scholarly journals Towards Big Data Electricity Theft Detection Based on Improved RUSBoost Classifiers in Smart Grid

Energies ◽  
2021 ◽  
Vol 14 (23) ◽  
pp. 8029
Author(s):  
Rehan Akram ◽  
Nasir Ayub ◽  
Imran Khan ◽  
Fahad R. Albogamy ◽  
Gul Rukh ◽  
...  
Keyword(s):  
Electric Power ◽  
Machine Learning Algorithms ◽  
Primary Sources ◽  
Space Technology ◽  
Electricity Theft ◽  
Bird Swarm Algorithm ◽  
Grave Problem ◽  
Advanced Metering ◽  
Energy Theft ◽  
Different Sources

The advent of the new millennium, with the promises of the digital age and space technology, favors humankind in every perspective. The technology provides us with electric power and has infinite use in multiple electronic accessories. The electric power produced by different sources is distributed to consumers by the transmission line and grid stations. During the electric transmission from primary sources, there are various methods by which to commit energy theft. Energy theft is a universal electric problem in many countries, with a possible loss of billions of dollars for electric companies. This energy contention is deep rooted, having so many root causes and rugged solutions of a technical nature. Advanced Metering Infrastructure (AMI) is introduced with no adequate results to control and minimize electric theft. Until now, so many techniques have been applied to overcome this grave problem of electric power theft. Many researchers nowadays use machine learning algorithms, trying to combat this problem, giving better results than previous approaches. Random Forest (RF) classifier gave overwhelmingly good results with high accuracy. In our proposed solution, we use a novel Convolution Neural Network (CNN) with RUSBoost Manta Ray Foraging Optimization (rus-MRFO) and RUSBoost Bird Swarm Algorithm (rus-BSA) models, which proves to be very innovative. The accuracy of our proposed approaches, rus-MRFO and rus-BSA, are 91.5% and a 93.5%, respectively. The proposed techniques have shown promising results and have strong potential to be applied in future.

scholarly journals Energy Theft Detection in Advanced Metering Infrastructure Based on Anomaly Pattern Detection

Energies ◽  
2020 ◽  
Vol 13 (15) ◽  
pp. 3832 ◽  
Author(s):  
Cheong Hee Park ◽  
Taegong Kim
Keyword(s):  
Machine Learning ◽  
Data Streams ◽  
Pattern Detection ◽  
Advanced Metering Infrastructure ◽  
Daily Consumption ◽  
Electricity Theft ◽  
Consumption Data ◽  
Anomaly Pattern ◽  
Advanced Metering ◽  
Energy Theft

Energy theft refers to the intentional and illegal usage of electricity by various means. A number of studies have been conducted on energy theft detection in the advanced metering infrastructure using machine learning methods. However, applying machine learning for energy theft detection has a problem in that it is difficult to obtain enough electricity theft data to train a machine learning model. In this paper, we propose a method based on anomaly pattern detection to detect electricity theft in data streams generated from smart meters. The proposed method requires only normal energy consumption data to train the model. Previous usage records of customers being monitored are not needed for energy theft detection. This characteristic makes the proposed method applicable in real situations. Experiments were conducted using real smart meter data and artificial attack data, including the preprocessing of daily consumption vectors by standard normalization, the construction of an outlier detection model on normal electricity consumption data of randomly chosen customers, and the application of anomaly pattern detection on test data streams. Some promising results were obtained, notably, that attacks of types 4, 5, 6 were detected with an average F1 value of 0.93 and average delay of 19 days.

