Please use this identifier to cite or link to this item: http://bura.brunel.ac.uk/handle/2438/23979
Full metadata record
DC FieldValueLanguage
dc.contributor.authorLi, J-
dc.contributor.authorWang, C-
dc.contributor.authorChen, J-
dc.contributor.authorZhang, H-
dc.contributor.authorDai, Y-
dc.contributor.authorWang, L-
dc.contributor.authorWang, L-
dc.contributor.authorNandi, AK-
dc.date.accessioned2022-01-22T08:15:42Z-
dc.date.available2022-01-22T08:15:42Z-
dc.date.issued2022-01-21-
dc.identifierORCID iDs: Jianqiang Li https://orcid.org/0000-0002-2208-962X; Cheng Wang https://orcid.org/0000-0002-6043-2150; Jie Chen https://orcid.org/0000-0002-9811-1694; Li Wang https://orcid.org/0000-0001-8707-3269; Asoke K. Nandi https://orcid.org/0000-0001-6248-2875.-
dc.identifier.citationLi, J. et al. (2022) 'Explainable CNN with Fuzzy Tree Regularization for Respiratory Sound Analysis', IEEE Transactions on Fuzzy Systems, 30 (6), pp. 1516 - 1528. doi: 10.1109/TFUZZ.2022.3144448.en_US
dc.identifier.issn1063-6706-
dc.identifier.urihttps://bura.brunel.ac.uk/handle/2438/23979-
dc.description.abstractCopyright © The Author(s) 2022. Auscultation is an important tool for diagnosing respiratory-related diseases. Unfortunately, the quality of auscultation is limited by the professional level of the doctor and the environment of the auscultation. Some studies have focused on automated auscultation techniques. However, existing approaches suffer from two challenges: 1) the models cannot learn from data distributed among multiple hospitals and 2) the predictions of the models are difficult to interpret for physicians. To address this issue, this article proposes a novel explainable respiratory sound analysis framework with fuzzy decision tree regularization. This framework develops an ensemble knowledge distillation technique to learn distributed data and achieves good performance in terms of model efficiency and accuracy. Fuzzy decision trees are used to explain the predictions of the model and produce decision rules that can be well accepted by physicians. The effectiveness of this framework is thoroughly validated on the Respiratory Sound database and compared with other existing approaches.-
dc.description.sponsorshipNational Key R&D Program of China (Grant Number: 2020YFA0908700); 10.13039/501100001809-National Natural Science Foundation of China (Grant Number: 62073225, 62072315, 61836005 and 62006157); 10.13039/501100003453-Natural Science Foundation of Guangdong Province (Grant Number: 2019B151502018); 10.13039/100016691-Guangdong Provincial Pearl River Talents Program (Grant Number: 2019ZT08X603); Shenzhen Science and Technology Program (Grant Number: JCYJ20210324093808021); 10.13039/501100010877-Shenzhen Science and Technology Innovation Commission (Grant Number: R2020A045),-
dc.format.extent1516 - 1528-
dc.format.mediumPrint-Electronic-
dc.language.isoen_USen_US
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en_US
dc.rightsCopyright © The Author(s) 2022. Published by Institute of Electrical and Electronics Engineers (IEEE). This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/-
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/-
dc.subjectrespiratory soundsen_US
dc.subjectinterpretableen_US
dc.subjectfuzzy decision treeen_US
dc.subjectconvolutional neural networken_US
dc.subjectknowledge distillationen_US
dc.titleExplainable CNN with fuzzy tree regularization for respiratory sound analysisen_US
dc.typeArticleen_US
dc.identifier.doihttps://doi.org/10.1109/TFUZZ.2022.3144448-
dc.relation.isPartOfIEEE Transactions on Fuzzy Systems-
pubs.issue6-
pubs.publication-statusPublished-
pubs.volume30-
dc.identifier.eissn1941-0034-
dc.rights.holderThe Author(s)-
Appears in Collections:Dept of Electronic and Electrical Engineering Research Papers

Files in This Item:
File Description SizeFormat 
FullText.pdfCopyright © The Author(s) 2022. Published by Institute of Electrical and Electronics Engineers (IEEE). This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/5.39 MBAdobe PDFView/Open


This item is licensed under a Creative Commons License Creative Commons