A New SVM-Based Fraud Detection Model for AMI

Zanetti, Marcelo Serrano; Jamhour, Edgard; Pellenz, Marcelo Eduardo; Penna, Manoel Camillo

doi:10.1007/978-3-319-45477-1_18

Cited by 11 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Sms Resultsmentioning

confidence: 99%

“…C9. Security Intrusion detection ( [8], [15], [52], [74], [76], [77], [143], [148], [209]),false data injection attacks ( [13], [16], [17], [31], [100], [119], [151], [163], [168], [184], [185], [230], [251], [257]), energy theft ( [54], [99], [169], [191], [254], [258]), distinguishing cyber-attacks from physical faults ( [18]) C10. SG failures fault status detection [41], [46], [61], [62], [126], [127], [142], [176], fault type classification [197], power distribution reliability [149], [195] As it can be seen, there is large variability in the aspects covered by the research.…”

Section: B Rq2mentioning

confidence: 99%

“…Privacy Fuzzy c-means clustering [85], Random Gaussian Noise [105], Colored Noise [217], Symmetric Geometric Noise [21], Secret Sharing Scheme [95],Elliptic Curve Based Data Aggregation (ECBDA) [238], Collaborative Anonymity Set Formation (CASF) [4], Wavelet-based Multi-resolution Analysis (MRA) [141], adversarial strategy algorithm [234], differentially private aggregated sums [97], Integer Linear Optimization (ILP) [39], Tolerable Deviation algorithm [89], partitioning algorithm [235], Haar Wavelet transform [72], Profile Matching protocol using Hamming distance [236], Kalman filter [216] C9. Security Principal Component Analysis (PCA) (8) ( [16]- [18], [74], [100], [148], [185], [257]), Support Vector Machines (SVM) (5) ( [18], [74], [151], [185], [258]), k-means clustering [13], [251], fuzzy c-means clustering [185], DBSCAN clustering [148], [185], Decision Trees [52], [54], Feedforward Neural Network (FFNN) [143], Multi-layer Perceptron (MLP) [185], k-Nearest Neighbor (kNN) [185], clustering-based anomaly detection [209], Ensemble Model [143], Exponential Smoothing [15], Hoeffding Tree…”

Section: C1 Customer Profilingmentioning

confidence: 99%

See 2 more Smart Citations

Smart Grids Data Analysis: A Systematic Mapping Study

Rossi

Chren

2020

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

Article under review. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.The article is structured as follows. In section II, we provide an overview of Smart Grids concepts: mainly architecture and components of the SG infrastructure. In section III, we define the goals, needs, process and research questions for the Systematic Mapping Study on data analysis in the SG context. In section IV, we present the results from the overall SMS process, divided into answers to the main research questions set. In Section V, we discuss the main threats to validity of the current study. Section VI provides the final conclusions.

show abstract

Section: Sms Resultsmentioning

confidence: 99%

Section: B Rq2mentioning

confidence: 99%

Section: C1 Customer Profilingmentioning

confidence: 99%

See 1 more Smart Citation

Smart Grids Data Analysis: A Systematic Mapping Study

Rossi

Chren

2020

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

show abstract

“…The rapid growth of data has become a challenging task to find patterns and information from the data. ML has been successfully applied in many disciplines like fraud detection in credit card transaction and object recognition [1][2][3], face recognition [4,5], and decision making systems [6,7]. ML-based algorithms are developed based on the patterns learned from the data and used these patterns to conclude unseen data samples.…”

Section: Introductionmentioning

confidence: 99%

WR-SVM Model Based on the Margin Radius Approach for Solving the Minimum Enclosing Ball Problem in Support Vector Machine Classification

et al. 2021

View full text Add to dashboard Cite

The generalization error of conventional support vector machine (SVM) depends on the ratio of two factors; radius and margin. The traditional SVM aims to maximize margin but ignore minimization of radius, which decreases the overall performance of the SVM classifier. However, different approaches are developed to achieve a trade-off between the margin and radius. Still, the computational cost of all these approaches is high due to the requirements of matrix transformation. Furthermore, a conventional SVM tries to set the best hyperplane between classes, and due to some robust kernel tricks, an SVM is used in many non-linear and complex problems. The configuration of the best hyperplane between classes is not effective; therefore, it is required to bind a class within its limited area to enhance the performance of the SVM classifier. The area enclosed by a class is called its Minimum Enclosing Ball (MEB), and it is one of the emerging problems of SVM. Therefore, a robust solution is needed to improve the performance of the conventional SVM to overcome the highlighted issues. In this research study, a novel weighted radius SVM (WR-SVM) is proposed to determine the tighter bounds of MEB. The proposed solution uses a weighted mean to find tighter bounds of radius, due to which the size of MEB decreases. Experiments are conducted on nine different benchmark datasets and one synthetic dataset to demonstrate the effectiveness of our proposed model. The experimental results reveal that the proposed WR-SVM significantly performed well compared to the conventional SVM classifier. Furthermore, experimental results are compared with F-SVM and traditional SVM in terms of classification accuracy to demonstrate the significance of the proposed WR-SVM.

show abstract

“…To address the issue of imbalanced data, researchers such as Zanetti et al [12], Rodriguez et al [13], and Martino et al [14] have proposed using one-class Support Vector Machines (SVM) for electricity theft detection. Unlike the classical SVM model that requires two classes of training samples (normal and abnormal), a one-class SVM only requires a specific course of training samples (in our case, using standard consumption patterns).…”

mentioning

confidence: 99%

Dynamic Generative Residual Graph Convolutional Neural Networks for Electricity Theft Detection

Zhuang,

Jiang,

Xia

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Driven by economic incentives, illegal electricity consumers pose significant threats to the economic and security aspects of the power system by illicitly accessing or manipulating electrical resources. With the widespread adoption of Advanced Metering Infrastructure (AMI), researchers have turned to leveraging smart meter data for electricity theft detection. However, existing models rely on methods that model a single electricity load curve and cannot capture the temporal dependencies, periodicity, and underlying features between electricity consumption cycles. This paper proposes a dynamic generation algorithm to address these issues to construct a topological structure between periodic nodes, updated during training. Subsequently, residual graph convolution operations extract temporal and spatial dependencies among nodes. Additionally, to address the issue of model instability caused by scarce theft data, we employ the SMOTE (Synthetic Minority Over-sampling Technique) oversampling technique and enhance overall classification performance by modifying class weights in the loss function. We trained this network architecture on the real SGCC (State Grid Corporation of China) dataset, and the results demonstrate its superiority over other mainstream existing models.

show abstract

A New SVM-Based Fraud Detection Model for AMI

Cited by 11 publications

References 12 publications

Smart Grids Data Analysis: A Systematic Mapping Study

Smart Grids Data Analysis: A Systematic Mapping Study

WR-SVM Model Based on the Margin Radius Approach for Solving the Minimum Enclosing Ball Problem in Support Vector Machine Classification

Dynamic Generative Residual Graph Convolutional Neural Networks for Electricity Theft Detection

Contact Info

Product

Resources

About