An open access database for the evaluation of respiratory sound classification algorithms

Basit Öğe Kaydı
dc.authoridJácome, Cristina/0000-0002-1151-8791
dc.authoridOliveira, Ana/0000-0003-4516-6904
dc.authoridUlukaya, Sezer/0000-0003-0473-7547
dc.authoridNatsiavas, Pantelis/0000-0002-4061-9815
dc.authoridJakovljevic, Niksa M/0000-0002-7283-3939
dc.authoridRocha, Bruno Miguel Machado/0000-0003-1643-667X
dc.authoridMaglaveras, Nicos/0000-0002-4919-0664
dc.authorwosidOliveira, Ana/JXM-9777-2024
dc.authorwosidJácome, Cristina/K-1185-2019
dc.authorwosidOliveira, Ana/K-7041-2013
dc.authorwosidUlukaya, Sezer/N-9772-2015
dc.authorwosidNatsiavas, Pantelis/P-1629-2018
dc.authorwosidJakovljevic, Niksa M/GPX-6593-2022
dc.authorwosidRocha, Bruno Miguel Machado/AAN-4350-2020
dc.contributor.authorRocha, Bruno M.
dc.contributor.authorFilos, Dimitris
dc.contributor.authorMendes, Luis
dc.contributor.authorSerbes, Gorkem
dc.contributor.authorUlukaya, Sezer
dc.contributor.authorKahya, Yasemin P.
dc.contributor.authorJakovljevic, Niksa
dc.date.accessioned2024-06-12T10:50:28Z
dc.date.available2024-06-12T10:50:28Z
dc.date.issued2019
dc.departmentTrakya Üniversitesien_US
dc.description.abstractObjective: Over the last few decades, there has been significant interest in the automatic analysis of respiratory sounds. However, currently there are no publicly available large databases with which new algorithms can be evaluated and compared. Further developments in the field are dependent on the creation of such databases. Approach: This paper describes a public respiratory sound database, which was compiled for an international competition, the first scientific challenge of the IFMBE' s International Conference on Biomedical and Health Informatics. The database includes 920 recordings acquired from 126 participants and two sets of annotations. One set contains 6898 annotated respiratory cycles, some including crackles, wheezes, or a combination of both, and some with no adventitious respiratory sounds. In the other set, precise locations of 10 775 events of crackles and wheezes were annotated. Main results: The best system that participated in the challenge achieved an average score of 52.5% with the respiratory cycle annotations and an average score of 91.2% with the event annotations. Significance: The creation and public release of this database will be useful to the research community and could bring attention to the respiratory sound classification problem.en_US
dc.description.sponsorshipWorking Group on Health Informatics and eHealth of the IFMBE; Fundacao para a Ciencia e Tecnologia (FCT) [SFRH/BD/135686/2018]; EU FP7 programme WELCOME [611223]; Fundo Europeu de Desenvolvimento Regional (FEDER) through Programa Operacional Competitividade e Internacionalizacao (COMPETE) [UID/BIM/04501/2013, POCI-01-0145-FEDER-007628-iBiMED]; FCT [UID/BIM/04501/2013, POCI-01-0145-FEDER-007628-iBiMED]; Ministry of Education, Science and Technological Development of the Republic of Serbia [TR32035, TR32040]; Bogazici University [16A02D2]; Turkish Scientific and Technological Research Council (TUBITAK) [2211]; Fundação para a Ciência e a Tecnologia [SFRH/BD/135686/2018] Funding Source: FCTen_US
dc.description.sponsorshipThe scientific challenge was sponsored by the Working Group on Health Informatics and eHealth of the IFMBE. We acknowledge their financial and organisational support. This work was partially supported by: Fundacao para a Ciencia e Tecnologia (FCT) PhD scholarship SFRH/BD/135686/2018; EU FP7 programme WELCOME under grant agreement 611223; Fundo Europeu de Desenvolvimento Regional (FEDER) through Programa Operacional Competitividade e Internacionalizacao (COMPETE) and FCT under the project UID/BIM/04501/2013 and POCI-01-0145-FEDER-007628-iBiMED; the Ministry of Education, Science and Technological Development of the Republic of Serbia under grant agreements TR32035 and TR32040; Bogazici University Research Fund under grant number 16A02D2 and the PhD scholarship (2211) from Turkish Scientific and Technological Research Council (TUBITAK).en_US
dc.identifier.doi10.1088/1361-6579/ab03ea
dc.identifier.issn0967-3334
dc.identifier.issn1361-6579
dc.identifier.issue3en_US
dc.identifier.pmid30708353en_US
dc.identifier.scopus2-s2.0-85063693056en_US
dc.identifier.scopusqualityQ2en_US
dc.identifier.urihttps://doi.org/10.1088/1361-6579/ab03ea
dc.identifier.urihttps://hdl.handle.net/20.500.14551/18003
dc.identifier.volume40en_US
dc.identifier.wosWOS:000462116800001en_US
dc.identifier.wosqualityQ3en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.indekslendigikaynakPubMeden_US
dc.language.isoenen_US
dc.publisherIop Publishing Ltden_US
dc.relation.ispartofPhysiological Measurementen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectAcoustic Signal Processingen_US
dc.subjectAudio Databasesen_US
dc.subjectRespiratory Soundsen_US
dc.subjectWheeze Detectionen_US
dc.subjectLung Soundsen_US
dc.subjectCracklesen_US
dc.subjectAuscultationen_US
dc.subjectValidationen_US
dc.titleAn open access database for the evaluation of respiratory sound classification algorithmsen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
PubMed İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu