Title of article :
A hybridradialbasisfunctionanddataenvelopmentanalysisneuralnetwork
for classification
Author/Authors :
Parag C.Pendharkar ، نويسنده ,
Issue Information :
ماهنامه با شماره پیاپی سال 2011
Abstract :
We proposeahybridradialbasisfunctionnetwork-dataenvelopmentanalysis(RBFN-DEA)neural
networkforclassificationproblems.Theprocedureusestheradialbasisfunctiontomaplow
dimensionalinputdatafrominputspace R to ahighdimensional R+ feature spacewhereDEAcanbe
used tolearntheclassificationfunction.Usingsimulateddatasetsforanon-linearlyseparablebinary
classificationproblem,weillustratehowtheRBFN-DEAneuralnetworkcanbeusedtosolveit.Wealso
show howasymmetricmisclassificationcostscanbeincorporatedinthehybridRBFN-DEAmodel.Our
preliminaryexperimentscomparingtheRBFN-DEAwithfeedforwardandprobabilisticneural
networksshowthattheRBFN-DEAfaresverywell.
Keywords :
Linear programming , Data envelopment analysis , Neural networks , Radial basis functions
Journal title :
Computers and Operations Research
Journal title :
Computers and Operations Research
