Electric power grids are a crucial infrastructure for the proper operation of any country and must be preserved from various threats. Detection of illegal electricity power consumption is a crucial issue for distribution system operators (DSOs). Minimizing non-technical losses is a challenging task for the smooth operation of electrical power system in order to increase electricity provider’s and nation’s revenue and to enhance the reliability of electrical power grid. The widespread popularity of smart meters enables a large volume of electricity consumption data to be collected and new artificial intelligence technologies could be applied to take advantage of these data to solve the problem of power theft more efficiently. In this study, a robust artificial intelligence algorithm adaptive neuro fuzzy inference system (ANFIS)—with many applications in many various areas—is presented in brief and applied to achieve more effective detection of electric power theft. To the best of our knowledge, there are no studies yet that involve the application of ANFIS for the detection of power theft. The proposed technique is shown that if applied properly it could achieve very high success rates in various cases of fraudulent activities originating from unauthorized energy usage.

Soft computing techniques are used, in this paper, to model and solve the inverse problem of a thin, circular, loop antenna that radiates in free space. The electromagnetic field intensity serves as the input to the inverse model, whereas the antenna radius is the output. Three different architectures, based on artificial neural networks (ANNs), are implemented and various training algorithms are tested in order to obtain the optimum performance. The effect of the size of the training data set and the number of the observers on the accuracy of the results are investigated. Specific information for the selection of the appropriate ANN architecture is provided, depending on the constraints imposed by various parameters of the problem. Extensive numerical tests indicate that the results predicted by the proposed models are in excellent agreement with the theoretical data obtained from the existing analytical solutions of the forward problem.

Single-layer 4 × 4 and 8 × 8 Butler matrices (BMs) that operate in the L and S bands are implemented in this paper. Easy-to-fabricate microstrip layout topologies are designed and constructed; the final arrangement of the BMs allows realization without any crossovers. The performance of the networks is evaluated by measuring their frequency response. The return loss (RL) and the isolation are below -15 dB over the operation bandwidth for all structures, whereas the average insertion loss is less than 1 dB for the 4 × 4 BM and does not exceed 3 dB for the 8 × 8 BM. The amplitude imbalance is at most 0.5 dB and 1.5 dB, for the 4 × 4 and the 8 × 8 BMs, respectively. Moreover, multibeam antenna arrays fed by the BMs are constructed. The radiation patterns are measured and compared with theoretical data; a good agreement is achieved. The side lobes are sufficiently low, compared to the theoretical predictions, whereas they are further reduced by applying appropriate excitation schemes to the input ports of the BMs.

Textile patch antennas of simple rectangular, triangular, and circular shape, for operation in the 2.4–2.5 GHz free industrial, scientific, and medical (ISM) band, are designed in this paper. Thirty-six patch antenna prototypes have been fabricated by engaging different patch geometries, patch materials, and substrate materials. Each patch antenna is designed after optimization by a genetic algorithm, which evolves the initial dimensions and feeding position of the prototype’s microstrip counterpart to the final optimal geometrical characteristics of the wearable prototype (with the originally selected shape and materials). The impact of the design and fabrication details on antenna performance were thoroughly investigated. Graphene sheet patches were tested against conductive fabric and copper sheet ones, while denim and felt textile substrates were competing. The comparative study between a large number of different graphene, all, and copper textile prototypes, which revealed the excellent suitability of graphene for wearable applications, is the main contribution of this paper. Additional novelty elements are the compact, flexible, and easy-to-fabricate structure of the proposed antennas, as well as the use of state-of-the-art conductive materials and commercially available fabrics and the extensive investigation of many prototypes in various bending conditions. Simulations and measurements of the proposed antennas are in very good agreement. All fabricated prototypes are characterized by flexibility, light weight, mechanical stability, resistance to shock, bending and vibrations, unhindered integration to clothes, low-cost implementation, simple, time-saving, and industry-compatible fabrication process, and low specific absorption rate (SAR) values (computed using rectangular and voxel models); the graphene prototypes are additionally resistant to corrosion, and the circular ones have very good performance under bending conditions. Many antenna prototypes demonstrate interesting characteristics, such as relatively wide bandwidth, adequate gain, firm radiation patterns, coverage of the ISM band even under bending, and very low SAR values. For example, the circular graphene patch (with 55.3 mm diameter attached upon a 165.9 × 165.9 mm) felt substrate CGsF1 prototype accomplishes 109 MHz measured bandwidth, 5.45 dBi gain, 56% efficiency, full coverage of the ISM band under bending, and SAR less than 0.003 W/Kg.

In this study, the growing scientific field of alternative biofuels was examined, with respect to hydrochars produced from renewable biomasses. Hydrochars are the solid products of hydrothermal carbonization (HTC) and their properties depend on the initial biomass and the temperature and duration of treatment. The basic (Scopus) and advanced (Citespace) analysis of literature showed that this is a dynamic research area, with several sub-fields of intense activity. The focus of researchers on sewage sludge and food waste as hydrochar precursors was highlighted and reviewed. It was established that hydrochars have improved behavior as fuels compared to these feedstocks. Food waste can be particularly useful in co-hydrothermal carbonization with ash-rich materials. In the case of sewage sludge, simultaneous P recovery from the HTC wastewater may add more value to the process. For both feedstocks, results from large-scale HTC are practically non-existent. Following the review, related data from the years 2014–2020 were retrieved and fitted into four different artificial neural networks (ANNs). Based on the elemental content, HTC temperature and time (as inputs), the higher heating values (HHVs) and yields (as outputs) could be successfully predicted, regardless of original biomass used for hydrochar production. ANN₃ (based on C, O, H content, and HTC temperature) showed the optimum HHV predicting performance (R² 0.917, root mean square error 1.124), however, hydrochars’ HHVs could also be satisfactorily predicted by the C content alone (ANN₁, R² 0.897, root mean square error 1.289).

Sewage sludge hydrochars (SSHs), which are produced by hydrothermal carbonization (HTC), offer a high calorific value to be applied as a biofuel. However, HTC is a complex processand the properties of the resulting product depend heavily on the process conditions and feedstock composition. In this work, we have applied artificial neural networks (ANNs) to contribute to the production of tailored SSHs for a specific application and with optimum properties. We collected data from the published literature covering the years 2014–2021, which was then fed into different ANN models where the input data (HTC temperature, process time, and the elemental content of hydrochars) were used to predict output parameters (higher heating value, (HHV) and solid yield (%)). The proposed ANN models were successful in accurately predicting both HHV and contents of C and H. While the model NN₁ (based on C, H, O content) exhibited HHV predicting performance with R² = 0.974, another model, NN₂, was also able to predict HHV with R² = 0.936 using only C and H as input. Moreover, the inverse model of NN₃ (based on H, O content, and HHV) could predict C content with an R² of 0.939.