Prediction of aircraft estimated time of arrival using machine learning methods

2021 ◽  
pp. 1-15
Author(s):  
O. Basturk ◽  
C. Cetek
Keyword(s):  
Machine Learning ◽  
Web Application ◽  
Absolute Error ◽  
Machine Learning Algorithms ◽  
Weather Data ◽  
Time Of Arrival ◽  
Learning Models ◽  
Trajectory Data ◽  
Different Sources ◽  
Machine Learning Models

ABSTRACT In this study, prediction of aircraft Estimated Time of Arrival (ETA) is proposed using machine learning algorithms. Accurate prediction of ETA is important for management of delay and air traffic flow, runway assignment, gate assignment, collaborative decision making (CDM), coordination of ground personnel and equipment, and optimisation of arrival sequence etc. Machine learning is able to learn from experience and make predictions with weak assumptions or no assumptions at all. In the proposed approach, general flight information, trajectory data and weather data were obtained from different sources in various formats. Raw data were converted to tidy data and inserted into a relational database. To obtain the features for training the machine learning models, the data were explored, cleaned and transformed into convenient features. New features were also derived from the available data. Random forests and deep neural networks were used to train the machine learning models. Both models can predict the ETA with a mean absolute error (MAE) less than 6min after departure, and less than 3min after terminal manoeuvring area (TMA) entrance. Additionally, a web application was developed to dynamically predict the ETA using proposed models.

scholarly journals Data Aggregation and Terror Group Prediction using Machine Learning Algorithms

2019 ◽  
Vol 8 (4) ◽  
pp. 1467-1469 ◽  
Keyword(s):  
Machine Learning ◽  
Detailed Analysis ◽  
Data Aggregation ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Classification Algorithms ◽  
Terrorist Groups ◽  
Different Sources

This paper is about to introduce a proposed system that examines growth or decay of the terrorist groups by the time, active locations, types of attack they carry out, motive targets, Weapon mastery and availability and many parameters to analyze the patterns and hidden structures in their activity and to predict the occasion and type of their future attack. We have done a detailed analysis of data we get from different sources and we also performed different classification algorithms on the available data to find the chances of probable attack on different regions.Based on results finding which of the algorithms works with highest accuracy.

scholarly journals Cyber-Infrastructure Connections and Smart Gird Security

2019 ◽  
Vol 8 (6) ◽  
pp. 2285-2287
Keyword(s):  
Smart Grid ◽  
Natural Disasters ◽  
Electric Power ◽  
Cyber Security ◽  
Cyber Attacks ◽  
Security Threats ◽  
Grid Environment ◽  
Energy Theft ◽  
Smart Gird ◽  
Regular Flow

The architecture of the smart grid combines the communication grid and physical power grid in a sole huge network. Smart grid has various security threats like cyber-attacks, physical attacks or natural disasters. The mentioned threats can lead to the breach of the user’s privacy, failure of the infrastructure, energy theft, blackouts endanger the safety of the operators among many more. For this reason, there is need to ensure that the smart grid cyber security is adequate to prevent any of these threats. Adequate security will as well ensure that the smart grid operates adequately as it is viewed that is by providing safe, reliable and uninterrupted supply of power to the consumers with a regular flow of end to end information that are all secure. The smart grid environment will ensure that the electric power infrastructure is modern. This is majorly by combining the present functionalities and the future ones with the upgraded requirements to the users

Detection and identification of energy theft in advanced metering infrastructures

2020 ◽  
Vol 182 ◽  
pp. 106258 ◽  
Author(s):  
Matheus Alberto de Souza ◽  
José L.R. Pereira ◽  
Guilherme de O. Alves ◽  
Bráulio C. de Oliveira ◽  
Igor D. Melo ◽  
...  
Keyword(s):  
Detection And Identification ◽  
Advanced Metering ◽  
Energy Theft

The Illusion of Consensus: A Failure to Distinguish Between True and False Consensus

2019 ◽  
Vol 30 (8) ◽  
pp. 1195-1204 ◽  
Author(s):  
Sami R. Yousif ◽  
Rosie Aboody ◽  
Frank C. Keil
Keyword(s):  
Primary Source ◽  
Primary Sources ◽  
Surface Level ◽  
False Consensus ◽  
Powerful Means ◽  
Different Sources

When evaluating information, we cannot always rely on what has been presented as truth: Different sources might disagree with each other, and sometimes there may be no underlying truth. Accordingly, we must use other cues to evaluate information—perhaps the most salient of which is consensus. But what counts as consensus? Do we attend only to surface-level indications of consensus, or do we also probe deeper and consider why sources agree? Four experiments demonstrated that individuals evaluate consensus only superficially: Participants were equally confident in conclusions drawn from a true consensus (derived from independent primary sources) and a false consensus (derived from only one primary source). This phenomenon was robust, occurring even immediately after participants explicitly stated that a true consensus was more believable than a false consensus. This illusion of consensus reveals a powerful means by which misinformation may spread.

