2.50
Hdl Handle:
http://hdl.handle.net/10547/293063
Title:
Classification of newborn EEG maturity with Bayesian averaging over decision trees
Authors:
Schetinin, Vitaly ( 0000-0003-1826-0153 ) ; Jakaite, Livija
Abstract:
EEG experts can assess a newborn’s brain maturity by visual analysis of age-related patterns in sleep EEG. It is highly desirable to make the results of assessment most accurate and reliable. However, the expert analysis is limited in capability to provide the estimate of uncertainty in assessments. Bayesian inference has been shown providing the most accurate estimates of uncertainty by using Markov Chain Monte Carlo (MCMC) integration over the posterior distribution. The use of MCMC enables to approximate the desired distribution by sampling the areas of interests in which the density of distribution is high. In practice, the posterior distribution can be multimodal, and so that the existing MCMC techniques cannot provide the proportional sampling from the areas of interest. The lack of prior information makes MCMC integration more difficult when a model parameter space is large and cannot be explored in detail within a reasonable time. In particular, the lack of information about EEG feature importance can affect the results of Bayesian assessment of EEG maturity. In this paper we explore how the posterior information about EEG feature importance can be used to reduce a negative influence of disproportional sampling on the results of Bayesian assessment. We found that the MCMC integration tends to oversample the areas in which a model parameter space includes one or more features, the importance of which counted in terms of their posterior use is low. Using this finding, we proposed to cure the results of MCMC integration and then described the results of testing the proposed method on a set of sleep EEG recordings.
Citation:
Schetinin, V. & Jakaite, L. (2012) 'Classification of newborn EEG maturity with bayesian averaging over decision trees', Expert Systems with Applications, 39 (10), pp.9340-9347.
Publisher:
Elsevier
Journal:
Expert Systems with Applications
Issue Date:
Aug-2012
URI:
http://hdl.handle.net/10547/293063
DOI:
10.1016/j.eswa.2012.02.184
Additional Links:
http://linkinghub.elsevier.com/retrieve/pii/S0957417412004538
Type:
Article
Language:
en
ISSN:
0957-4174
Appears in Collections:
Centre for Research in Distributed Technologies (CREDIT)

Full metadata record

DC FieldValue Language
dc.contributor.authorSchetinin, Vitalyen_GB
dc.contributor.authorJakaite, Livijaen_GB
dc.date.accessioned2013-05-30T13:04:55Z-
dc.date.available2013-05-30T13:04:55Z-
dc.date.issued2012-08-
dc.identifier.citationSchetinin, V. & Jakaite, L. (2012) 'Classification of newborn EEG maturity with bayesian averaging over decision trees', Expert Systems with Applications, 39 (10), pp.9340-9347.en_GB
dc.identifier.issn0957-4174-
dc.identifier.doi10.1016/j.eswa.2012.02.184-
dc.identifier.urihttp://hdl.handle.net/10547/293063-
dc.description.abstractEEG experts can assess a newborn’s brain maturity by visual analysis of age-related patterns in sleep EEG. It is highly desirable to make the results of assessment most accurate and reliable. However, the expert analysis is limited in capability to provide the estimate of uncertainty in assessments. Bayesian inference has been shown providing the most accurate estimates of uncertainty by using Markov Chain Monte Carlo (MCMC) integration over the posterior distribution. The use of MCMC enables to approximate the desired distribution by sampling the areas of interests in which the density of distribution is high. In practice, the posterior distribution can be multimodal, and so that the existing MCMC techniques cannot provide the proportional sampling from the areas of interest. The lack of prior information makes MCMC integration more difficult when a model parameter space is large and cannot be explored in detail within a reasonable time. In particular, the lack of information about EEG feature importance can affect the results of Bayesian assessment of EEG maturity. In this paper we explore how the posterior information about EEG feature importance can be used to reduce a negative influence of disproportional sampling on the results of Bayesian assessment. We found that the MCMC integration tends to oversample the areas in which a model parameter space includes one or more features, the importance of which counted in terms of their posterior use is low. Using this finding, we proposed to cure the results of MCMC integration and then described the results of testing the proposed method on a set of sleep EEG recordings.en_GB
dc.language.isoenen
dc.publisherElsevieren_GB
dc.relation.urlhttp://linkinghub.elsevier.com/retrieve/pii/S0957417412004538en_GB
dc.rightsArchived with thanks to Expert Systems with Applicationsen_GB
dc.subjectG760 Machine Learningen_GB
dc.subjectelectroencephalogramen_GB
dc.subjectelectroencephalographyen_GB
dc.subjectMarkov Chain Monte Carlo integrationen_GB
dc.subjectMCMC integrationen_GB
dc.subjectEEG maturityen_GB
dc.subjectnewborn brain maturityen_GB
dc.titleClassification of newborn EEG maturity with Bayesian averaging over decision treesen
dc.typeArticleen
dc.identifier.journalExpert Systems with Applicationsen_GB
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.