Given the continually rising frequency of cyberattacks, the adoption of artificial intelligence methods, particularly Machine Learning (ML), Deep Learning (DL), and Reinforcement Learning (RL), has become essential in the realm of cybersecurity. These techniques have proven to be effective in detecting and mitigating cyberattacks, which can cause significant harm to individuals, organizations, and even countries. Machine learning algorithms use statistical methods to identify patterns and anomalies in large datasets, enabling security analysts to detect previously unknown threats. Deep learning, a subfield of ML, has shown great potential in improving the accuracy and efficiency of cybersecurity systems, particularly in image and speech recognition. On the other hand, RL is again a subfield of machine learning that trains algorithms to learn through trial and error, making it particularly effective in dynamic environments. We also evaluated the usage of ChatGPT-like AI tools in cyber-related problem domains on both sides, positive and negative. This article provides an overview of how ML, DL, and RL are applied in cybersecurity, including their usage in malware detection, intrusion detection, vulnerability assessment, and other areas. The paper also specifies several research questions to provide a more comprehensive framework to investigate the efficiency of AI and ML models in the cybersecurity domain. The state-of-the-art studies using ML, DL, and RL models are evaluated in each Section based on the main idea, techniques, and important findings. It also discusses these techniques’ challenges and limitations, including data quality, interpretability, and adversarial attacks. Overall, the use of ML, DL, and RL in cybersecurity holds great promise for improving the effectiveness of security systems and enhancing our ability to protect against cyberattacks. Therefore, it is essential to continue developing and refining these techniques to address the ever-evolving nature of cyber threats. Besides, some promising solutions that rely on machine learning, deep learning, and reinforcement learning are susceptible to adversarial attacks, underscoring the importance of factoring in this vulnerability when devising countermeasures against sophisticated cyber threats. We also concluded that ChatGPT can be a valuable tool for cybersecurity, but it should be noted that ChatGPT-like tools can also be manipulated to threaten the integrity, confidentiality, and availability of data.

This paper presents a review on current and emerging application possibilities for unmanned aerial vehicles (UAVs). The introduction section of the paper briefly describes some of the application areas in which drones are currently being used. The next chapters of the paper describe more detailly the use of UAVs for aerial photography, filming, security and logistics, GIS, land and water surveys. The main focus of the last chapters is on the advantages and the disadvantages of the drones usage in precision agriculture, wildlife and nature observations and archaeology. The last chapters also provide information on how the advanced information technology solutions can be implemented in order to provide means for fighting invasive species, to increase the yield of certain crops, to monitor and predict flooding, wildfires and other disasters, etc. This paper provides only overview of the most interesting and widely available applications of the UAVs, but there are also many other more specific and dedicated solutions for implementation of the drones for different purposes.

Fuel cells are a promising source of clean energy. To find optimal parameters for their operation, modeling is necessary, which is quite difficult to implement taking into account all the significant effects occurring in them. We aim to develop a previously unrealized model in COMSOL Multiphysics that, on one hand, will consider the influence of electrochemical heating and non-isothermal fluid flow on the temperature field and reaction rates, and on the other hand, will demonstrate the operating mode of the Solid Oxide Fuel Cell (SOFC) on carbonaceous fuel. This model incorporates a range of physical phenomena, including electron and ion transport, gas species diffusion, electrochemical reactions, and heat transfer, to simulate the performance of the SOFC. The findings provide a detailed view of reactant concentration, temperature, and current distribution, enabling the calculation of power output. The developed model was compared with a 1-kW industrial prototype operating on hydrogen and showed good agreement in the volt-ampere characteristic with a deviation not exceeding 5% for the majority of the operating range. The fuel cell exhibits enhanced performance on hydrogen, generating 1340 W/m² with a current density of 0.25 A/cm². When fueled by methane, it produces 1200 W/m² at the same current density. Using synthesis gas, it reaches its peak power of 1340 W/m² at a current density of 0.3 A/cm².

Rice, as one of the significant grain products across the world, features a wide range of varieties in terms of usability and efficiency. It may be known with various varieties and regional names depending on the specific locations. To specify a particular rice type, different features are considered, such as shape and color. This study uses an available dataset in Turkey consisting of five different varieties: Ipsala, Arborio, Basmati, Jasmine, and Karacadag. The dataset introduces 75,000 grain images in total; each of the 5 varieties has 15,000 samples with a 256 × 256-pixel dimension. The main contribution of this paper is to create Quantized Neural Network (QNN) models to efficiently classify rice varieties with the purpose of reducing resource usage on edge devices. It is well-known that QNN is a successful method for alleviating high computational costs and power requirements in response to many Deep Learning (DL) algorithms. These advantages of the quantization process have the potential to provide an efficient environment for artificial intelligence applications on microcontroller-driven edge devices. For this purpose, we created eight different QNN networks using the MLP and Lenet-5-based deep learning models with varying quantization levels to be trained by the dataset. With the Lenet-5-based QNN network created at the W3A3 quantization level, a 99.87% classification accuracy level was achieved with only 23.1 Kb memory size used for the parameters. In addition to this tremendous benefit of memory usage, the number of billion transactions per second (GOPs) is 23 times less than similar classification studies.

In the context of increasing demands for the reliability and efficiency of electrical complexes and systems, the problem of assessing and monitoring the technical condition (TC) of electrical equipment is becoming particularly relevant. This review is devoted to a comprehensive analysis of the factors affecting the performance of electrical equipment and modern methods for diagnosing its TC. The review article examines in detail the impact of various operational factors, including climatic conditions (temperature fluctuations, humidity, contamination) and electrical equipment operating modes. Special attention is paid to modern methods of technical diagnostics, such as thermographic diagnostics, vibration diagnostics, and chromatographic analysis of dissolved gases, which make it possible to identify defects and predict failures at early stages of their development. A significant part of the review is devoted to modern approaches to predicting the durability indicators of electrical equipment using mathematical modeling and neural networks. The advantages of a condition-based maintenance (CBM) and repair strategy, based on assessing the actual TC of the equipment, are analyzed in detail and compared with the strategy of scheduled preventive maintenance. This review particularly emphasizes the importance of integrating digital technologies, including the internet of things (IoT), digital twins (DT), and intelligent diagnostic monitoring systems, to create effective systems for predicting and managing TC. The review demonstrates that a comprehensive consideration of the actual TC of electrical equipment and its operating conditions can significantly increase the reliability of power systems, optimize maintenance and repair costs, and extend the service life of electrical equipment under various intensities of impacting operational factors.