Please use this identifier to cite or link to this item:
https://hdl.handle.net/10316/105468
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Rocha, Bruno Machado | - |
dc.contributor.author | Pessoa, Diogo | - |
dc.contributor.author | Marques, Alda | - |
dc.contributor.author | Carvalho, Paulo de | - |
dc.contributor.author | Paiva, Rui Pedro | - |
dc.date.accessioned | 2023-03-01T11:59:10Z | - |
dc.date.available | 2023-03-01T11:59:10Z | - |
dc.date.issued | 2020-12-24 | - |
dc.identifier.issn | 1424-8220 | pt |
dc.identifier.uri | https://hdl.handle.net/10316/105468 | - |
dc.description.abstract | (1) Background: Patients with respiratory conditions typically exhibit adventitious respiratory sounds (ARS), such as wheezes and crackles. ARS events have variable duration. In this work we studied the influence of event duration on automatic ARS classification, namely, how the creation of the Other class (negative class) affected the classifiers' performance. (2) Methods: We conducted a set of experiments where we varied the durations of the other events on three tasks: crackle vs. wheeze vs. other (3 Class); crackle vs. other (2 Class Crackles); and wheeze vs. other (2 Class Wheezes). Four classifiers (linear discriminant analysis, support vector machines, boosted trees, and convolutional neural networks) were evaluated on those tasks using an open access respiratory sound database. (3) Results: While on the 3 Class task with fixed durations, the best classifier achieved an accuracy of 96.9%, the same classifier reached an accuracy of 81.8% on the more realistic 3 Class task with variable durations. (4) Conclusion: These results demonstrate the importance of experimental design on the assessment of the performance of automatic ARS classification algorithms. Furthermore, they also indicate, unlike what is stated in the literature, that the automatic classification of ARS is not a solved problem, as the algorithms' performance decreases substantially under complex evaluation scenarios. | pt |
dc.language.iso | eng | pt |
dc.publisher | MDPI | pt |
dc.relation | SFRH/BD/135686/2018 | pt |
dc.relation | Horizon 2020 Framework Programme of the European Union under grant agreement number 825572 (projectWELMO) | pt |
dc.relation | UID/BIM/04501/2013 | pt |
dc.relation | POCI-01-0145-FEDER-007628—iBiMED | pt |
dc.rights | openAccess | pt |
dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | pt |
dc.subject | adventitious respiratory sounds | pt |
dc.subject | experimental design | pt |
dc.subject | machine learning | pt |
dc.subject.mesh | Adult | pt |
dc.subject.mesh | Algorithms | pt |
dc.subject.mesh | Child | pt |
dc.subject.mesh | Female | pt |
dc.subject.mesh | Humans | pt |
dc.subject.mesh | Male | pt |
dc.subject.mesh | Neural Networks, Computer | pt |
dc.subject.mesh | Support Vector Machine | pt |
dc.subject.mesh | Respiratory Sounds | pt |
dc.subject.mesh | Signal Processing, Computer-Assisted | pt |
dc.title | Automatic Classification of Adventitious Respiratory Sounds: A (Un)Solved Problem? | pt |
dc.type | article | - |
degois.publication.firstPage | 57 | pt |
degois.publication.issue | 1 | pt |
degois.publication.title | Sensors (Switzerland) | pt |
dc.peerreviewed | yes | pt |
dc.identifier.doi | 10.3390/s21010057 | pt |
degois.publication.volume | 21 | pt |
dc.date.embargo | 2020-12-24 | * |
uc.date.periodoEmbargo | 0 | pt |
item.grantfulltext | open | - |
item.cerifentitytype | Publications | - |
item.languageiso639-1 | en | - |
item.openairetype | article | - |
item.openairecristype | http://purl.org/coar/resource_type/c_18cf | - |
item.fulltext | Com Texto completo | - |
crisitem.author.researchunit | CISUC - Centre for Informatics and Systems of the University of Coimbra | - |
crisitem.author.researchunit | CISUC - Centre for Informatics and Systems of the University of Coimbra | - |
crisitem.author.researchunit | CISUC - Centre for Informatics and Systems of the University of Coimbra | - |
crisitem.author.researchunit | CISUC - Centre for Informatics and Systems of the University of Coimbra | - |
crisitem.author.parentresearchunit | Faculty of Sciences and Technology | - |
crisitem.author.parentresearchunit | Faculty of Sciences and Technology | - |
crisitem.author.parentresearchunit | Faculty of Sciences and Technology | - |
crisitem.author.parentresearchunit | Faculty of Sciences and Technology | - |
crisitem.author.orcid | 0000-0003-1643-667X | - |
crisitem.author.orcid | 0000-0002-7783-7488 | - |
crisitem.author.orcid | 0000-0003-4980-6200 | - |
crisitem.author.orcid | 0000-0002-9847-0590 | - |
crisitem.author.orcid | 0000-0003-3215-3960 | - |
Appears in Collections: | I&D CISUC - Artigos em Revistas Internacionais |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Automatic-classification-of-adventitious-respiratory-sounds-A-unsolved-problemSensors-Switzerland.pdf | 607.11 kB | Adobe PDF | View/Open |
SCOPUSTM
Citations
49
checked on Apr 29, 2024
WEB OF SCIENCETM
Citations
38
checked on May 2, 2024
Page view(s)
54
checked on May 7, 2024
Download(s)
19
checked on May 7, 2024
Google ScholarTM
Check
Altmetric
Altmetric
This item is licensed under a Creative Commons License