2013
DOI: 10.5121/ijaia.2013.4602
|View full text |Cite
|
Sign up to set email alerts
|

Fraud Detection in Electric Power Distribution Networks using an Ann-Based Knowledge-Discovery Process

Abstract: ABSTRACT

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
45
0

Year Published

2016
2016
2024
2024

Publication Types

Select...
3
3
1

Relationship

0
7

Authors

Journals

citations
Cited by 79 publications
(52 citation statements)
references
References 11 publications
0
45
0
Order By: Relevance
“…Other case studies of well-established machine learning methods focused on fraud detection in electricity consumption are the use of decision trees [Monedero et al 2012, Cody et al 2015b, logistic regression, linear discriminant analysis ( [Lawi et al 2017]) and time series [Nogales et al 2002]. Additionally, recent studies have provided new insights with the use of more complex machine learning models, such as Neural Networks [Nizar et al 2008, Monedero et al 2006, Costa et al 2013 and rough set theory [Spiri et al 2014]. Within the scope of Unsupervised Learning, Cabral et al in [E. Cabral et al 2008] present self-organizing maps that learns historical consumer energy consumption behavior.…”
Section: Related Workmentioning
confidence: 99%
“…Other case studies of well-established machine learning methods focused on fraud detection in electricity consumption are the use of decision trees [Monedero et al 2012, Cody et al 2015b, logistic regression, linear discriminant analysis ( [Lawi et al 2017]) and time series [Nogales et al 2002]. Additionally, recent studies have provided new insights with the use of more complex machine learning models, such as Neural Networks [Nizar et al 2008, Monedero et al 2006, Costa et al 2013 and rough set theory [Spiri et al 2014]. Within the scope of Unsupervised Learning, Cabral et al in [E. Cabral et al 2008] present self-organizing maps that learns historical consumer energy consumption behavior.…”
Section: Related Workmentioning
confidence: 99%
“…For the last ten years, most of the research on NTL detection have been focusing on data oriented solutions employing supervised machine learning methods, such as Support Vector Machines (SVM) [Coma-Puig et al 2016, Jindal et al 2016, Nagi et al 2010, Nagi et al 2011, statistical models [Faria et al 2016], artificial neural networks (ANNs) [Coma-Puig et al 2016, Costa et al 2013 and decision trees [Costa et al 2013, León et al 2011. Other methods included rule induction [Leon et al 2011, Nagi et al 2011, Bayesian classifiers [Monedero et al 2012] and Op-timum Path Forests (OPF) [Ramos et al 2011].…”
Section: Related Workmentioning
confidence: 99%
“…Another typical method employed to detect NTL frauds is user profile analysis, which includes feature extraction, machine learning, data mining, pattern recognition, etc. . User profile analysis is based on analyzing the electricity usage of customers and generating profiles for them.…”
Section: Related Workmentioning
confidence: 99%
“…Generating profiles requires large volumes of historical data to generalize common features of normal customers, as well as abnormal customers. The paper employs machine learning to detect NTL frauds. The authors build a knowledge‐discovery process to classify customers.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation