A knowledge discovery methodology from EEG data for cyclic alternating pattern detection
Autor(a) principal: | |
---|---|
Data de Publicação: | 2018 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10316/107514 https://doi.org/10.1186/s12938-018-0616-z |
Resumo: | Background: Detection and quantification of cyclic alternating patterns (CAP) components has the potential to serve as a disease bio-marker. Few methods exist to discriminate all the different CAP components, they do not present appropriate sensitivities, and often they are evaluated based on accuracy (AC) that is not an appropriate measure for imbalanced datasets. Methods: We describe a knowledge discovery methodology in data (KDD) aiming the development of automatic CAP scoring approaches. Automatic CAP scoring was faced from two perspectives: the binary distinction between A-phases and B-phases, and also for multi-class classification of the different CAP components. The most important KDD stages are: extraction of 55 features, feature ranking/transformation, and classification. Classification is performed by (i) support vector machine (SVM), (ii) k-nearest neighbors (k-NN), and (iii) discriminant analysis. We report the weighted accuracy (WAC) that accounts for class imbalance. Results: The study includes 30 subjects from the CAP Sleep Database of Physionet. The best alternative for the discrimination of the different A-phase subtypes involved feature ranking by the minimum redundancy maximum relevance algorithm (mRMR) and classification by SVM, with a WAC of 51%. Concerning the binary discrimination between A-phases and B-phases, k-NN with mRMR ranking achieved the best WAC of 80%. Conclusions: We describe a KDD that, to the best of our knowledge, was for the first time applied to CAP scoring. In particular, the fully discrimination of the three different A-phases subtypes is a new perspective, since past works tried multi-class approaches but based on grouping of different sub-types. We also considered the weighted accuracy, in addition to simple accuracy, resulting in a more trustworthy performance assessment. Globally, better subtype sensitivities than other published approaches were achieved. |
id |
RCAP_6d1b2e240f9e92be3aee6e973740ae85 |
---|---|
oai_identifier_str |
oai:estudogeral.uc.pt:10316/107514 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
A knowledge discovery methodology from EEG data for cyclic alternating pattern detectionCyclic alternating patternA-phase detectionEEG processingKnowledge discovery in dataAdolescentAdultAgedDiscriminant AnalysisFemaleHumansMaleMiddle AgedPattern Recognition, AutomatedSleep StagesSupport Vector MachineYoung AdultElectroencephalographySignal Processing, Computer-AssistedBackground: Detection and quantification of cyclic alternating patterns (CAP) components has the potential to serve as a disease bio-marker. Few methods exist to discriminate all the different CAP components, they do not present appropriate sensitivities, and often they are evaluated based on accuracy (AC) that is not an appropriate measure for imbalanced datasets. Methods: We describe a knowledge discovery methodology in data (KDD) aiming the development of automatic CAP scoring approaches. Automatic CAP scoring was faced from two perspectives: the binary distinction between A-phases and B-phases, and also for multi-class classification of the different CAP components. The most important KDD stages are: extraction of 55 features, feature ranking/transformation, and classification. Classification is performed by (i) support vector machine (SVM), (ii) k-nearest neighbors (k-NN), and (iii) discriminant analysis. We report the weighted accuracy (WAC) that accounts for class imbalance. Results: The study includes 30 subjects from the CAP Sleep Database of Physionet. The best alternative for the discrimination of the different A-phase subtypes involved feature ranking by the minimum redundancy maximum relevance algorithm (mRMR) and classification by SVM, with a WAC of 51%. Concerning the binary discrimination between A-phases and B-phases, k-NN with mRMR ranking achieved the best WAC of 80%. Conclusions: We describe a KDD that, to the best of our knowledge, was for the first time applied to CAP scoring. In particular, the fully discrimination of the three different A-phases subtypes is a new perspective, since past works tried multi-class approaches but based on grouping of different sub-types. We also considered the weighted accuracy, in addition to simple accuracy, resulting in a more trustworthy performance assessment. Globally, better subtype sensitivities than other published approaches were achieved.Springer Nature2018-12-18info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://hdl.handle.net/10316/107514http://hdl.handle.net/10316/107514https://doi.org/10.1186/s12938-018-0616-zeng1475-925XMachado, FátimaSales, FranciscoSantos, ClaraDourado, AntónioTeixeira, C. A.info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-07-18T09:26:51Zoai:estudogeral.uc.pt:10316/107514Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T21:23:51.678052Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
