Publicação

Accuracy Optimization in Speech Pathology Diagnosis with Data Preprocessing Techniques

Ver documento

Detalhes bibliográficos
Resumo:Using acoustic analysis to classify and identify speech disorders noninvasively can reduce waiting times for patients and specialists while also increasing the accuracy of diagnoses. In order to identify models to use in a vocal disease diagnosis system, we want to know which models have higher success rates in distinguishing between healthy and pathological sounds. For this purpose, 708 diseased people spread throughout 19 pathologies, and 194 control people were used. There are nine sound files per subject, three vowels in three tones, for each subject. From each sound file, 13 parameters were extracted. For the classification of healthy/pathological individuals, a variety of classifiers based on Machine Learning models were used, including decision trees, discriminant analyses, logistic regression classifiers, naive Bayes classifiers, support vector machines, classifiers of closely related variables, ensemble classifiers and artificial neural network classifiers. For each patient, 118 parameters were used initially. The first analysis aimed to find the best classifier, thus obtaining an accuracy of 81.3% for the Ensemble Sub-space Discriminant classifier. The second and third analyses aimed to improve ground accuracy using preprocessingmethodologies. Therefore, in the second analysis, the PCA technique was used, with an accuracy of 80.2%. The third analysis combined several outlier treatment models with several data normalizationmodels and, in general, accuracy improved, obtaining the best accuracy (82.9%) with the combination of the Greebs model for outliers treatment and the range model for the normalization of data procedure.
Autores principais:Fernandes, Joana Filipa Teixeira
Outros Autores:Freitas, Diamantino Rui; Teixeira, João Paulo
Assunto:Outliers Normalization Speech Pathologies Speech Features Machine Learning Vocal Acoustic Analysis
Ano:2024
País:Portugal
Tipo de documento:comunicação em conferência
Tipo de acesso:acesso aberto
Instituição associada:Instituto Politécnico de Bragança
Idioma:inglês
Origem:Biblioteca Digital do IPB
_version_ 1867173073115938816
author Fernandes, Joana Filipa Teixeira
author2 Freitas, Diamantino Rui
Teixeira, João Paulo
author2_role author
author
author_facet Fernandes, Joana Filipa Teixeira
Freitas, Diamantino Rui
Teixeira, João Paulo
author_role author
contributor_name_str_mv Biblioteca Digital do IPB
country_str PT
creators_json_txt [{\"Person.name\":\"Fernandes, Joana Filipa Teixeira\",\"Person.identifier.orcid\":\"0000-0002-0618-4627\"},{\"Person.name\":\"Freitas, Diamantino Rui\"},{\"Person.name\":\"Teixeira, João Paulo\",\"Person.identifier.orcid\":\"0000-0002-6679-5702\"}]
datacite.contributors.contributor.contributorName.fl_str_mv Biblioteca Digital do IPB
datacite.creators.creator.creatorName.fl_str_mv Fernandes, Joana Filipa Teixeira
Freitas, Diamantino Rui
Teixeira, João Paulo
datacite.date.Accepted.fl_str_mv 2024-01-01T00:00:00Z
datacite.date.available.fl_str_mv 2024-10-07T10:59:18Z
datacite.date.embargoed.fl_str_mv 2024-10-07T10:59:18Z
datacite.rights.fl_str_mv http://purl.org/coar/access_right/c_abf2
datacite.subjects.subject.fl_str_mv Outliers
Normalization
Speech Pathologies
Speech Features
Machine Learning
Vocal Acoustic Analysis
datacite.titles.title.fl_str_mv Accuracy Optimization in Speech Pathology Diagnosis with Data Preprocessing Techniques
dc.contributor.none.fl_str_mv Biblioteca Digital do IPB
dc.creator.none.fl_str_mv Fernandes, Joana Filipa Teixeira
Freitas, Diamantino Rui
Teixeira, João Paulo
dc.date.Accepted.fl_str_mv 2024-01-01T00:00:00Z
dc.date.available.fl_str_mv 2024-10-07T10:59:18Z
dc.date.embargoed.fl_str_mv 2024-10-07T10:59:18Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv http://hdl.handle.net/10198/30321
dc.language.none.fl_str_mv eng
dc.publisher.none.fl_str_mv Springer Nature
dc.rights.cclincense.fl_str_mv http://creativecommons.org/licenses/by/4.0/
dc.rights.none.fl_str_mv http://purl.org/coar/access_right/c_abf2
dc.subject.none.fl_str_mv Outliers
Normalization
Speech Pathologies
Speech Features
Machine Learning
Vocal Acoustic Analysis
dc.title.fl_str_mv Accuracy Optimization in Speech Pathology Diagnosis with Data Preprocessing Techniques
dc.type.none.fl_str_mv http://purl.org/coar/resource_type/c_5794
