Vasyl Lytvyn

Lviv Polytechnic National University · Department of Information Systems and Networks

It has been noted in the research that classical methods are not sufficiently effective for finding optimal solutions in industry-specific geographic information systems (IGIS) because they do not consider logical parameters. It has been proposed to use clustering methods with the use of a conceptual model for selecting an optimization method, base...

This paper investigates the problem of embedding features used in datasets for training neural networks. The use of embeddings increases the performance of neural networks, and therefore is an important part of data preparation for deep learning methods. Such a process is based on semantic metrics. It is proposed to use ontologies of the subject ar...

Military symbols play a key role in the command and control of military forces. By communicating information that meets basic requirements, situational awareness can be quickly achieved; by its graphical nature, it provides a common operating language that greatly facilitates interaction across cultural and linguistic barriers. With the advent of i...

The object of the study is the architecture of a hybrid neural network for mine recognition using ultra-wideband radar data. The work solves the problem of filtering reflected signals with interference and recognizing mines detected by ultra-wideband (UWB) radar. A hybrid neural network model in combination with the Adam learning algorithm is propo...

The article develops a technology for finding tweet trends based on clustering, which forms a data stream in the form of short representations of clusters and their popularity for further research of public opinion. The accuracy of their result is affected by the natural language feature of the information flow of tweets. An effective approach to t...

The paper examines the process of building and functioning of the system for identifying terms and abbreviations in text documents. The task of developing such a system is urgent, since such an identification problem often arises in the military sphere. During the implementation of the system, it was taken into account that a single term or abbrevi...

In the paper, we introduce the structure of a convolutional neural network with diagonalized pooling (DiagPooling). Existing deterministic poolings, like max or Average, cause loss of some critical information, which may be helpful for a further classification task. To minimize that loss, we propose an algorithm that considers information from all...

Citation: Lytvyn, V.; Pukach, P.; Vysotska, V.; Vovk, M.; Kholodna, N. Identification and Correction of Grammatical Errors in Ukrainian Texts Based on Machine Learning Technology. Mathematics 2023, 11, 904. Abstract: A machine learning model for correcting errors in Ukrainian texts has been developed. It was established that the neural network has...

This paper solves two problems: the first problem is devoted to the recognition of distorted symbolic images by a single-layer incompatible dipole neural network, and the second - the optimization of computing resources in the recognition of distorted symbolic images. In particular, the architecture of an incompatible single-layer network with dipo...

In this article, we deal with the problem of increasing the accuracy of the automatic determination of the coordinates of the sound source location. We propose a new algorithm for the identification of the sound source’s position coordinates based on a system of three equations of the second order describing the dynamics of acoustic wavefront propa...

The growing complexity of software reflects the trend of mobility and changeability of business processes in our increasingly interconnected world. The change in the business process entails the difference in the supporting software, which should updated quickly and efficiently. Existing software architectures and approaches to design cannot provid...

The problems that occurred during decision-making and supported by the stochastic game model with the environment are investigated and analysed. A method of adaptive choice of solutions based on stimulatory learning and application of Boltzmann distribution is developed. The algorithm and software of the decision-making system in the games with the...

Context. This article describes how to solve the game problem of assigning staff to work on projects based on an ontological approach. The essence of the problem is this. There is a need to create teams to carry out several projects. Each project is defined by a set of necessary ontological knowledge. To implement projects, managers invite qualifie...

Context. Today, the problem of visual simulation of passenger flow in public transport is essential in creating information systems for the development of modern Smart City. In Industry 4.0, it is crucial to develop technologies, means, and tools for implementing a single self-regulatory intelligent data exchange system in the provision of appropri...

Large enough structured neural networks are used for solving the tasks to recognize distorted images involving computer systems. One such neural network that can completely restore a distorted image is a fully connected pseudospin (dipole) neural network that possesses associative memory. When submitting some image to its input, it automatically se...

