Fast non-technical losses identification through Optimum-Path Forest

dc.contributorUniversidade Estadual Paulista (UNESP)
dc.creatorRamos, Caio C. O.
dc.creatorSouza, André N.
dc.creatorPapa, João P.
dc.creatorFalcão, Alexandre X.
dc.date2014-05-27T11:24:34Z
dc.date2016-10-25T18:28:09Z
dc.date2014-05-27T11:24:34Z
dc.date2016-10-25T18:28:09Z
dc.date2009-12-09
dc.date.accessioned2017-04-06T01:39:50Z
dc.date.available2017-04-06T01:39:50Z
dc.identifier2009 15th International Conference on Intelligent System Applications to Power Systems, ISAP '09.
dc.identifierhttp://hdl.handle.net/11449/71478
dc.identifierhttp://acervodigital.unesp.br/handle/11449/71478
dc.identifier10.1109/ISAP.2009.5352910
dc.identifier2-s2.0-76549090785
dc.identifierhttp://dx.doi.org/10.1109/ISAP.2009.5352910
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/892467
dc.descriptionFraud detection in energy systems by illegal consumers is the most actively pursued study in non-technical losses by electric power companies. Commonly used supervised pattern recognition techniques, such as Artificial Neural Networks and Support Vector Machines have been applied for automatic commercial frauds identification, however they suffer from slow convergence and high computational burden. We introduced here the Optimum-Path Forest classifier for a fast non-technical losses recognition, which has been demonstrated to be superior than neural networks and similar to Support Vector Machines, but much faster. Comparisons among these classifiers are also presented. © 2009 IEEE.
dc.languageeng
dc.relation2009 15th International Conference on Intelligent System Applications to Power Systems, ISAP '09
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectNon-technical losses
dc.subjectOptimum-path forest
dc.subjectArtificial Neural Network
dc.subjectComputational burden
dc.subjectElectric power company
dc.subjectEnergy systems
dc.subjectForest classifiers
dc.subjectFraud detection
dc.subjectNon-technical loss
dc.subjectSupervised pattern recognition
dc.subjectClassifiers
dc.subjectElectric losses
dc.subjectElectric utilities
dc.subjectIntelligent systems
dc.subjectPattern recognition
dc.subjectSupport vector machines
dc.subjectNeural networks
dc.titleFast non-technical losses identification through Optimum-Path Forest
dc.typeOtro


Este ítem pertenece a la siguiente institución