description Using acoustic analysis to classify and identify speech disorders noninvasively can reduce waiting times for patients and specialists while also increasing the accuracy of diagnoses. In order to identify models to use in a vocal disease diagnosis system, we want to know which models have higher success rates in distinguishing between healthy and pathological sounds. For this purpose, 708 diseased people spread throughout 19 pathologies, and 194 control people were used. There are nine sound files per subject, three vowels in three tones, for each subject. From each sound file, 13 parameters were extracted. For the classification of healthy/pathological individuals, a variety of classifiers based on Machine Learning models were used, including decision trees, discriminant analyses, logistic regression classifiers, naive Bayes classifiers, support vector machines, classifiers of closely related variables, ensemble classifiers and artificial neural network classifiers. For each patient, 118 parameters were used initially. The first analysis aimed to find the best classifier, thus obtaining an accuracy of 81.3% for the Ensemble Sub-space Discriminant classifier. The second and third analyses aimed to improve ground accuracy using preprocessingmethodologies. Therefore, in the second analysis, the PCA technique was used, with an accuracy of 80.2%. The third analysis combined several outlier treatment models with several data normalizationmodels and, in general, accuracy improved, obtaining the best accuracy (82.9%) with the combination of the Greebs model for outliers treatment and the range model for the normalization of data procedure.
dirty 0
eu_rights_str_mv openAccess
format conferencePaper
fulltext.url.fl_str_mv https://bibliotecadigital.ipb.pt/bitstreams/ba1b6f51-be5f-46d5-ab44-c3271745974d/download
funding.funder.alternateName_str_mv FCT
FCT
FCT
FCT
funding.funder.identifier_str_mv http://doi.org/10.13039/501100001871
http://doi.org/10.13039/501100001871
http://doi.org/10.13039/501100001871
http://doi.org/10.13039/501100001871
funding.funder.name_str_mv Fundação para a Ciência e a Tecnologia
Fundação para a Ciência e a Tecnologia
Fundação para a Ciência e a Tecnologia
Fundação para a Ciência e a Tecnologia
funding.identifier_str_mv UIDB/05757/2020
UIDP/05757/2020
LA/P/0007/2020
2021.04729.BD
funding.name_str_mv 6817 - DCRRNI ID
6817 - DCRRNI ID
6817 - DCRRNI ID
OE
funding_str_mv UIDB/05757/2020
info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F05757%2F2020/PT
UIDP/05757/2020
info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDP%2F05757%2F2020/PT
LA/P/0007/2020
info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/LA%2FP%2F0007%2F2020/PT
2021.04729.BD
info:eu-repo/grantAgreement/FCT/OE/2021.04729.BD/PT
id ipb_e812fe95aa5752a711fc83f3b85fa721
identifier.url.fl_str_mv http://hdl.handle.net/10198/30321
instacron_str ipb
institution Instituto Politécnico de Bragança
instname_str Instituto Politécnico de Bragança
language eng
network_acronym_str ipb
network_name_str Biblioteca Digital do IPB
oai_identifier_str oai:bibliotecadigital.ipb.pt:10198/30321
organization_str_mv urn:organizationAcronym:ipb
person_str_mv Fernandes, Joana Filipa Teixeira
Fernandes, Joana Filipa Teixeira
https://www.ciencia-id.pt/AE12-440A-299D
AE12-440A-299D
http://orcid.org/0000-0002-0618-4627
0000-0002-0618-4627
Freitas, Diamantino Rui
Teixeira, João Paulo
Teixeira, João Paulo
https://www.ciencia-id.pt/4F15-B322-59B4
4F15-B322-59B4
http://orcid.org/0000-0002-6679-5702
0000-0002-6679-5702
publishDate 2024
publisher.none.fl_str_mv Springer Nature
reponame_str Biblioteca Digital do IPB
repository_id_str urn:repositoryAcronym:ipb
service_str_mv urn:repositoryAcronym:ipb
spelling engSpringer Naturept_PTUsing acoustic analysis to classify and identify speech disorders noninvasively can reduce waiting times for patients and specialists while also increasing the accuracy of diagnoses. In order to identify models to use in a vocal disease diagnosis system, we want to know which models have higher success rates in distinguishing between healthy and pathological sounds. For this purpose, 708 diseased people spread throughout 19 pathologies, and 194 control people were used. There are nine sound files per subject, three vowels in three tones, for each subject. From each sound file, 13 parameters were extracted. For the classification of healthy/pathological individuals, a variety of classifiers based on Machine Learning models were used, including decision trees, discriminant analyses, logistic regression classifiers, naive Bayes classifiers, support vector machines, classifiers of closely