Diffuse outlier time series detection technique for functional magnetic resonance imaging

Autores
Giacomantone, Javier; Tarutina, Tatiana; De Giusti, Armando Eduardo
Año de publicación
2010
Idioma
español castellano
Tipo de recurso
documento de conferencia
Estado
versión publicada
Descripción
We propose a new support vector machine (SVM) based method that improves the time series classi cation in magnetic resonance imaging (fMRI). We exploit the robust anisotropic di usion (RAD) technique to increase the classi cation performance of the one class support vector machine by taking into account the hypothesis of spatial relationship between active voxels. The proposed method was called Di use One Class Support Vector Machine (DOCSVM). DOCSVM method treats activated voxels as outliers and applies one class support vector machine to generate an activation map and RAD to include the neighborhood hypothesis, improving the classi cation and reducing the iteration steps with respect to RADSPM. We give a brief review of the main methods, present receiver operating characteristic (ROC) results and conclude suggesting further research alternatives.
Presentado en el I Workshop Procesamiento de señales y Sistemas de Tiempo Real (WPSTR)
Red de Universidades con Carreras en Informática (RedUNCI)
Materia
Ciencias Informáticas
Time Series
Functional Magnetic Resonance Imaging
classification
Support Vector Machines
Robust Anisotropic Diffusión
Time series analysis
Nivel de accesibilidad
acceso abierto
Condiciones de uso
http://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
SEDICI (UNLP)
Institución
Universidad Nacional de La Plata
OAI Identificador
oai:sedici.unlp.edu.ar:10915/19379

id SEDICI_3c3aacb0e7a60b4815624e884f612b0a
oai_identifier_str oai:sedici.unlp.edu.ar:10915/19379
network_acronym_str SEDICI
repository_id_str 1329
network_name_str SEDICI (UNLP)
spelling Diffuse outlier time series detection technique for functional magnetic resonance imagingGiacomantone, JavierTarutina, TatianaDe Giusti, Armando EduardoCiencias InformáticasTime SeriesFunctional Magnetic Resonance ImagingclassificationSupport Vector MachinesRobust Anisotropic DiffusiónTime series analysisWe propose a new support vector machine (SVM) based method that improves the time series classi cation in magnetic resonance imaging (fMRI). We exploit the robust anisotropic di usion (RAD) technique to increase the classi cation performance of the one class support vector machine by taking into account the hypothesis of spatial relationship between active voxels. The proposed method was called Di use One Class Support Vector Machine (DOCSVM). DOCSVM method treats activated voxels as outliers and applies one class support vector machine to generate an activation map and RAD to include the neighborhood hypothesis, improving the classi cation and reducing the iteration steps with respect to RADSPM. We give a brief review of the main methods, present receiver operating characteristic (ROC) results and conclude suggesting further research alternatives.Presentado en el I Workshop Procesamiento de señales y Sistemas de Tiempo Real (WPSTR)Red de Universidades con Carreras en Informática (RedUNCI)2010-10info:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/publishedVersionObjeto de conferenciahttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdf990-998http://sedici.unlp.edu.ar/handle/10915/19379spainfo:eu-repo/semantics/altIdentifier/isbn/978-950-9474-49-9info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-sa/2.5/ar/Creative Commons Attribution-NonCommercial-ShareAlike 2.5 Argentina (CC BY-NC-SA 2.5)reponame:SEDICI (UNLP)instname:Universidad Nacional de La Platainstacron:UNLP2025-09-29T10:53:51Zoai:sedici.unlp.edu.ar:10915/19379Institucionalhttp://sedici.unlp.edu.ar/Universidad públicaNo correspondehttp://sedici.unlp.edu.ar/oai/snrdalira@sedici.unlp.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:13292025-09-29 10:53:51.784SEDICI (UNLP) - Universidad Nacional de La Platafalse
dc.title.none.fl_str_mv Diffuse outlier time series detection technique for functional magnetic resonance imaging
title Diffuse outlier time series detection technique for functional magnetic resonance imaging
spellingShingle Diffuse outlier time series detection technique for functional magnetic resonance imaging
Giacomantone, Javier
Ciencias Informáticas
Time Series
Functional Magnetic Resonance Imaging
classification
