Pattern recognition with applications to pre-diagnosis of pathologies in the vocal tract

Detalhes bibliográficos
Autor(a) principal: Solgon Bassi, Regiane Denise
Data de Publicação: 2015
Outros Autores: Dezani, Henrique [UNESP], Silva Paulo, Kátia Cristina, Capobianco Guido, Rodrigo [UNESP], Nunes da Silva, Ivan, Marranghello, Norian [UNESP]
Tipo de documento: Artigo de conferência
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://dx.doi.org/10.1201/b18660-143
http://hdl.handle.net/11449/234382
Resumo: For the detection of laryngeal pathologies, in general medical examinations, for example laryngoscopy and stroboscopy, are adopted. Besides being considered invasive and uncomfortable procedures, they are made only by medical request when the diseases are already on advanced levels. In order to perform a computational pre-diagnosis of such conditions, this paper presents a non-invasive technique in which three classifiers are tested and compared: Euclidian distance, RBF Neural Network with the Gaussian kernel, and RBF Neural Network with the modified Gaussian kernel. Based on a database of normal and pathological voices, tests that demonstrate the effectiveness of the proposed technique, which can be implemented in real-time, were performed.
id UNSP_d512b7b6882bc97abdc5e0a98638cb8c
oai_identifier_str oai:repositorio.unesp.br:11449/234382
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Pattern recognition with applications to pre-diagnosis of pathologies in the vocal tractEuclidian distanceLarynx pathologiesRBF neural networksSignal processingFor the detection of laryngeal pathologies, in general medical examinations, for example laryngoscopy and stroboscopy, are adopted. Besides being considered invasive and uncomfortable procedures, they are made only by medical request when the diseases are already on advanced levels. In order to perform a computational pre-diagnosis of such conditions, this paper presents a non-invasive technique in which three classifiers are tested and compared: Euclidian distance, RBF Neural Network with the Gaussian kernel, and RBF Neural Network with the modified Gaussian kernel. Based on a database of normal and pathological voices, tests that demonstrate the effectiveness of the proposed technique, which can be implemented in real-time, were performed.University of São PauloNorth of São Paulo UniversitySão Paulo State UniversitySão Paulo State UniversityUniversidade de São Paulo (USP)Universidade Estadual Paulista (UNESP)Solgon Bassi, Regiane DeniseDezani, Henrique [UNESP]Silva Paulo, Kátia CristinaCapobianco Guido, Rodrigo [UNESP]Nunes da Silva, IvanMarranghello, Norian [UNESP]2022-05-02T13:30:31Z2022-05-02T13:30:31Z2015-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject645-648http://dx.doi.org/10.1201/b18660-143Network Security and Communication Engineering - Proceedings of the 2014 International Conference on Network Security and Communication Engineering, NSCE 2014, p. 645-648.http://hdl.handle.net/11449/23438210.1201/b18660-1432-s2.0-84961619752Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengNetwork Security and Communication Engineering - Proceedings of the 2014 International Conference on Network Security and Communication Engineering, NSCE 2014info:eu-repo/semantics/openAccess2022-05-02T13:30:32Zoai:repositorio.unesp.br:11449/234382Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462022-05-02T13:30:32Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Pattern recognition with applications to pre-diagnosis of pathologies in the vocal tract
title Pattern recognition with applications to pre-diagnosis of pathologies in the vocal tract
spellingShingle Pattern recognition with applications to pre-diagnosis of pathologies in the vocal tract
Solgon Bassi, Regiane Denise
Euclidian distance
Larynx pathologies
RBF neural networks
Signal processing
title_short Pattern recognition with applications to pre-diagnosis of pathologies in the vocal tract
title_full Pattern recognition with applications to pre-diagnosis of pathologies in the vocal tract
title_fullStr Pattern recognition with applications to pre-diagnosis of pathologies in the vocal tract
title_full_unstemmed Pattern recognition with applications to pre-diagnosis of pathologies in the vocal tract
title_sort Pattern recognition with applications to pre-diagnosis of pathologies in the vocal tract
author Solgon Bassi, Regiane Denise
author_facet Solgon Bassi, Regiane Denise
Dezani, Henrique [UNESP]
Silva Paulo, Kátia Cristina
Capobianco Guido, Rodrigo [UNESP]
Nunes da Silva, Ivan
Marranghello, Norian [UNESP]
author_role author
author2 Dezani, Henrique [UNESP]
Silva Paulo, Kátia Cristina
Capobianco Guido, Rodrigo [UNESP]
Nunes da Silva, Ivan
Marranghello, Norian [UNESP]
author2_role author
author
author
author
author
dc.contributor.none.fl_str_mv Universidade de São Paulo (USP)
Universidade Estadual Paulista (UNESP)
dc.contributor.author.fl_str_mv Solgon Bassi, Regiane Denise
Dezani, Henrique [UNESP]
Silva Paulo, Kátia Cristina
Capobianco Guido, Rodrigo [UNESP]
Nunes da Silva, Ivan
Marranghello, Norian [UNESP]
dc.subject.por.fl_str_mv Euclidian distance
Larynx pathologies
RBF neural networks
Signal processing
topic Euclidian distance
Larynx pathologies
RBF neural networks
Signal processing
description For the detection of laryngeal pathologies, in general medical examinations, for example laryngoscopy and stroboscopy, are adopted. Besides being considered invasive and uncomfortable procedures, they are made only by medical request when the diseases are already on advanced levels. In order to perform a computational pre-diagnosis of such conditions, this paper presents a non-invasive technique in which three classifiers are tested and compared: Euclidian distance, RBF Neural Network with the Gaussian kernel, and RBF Neural Network with the modified Gaussian kernel. Based on a database of normal and pathological voices, tests that demonstrate the effectiveness of the proposed technique, which can be implemented in real-time, were performed.
publishDate 2015
dc.date.none.fl_str_mv 2015-01-01
2022-05-02T13:30:31Z
2022-05-02T13:30:31Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/conferenceObject
format conferenceObject
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://dx.doi.org/10.1201/b18660-143
Network Security and Communication Engineering - Proceedings of the 2014 International Conference on Network Security and Communication Engineering, NSCE 2014, p. 645-648.
http://hdl.handle.net/11449/234382
10.1201/b18660-143
2-s2.0-84961619752
url http://dx.doi.org/10.1201/b18660-143
http://hdl.handle.net/11449/234382
identifier_str_mv Network Security and Communication Engineering - Proceedings of the 2014 International Conference on Network Security and Communication Engineering, NSCE 2014, p. 645-648.
10.1201/b18660-143
2-s2.0-84961619752
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Network Security and Communication Engineering - Proceedings of the 2014 International Conference on Network Security and Communication Engineering, NSCE 2014
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 645-648
dc.source.none.fl_str_mv Scopus
reponame:Repositório Institucional da UNESP
instname:Universidade Estadual Paulista (UNESP)
instacron:UNESP
instname_str Universidade Estadual Paulista (UNESP)
instacron_str UNESP
institution UNESP
reponame_str Repositório Institucional da UNESP
collection Repositório Institucional da UNESP
repository.name.fl_str_mv Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)
repository.mail.fl_str_mv
_version_ 1803046838509502464

Registros relacionados