Theft Detection Research Articles

A Novel Electricity Theft Detection Strategy Based on Dual-Time Feature Fusion and Deep Learning Methods

To enhance the accuracy of theft detection for electricity consumers, this paper introduces a novel strategy based on the fusion of the dual-time feature and deep learning methods. Initially, considering electricity-consumption features at dual temporal scales, the paper employs temporal convolutional networks (TCN) with a long short-term memory (LSTM) multi-level feature extraction module (LSTM-TCN) and deep convolutional neural network (DCNN) to parallelly extract features at these scales. Subsequently, the extracted features are coupled and input into a fully connected (FC) layer for classification, enabling the precise detection of theft users. To validate the method’s effectiveness, real electricity-consumption data from the State Grid Corporation of China (SGCC) is used for testing. The experimental results demonstrate that the proposed method achieves a remarkable detection accuracy of up to 94.7% during testing, showcasing excellent performance across various evaluation metrics. Specifically, it attained values of 0.932, 0.964, 0.948, and 0.986 for precision, recall, F1 score, and AUC, respectively. Additionally, the paper conducts a comparative analysis with mainstream theft identification approaches. In the comparison of training processes, the proposed method exhibits significant advantages in terms of identification accuracy and fitting degree. Moreover, with adjustments to the training set proportions, the proposed method shows minimal impact, indicating robustness.

Early detection and prevention of motorcycle theft by using microcontroller system and mobile platform

Old models of motorcycles which use manual transmission do not have security features as the latest model. The objective of this publication is to develop and test the system for early detection and prevention of motorcycles by detecting the position of its side stand, the presence of vibration, the beep of horn, monitoring the actual position of the motorcycle and turning off the motorcycle remotely from a distance. The proposed system was developed based on the ESP32 microcontroller by using a limit switch sensor, vibration sensor, and Blynk platform on smartphones to monitor the motorcycle position on google maps. The obtained system was powered by using an external battery to separate from internal electricity of the motorcycle to prevent any kickback current which could damage the Capacitor Discharge Ignition of the motorcycle. The proposed system was tested on various locations to simulate when there was any theft attempt. The test results showed that the proposed system was able to give the actual position of the motorcycle, able to turn on the horn of the motorcycle as well as to turn off the motorcycle engine remotely from a distance by using the Blynk platform on the smartphone.

IOT based Smart Unlawful Electricity Usage Surveillance and Warning System

The global issue of electricity theft has a negative impact on both the utilities and the people who use the energy. It impairs utility company economic growth, creates electrical risks, and has an effect on consumers' expenses for electricity. The emergence of smart grids is crucial for the detection of power theft as they provide vast amounts of data, including information on consumer consumption that can be used to identify theft using over voltage and over current detection methods. The solution presented in this article employs an Arduino uno micro controller board and IOT to monitor and maintain surveillance on power theft. An alarm with SMS notification will be sent to the officials and the power will be shut off whenever there is a power outage or tampering with an energy meter.

Improving Smart Grids Security: An Active Learning Approach for Smart Grid-Based Energy Theft Detection

Improving Smart Grids Security: An Active Learning Approach for Smart Grid-Based Energy Theft Detection

Electricity Theft Detection Method Based on Ensemble Learning and Prototype Learning

Electricity Theft Detection Method Based on Ensemble Learning and Prototype Learning

Deep Active Learning-Enabled Cost-Effective Electricity Theft Detection in Smart Grids

In industrial informatics-enabled smart grids, machine learning approaches have exhibited high potential in data-driven electricity theft detection (ETD), whereas none of the existing studies pay sufficient attention to the high costs of manually labeling massive sensing data during learning data preparation. To address this defect, this paper develops a cost-effective data-driven ETD approach that significantly reduces the data labeling costs without sacrificing the reliability of ETD. Specifically, the approach is systematically realized via an intelligent deep active learning (DAL) scheme. By seamlessly incorporating convolutional neural network (CNN) learning with Monte Carlo dropout-based Bayesian active query, the DAL scheme efficiently selects the most valuable instances for ETD model training. In this way, the proposed approach is able to derive a reliable CNN-based ETD model with limited labeled learning instances, thus largely reducing the data labeling costs. Experimental test results on an actual ETD dataset provided by the State Grid Corporation of China extensively illustrate the efficacy of the proposed approach.

IoT based electric power theft detection system

Science and technology, with their miraculous advancements, have fascinated human life to such an extent that imagining a world without these innovations is hardly possible. While technology is on the rise, an increase in immoral activities should also be noted. From a technical perspective, “power theft” is a non-ignorable crime that is highly prevalent and directly affects the economy of a nation. Today's life is unimaginable without electricity, almost all things, equipment, and appliances used daily rely on electric power to run smoothly. Solar energy is an alternative but has limitations, such as environmental changes and high initial costs. From rural to urban areas and from domestic to industrial sectors, the use of electricity has increased, but so has power theft. Detecting and eradicating such crimes with the help of the developing scientific field is the “need of the hour.” With these views, the paper was conceived and designed. The paper provides a complete and comprehensive tool to stop power theft, which is extremely simple to understand and easy to implement.

Mitigating Class Imbalance Issues in Electricity Theft Detection via a Sample-Weighted Loss

Mitigating Class Imbalance Issues in Electricity Theft Detection via a Sample-Weighted Loss

Electric Theft Detection Based on Multilayer Backpropagation Neural Network Optimized by Sine Chaotic Genetic Algorithm

Abstract In the era of big data, the growing volume of data in electrical systems has led to a rise in electric theft incidents, posing challenges to grid security. This paper introduces a detection method using the Sine chaotic genetic algorithm to optimize multilayer Backpropagation (BP) neural networks. Initially, a comprehensive dataset is compiled through extensive data collection. A multilayer BP neural network is then trained on this dataset for automated theft identification. Leveraging the Sine chaotic genetic algorithm further enhances network performance. Experimental results show an 88% prediction accuracy, offering improved accuracy, speed, and usability over traditional methods.

