Abnormalities and fraud electric meter detection using hybrid support vector machine & genetic algorithm
This 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...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Published: |
2023
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
my.uniten.dspace-29727 |
|---|---|
| record_format |
dspace |
| spelling |
my.uniten.dspace-297272024-04-16T15:45:37Z Abnormalities and fraud electric meter detection using hybrid support vector machine & genetic algorithm Yap K.S. Abidin I.Z. Ahmad A.R. Hussien Z.F. Pok H.L. Ismail F.I. Mohamad A.M. 24448864400 35606640500 35589598800 11640353300 25646345800 25645748900 24448210200 Dual lagrangian optimization Dynamic crossover point Genetic algorithm Pre-populated database Support vector machine Algorithms Computer science Computers Database systems Diesel engines Genetic algorithms Image retrieval Intelligent systems Learning systems Multilayer neural networks Neural networks Vectors 10 fold cross validations And genetic algorithms Classification techniques Comparison results Consumption patterns Customer consumption datums Detection accuracies Distribution losses Dual lagrangian optimization Dynamic crossover point Fraud detections Gaussian Generalization performances Hybrid algorithms Kernel parameters Malaysia Optimized solutions Pre-populated database RBF kernels Support vector machine Support vectors SVM classifications Technical losses Support vector machines This 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%. Final 2023-12-28T07:56:35Z 2023-12-28T07:56:35Z 2007 Conference Paper 2-s2.0-56149083812 https://www.scopus.com/inward/record.uri?eid=2-s2.0-56149083812&partnerID=40&md5=c2936eab15b67d94c5fcc9005e0ddf88 https://irepository.uniten.edu.my/handle/123456789/29727 388 392 Scopus |
| institution |
Universiti Tenaga Nasional |
| building |
UNITEN Library |
| collection |
Institutional Repository |
| continent |
Asia |
| country |
Malaysia |
| content_provider |
Universiti Tenaga Nasional |
| content_source |
UNITEN Institutional Repository |
| url_provider |
http://dspace.uniten.edu.my/ |
| topic |
Dual lagrangian optimization Dynamic crossover point Genetic algorithm Pre-populated database Support vector machine Algorithms Computer science Computers Database systems Diesel engines Genetic algorithms Image retrieval Intelligent systems Learning systems Multilayer neural networks Neural networks Vectors 10 fold cross validations And genetic algorithms Classification techniques Comparison results Consumption patterns Customer consumption datums Detection accuracies Distribution losses Dual lagrangian optimization Dynamic crossover point Fraud detections Gaussian Generalization performances Hybrid algorithms Kernel parameters Malaysia Optimized solutions Pre-populated database RBF kernels Support vector machine Support vectors SVM classifications Technical losses Support vector machines |
| spellingShingle |
Dual lagrangian optimization Dynamic crossover point Genetic algorithm Pre-populated database Support vector machine Algorithms Computer science Computers Database systems Diesel engines Genetic algorithms Image retrieval Intelligent systems Learning systems Multilayer neural networks Neural networks Vectors 10 fold cross validations And genetic algorithms Classification techniques Comparison results Consumption patterns Customer consumption datums Detection accuracies Distribution losses Dual lagrangian optimization Dynamic crossover point Fraud detections Gaussian Generalization performances Hybrid algorithms Kernel parameters Malaysia Optimized solutions Pre-populated database RBF kernels Support vector machine Support vectors SVM classifications Technical losses Support vector machines Yap K.S. Abidin I.Z. Ahmad A.R. Hussien Z.F. Pok H.L. Ismail F.I. Mohamad A.M. Abnormalities and fraud electric meter detection using hybrid support vector machine & genetic algorithm |
| description |
This 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%. |
| author2 |
24448864400 |
| author_facet |
24448864400 Yap K.S. Abidin I.Z. Ahmad A.R. Hussien Z.F. Pok H.L. Ismail F.I. Mohamad A.M. |
| format |
Conference Paper |
| author |
Yap K.S. Abidin I.Z. Ahmad A.R. Hussien Z.F. Pok H.L. Ismail F.I. Mohamad A.M. |
| author_sort |
Yap K.S. |
| title |
Abnormalities and fraud electric meter detection using hybrid support vector machine & genetic algorithm |
| title_short |
Abnormalities and fraud electric meter detection using hybrid support vector machine & genetic algorithm |
| title_full |
Abnormalities and fraud electric meter detection using hybrid support vector machine & genetic algorithm |
| title_fullStr |
Abnormalities and fraud electric meter detection using hybrid support vector machine & genetic algorithm |
| title_full_unstemmed |
Abnormalities and fraud electric meter detection using hybrid support vector machine & genetic algorithm |
| title_sort |
abnormalities and fraud electric meter detection using hybrid support vector machine & genetic algorithm |
| publishDate |
2023 |
| _version_ |
1806423303547518976 |
| score |
13.211869 |