Support Vector Machines
Robust Anisotropic Diffusión
Time series analysis
title_short Diffuse outlier time series detection technique for functional magnetic resonance imaging
title_full Diffuse outlier time series detection technique for functional magnetic resonance imaging
title_fullStr Diffuse outlier time series detection technique for functional magnetic resonance imaging
title_full_unstemmed Diffuse outlier time series detection technique for functional magnetic resonance imaging
title_sort Diffuse outlier time series detection technique for functional magnetic resonance imaging
dc.creator.none.fl_str_mv Giacomantone, Javier
Tarutina, Tatiana
De Giusti, Armando Eduardo
author Giacomantone, Javier
author_facet Giacomantone, Javier
Tarutina, Tatiana
De Giusti, Armando Eduardo
author_role author
author2 Tarutina, Tatiana
De Giusti, Armando Eduardo
author2_role author
author
dc.subject.none.fl_str_mv Ciencias Informáticas
Time Series
Functional Magnetic Resonance Imaging
classification
Support Vector Machines
Robust Anisotropic Diffusión
Time series analysis
topic Ciencias Informáticas
Time Series
Functional Magnetic Resonance Imaging
classification
Support Vector Machines
Robust Anisotropic Diffusión
Time series analysis
dc.description.none.fl_txt_mv We propose a new support vector machine (SVM) based method that improves the time series classi cation in magnetic resonance imaging (fMRI). We exploit the robust anisotropic di usion (RAD) technique to increase the classi cation performance of the one class support vector machine by taking into account the hypothesis of spatial relationship between active voxels. The proposed method was called Di use One Class Support Vector Machine (DOCSVM). DOCSVM method treats activated voxels as outliers and applies one class support vector machine to generate an activation map and RAD to include the neighborhood hypothesis, improving the classi cation and reducing the iteration steps with respect to RADSPM. We give a brief review of the main methods, present receiver operating characteristic (ROC) results and conclude suggesting further research alternatives.
Presentado en el I Workshop Procesamiento de señales y Sistemas de Tiempo Real (WPSTR)
Red de Universidades con Carreras en Informática (RedUNCI)
description We propose a new support vector machine (SVM) based method that improves the time series classi cation in magnetic resonance imaging (fMRI). We exploit the robust anisotropic di usion (RAD) technique to increase the classi cation performance of the one class support vector machine by taking into account the hypothesis of spatial relationship between active voxels. The proposed method was called Di use One Class Support Vector Machine (DOCSVM). DOCSVM method treats activated voxels as outliers and applies one class support vector machine to generate an activation map and RAD to include the neighborhood hypothesis, improving the classi cation and reducing the iteration steps with respect to RADSPM. We give a brief review of the main methods, present receiver operating characteristic (ROC) results and conclude suggesting further research alternatives.
publishDate 2010
dc.date.none.fl_str_mv 2010-10
dc.type.none.fl_str_mv info:eu-repo/semantics/conferenceObject
info:eu-repo/semantics/publishedVersion
Objeto de conferencia
http://purl.org/coar/resource_type/c_5794
info:ar-repo/semantics/documentoDeConferencia
format conferenceObject
status_str publishedVersion
dc.identifier.none.fl_str_mv http://sedici.unlp.edu.ar/handle/10915/19379
url http://sedici.unlp.edu.ar/handle/10915/19379
dc.language.none.fl_str_mv spa
language spa
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/isbn/978-950-9474-49-9
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Creative Commons Attribution-NonCommercial-ShareAlike 2.5 Argentina (CC BY-NC-SA 2.5)
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Creative Commons Attribution-NonCommercial-ShareAlike 2.5 Argentina (CC BY-NC-SA 2.5)
dc.format.none.fl_str_mv application/pdf
990-998
dc.source.none.fl_str_mv reponame:SEDICI (UNLP)
instname:Universidad Nacional de La Plata
instacron:UNLP
reponame_str SEDICI (UNLP)
collection SEDICI (UNLP)
instname_str Universidad Nacional de La Plata
instacron_str UNLP
institution UNLP
repository.name.fl_str_mv SEDICI (UNLP) - Universidad Nacional de La Plata
repository.mail.fl_str_mv alira@sedici.unlp.edu.ar
_version_ 1844615795035865088
score 13.070432