Please use this identifier to cite or link to this item: http://repo.lib.jfn.ac.lk/ujrr/handle/123456789/10015
Full metadata record
DC FieldValueLanguage
dc.contributor.authorMukunthan, T.-
dc.contributor.authorBrian, G.-
dc.contributor.authorRoberto La, R.-
dc.contributor.authorAnil, F.-
dc.date.accessioned2023-12-29T05:54:16Z-
dc.date.available2023-12-29T05:54:16Z-
dc.date.issued2022-
dc.identifier.urihttp://repo.lib.jfn.ac.lk/ujrr/handle/123456789/10015-
dc.description.abstractPredictingAntimicrobialResistance(AMR)fromgenomicsequencedatahasbecomea significantcomponentofovercomingtheAMRchallenge,especiallygivenitspotentialforfacilitatingmore rapiddiagnosticsandpersonalisedantibiotictreatments.Withtherecentadvancesinsequencingtechnologies andcomputingpower,deeplearningmodelsforgenomicsequencedatahavebeenwidelyadoptedtopredict AMRmorereliablyanderror-free.TherearemanydifferenttypesofAMR;therefore,anypracticalAMR predictionsystemmustbeabletoidentifymultipleAMRspresentinagenomicsequence.Unfortunately, mostgenomicsequencedatasetsdonothaveallthelabelsmarked,therebymakingadeeplearningmodelling approachchallengingowingtoitsrelianceonlabelsforreliabilityandaccuracy.Thispaperaddresses thisissuebypresentinganeffectivedeeplearningsolution,Mask-Loss1Dconvolutionneuralnetwork (ML-ConvNet),forAMRpredictionondatasetswithmanymissinglabels.Thecorecomponentof ML-ConvNetutilisesamaskedlossfunctionthatovercomestheeffectofmissinglabelsinpredicting AMR.TheproposedML-ConvNetisdemonstratedtooutperformstate-of-the-artmethodsintheliteratureby 10.5%,accordingtotheF1score.Theproposedmodel’sperformanceisevaluatedusingdifferentdegrees ofthemissinglabelandisfoundtooutperformtheconventionalapproachby76%intheF1scorewhen 86.68%oflabelsaremissing.Furthermore,theML-ConvNetwasestablishedwithanexplainableartificial intelligence(XAI)pipeline,therebymakingitideallysuitedforhospitalandhealthcaresettings,wheremodel interpretabilityisanessentialrequirement.en_US
dc.language.isoenen_US
dc.publisherIEEEen_US
dc.subjectMulti label classificationen_US
dc.subjectDeep neural networken_US
dc.subjectMulti-drug AMRen_US
dc.subjectMissing labelsen_US
dc.subjectExplainable AIen_US
dc.titleExplainable Deep Learning Approach for Multi label Classification of Antimicrobial Resistance with Missing Labelsen_US
dc.typeArticleen_US
Appears in Collections:Electrical & Electronic Engineering



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.