related variables, ensemble classifiers and artificial neural network classifiers. For each patient, 118 parameters were used initially. The first analysis aimed to find the best classifier, thus obtaining an accuracy of 81.3% for the Ensemble Sub-space Discriminant classifier. The second and third analyses aimed to improve ground accuracy using preprocessingmethodologies. Therefore, in the second analysis, the PCA technique was used, with an accuracy of 80.2%. The third analysis combined several outlier treatment models with several data normalizationmodels and, in general, accuracy improved, obtaining the best accuracy (82.9%) with the combination of the Greebs model for outliers treatment and the range model for the normalization of data procedure.application/pdfpt_PTAccuracy Optimization in Speech Pathology Diagnosis with Data Preprocessing TechniquesPersonalFernandes, Joana Filipa TeixeiraDSpacehttp://dspace.org/items/a6f7a119-fbc9-439f-8dd9-0bbc9ec82fadDSpacehttp://dspace.org/items/a6f7a119-fbc9-439f-8dd9-0bbc9ec82fadFernandesJoana Filipa TeixeiraCiência IDhttps://www.ciencia-id.ptAE12-440A-299DORCIDhttp://orcid.org0000-0002-0618-4627Freitas, Diamantino RuiPersonalTeixeira, João PauloDSpacehttp://dspace.org/items/33f4af65-7ddf-46f0-8b44-a7470a8ba2bfDSpacehttp://dspace.org/items/33f4af65-7ddf-46f0-8b44-a7470a8ba2bfTeixeiraJoão PauloCiência IDhttps://www.ciencia-id.pt4F15-B322-59B4ORCIDhttp://orcid.org0000-0002-6679-5702Researcher IDhttps://www.researcherid.comN-6576-2013Scopus Author IDhttps://www.scopus.com57069567500HostingInstitutionOrganizationalBiblioteca Digital do IPBe-mailmailto:dspace@ipb.ptdspace@ipb.ptISBNIsPartOf978-3-031-53024-1ISBNIsPartOf978-3-031-53025-8DOIIsPartOf10.1007/978-3-031-53025-8_202024-10-07T10:59:18Z20242024-01-01T00:00:00ZHandlehttp://hdl.handle.net/10198/30321http://purl.org/coar/access_right/c_abf2open accessOutliersNormalizationSpeech PathologiesSpeech FeaturesMachine LearningVocal Acoustic Analysis615241 bytesFundação para a Ciência e a TecnologiaResearch Centre in Digitalization and Intelligent Roboticsinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F05757%2F2020/PTUIDB/05757/20206817 - DCRRNI IDCrossref Funder IDhttp://doi.org/10.13039/501100001871Fundação para a Ciência e a TecnologiaResearch Centre in Digitalization and Intelligent Roboticsinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDP%2F05757%2F2020/PTUIDP/05757/20206817 - DCRRNI IDCrossref Funder IDhttp://doi.org/10.13039/501100001871Fundação para a Ciência e a TecnologiaAssociate Laboratory for Sustainability and Tecnology in Mountain Regionsinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/LA%2FP%2F0007%2F2020/PTLA/P/0007/20206817 - DCRRNI IDCrossref Funder IDhttp://doi.org/10.13039/501100001871Fundação para a Ciência e a TecnologiaSistema de Apoio ao Diagnóstico de Patologias Vocaisinfo:eu-repo/grantAgreement/FCT/OE/2021.04729.BD/PT2021.04729.BDOECrossref Funder IDhttp://doi.org/10.13039/501100001871other research producthttp://purl.org/coar/resource_type/c_5794conference paper2024http://creativecommons.org/licenses/by/4.0/http://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://bibliotecadigital.ipb.pt/bitstreams/ba1b6f51-be5f-46d5-ab44-c3271745974d/download287299
spellingShingle Accuracy Optimization in Speech Pathology Diagnosis with Data Preprocessing Techniques
Fernandes, Joana Filipa Teixeira
Outliers
Normalization
Speech Pathologies
Speech Features
Machine Learning
Vocal Acoustic Analysis
status SINGLETON
subject.fl_str_mv Outliers
Normalization
Speech Pathologies
Speech Features
Machine Learning
Vocal Acoustic Analysis
title Accuracy Optimization in Speech Pathology Diagnosis with Data Preprocessing Techniques
title_full Accuracy Optimization in Speech Pathology Diagnosis with Data Preprocessing Techniques
title_fullStr Accuracy Optimization in Speech Pathology Diagnosis with Data Preprocessing Techniques
title_full_unstemmed Accuracy Optimization in Speech Pathology Diagnosis with Data Preprocessing Techniques
title_short Accuracy Optimization in Speech Pathology Diagnosis with Data Preprocessing Techniques
title_sort Accuracy Optimization in Speech Pathology Diagnosis with Data Preprocessing Techniques
topic Outliers
Normalization
Speech Pathologies
Speech Features
Machine Learning
Vocal Acoustic Analysis
topic_facet Outliers
Normalization
Speech Pathologies
Speech Features
Machine Learning
Vocal Acoustic Analysis
url http://hdl.handle.net/10198/30321
visible 1

Atividades financiadas

Carregando projetos financiados...