Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Vadym Slyusar has a total of 153 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • A Multi-Agent Environment With Artificial Intelligence for English Language Learning and Teaching

    by Vadym Slyusar

    This chapter explores the innovative application of multi-agent artificial intelligence systems for enhancing English language teaching and learning. Author presents an architecture composed of specialized AI agents performing distinct educational roles such as consulting, lecturing, methodology development, career advising, psychological support, and technical assistance. The system capitalizes on advanced large language models (LLMs) to create personalized, interactive, and adaptive learning experiences, seamlessly integrating into traditional educational structures while also offering flexibility and scalability. Furthermore, the chapter investigates immersive virtual environments powered by AI, proposing metrics to systematically evaluate their coherence, immersion, novelty, and interactivity. These metrics provide a foundation for future advancements in digital language education, suggesting new avenues for individualized learning trajectories and enhanced learner engagement within AI-driven environments.

  • The Role of AI and Technology in Interpretation

    by Vadym Slyusar

    The chapter highlights the role of AI and modern language models in the transformation of spoken translation, combining a historical overview with practical architectures. Central to the chapter is the model of a multi-agent translator assistant that performs speaker identification, segmentation, translation, and quality control in real time. The use of Retrieval Augmented Generation is considered for loading glossaries and reference materials from local storage. The application of AR glasses for subtitles and prompts without diverting attention is demonstrated. The concept of personal conferences with agent-based avatars delivering presentations from preloaded materials is proposed. This supports event preparation and skill development. Modern methods of translation quality evaluation are discussed, including the GEMBA metric, multi-agent evaluation, and new indicators integrated into INFERScore. The development of these approaches will enable cognitive alignment with human understanding.

  • An Embedded Approach to the Implementation of a Multi-Agent Energy Management System for Unmanned Systems

    by Vadym Slyusar, Serhii Pochernin

    The paper proposes a multi-agent energy management system for autonomous unmanned platforms, specifically unmanned aerial vehicles (UAVs) and unmanned ground robotic complexes (UGRCs). For the first time, an embedding-based approach is employed to represent the technical state of the battery pack: a multidimensional feature vector is mapped into an embedding space for subsequent analysis, classification, and prediction. The effectiveness of clustering and short-term degradation forecasting of battery cells-implemented via the embedding method using MLP models-is demonstrated. Simulation results confirm the feasibility of early detection of critical battery operating modes and adaptive energy management. The integration of the embedding approach within a multi-agent architecture is examined, assigning distinct roles to monitoring, classification, prediction, and decision-making agents. Attention is also given to the potential integration with digital twin models of batteries. The proposed method is suitable for deployment on edge devices and is promising for application in high-reliability power systems operating under resource-constrained and highly dynamic conditions.

  • Open Access

    Conceptual foundations of the swarm employment of unmanned aerial vehicles as intelligent means of electronic warfare

    by Vadym Slyusar, Vadym Kozlov, Serhii Pochernin, Iryna Nalapko

    The object of research is the process of functioning of a swarm of unmanned aerial vehicles (UAVs), equipped with artificial intelligence technologies, as intelligent means of electronic warfare (EW). The main attention is focused on their interaction and efficiency of functioning, their adaptive capabilities in a dynamically changing and complex electromagnetic environment. One of the key problems is ensuring reliable, stable and flexible coordination of swarm actions in conditions of electromagnetic influence of enemy radioelectronic means (REM). Coordination of swarm actions and measures should include continuous monitoring of the spectrum, timely adaptation to enemy countermeasures. To solve this problem, it is proposed to create an adaptive swarm architecture that implements the principles of decentralized control using machine learning algorithms, a multi-agent approach and software-configuration architecture of radio systems (SDR). The developed approach is based on the application of cognitive strategies for interaction between UAVs and the formation of a dynamic network structure that is self-repairing in the event of damage or interference. The proposed conceptual approach allows for significantly increasing the effectiveness of influencing the enemy's REM environment through dynamic spatial-temporal distribution of interference, taking into account the tactical situation and spectral characteristics of threats. It is envisaged to integrate strike and reconnaissance UAVs into a single swarm structure with autonomous coordination of actions, which expands the functionality of the swarm from the placement of multi-frequency interference to the detection, tracking and neutralization of critically important objects. This approach provides a high level of autonomy, adaptability and survivability of unmanned platforms in difficult conditions of electronic warfare, and also creates the prerequisites for significantly increasing the effectiveness of combat operations in a modern high-tech environment by integrating reconnaissance and strike functions and EW means into a single information system.


