appears in Collections:
Computing

Full metadata record

DC FieldValue Language
dc.contributor.authorSchetinin, Vitalyen
dc.contributor.authorJakaite, Livijaen
dc.date.accessioned2017-03-27T12:18:53Z-
dc.date.available2017-03-27T12:18:53Z-
dc.date.issued2017-03-21-
dc.identifier.citationSchetinin V, Jakaite L (2017) 'Extraction of features from sleep EEG for Bayesian assessment of brain development', PLoS ONE, 12 (3).en
dc.identifier.issn1932-6203-
dc.identifier.pmid28323852-
dc.identifier.doi10.1371/journal.pone.0174027-
dc.identifier.urihttp://hdl.handle.net/10547/622072-
dc.description.abstractBrain development can be evaluated by experts analysing age-related patterns in sleep electroencephalograms (EEG). Natural variations in the patterns, noise, and artefacts affect the evaluation accuracy as well as experts' agreement. The knowledge of predictive posterior distribution allows experts to estimate confidence intervals within which decisions are distributed. Bayesian approach to probabilistic inference has provided accurate estimates of intervals of interest. In this paper we propose a new feature extraction technique for Bayesian assessment and estimation of predictive distribution in a case of newborn brain development assessment. The new EEG features are verified within the Bayesian framework on a large EEG data set including 1,100 recordings made from newborns in 10 age groups. The proposed features are highly correlated with brain maturation and their use increases the assessment accuracy.en
dc.description.sponsorshipLeverhulme Trusten
dc.language.isoenen
dc.publisherPublic Library of Scienceen
dc.relation.urlhttp://journals.plos.org/plosone/article?id=10.1371/journal.pone.0174027en
dc.rightsGreen - can archive pre-print and post-print or publisher's version/PDF-
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.subjectfeature extractionen
dc.subjectdiscontinuityen
dc.subjectsegmentationen
dc.subjectEEG dataen
dc.subjectpredictive posterioren
dc.subjectBayesian learningen
dc.titleExtraction of features from sleep EEG for Bayesian assessment of brain developmenten
dc.typeArticleen
dc.identifier.journalPLoS ONEen
dc.date.updated2017-03-27T12:16:39Z-

Related articles on PubMed

This item is licensed under a Creative Commons License
Creative Commons
All Items in UOBREP are protected by copyright, with all rights reserved, unless otherwise indicated.