Recently, the distribution network has been integrated with an increasing number of renewable energy sources (RESs) to create hybrid power systems. Due to the interconnection of RESs, there is an increase in power quality disturbances (PQDs). The aim of this article was to present an innovative method for detecting and classifying PQDs that combines convolutional neural networks (CNNs) and long short-term memory (LSTM). The disturbance signals are fed into a combined CNN and LSTM model, which automatically recognizes and classifies the features associated with power quality disturbances. In comparison with other methods, the proposed method overcomes the limitations associated with conventional signal analysis and feature selection. Additionally, to validate the proposed method's robustness, data samples from a modified IEEE 13-node hybrid system are collected and tested using MATLAB/Simulink. The results are good and encouraging.

Introduction. Off-grid wind energy systems play a pivotal role in providing clean and sustainable power to remote areas. However, the intermittent nature of wind and the absence of grid connectivity pose significant challenges to maintaining consistent power quality. The wind energy conversion system plays a central role in tapping renewable energy from wind sources. Operational parameters such as rotor and stator currents, output voltages of rectifiers and converters, and grid phase voltage variations are crucial for stable power generation and grid integration. Additionally, optimizing power conversion output through voltage gain analysis in boost converters is essential. Moreover, ensuring electricity quality via total harmonic distortion reduction in inverters is vital for grid compatibility. Goal. Enhancing the power quality of grid-integrated wind energy conversion systems. Methods. The proposed topology is implemented in MATLAB/Simulink with optimized control strategies for enhancing power quality in off-grid wind energy systems. Results. Control strategies with a grid-connected wind energy conversion system yields substantial improvements in power quality. This includes effectively mitigating voltage fluctuations and harmonics, resulting in smoother operation and reduced disturbances on the grid. Practical value. The proposed topology has proven to be extremely useful for off grid-integrated wind system. References 18, table 1, figures 11.

Introduction. To enhance the quality of power and ensure a consistent electricity supply, this study proposes the utilization of a unified power quality conditioner (UPQC) system integrated with solar photovoltaic (PV) technology. The innovation involves single DC-link connecting back-to-back voltage-compensating components arranged in series and shunt, forming the PV-UPQC. The shunt compensator utilizes energy from a PV array to address harmonics in the load current. The objective is to mitigate voltage dips and spikes by injecting voltage that is either in phase with or out of phase with the common coupling point through a series compensator. The method combines the benefits of generating renewable energy to enhance electrical quality. The goal of the paper is the power quality enhancement of grid-integrated solar PV system. The novelty of the proposed work consists of enhancement of grid-integrated solar PV system with UPQC. The purpose of integrating a UPQC into a grid-connected solar PV system is to enhance power quality by mitigating issues such as voltage fluctuations, harmonics and reactive power imbalance. Methods. The proposed topology is implemented in MATLAB/Simulink with grid-integrated solar PV system with UPQC. Results. Integrating UPQC with a grid-connected solar PV system yields substantial improvements in power quality. This includes effectively mitigating voltage fluctuations and harmonics, resulting in smoother operation and reduced disturbances on the grid. Practical value. The proposed topology has proven to be extremely useful for grid-integrated solar PV system with UPQC applications. References 15, table 2, figures 9.

Hallucinations and delusions are symptoms of schizophrenia. Due to persistent auditory and visual hallucinations, a person with schizophrenia cannot process reality clearly. Abnormal brain activity results from delusion and hallucination. During the capture of EEG signals, aberrant behavior is detected. The EEG electrodes do not well detect the brain's current distribution. Schizophrenia causes the EEG signal to be warped and less sensitive, which results in incorrect interpretation of brain activity. In this paper, an EEG electrode constructed of graphene nanopowder is suggested that is sensitive to the brain's weak electrical activity. The cold spray approach created graphene EEG electrodes, improving the material bonding and chemical characteristics. By obtaining EEG readings from schizophrenic patients, the sensitivity of the graphene electrode was assessed. The EEG signal was collected from the subject when taking part in cognitive tests like question sessions and numerical problems. Several neural networks (NN) algorithms can be used to identify hallucination and delusion aspects in EEG recordings. Further details regarding the hallucination and delusion aspects in the EEG signal were provided by the NN, showing a Graphene electrode. As compared to other NN models, the comparative study of several NN models revealed that the BFGS quasi-Newtonian backpropagation algorithm accurately recognized hallucination and delusion features.

Atmospheric Cherenkov telescopes have enabled recent breakthroughs in gamma-ray astronomy, enabling the study of high-energy gamma particles in over 90 galactic and extragalactic regions. The significance of this work arises from the complexity of the data captured by the telescope. Traditional methods may struggle to effectively distinguish between gamma (signal) and hadron (background) events, due to intricate temporal relationships inherent in the data. The dataset used for this research, sourced from the UCI ML repository, simulates the registration of gamma particles. The challenge is to develop a classification model that accurately identifies these gamma events while handling inherent data complexities and normalizing skewed distributions. To address this challenge, a classification model is developed using ten features from the MAGIC gamma telescope dataset. This research introduces the innovative application of deep learning techniques, specifically Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Bidirectional LSTM (Bi-LSTM), to the field of gamma-ray astronomy to classify high-energy gamma particles detected by the Atmospheric Cherenkov telescopes. Furthermore, the research introduces the application of square root transformation as a method to address skewness and kurtosis in the dataset. This preprocessing technique aids in normalizing data distributions, which is crucial for accurate model training and classification. By leveraging the power of deep learning and innovative data transformations, the best accuracy of 88.71% is achieved by the LSTM+ReLU model with three layers for gamma and hadron particle classification. These findings offer insights into fundamental astrophysical processes and contribute to the advancement of gamma-ray astronomy.