Has been carried out analysis of the subject area and main functions of the intellectual system for research of space weather parameters are identified. The model of static structure of intellectual system is developed as well as its dynamic aspects are modeled. Also is constructed an architecture of intellectual system for research of space weathe...

In the era of limited resources and progressive environmental degradation, the circular economy is a practical application of sustainable development. It is an alternative, but also competitive way to achieve economic growth in accordance with the principles of sustainable development. This issue was considered in this paper in the context of the U...

A model of matrix stochastic game for decision making in conditions of uncertainty is developed. A Q-learning method is proposed for solving a stochastic game with a priori unknown payoff matrices. The formulation of the game problem is performed, the Markov recurrent method and the algorithm for its solution are described. The results of computer...

The optimal decision-making task based on the Markovian learning methods is investigated. The stochastic and deterministic learning methods are described. The decision-making problem is formulated. The problem of Markovian learning of an agent making optimal decisions in a deterministic environment was solved on the example of finding the shortest...

In this paper, we propose a method for optimizing the structure of a multilayer neural network based on minimizing nonlinear generalized error, which is based on the principle of minimum length of description. According to this principle, the generalized error is determined by the error in the description of the model and the error in the approxima...

Context. In today’s information society with advanced telecommunications through mobile devices and computer networks, it is important to form a variety of virtual organizations and communities. Such virtual associations of people by professional or other interests are designed to quickly solve various tasks: to perform project tasks, create startu...

Dynamic coordination of multi-agent systems (MAS) strategies under uncertainty based on a stochastic game model is solved. Dynamic coordination is teaching of the system of generating spatially distributed periodic signals. A stochastic game model is built, criteria for dynamic coordination of player strategies are determined, a recurrent method, a...

The content management method is proposed as a stage of its life cycle, which is based on the application of fuzzy logic. This method describes the processes of generating commercial information resources and simplifies content management technology. The article describes the methods and procedures for forming design decisions in the management of...

This paper shows a new type of artificial neural network with dynamic (oscillatory) neurons that have natural frequencies. Artificial neural network in the mode of information resonance implements a new method of recognition of multispectral images. A computer experiment was performed to recognize multispectral images by a dynamic neural network ba...

The article deals with a comparative experimental study of methods of searching for significant keywords of Ukrainian-language content. The approach to the automatic definition of keywords is based on Porter’s stemming of words of the Ukrainian language for the Levenshtein distance, taking into account the possibility of using a thematic dictionary...

Analysis of the specifics and methods of building intelligent systems of information resource processing by classifying them according to the principle and space of functioning, which will distinguish the types of such systems depending on the mathematical support of their functioning;

The article considers the development of a program for predicting areas on the design of the graphical interface, where users’ attention will be greatest. Current methods of improving graphic design in accordance with UX and software for getting UX information are considered. In this project the problem in complexity of creation of the graphic user...

Today, one of lot global problems is forest deforestation and monitoring. The article describes the system creation for forests control and monitoring. This work aims is to develop a model for the forest cover type determination based on environmental characteristics and machine learning as the currently developing project part “Monitoring the tree...

The system providing the automated monitoring of changes in web resources was designed and developed. The entire process is divided into five parts. Each subsequent stage included some parts of the previous one. The practical value of this system resides in the ability to detect, in the shortest possible time, the changes in web-resource. In case,...

In this paper we address the problem of designing an information system for methods and means of commercial distribution of information products using a personalized approach to visitors based on categories and tags for visitors that have interest to these information products. The designed system is the methods and means of reorganization in the o...

Information system for analyzing video stream data is developed, intended for conducting various types of video stream analysis. The optimal tools to develop the system are chosen, which allowed us to create a fast, reliable, optimized and user-friendly system with a comfortable web-based interface for users. The optimal hardware and software requi...

The intelligent system of a smart house, which is designed to create from any house, office, or building a smart room, was created in the overall process. Recent trends in technology development demonstrate that more and more things are being automated around us. Even ordinary things become «smarter» and open a new functional use. This has led to a...