scholarly journals Trend analysis of university placement by using machine learning algorithms

2018 ◽  
Vol 7 (2.4) ◽  
pp. 178
Author(s):  
Chandrasekhar Kumbhar ◽  
Dr S. S. Sridhar
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Data Analysis ◽  
Trend Analysis ◽  
Model Building ◽  
Machine Learning Algorithms ◽  
Complex Data ◽  
Student Placement ◽  
The University ◽  
Different Sources

Machine learning is a method of data analysis that automates analytical model building. These models help you to make a trend analysis of university placements data, to predict a placement rate for the students of an upcoming year which will help the university to analyze the performance during placements. Many students look at universities as a means of investment which can help them make a great future by getting placed in good companies and which will relieve their stress and unease from their lives before graduating from the university. The trend will also help in giving the companies reasons as to why they should visit university again and again. Some attributes play the very important role while analyzing the student for e.g. Student’s name, Department, Company, Location and Annual package. So, classification can help you to classify those data and clustering helps to make the clusters department wise. In this paper we have used neural networks to predict the upcoming student placement and got 77% of accuracy while testing were iteration are 1000. Through extensive trend analysis of varies complex data collected from different sources, we can demonstrate that our analysis can provide a good pragmatic solution for future placement of students. 

The Mortuary Behavior at Sunghir

2014 ◽  
Author(s):  
Erik Trinkaus ◽  
Alexandra P. Buzhilova ◽  
Maria B. Mednikova ◽  
Maria V. Dobrovolskaya
Keyword(s):  
Upper Paleolithic ◽  
Primary Sources ◽  
Arctic Fox ◽  
Original Material ◽  
Cultural Layer ◽  
Small Stone ◽  
Shell Beads ◽  
Different Sources ◽  
Tubular Bones

Considerations of the mortuary behavior at Sunghir concern principally the two elaborate graves, Graves 1 and 2. Although each exhibits patterns evident elsewhere in Mid Upper Paleolithic burials, the combinations of features and the richness of the two graves is truly exceptional. Yet there is additional evidence for mortuary behavior, principally associated with the Sunghir 5 cranium and for the burial above Grave 2 (here designated as Grave 2bis). The Sunghir graves have been described in detail by O.N. Bader (1998), and additional analyses of the associated materials have been done by White (1993, 1999) and Khlopachev (2006). Information on them is available from additional sources (e.g., Bader 1978; Soffer 1985; Abramova 1995; Bader and Bader 2000; Pettitt 2011), as well as from numerous short reports. Of these, the primary sources are those of O.N. Bader from the excavations and excavation analysis and of White and Khlopachev from analysis of the original material in the Vladimir District Regional Museum. The description here is an amalgamation of information from these and other sources. There are some inconsistencies between the different sources, and when possible they have been sorted out using the diagrams, and especially the discussion and in situ photographs, provided by O.N. Bader (1998). In the discussions of the graves and their contents, it should be kept in mind that many of the objects found in the graves and clearly associated with the human remains also occur in reasonable numbers in the cultural layer (cf. Bader 1978). This applies to the ochre, the several varieties of ivory beads, small stone pendants, animal figurines, tubular bones, pierced canines (arctic fox and wolf), and ivory spears (or fragments thereof). Additional decorative objects not found in the burials, such as shell beads and engravings, also derive from the cultural layer. It remains unclear whether these finds from the cultural layer were artifacts and aspects of body decoration that were common among the individuals at Sunghir (some of which happened to be preserved in abundance in the graves), whether their occurrence in the cultural layer is the result of pieces lost in the process of preparing the burials, whether the isolated pieces are from disturbed (unknown) burials, or whether (as suggested by Bader 1978) they come from discarded pieces of clothing.

Sign in / Sign up

Export Citation Format

Share Document