Reducing Annotation Efforts in Electricity Theft Detection Through Optimal Sample Selection

Reducing Annotation Efforts in Electricity Theft Detection Through Optimal Sample Selection

Feature Attention Distillation Defense for Backdoor Attack in Artificial Neural Network-Based Electricity Theft Detection

Feature Attention Distillation Defense for Backdoor Attack in Artificial Neural Network-Based Electricity Theft Detection

Dynamic Generative Residual Graph Convolutional Neural Networks for Electricity Theft Detection

Dynamic Generative Residual Graph Convolutional Neural Networks for Electricity Theft Detection

Electricity Theft Detection in Smart Grids Based on Omni-Scale CNN and AutoXGB

Electricity Theft Detection in Smart Grids Based on Omni-Scale CNN and AutoXGB

COMPOSITE BEHAVIORAL MODELING FOR IDENTITY THEFT DETECTION MIXTURE OF CLINICAL CONCEPTS

In this work, we aim at building a bridge from coarse behavioral data to an effective, quick-response, and robust behavioral model for online identity theft detection. We concentrate on this issue in online social networks (OSNs) where users usually have composite behavioral records, consisting of multidimensional low-quality data, e.g., offline check-ins and online user-generated content (UGC). As an insightful result, we validate that there is a complementary effect among different dimensions of records for modeling users’ behavioral patterns. To deeply exploit such a complementary effect, we propose a joint (instead of fused) model to capture both online and offline features of a user’s composite behavior. We evaluate the proposed joint model by comparing it with typical models and their fused model on two real-world datasets: Foursquare and Yelp. The experimental results show that our model outperforms the existing ones, with the area under the receiver operating characteristic curve (AUC) values 0.956 in Foursquare and 0.947 in Yelp, respectively. Particularly, the recall (true positive rate) can reach up to 65.3% in Foursquare and 72.2% in Yelp with the corresponding disturbance rate (false-positive rate) below 1%. It is worth mentioning that these performances can be achieved by examining only one composite behavior, which guarantees the low response latency of our method. This study would give the cybersecurity community new insights into whether and how real-time online identity authentication can be improved via modeling users’ composite behavioral patterns.

Electricity Theft Detection for Smart Homes: Harnessing the Power of Machine Learning With Real and Synthetic Attacks

Electricity Theft Detection for Smart Homes: Harnessing the Power of Machine Learning With Real and Synthetic Attacks

Genetic Artificial Hummingbird Algorithm-Support Vector Machine for Timely Power Theft Detection.

Utilities face serious obstacles from power theft, which calls for creative ways to maintain income and improve operational effectiveness. This study presents a novel hybrid genetic artificial hummingbird algorithm-support vector machine classifier to detect power theft. The proposed algorithm combines the artificial hummingbird algorithm exploration phase with the genetic algorithm's mutation and crossover operators, to optimize the support vector machine's hyperparameters and categorize users as fraudulent or nonfraudulent. It utilizes 7,270 rows of labeled historical electricity consumption data from the Liberia Electricity Corporation over 15 independent runs. The methodology entailed data preprocessing, data split into training, validation, and testing sets in an 80-10-10 ratio, z-score normalization, optimization, training, validation, testing, and computation of six evaluation metrics. Its performance is compared with 13 metaheuristic classifiers and the conventional support vector machine. Findings indicate that the genetic artificial hummingbird algorithm-support vector machine outperforms the 13 rivals and the standard support vector machine in the six assessment measures with an accuracy score of 0.9986, precision of 0.9971, f_score of 0.9986, recall of 1, Matthews correlation coefficient of 0.9972, and g_mean of 0.9987. Furthermore, 90% of the time, Wilcoxon rank-sum tests revealed statistically significant differences between the algorithm and its rivals, demonstrating its superiority. The average run time is 4,656 seconds, the 3rd highest among its competitors. Despite the time complexity trade-off, its excellent performance on the unimodal and multimodal benchmark test functions, placing joint best in 7 out of 7 and 5 out of 6, respectively, provides important insights into the model's capacity to balance exploitation and exploration, improve local search, and avoid becoming stuck in the local optimum. These findings address important metaheuristic optimization gaps highlighting the model's potential for power theft detection.

Corrigendum: Deep learning-based meta-learner strategy for electricity theft detection

Corrigendum: Deep learning-based meta-learner strategy for electricity theft detection

A new electricity theft detection method using hybrid adaptive sampling and pipeline machine learning

A new electricity theft detection method using hybrid adaptive sampling and pipeline machine learning

The Development of a Web-based Library Management System using RFID Technology

A library is a non-profit repository that stores a valuable collection of human knowledge and information. Next, RFID stands for Radio-Frequency Identification, which uses RFID tags to gather digital data. The main research objectives are to design, develop and test a Web-based Library Management System using RFID Technology. The Waterfall model was employed in the development of this system which requires each phase of work to be completed before going on to the next. It is easy to comprehend and use. The proposed system worked effectively for handling book borrowing and return tasks and minimized errors that may occur while utilising manual library management. Future improvements that may be made to the project to make it more effective are based on the book tracing and future security issues such as theft detection.

LITE-FORT: Lightweight three-stage energy theft detection based on time series forecasting of consumption patterns

LITE-FORT: Lightweight three-stage energy theft detection based on time series forecasting of consumption patterns