Since the airspace is subordinated to the territories of different states, different authorities, such as Eurocontrol in Europe and FAA in America, etc., an acute need for a product that would provide easy, fast, high-quality flight planning, their proper dissemination, formation of necessary documents, etc. arises. Purpose is to cluster all necess...

Актуальність. Сьогодні більшість корпорацій постійно переосмислює бізнес з точки зору можливостей Інтернет, а самейого доступність, широке охоплення і постійно мінливі потреби користувача. Web-ресурс е-комерції, який забезпечуєзручний для користувача досвід, зокрема, можливість швидко знаходити необхідні згідно його портеб та смаку товари,більше пі...

The paper reports a study into recommendation algorithms and determination of their advantages and disadvantages. The method for developing recommendations based on collaborative filtering such as Content-Based Filtering (CBF), Collaborative Filtering (CF), and hybrid methods of Machine Learning (ML) has been improved. The paper describes the desig...

Unlike traditional databases, Big Data stored as NoSQL data resources. Therefore such resources are not ready for efficient use in its original form in most cases. It is due to the availability of various kinds of data anomalies. Most of these anomalies are such as data duplication, ambiguity, inaccuracy, contradiction , absence, the incompleteness...

In this paper, we propose a method for optimizing the structure of a multilayer neural network based on minimizing nonlinear generalized error, which is based on the principle of minimum length of description. According to this principle, the generalized error is determined by the error in the description of the model and the error in the approxima...

We have considered a task on designing an intelligent system of commercial distribution of informational products using a personalized approach to visitors based on the categories and tags of content that interests visitors. A general standard architecture of appropriate system has been developed using methods and personalization tools in the Inter...

In this paper, we propose a decision-making model based on the architecture of a three-layer perceptron with diagonal weighted synaptic connections between the neurons of the input, the latent and the original layers. The evolution of the model is carried out as a task of adaptation of the neural network, which consists of procedures for correction...

The approach to the development of computer system for automated construction of the basic ontology is presented. The mathematical support of functioning of intellectual agents of activity planning on the basis of ontologies was developed, which allowed to formalize their behavior in the space of states. Using ontologies allows to narrow the search...

Annotation. An overview of the design and development features of the Virtual Library information system was conducted. A new approach is proposed for designing and developing the Virtual Library information system for saving and development of e-books in the MARC 21 format. The model of information system Virtual Library is proposed.

The article describes the peculiarities of linguometry information technologies usage to determine the linguometric coefficients dynamics of the text content authorship. The linguistic and statistical analysis of the author texts within a certain time period takes advantage of the text content-monitoring based on the NLP methods to determine the se...

A formal approach was proposed to implement text content attribution. The study was conducted with Ukrainian scientific and technical texts. The results of application of the designed algorithms of automatic attribution of the text content based on the NLP and stylemetry methods were analyzed. Prospects and features of application of stylemetry inf...

The complex dynamic structure of the ontology and its content requires implementing of op-timization procedures to better ontology processing performance and resolve conflicts be-tween data. This paper addresses the issues of ontology optimization with the purpose of adapting its content to the needs of users by excluding those items that are rarel...

Розробленно лiнгвометричний метод алгоритмiчного забезпечення процесiв кон-тент-монiторiнгу для розв’язання задачi авто-матичного визначення автора україномовного текстового контенту на основi технологiї ста-тистичного аналiзу коефiцiєнтiв мовної рiз-номанiтностi. Проведено декомпозицiю мето-ду визначення автора на основi аналiзу таких коефiцiєнтiв...

The growth of volume of text resources on Internet and natural limitations of human cognition justifies the development of search enhancement systems. This paper proposes a contextual search method based on domain thesaurus. The method uses semantic metrics defined on thesaurus and weighted conceptual graph model for search enhancement. As an examp...