About: Combining Individual and Global Tree-based Models in EEG Classification     Goto   Sponge   NotDistinct   Permalink

An Entity of Type : http://linked.opendata.cz/ontology/domain/vavai/Vysledek, within Data Space : linked.opendata.cz associated with source document(s)

AttributesValues
rdf:type
Description
  • The study is a part of a project aimed at preventing drivers’ microsleeps by detection of somnolence based on EEG spectra. Classification forests grown by the Random Forests method are used for classifying EEG segments, and distinguishing somnolence from other brain states. A novel approach to classifier (forest) construction is proposed: An individual model tailored for a single subject, using only the subject’s own data, may be combined with a global model trained on data of a number of different subjects. Combining is realized via a weighted average of votes for classes, where the weights result from a simple optimization procedure. A modification of OOB estimates was implemented in order to keep the misclassification error estimates unbiased. The results of a computational experiment with several hundreds of EEG spectra from 18 subjects prove the superiority of the mixed model over both of its components, i.e. individual and global models.
  • The study is a part of a project aimed at preventing drivers’ microsleeps by detection of somnolence based on EEG spectra. Classification forests grown by the Random Forests method are used for classifying EEG segments, and distinguishing somnolence from other brain states. A novel approach to classifier (forest) construction is proposed: An individual model tailored for a single subject, using only the subject’s own data, may be combined with a global model trained on data of a number of different subjects. Combining is realized via a weighted average of votes for classes, where the weights result from a simple optimization procedure. A modification of OOB estimates was implemented in order to keep the misclassification error estimates unbiased. The results of a computational experiment with several hundreds of EEG spectra from 18 subjects prove the superiority of the mixed model over both of its components, i.e. individual and global models. (en)
Title
  • Combining Individual and Global Tree-based Models in EEG Classification
  • Combining Individual and Global Tree-based Models in EEG Classification (en)
skos:prefLabel
  • Combining Individual and Global Tree-based Models in EEG Classification
  • Combining Individual and Global Tree-based Models in EEG Classification (en)
skos:notation
  • RIV/67985807:_____/08:00390801!RIV13-AV0-67985807
http://linked.open...avai/riv/aktivita
http://linked.open...avai/riv/aktivity
  • P(ME 701), Z(AV0Z10300504)
http://linked.open...vai/riv/dodaniDat
http://linked.open...aciTvurceVysledku
http://linked.open.../riv/druhVysledku
http://linked.open...iv/duvernostUdaju
http://linked.open...titaPredkladatele
http://linked.open...dnocenehoVysledku
  • 360422
http://linked.open...ai/riv/idVysledku
  • RIV/67985807:_____/08:00390801
http://linked.open...riv/jazykVysledku
http://linked.open.../riv/klicovaSlova
  • EEG spectra; classification forest; random forests; OOB estimates (en)
http://linked.open.../riv/klicoveSlovo
http://linked.open...ontrolniKodProRIV
  • [A826FD2E9CA2]
http://linked.open...v/mistoKonaniAkce
  • Lisboa
http://linked.open...i/riv/mistoVydani
  • Lisabon
http://linked.open...i/riv/nazevZdroje
  • Bulletin of the International Statistical Institute
http://linked.open...in/vavai/riv/obor
http://linked.open...ichTvurcuVysledku
http://linked.open...cetTvurcuVysledku
http://linked.open...vavai/riv/projekt
http://linked.open...UplatneniVysledku
http://linked.open...iv/tvurceVysledku
  • Klaschka, Jan
http://linked.open...vavai/riv/typAkce
http://linked.open.../riv/zahajeniAkce
http://linked.open...n/vavai/riv/zamer
number of pages
http://purl.org/ne...btex#hasPublisher
  • Instituto Nacional de Estatística
https://schema.org/isbn
  • 978-972-673-992-0
is http://linked.open...avai/riv/vysledek of
Faceted Search & Find service v1.16.118 as of Jun 21 2024


Alternative Linked Data Documents: ODE     Content Formats:   [cxml] [csv]     RDF   [text] [turtle] [ld+json] [rdf+json] [rdf+xml]     ODATA   [atom+xml] [odata+json]     Microdata   [microdata+json] [html]    About   
This material is Open Knowledge   W3C Semantic Web Technology [RDF Data] Valid XHTML + RDFa
OpenLink Virtuoso version 07.20.3240 as of Jun 21 2024, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (126 GB total memory, 58 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software