Outliers resistant methods for motor imagery classification

"Common spatial patterns analysis (CSP) and linear discriminant analysis (LDA) are widely used techniques for spatial filtering and classifying in motor imagery (MI). However, CSP is very sensitive to noise and artifacts. A method to detect and eliminate anomalous electroencephalogram (EGG) sig...

Descripción completa

Detalles Bibliográficos
Autor principal: Villar, Ana Julia
Formato: Ponencias en Congresos acceptedVersion
Lenguaje:Inglés
Publicado: 2019
Materias:
ELECTROENCEFALOGRAFIA
PROCESAMIENTO DE SEÑALES DIGITALES
Acceso en línea:http://ri.itba.edu.ar/handle/123456789/1636
Aporte de:
Repositorio Institucional Instituto Tecnológico de Buenos Aires (ITBA) de Instituto Tecnológico de Buenos Aires (ITBA)
id I32-R138-123456789-1636
record_format dspace
spelling I32-R138-123456789-16362022-12-07T14:13:46Z Outliers resistant methods for motor imagery classification Villar, Ana Julia ELECTROENCEFALOGRAFIA PROCESAMIENTO DE SEÑALES DIGITALES "Common spatial patterns analysis (CSP) and linear discriminant analysis (LDA) are widely used techniques for spatial filtering and classifying in motor imagery (MI). However, CSP is very sensitive to noise and artifacts. A method to detect and eliminate anomalous electroencephalogram (EGG) signals before applying CSP is presented. An outlier score of the signal is obtained by calculating the similarities with the other signals of the sample through the Bounded Coordinate System (BCS). Besides, it is proposed to replace the usual estimators of mean, covariance and scale, used in the algorithms, by Olive and Hawkins estimators to get robust versions of BCS and CSP. The assumption done in LDA that the covariance of each of the classes in MI are identical may not be true; if it is not satisfied, it is better to use quadratic discrimination. Tests to verify this hypothesis and decide which discriminant function must be used are considered. The performances of the methods are evaluated and compared on EGG data from BCI competition datasets; results show that robust methods outperformed classical techniques, especially for subjects with poor classification accuracy." 2019-07-05T19:51:27Z 2019-07-05T19:51:27Z 2018-08 Ponencias en Congresos info:eu-repo/semantics/acceptedVersion 978-1450-36-474-4 http://ri.itba.edu.ar/handle/123456789/1636 en info:eu-repo/semantics/altIdentifier/doi/10.1145 / 3264560.3264574 application/pdf
institution Instituto Tecnológico de Buenos Aires (ITBA)
institution_str I-32
repository_str R-138
collection Repositorio Institucional Instituto Tecnológico de Buenos Aires (ITBA)
language Inglés
topic ELECTROENCEFALOGRAFIA
PROCESAMIENTO DE SEÑALES DIGITALES
spellingShingle ELECTROENCEFALOGRAFIA
PROCESAMIENTO DE SEÑALES DIGITALES
Villar, Ana Julia
Outliers resistant methods for motor imagery classification
topic_facet ELECTROENCEFALOGRAFIA
PROCESAMIENTO DE SEÑALES DIGITALES
description "Common spatial patterns analysis (CSP) and linear discriminant analysis (LDA) are widely used techniques for spatial filtering and classifying in motor imagery (MI). However, CSP is very sensitive to noise and artifacts. A method to detect and eliminate anomalous electroencephalogram (EGG) signals before applying CSP is presented. An outlier score of the signal is obtained by calculating the similarities with the other signals of the sample through the Bounded Coordinate System (BCS). Besides, it is proposed to replace the usual estimators of mean, covariance and scale, used in the algorithms, by Olive and Hawkins estimators to get robust versions of BCS and CSP. The assumption done in LDA that the covariance of each of the classes in MI are identical may not be true; if it is not satisfied, it is better to use quadratic discrimination. Tests to verify this hypothesis and decide which discriminant function must be used are considered. The performances of the methods are evaluated and compared on EGG data from BCI competition datasets; results show that robust methods outperformed classical techniques, especially for subjects with poor classification accuracy."
format Ponencias en Congresos
acceptedVersion
author Villar, Ana Julia
author_facet Villar, Ana Julia
author_sort Villar, Ana Julia
title Outliers resistant methods for motor imagery classification
title_short Outliers resistant methods for motor imagery classification
title_full Outliers resistant methods for motor imagery classification
title_fullStr Outliers resistant methods for motor imagery classification
title_full_unstemmed Outliers resistant methods for motor imagery classification
title_sort outliers resistant methods for motor imagery classification
publishDate 2019
url http://ri.itba.edu.ar/handle/123456789/1636
work_keys_str_mv AT villaranajulia outliersresistantmethodsformotorimageryclassification
_version_ 1765661092116168704

Ejemplares similares