  • Open Access

    Integration and coordination of electronic warfare assets through large-scale language models

    by Vadym Kozlov, Vadym Slyusar, Volodymyr Tverdokhlibov, Zoia Andriichuk

    As an object of research, the work considers the process of functioning of electronic warfare (EW) means using artificial intelligence (AI) technologies based on large language models (LLM). One of the most problematic issues in increasing the efficiency of their functioning is ensuring the adaptability function in EW means, as well as timely detection of threats and formation of appropriate countermeasures. This problem is solved by implementing a multi-agent architecture, the task of which is to ensure continuous exchange of information, both between agents in the EW means themselves and in the system as a whole. The considered method of increasing the adaptability of the system due to LLM with self-learning mechanisms provides the system with the opportunity to improve its data processing algorithms, promptly detect new types of signals and respond to changes in the parameters of the enemy's REM. Using the Retrieval-Augmented Generation (RAG) approach allows to detect and enter new types of signals into the database and quickly form appropriate recommendations for countermeasures. An equally important component is the use of combining several EW tools into a single information network. This approach will ensure the consistency of the actions of all EW tools (agents) and the rapid exchange of information between them. Taking into account the above, there is a possibility of significantly increasing the adaptability and efficiency of EW systems by integrating multi-agent structures using LLM, which allow optimizing resource allocation and making decisions in real time. This will ensure a high level of adaptation of EW tools, which is an important feature for working in conditions of dynamically changing electromagnetic environments. Thanks to the proposed architecture and the use of appropriate algorithms, it is possible to obtain high indicators of classification accuracy and signal processing speed, which positively affects the adaptability of the system and the overall effectiveness of countering threats.

  • Open Access

    DEVELOPMENT OF A VIRTUAL PSYCHOLOGICAL ASSISTANT WITH ARTIFICIAL INTELLIGENCE IN THE HEALTHCARE SECTOR

    by Anatoly I. Shevchenko, Vitalii G. Panok, Andrii G. Shevtsov, Vadym I. Slyusar, Roman I. Malyi, Tetiana V. Yeroshenko, Maksym M. Nazar, Андрій Г. Шевцов, Вадим І. Слюсар, Тетяна В. Єрошенко

    Introduction. The global transformative changes that the modern world has been undergoing since the beginning of the 21st century have brought mental health to the forefront as one of the most pressing challenges of our time. According to the World Health Organization, approximately 970 million people live with cognitive disorders, with anxiety and depression being the most common, affecting about 264 million individuals (World Health Organization, 2019). As experts conclude, this trend shows a steady increase, which is especially pronounced during wars, pandemics, and natural and man-made disasters. The demand for psychological assistance is evident and, in some cases, grows during post-catastrophic, post-pandemic, and post-traumatic periods. One of the major challenges faced by mental health services is limited access to care. Some of the primary reasons for the lack of access to mental health services include high costs, absence or shortage of service providers, long distances, lack of time, societal stigma, and many other factors. To bridge this gap, many digital intervention services and professional support tools are being developed in mental health care. Aim. This work aims to provide scientific and methodological justification and practical development of an online platform for the chatbot "Virtual Psychological Assistant," powered by artificial intelligence (AI), to provide psychological assistance to the population during wartime, disasters, and other emergencies. Materials and methods. The functional capabilities of the online platform "Virtual Psychological Assistant," its operating algorithms, and its effectiveness in supporting users' mental health are considered. Special attention is given to potential risks, such as the spread of misinformation and privacy concerns, as well as proposed measures to mitigate them. Results. The results of the practical development and pilot application of the AI-based online platform "Virtual Psychological Assistant" are presented, particularly the chatbot for psychological counseling, which was created by a joint working group of scientists from the National Academy of Educational Sciences of Ukraine and the Institute of Artificial Intelligence Problems of the Ministry of Education and Science and the National Academy of Sciences of Ukraine. Conclusions. The developed AI-powered chatbot is a powerful tool for addressing the mental health issues of the population of Ukraine, making mental health services accessible to all who need them.


  • Inverse Architecture U-Net – InvU-Net

    by Slyusar V

    The article proposes an inverse architecture of the U-Net neural network, named InvU-Net, which differs from the traditional scheme by increasing the dimensionality of images during the initial stages of processing. A comparison was conducted between two approaches for increasing image resolution: UpSampling2D layers and transposed Conv2DTranspose convolutional layers. The latter demonstrated superior results due to its ability to learn weighting coefficients. As part of the study, several InvU-Net modifications were developed and tested: Small, Medium, and Large, differing in structural complexity, the number of layers, and parameters. To improve segmentation accuracy, the integration of attention mechanisms was proposed to enhance the relevance of feature processing. Experiments revealed that simplifying attention mechanisms, including reducing the number of parameters and optimizing integration points, achieves high performance with lower computational complexity. The best-performing model, which incorporated a simplified attention mechanism, achieved 95.6% accuracy, surpassing larger architectures. The results highlight the potential of InvU-Net for segmentation tasks and suggest further optimization directions, such as employing adaptive attention mechanisms and automating the selection of neural network parameters


  • Method for Differentiating Complex Matrix Functions in Digital Antenna Array Response Models

    by Vadym Slyusar

    The paper proposes a method for differentiating the Khatri–Rao products of several matrix functions used in digital antenna array (DAA) response mode