An evidence-based combining classifier for brain signal analysis.

Nowadays, brain signals are employed in various scientific and practical fields such as Medical Science, Cognitive Science, Neuroscience, and Brain Computer Interfaces. Hence, the need for robust signal analysis methods with adequate accuracy and generalizability is inevitable. The brain signal anal...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Saeed Reza Kheradpisheh, Abbas Nowzari-Dalini, Reza Ebrahimpour, Mohammad Ganjtabesh
Formato: article
Lenguaje:EN
Publicado: Public Library of Science (PLoS) 2014
Materias:
R
Q
Acceso en línea:https://doaj.org/article/890cfc6f649641549555d341ef2d180a
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:890cfc6f649641549555d341ef2d180a
record_format dspace
spelling oai:doaj.org-article:890cfc6f649641549555d341ef2d180a2021-11-18T08:39:06ZAn evidence-based combining classifier for brain signal analysis.1932-620310.1371/journal.pone.0084341https://doaj.org/article/890cfc6f649641549555d341ef2d180a2014-01-01T00:00:00Zhttps://www.ncbi.nlm.nih.gov/pmc/articles/pmid/24392125/pdf/?tool=EBIhttps://doaj.org/toc/1932-6203Nowadays, brain signals are employed in various scientific and practical fields such as Medical Science, Cognitive Science, Neuroscience, and Brain Computer Interfaces. Hence, the need for robust signal analysis methods with adequate accuracy and generalizability is inevitable. The brain signal analysis is faced with complex challenges including small sample size, high dimensionality and noisy signals. Moreover, because of the non-stationarity of brain signals and the impacts of mental states on brain function, the brain signals are associated with an inherent uncertainty. In this paper, an evidence-based combining classifiers method is proposed for brain signal analysis. This method exploits the power of combining classifiers for solving complex problems and the ability of evidence theory to model as well as to reduce the existing uncertainty. The proposed method models the uncertainty in the labels of training samples in each feature space by assigning soft and crisp labels to them. Then, some classifiers are employed to approximate the belief function corresponding to each feature space. By combining the evidence raised from each classifier through the evidence theory, more confident decisions about testing samples can be made. The obtained results by the proposed method compared to some other evidence-based and fixed rule combining methods on artificial and real datasets exhibit the ability of the proposed method in dealing with complex and uncertain classification problems.Saeed Reza KheradpishehAbbas Nowzari-DaliniReza EbrahimpourMohammad GanjtabeshPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 9, Iss 1, p e84341 (2014)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Saeed Reza Kheradpisheh
Abbas Nowzari-Dalini
Reza Ebrahimpour
Mohammad Ganjtabesh
An evidence-based combining classifier for brain signal analysis.
description Nowadays, brain signals are employed in various scientific and practical fields such as Medical Science, Cognitive Science, Neuroscience, and Brain Computer Interfaces. Hence, the need for robust signal analysis methods with adequate accuracy and generalizability is inevitable. The brain signal analysis is faced with complex challenges including small sample size, high dimensionality and noisy signals. Moreover, because of the non-stationarity of brain signals and the impacts of mental states on brain function, the brain signals are associated with an inherent uncertainty. In this paper, an evidence-based combining classifiers method is proposed for brain signal analysis. This method exploits the power of combining classifiers for solving complex problems and the ability of evidence theory to model as well as to reduce the existing uncertainty. The proposed method models the uncertainty in the labels of training samples in each feature space by assigning soft and crisp labels to them. Then, some classifiers are employed to approximate the belief function corresponding to each feature space. By combining the evidence raised from each classifier through the evidence theory, more confident decisions about testing samples can be made. The obtained results by the proposed method compared to some other evidence-based and fixed rule combining methods on artificial and real datasets exhibit the ability of the proposed method in dealing with complex and uncertain classification problems.
format article
author Saeed Reza Kheradpisheh
Abbas Nowzari-Dalini
Reza Ebrahimpour
Mohammad Ganjtabesh
author_facet Saeed Reza Kheradpisheh
Abbas Nowzari-Dalini
Reza Ebrahimpour
Mohammad Ganjtabesh
author_sort Saeed Reza Kheradpisheh
title An evidence-based combining classifier for brain signal analysis.
title_short An evidence-based combining classifier for brain signal analysis.
title_full An evidence-based combining classifier for brain signal analysis.
title_fullStr An evidence-based combining classifier for brain signal analysis.
title_full_unstemmed An evidence-based combining classifier for brain signal analysis.
title_sort evidence-based combining classifier for brain signal analysis.
publisher Public Library of Science (PLoS)
publishDate 2014
url https://doaj.org/article/890cfc6f649641549555d341ef2d180a
work_keys_str_mv AT saeedrezakheradpisheh anevidencebasedcombiningclassifierforbrainsignalanalysis
AT abbasnowzaridalini anevidencebasedcombiningclassifierforbrainsignalanalysis
AT rezaebrahimpour anevidencebasedcombiningclassifierforbrainsignalanalysis
AT mohammadganjtabesh anevidencebasedcombiningclassifierforbrainsignalanalysis
AT saeedrezakheradpisheh evidencebasedcombiningclassifierforbrainsignalanalysis
AT abbasnowzaridalini evidencebasedcombiningclassifierforbrainsignalanalysis
AT rezaebrahimpour evidencebasedcombiningclassifierforbrainsignalanalysis
AT mohammadganjtabesh evidencebasedcombiningclassifierforbrainsignalanalysis
_version_ 1718421512966373376