Repository logo
 
Publication

Outliers treatment to improve the recognition of voice pathologies

2019Conference paper Open access
Simple item page
dc.contributor.authorSilva, Letícia
dc.contributor.authorHermsdorf, Juliana
dc.contributor.authorGuedes, Victor
dc.contributor.authorTeixeira, Felipe
dc.contributor.authorFernandes, Joana Filipa Teixeira
dc.contributor.authorBispo, Bruno
dc.contributor.authorTeixeira, João Paulo
dc.date.accessioned2020-04-23T09:27:03Z
dc.date.available2020-04-23T09:27:03Z
dc.date.issued2019
dc.description.abstractIn some of the processes used in data analysis, such as the recognition of pathologies and pathological subjects, the presence of anomalous instances in the dataset is an unfavorable situation that can lead to misleading results. This article presents a function that implements the identification of anomalies in dataset using the boxplot and standard deviation methods. Also was used the filling technique to treat these anomalies, in which the anomalous point value were substituted by a limit value determined by the boxplot or standard deviation methods. To improve the outliers methods some normalization processes based on the z-score, logarithmic and squared root methodologies were experimented. These outliers treatment were applied to the dataset used in the recognition of vocal pathologies (dysphonia, chronic laryngitis and vocal cords paralysis vs control), performed by a MLP and LSTM neural networks. After the experiments, both the standard deviation and the boxplot methods with z-score normalization showed very useful for pre-processing the dataset for voice pathologies recognition. The accuracy was improved between 3 and 13 points in percentage.pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.citationSilva, Letícia; Hermsdorf, Juliana; Guedes, Victor; Teixeira, Felipe; Fernandes, Joana; Bispo, Bruno; Teixeira, João Paulo (2019). Outliers treatment to improve the recognition of voice pathologies. In International Conference on ENTERprise Information Systems. Tunisia. 164, p. 678-685pt_PT
dc.identifier.doi10.1016/j.procs.2019.12.235pt_PT
dc.identifier.urihttp://hdl.handle.net/10198/21794
dc.language.isodeupt_PT
dc.peerreviewedyespt_PT
dc.publisherElsevierpt_PT
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/pt_PT
dc.subjectStandard deviationpt_PT
dc.subjectBox plotpt_PT
dc.subjectZ-score normalizationpt_PT
dc.subjectLogaritmic normalizationpt_PT
dc.subjectSquared root normalizationpt_PT
dc.subjectLSTMpt_PT
dc.subjectMLPpt_PT
dc.titleOutliers treatment to improve the recognition of voice pathologiespt_PT
dc.typeconference paper
dspace.entity.typePublication
oaire.citation.conferencePlaceTunisiapt_PT
oaire.citation.endPage685pt_PT
oaire.citation.startPage678pt_PT
oaire.citation.titleInternational Conference on ENTERprise Information Systemspt_PT
oaire.citation.volume164pt_PT
person.familyNameSilva
person.familyNameTeixeira
person.familyNameFernandes
person.familyNameTeixeira
person.givenNameLetícia
person.givenNameFelipe
person.givenNameJoana Filipa Teixeira
person.givenNameJoão Paulo
person.identifierABC-9055-2020
person.identifier663194
person.identifier.ciencia-idC01E-87BA-67D7
person.identifier.ciencia-id0E17-62FB-AA17
person.identifier.ciencia-idAE12-440A-299D
person.identifier.ciencia-id4F15-B322-59B4
person.identifier.orcid0000-0003-3812-2794
person.identifier.orcid0000-0002-0618-4627
person.identifier.orcid0000-0002-6679-5702
person.identifier.ridN-6576-2013
person.identifier.scopus-author-id57069567500
rcaap.rightsopenAccesspt_PT
rcaap.typeconferenceObjectpt_PT
relation.isAuthorOfPublicationa2aa1be8-574c-4e0b-afd6-d3c61efad820
relation.isAuthorOfPublication764c5209-b9ab-479e-b5be-59fbe07c784b
relation.isAuthorOfPublicationa6f7a119-fbc9-439f-8dd9-0bbc9ec82fad
relation.isAuthorOfPublication33f4af65-7ddf-46f0-8b44-a7470a8ba2bf
relation.isAuthorOfPublication.latestForDiscoverya2aa1be8-574c-4e0b-afd6-d3c61efad820

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
artigopublicado.pdf
Size:
750.94 KB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.75 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

ESTiG - Publicações em Proceedings Indexadas à WoS/Scopus