A knowledge discovery methodology from EEG data for cyclic alternating pattern detection |
title |
A knowledge discovery methodology from EEG data for cyclic alternating pattern detection |
spellingShingle |
A knowledge discovery methodology from EEG data for cyclic alternating pattern detection Machado, Fátima Cyclic alternating pattern A-phase detection EEG processing Knowledge discovery in data Adolescent Adult Aged Discriminant Analysis Female Humans Male Middle Aged Pattern Recognition, Automated Sleep Stages Support Vector Machine Young Adult Electroencephalography Signal Processing, Computer-Assisted |
title_short |
A knowledge discovery methodology from EEG data for cyclic alternating pattern detection |
title_full |
A knowledge discovery methodology from EEG data for cyclic alternating pattern detection |
title_fullStr |
A knowledge discovery methodology from EEG data for cyclic alternating pattern detection |
title_full_unstemmed |
A knowledge discovery methodology from EEG data for cyclic alternating pattern detection |
title_sort |
A knowledge discovery methodology from EEG data for cyclic alternating pattern detection |
author |
Machado, Fátima |
author_facet |
Machado, Fátima Sales, Francisco Santos, Clara Dourado, António Teixeira, C. A. |
author_role |
author |
author2 |
Sales, Francisco Santos, Clara Dourado, António Teixeira, C. A. |
author2_role |
author author author author |
dc.contributor.author.fl_str_mv |
Machado, Fátima Sales, Francisco Santos, Clara Dourado, António Teixeira, C. A. |
dc.subject.por.fl_str_mv |
Cyclic alternating pattern A-phase detection EEG processing Knowledge discovery in data Adolescent Adult Aged Discriminant Analysis Female Humans Male Middle Aged Pattern Recognition, Automated Sleep Stages Support Vector Machine Young Adult Electroencephalography Signal Processing, Computer-Assisted |
topic |
Cyclic alternating pattern A-phase detection EEG processing Knowledge discovery in data Adolescent Adult Aged Discriminant Analysis Female Humans Male Middle Aged Pattern Recognition, Automated Sleep Stages Support Vector Machine Young Adult Electroencephalography Signal Processing, Computer-Assisted |
description |
Background: Detection and quantification of cyclic alternating patterns (CAP) components has the potential to serve as a disease bio-marker. Few methods exist to discriminate all the different CAP components, they do not present appropriate sensitivities, and often they are evaluated based on accuracy (AC) that is not an appropriate measure for imbalanced datasets. Methods: We describe a knowledge discovery methodology in data (KDD) aiming the development of automatic CAP scoring approaches. Automatic CAP scoring was faced from two perspectives: the binary distinction between A-phases and B-phases, and also for multi-class classification of the different CAP components. The most important KDD stages are: extraction of 55 features, feature ranking/transformation, and classification. Classification is performed by (i) support vector machine (SVM), (ii) k-nearest neighbors (k-NN), and (iii) discriminant analysis. We report the weighted accuracy (WAC) that accounts for class imbalance. Results: The study includes 30 subjects from the CAP Sleep Database of Physionet. The best alternative for the discrimination of the different A-phase subtypes involved feature ranking by the minimum redundancy maximum relevance algorithm (mRMR) and classification by SVM, with a WAC of 51%. Concerning the binary discrimination between A-phases and B-phases, k-NN with mRMR ranking achieved the best WAC of 80%. Conclusions: We describe a KDD that, to the best of our knowledge, was for the first time applied to CAP scoring. In particular, the fully discrimination of the three different A-phases subtypes is a new perspective, since past works tried multi-class approaches but based on grouping of different sub-types. We also considered the weighted accuracy, in addition to simple accuracy, resulting in a more trustworthy performance assessment. Globally, better subtype sensitivities than other published approaches were achieved. |
publishDate |
2018 |
dc.date.none.fl_str_mv |
2018-12-18 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10316/107514 http://hdl.handle.net/10316/107514 https://doi.org/10.1186/s12938-018-0616-z |
url |
http://hdl.handle.net/10316/107514 https://doi.org/10.1186/s12938-018-0616-z |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
1475-925X |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Springer Nature |
publisher.none.fl_str_mv |
Springer Nature |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799134124540166144 |