Publication:
Abnormalities and fraud electric meter detection using hybrid support vector machine & genetic algorithm

Simple item page
dc.citedby11
dc.contributor.authorYap K.S.en_US
dc.contributor.authorAbidin I.Z.en_US
dc.contributor.authorAhmad A.R.en_US
dc.contributor.authorHussien Z.F.en_US
dc.contributor.authorPok H.L.en_US
dc.contributor.authorIsmail F.I.en_US
dc.contributor.authorMohamad A.M.en_US
dc.contributor.authorid24448864400en_US
dc.contributor.authorid35606640500en_US
dc.contributor.authorid35589598800en_US
dc.contributor.authorid11640353300en_US
dc.contributor.authorid25646345800en_US
dc.contributor.authorid25645748900en_US
dc.contributor.authorid24448210200en_US
dc.date.accessioned2023-12-28T07:56:35Z
dc.date.available2023-12-28T07:56:35Z
dc.date.issued2007
dc.description.abstractThis paper presents an intelligent system to reduce Non Technical Loss (NTL) using hybrid Support Vector Machine (SVM) and Genetic Algorithm (GA). The main motivation for this research is to assist Sabah Electricity Sdn. Bhd. (SESB) to reduce their distribution loss, estimated around 15% at present in Sabah State, Malaysia. The hybrid algorithm is able to preselect customers to be inspected on-site for abnormalities or potential fraud according to their consumption patterns. SVM is a classification technique developed by Vapnik [1] but a practical difficulty of using SVM is the selection of parameters such as C and kernel parameter, � in Gaussian RBF kernel. The purpose of choosing parameters is to get the best generalization performance. Genetic Algorithm (GA) is used to search for the best parameter of SVM classification by using combination of random and pre-populated genomes from Pre-Populated Database (PPD). It provides an increased convergence and globally optimized solutions. The algorithm has been tested using actual customer consumption data from SESB. 10 fold cross validation method is used to confirm the consistency of the detection accuracy. The paper also highlights comparison results between typical SVM and SVM-GA. The highest fraud detection accuracy for SVMGA is 94%.en_US
dc.description.natureFinalen_US
dc.identifier.epage392
dc.identifier.scopus2-s2.0-56149083812
dc.identifier.spage388
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-56149083812&partnerID=40&md5=c2936eab15b67d94c5fcc9005e0ddf88
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/29727
dc.pagecount4
dc.sourceScopus
dc.sourcetitleProceedings of the 3rd IASTED International Conference on Advances in Computer Science and Technology, ACST 2007
dc.subjectDual lagrangian optimization
dc.subjectDynamic crossover point
dc.subjectGenetic algorithm
dc.subjectPre-populated database
dc.subjectSupport vector machine
dc.subjectAlgorithms
dc.subjectComputer science
dc.subjectComputers
dc.subjectDatabase systems
dc.subjectDiesel engines
dc.subjectGenetic algorithms
dc.subjectImage retrieval
dc.subjectIntelligent systems
dc.subjectLearning systems
dc.subjectMultilayer neural networks
dc.subjectNeural networks
dc.subjectVectors
dc.subject10 fold cross validations
dc.subjectAnd genetic algorithms
dc.subjectClassification techniques
dc.subjectComparison results
dc.subjectConsumption patterns
dc.subjectCustomer consumption datums
dc.subjectDetection accuracies
dc.subjectDistribution losses
dc.subjectDual lagrangian optimization
dc.subjectDynamic crossover point
dc.subjectFraud detections
dc.subjectGaussian
dc.subjectGeneralization performances
dc.subjectHybrid algorithms
dc.subjectKernel parameters
dc.subjectMalaysia
dc.subjectOptimized solutions
dc.subjectPre-populated database
dc.subjectRBF kernels
dc.subjectSupport vector machine
dc.subjectSupport vectors
dc.subjectSVM classifications
dc.subjectTechnical losses
dc.subjectSupport vector machines
dc.titleAbnormalities and fraud electric meter detection using hybrid support vector machine & genetic algorithmen_US
dc.typeConference Paperen_US
dspace.entity.typePublication
Files
Collections
SCOPUS