您好,欢迎访问三七文档
当前位置:首页 > 临时分类 > 基于机器学习技术的泌尿系统疾病诊断(IJISA-V7-N5-1)
1、I.J.IntelligentSystemsandApplications,2015,05,1-7PublishedOnlineApril2015inMECS()DOI:10.5815/ijisa.2015.05.01Copyright©2015MECSI.J.IntelligentSystemsandApplications,2015,05,1-7UrinarySystemDiseasesDiagnosisUsingMachineLearningTechniquesSeyyidAhmedMedjahedUniversityofSciencesandTechnologyMohamedBoudiafUSTO-MB,FacultyofMathematicsandComputerScience,Oran,31000,AlgeriaEmail:sa.medjahed@gmail.comTamazouztAitSaadiUniversityofHave,Havre,76600,FranceEmail:tamazouzt.ait.saadi@univ-lehavre.frAbdelkaderBe。
2、nyettouUniversityofSciencesandTechnologyMohamedBoudiafUSTO-MB,FacultyofMathematicsandComputerScience,Oran,31000,AlgeriaEmail:aek.benyettou@univ-usto.dzAbstract—Theurinarysystemistheorgansystemresponsiblefortheproduction,storageandeliminationofurine.Thissystemincludeskidneys,bladder,uretersandurethra.Itrepresentsthemajorsystemwhichfiltersthebloodandanyimbalanceofthisorgancanincreasestherateofbeinginfectedwithdiseases.TheaimofthispaperistoevaluatetheperformanceofdifferentvariantsofSupportVectorMac。
3、hinesandk-NearestNeighborwithdifferentdistancesandtrytoachieveasatisfactoryrateofdiagnosis(infectedornon-infectedurinarysystem).Weconsiderbothdiseasesthataffecttheurinarysystem:inflammationofurinarybladderandnephritisofrenalpelvisorigin.Ourexperimentationwillbeconductedonthedatabase“AcuteInflammationsDataSet”obtainedfromUCIMachineLearningRepository.Weusethefollowingmeasurestoevaluatetheresults:classificationaccuracyrate,classificationtime,sensitivity,specificity,positiveandnegativepredictivevalu。
4、es.IndexTerms—UrinarySystem,Diagnosis,SupportVectorMachine,k-NearestNeighbor,Distance.I.INTRODUCTIONMachinelearningisthescientificdisciplineconcernedwiththedevelopment,analysisandimplementationofautomatedmethodsthatallowtoamachinetoevolvethroughalearningprocess,andsofulfillthetasksthataredifficultorimpossibletofillbymoreconventionalalgorithmicmeans.Learningalgorithmscanbecategorizedaccordingtothelearningmode:supervisedlearning,unsupervisedlearningandsemi-supervisedlearning.Supervisedlearningiswi。
5、delyusedinthemedicalfieldasanensembleofmethodsforthemedicaldiagnosistohelpthedoctorandtogetabetterdiagnosis.Amongthesemethodsare:SupportVectorMachines,NeuronNetwork,k-NearestNeighbor,etc.Manyresearchershavedevelopedexpertsystemstosolvecomplexproblemsofmedicaldiagnosis(suchascancerdiagnosis[1],[2],acuteinflammationinurinarysystemdiagnosis[3],[4],etc.)byreasoningaboutknowledgeandalsobyusingdifferentlearningmethods.Supportvectormachineandk-nearestneighborhavebeenwidelyusedinmedicaldiagnosisfield.In。
6、[5],theauthorshaveusedSVMwithRBFkerneltodiagnosistheheartdisease.Leungetal.[6],havedevelopedadataminingframeworktodiagnosistheHepatitisB.In[7],theauthorshaveproposedthreeneuralnetworkapproachesandappliedinhepatitisdiseases.A.Kharratetal.[8],proposedanovelvariantofSupportvectormachinecalledEvolutionarySVMformedicaldiagnostic.Inthispaper,thefirstworkistoanalysisandtoevaluatetheperformanceofdifferentvariantofSupportVectorMachinesandk-NearestNeighboralgorithmwithdifferentdistances,inthecontextofthed。
7、iagnosisofacuteinflammationinurinarysystem(infectedornon-infectedwithinflammationofurinarybladderornephritisofrenalpelvisorigin).Thesecondworkistoreachahighclassificationaccuracyrate.Theevaluationsofperformancehavebeenconductedintermof:classificationaccuracyrate,classificationtime,sensitivity,specificity,positiveandnegativepredictivevalues.Thepaperisorganizedasfollows:FirstwerecallsomedefinitionofSupportVectorMachinesandthedifferentapproachesusinginthisstudy.InSec.IV,wepresentthek-NearestNeighbo。
8、randthedifferentdistance.InSec.V,weanalyzetheresultofthedifferentmethodsandfinallyweconcludewithsomeperspectives.II.SUPPORTVECTORMACHINESSupportVectorMachinewasintroducedbyVladimirN.Vapnikin1995[9],[10]anditbecomesratherpopularsince.SVMperformsclassificationbyconstructingahyperplanethatoptimallyseparatesthedataintotwocategories(inthecaseofbinaryclassification).ThemodelsofSVMarecloselyrelatedtoNeuralNetworks.2UrinarySystemDiseasesDiagnosisUsingMachineLearningTechniquesCopyright©2015MECSI.J.Intell。
9、igentSystemsandApplications,2015,05,1-7SVMworkswellinpracticeandhasbeenusedacrossawiderangeofapplicationsfromrecognizedhand-writtendigits,faceidentification,bioinformatics,etc.ThegoalofSVMistofindtheoptimalhyperplanethatseparatesclustersofvectorinsuchawaythatcaseswithonecategoryofthetargetvariableareononesideoftheplaneandcaseswiththeothercategoryareontheothersizeoftheplane[11].Thevectorsnearthehyperplanearethesupportvectors.Findtheoptimalhyperplaneisequivalenttoreformulatetheclassificationproble。
10、mtoanoptimizationproblem[12].Fig.1.TheoptimalHyperplane.A.MathematicalformulationConsiderabinaryclassificationproblemwithNtrainingpointsiiyx,,Ni,...,1,whereeachinputixhasDattributesandisoneoftwoclasses1,1iy.Thedatatraininghavethefollowingform:iiyx,whereDiiRxyNi,1,1,,...,1(1)Thehyperplanecanbedescribedby:0,bxwi(2)wherewisthenormtothehyperplaneandwbistheperpendiculardistancefromthehyperplanetotheorigin.Findingtheoptimalhyperplaneisequivalenttosolvingthefol。
本文标题:基于机器学习技术的泌尿系统疾病诊断(IJISA-V7-N5-1)
链接地址:https://www.777doc.com/doc-8495903 .html