Show simple item record

dc.contributor.authorAltan, Gökhan
dc.contributor.authorKutlu, Yakup
dc.contributor.authorPekmezci, Adnan Özhan
dc.contributor.authorNural, Serkan
dc.date.accessioned12.07.201910:50:10
dc.date.accessioned2019-07-12T22:06:08Z
dc.date.available12.07.201910:50:10
dc.date.available2019-07-12T22:06:08Z
dc.date.issued2018
dc.identifier.citationAltan, G., Kutlu, Y., Pekmezci, A.Ö., Nural, S. (2018). Deep learning with 3D-second order difference plot on respiratory sounds. Biomedical Signal Processing and Control, 45, pp. 58-69. https://doi.org/10.1016/j.bspc.2018.05.014en_US
dc.identifier.issn1746-8094
dc.identifier.issn1746-8108
dc.identifier.urihttps://doi.org/10.1016/j.bspc.2018.05.014
dc.identifier.urihttps://hdl.handle.net/20.500.12508/646
dc.descriptionWOS: 000440774700006en_US
dc.description.abstractThe second order difference plot (SODP) is a nonlinear signal analysis method that visualizes two consecutive data points for many types of biomedical signals. The proposed method is based on analysing quantization of 3D-space which is originated using three consecutive data points in signal. The obtained 3D-SODP space was segmented into 3-10 spaces using octants, spheres and cuboid polyhedrons of which centroids are at the origin. Lung sound is an indispensable tool for respiratory and cardiac diseases. The study is focused on classifying the lung sounds from at risk level and the interior level of chronic obstructive pulmonary disease (COPD). The COPD is one of the most deadliest and common respiratory diseases which come into existence as a consequence of smoking. The smokers for a few years are qualified as at risk level of COPD (COPD-0). The 12 channels of lung sounds from the Respiratory Database@TR were utilized in the analysis of the proposed 3D-SODP quantization method. The lung sounds are auscultated synchronously from posterior and anterior sides of subjects using two digital stethoscopes by a pulmonol ogist clinician in Antakya State Hospital, Turkey. Deep Belief Networks (DBN) algorithm was preferred in the classification stage. It has a greedy layer-wise pre-training which is based on restricted Boltzmann machines and optimizes the pre-trained weights using supervised iterations. The proposed DBN model had 2 hidden layers with 270 and 580 neurons, respectively. The conjunction usage of 3D-SODP quantization features with the DBN separated the lung sounds from different levels of COPD with high classification performance rates of 95.84%, 93.34% and 93.65% for accuracy, sensitivity and specificity, respectively. The results indicate that the 3D-SODP quantization on respiratory sounds has ability to diagnose the levels of the COPD using the deep learning model. Especially, the octant-based quantization is effective on lung sounds with high generalization capability using a small number of feature set dimension. (C) 2018 Elsevier Ltd. All rights reserved.en_US
dc.description.sponsorshipScientific and Technological Research Council of Turkish [TUBITAK-116E190]; TUBITAKen_US
dc.description.sponsorshipThis study is supported by Scientific and Technological Research Council of Turkish (TUBITAK-116E190). The authors express their thanks to TUBITAK for providing fully support.en_US
dc.language.isoengen_US
dc.publisherElsevieren_US
dc.relation.isversionof10.1016/j.bspc.2018.05.014en_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectLung soundsen_US
dc.subjectCOPDen_US
dc.subjectChronic obstructive pulmonary diseaseen_US
dc.subjectSecond order difference ploten_US
dc.subject3D-SODPen_US
dc.subjectDeep learningen_US
dc.subjectDeep Belief Networksen_US
dc.subjectDBNen_US
dc.subject.classificationEngineeringen_US
dc.subject.classificationBiomedicalen_US
dc.subject.classificationRespiratory Sound | Auscultation | Stethoscopeen_US
dc.subject.otherObstructive pulmonary-diseaseen_US
dc.subject.otherCongestive-heart-failureen_US
dc.subject.otherLung soundsen_US
dc.subject.otherClassificationen_US
dc.subject.otherDiagnosisen_US
dc.subject.otherSystemen_US
dc.subject.otherPredictionen_US
dc.subject.otherBioelectric phenomenaen_US
dc.subject.otherBiological organsen_US
dc.subject.otherBiomedical signal processingen_US
dc.subject.otherPulmonary diseasesen_US
dc.subject.otherQuantization (signal)en_US
dc.subject.other3D-SODPen_US
dc.subject.otherChronic obstructive pulmonary diseaseen_US
dc.subject.otherDeep belief networksen_US
dc.subject.otherLung soundsen_US
dc.subject.otherSecond ordersen_US
dc.subject.otherAbnormal respiratory sounden_US
dc.subject.otherArtificial neural networken_US
dc.subject.otherChronic obstructive lung diseaseen_US
dc.subject.otherClassification algorithmen_US
dc.subject.otherClassifieren_US
dc.subject.otherData baseen_US
dc.subject.otherDeep belief network algorithmen_US
dc.subject.otherDiagnostic accuracyen_US
dc.subject.otherHumanen_US
dc.subject.otherLearning algorithmen_US
dc.subject.otherLung auscultationen_US
dc.subject.otherMachine learningen_US
dc.subject.otherPriority journalen_US
dc.subject.otherRisken_US
dc.subject.otherSensitivity and specificityen_US
dc.subject.otherSmokingen_US
dc.subject.otherTurkey (republic)en_US
dc.titleDeep learning with 3D-second order difference plot on respiratory soundsen_US
dc.typearticleen_US
dc.relation.journalBiomedical Signal Processing and Controlen_US
dc.contributor.departmentMühendislik ve Doğa Bilimleri Fakültesi -- Bilgisayar Mühendisliği Bölümüen_US
dc.identifier.volume45en_US
dc.identifier.startpage58en_US
dc.identifier.endpage69en_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.contributor.isteauthorAltan, Gökhanen_US
dc.contributor.isteauthorKutlu, Yakupen_US
dc.relation.indexWeb of Science - Scopusen_US
dc.relation.indexWeb of Science Core Collection - Science Citation Index Expandeden_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record