“…Uptonow,anumberofmethodsforautomaticarrhythmiaclassificationintheECGsignalshave beenpreviouslyreportedintheliterature (Luz,Schwartz,Cámara-Chávez,&Menotti,2016).These mainly focus on linear discriminant analysis (Sharma & Singh, 2014), artificial neural networks (Ebrahimzadeh, Ahmadi, & Safarnejad, 2016;Sarkaleh & Shahbahrami, 2012), support vector machines (Khazaee&Zadeh,2014),mixture-of-expertsalgorithms (Übeyli,2008)andstatistical Markovmodels (Liang,Zhang,Tan,&Li,2014).Themostdifficultproblemfacedduringautomated ECGclassificationisthatthereisagreatvarietyofmorphologiesamongtheheartbeatsbelonging tooneclass,evenforthesamepatient (Osowski&Linh,2002).Moreover,heartbeatsbelongingto differentclassescanbemorphologicallysimilartoeachother.Therefore,aneffectivefeatureextraction techniqueisneededtoproducesuchrepresentationoftheoriginalECGsignalthatwillsuppress thedifferencesamongtheECGwaveformsofthesameclassand,atthesametime,emphasizethe differencesforthewaveformsbelongingtodifferenttypesofarrhythmias.Variousfeatureshavebeen usedbyotherresearcherstocharacterizearrhythmiasincluding:morphologicalfeaturesandheartbeat time intervals (de Chazal & Reilly, 2006), statistical and mixture modelling features (Afkhami, Azarnia,&Tinati,2016),temporalfeatures (SyamaUday,Mohanalin,&Devi,2016),frequency domain features (Gothwal, Kedawat, & Kumar, 2011;Ganesh Kumar & Kumaraswamy, 2014), hybridfeatures (Muthuvel,Suresh,Alexander,&Veni,2014),Hermitepolynomials (Ebrahimzadeh, Ahmadi,&Safarnejad,2016)andwavelettransformcoefficients (Sarkaleh&Shahbahrami,2012). Randomforest,proposedbyBreiman(2001),isaschemeforbuildingapredictorensemblewith asetofdecisiontreesthatgrowinrandomlyselectedsubspacesofdata.Inrecentyears,randomforest classifierishotinthemachinelearningcommunityduetoitsexcellentclassificationperformance, itsefficiencyintrainingandtestinganditsuncannyabilitytohandleaverylargenumberofinput variableswithoutoverfitting.Ashighlightedbyvariousempiricalstudies,randomforesthasemerged asastrongcontendertostate-of-the-artmethods,suchasneuralnetworksandsupportvectormachines.…”