Electricity theft is a global problem that negatively affects both utility companies and electricity users. It destabilizes the economic development of utility companies, causes electric hazards and impacts the high cost of energy for users. The development of smart grids plays an important role in electricity theft detection since they generate massive data that includes customer consumption data which, through machine learning and deep learning techniques, can be utilized to detect electricity theft. This paper introduces the theft detection method which uses comprehensive features in time and frequency domains in a deep neural network-based classification approach. We address dataset weaknesses such as missing data and class imbalance problems through data interpolation and synthetic data generation processes. We analyze and compare the contribution of features from both time and frequency domains, run experiments in combined and reduced feature space using principal component analysis and finally incorporate minimum redundancy maximum relevance scheme for validating the most important features. We improve the electricity theft detection performance by optimizing hyperparameters using a Bayesian optimizer and we employ an adaptive moment estimation optimizer to carry out experiments using different values of key parameters to determine the optimal settings that achieve the best accuracy. Lastly, we show the competitiveness of our method in comparison with other methods evaluated on the same dataset. On validation, we obtained 97% area under the curve (AUC), which is 1% higher than the best AUC in existing works, and 91.8% accuracy, which is the second-best on the benchmark.
With advancements in telecommunications, data transmission over increasingly harsher channels that produce synchronisation errors is inevitable. Coding schemes for such channels are available through techniques such as the Davey-MacKay watermark coding; however, this is limited to memoryless channel estimates. Memory must be accounted for to ensure a realistic channel approximation -similar to a Finite State Markov Chain or Fritchman Model. A novel code construction and decoder are developed to correct synchronisation errors while considering the channel's correlated memory effects by incorporating ideas from the watermark scheme and memory modelling. Simulation results show that the proposed code construction and decoder rival the first and second-order Davey-MacKay type watermark decoder and even perform slightly better when the inner-channel capacity is higher than 0.9. The proposed system and decoder may prove helpful in fields such as free-space optics and possibly molecular communication, where harsh channels are used for communication.
Interest in the mathematical modeling of infectious diseases has increased due to the COVID-19 pandemic. However, many medical students do not have the required background in coding or mathematics to engage optimally in this approach. System dynamics is a methodology for implementing mathematical models as easy-to-understand stock-flow diagrams. Remarkably, creating stock-flow diagrams is the same process as creating the equivalent differential equations. Yet, its visual nature makes the process simple and intuitive. We demonstrate the simplicity of system dynamics by applying it to epidemic models including a model of COVID-19 mutation. We then discuss the ease with which far more complex models can be produced by implementing a model comprising eight differential equations of a Chikungunya epidemic from the literature. Finally, we discuss the learning environment in which the teaching of the epidemic modeling occurs. We advocate the widespread use of system dynamics to empower those who are engaged in infectious disease epidemiology, regardless of their mathematical background.
Errors in realistic channels contain not only substitution errors, but synchronisation errors as well. Moreover, these errors are rarely statistically independent in nature. By extending on the idea of the Fritchman channel model, a novel error category-based methodology for determining channel characteristics is described for memory channels that contain insertion, deletion, and substitution errors. The practicality of such a methodology is reinforced by making use of real communication data from a visible light communication system. Simulation results show that the error-free and error runs using this new method of defining the channel clearly deviates from the Davey-Mackay synchronisation model which is memoryless in nature. This further emphasises the inherent memory in these synchronisation channels which we are now able to characterise. Additionally, a new method to determine the parameters of a synchronisation memory channel using the Levenshtein distance metric is detailed. This method of channel modelling allows for more realistic communication models to be simulated and can easily extend to other areas of research such as DNA barcoding in the medical domain.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.