Факультет інформатики

Permanent URI for this community

https://ekmair.ukma.edu.ua/handle/123456789/17456

Browse

Now showing 1 - 20 of 840

3-D сегментація та візуалізація об'єктів на основі медичних зображень
(2020) Нгуєн, Сан Бинь; Бучко, Олена
Мета курсової роботи написати застосунок, на вхід якого подається набір медичних зображень, що являють собою 2D зрізи певної ділянки людського тіла, а на виході отримати модель, проекцію якої можна переглянути у 3D просторі. Були розглянуті стандартні алгоритми для побудови 3D-моделей та сегментації. Наведені методи покращення, оптимізації та виявлені певні недоліки наведених алгоритмів. Реалізація, тестування та дослідження основної частини програми були проведені за допомогою мови програмування Python та написаних під неї бібліотек. Для візуалізації отриманих 3D-моделей було додатково створено застосунок під операційну систему iOS з використанням методів доповненої реальності за допомогою бібліотеки ARKit. Оглянуто готові рішення.
3D-візуалізація об’єктів на основі медичних зображень
(2022) Першута, П.; Бучко, Олена
Метою даної курсової роботи є дослідження роботи алгоритмів побудови 3D-моделей на основі зрізів, отриманих в результаті томографії голови. Проведено аналіз актуальності теми та проаналізовано два алгоритми побудови 3D-зображень, а саме “крокуючі куби” та “крокуючі тетраедри”. Також було розглянуто алгоритми сегментації для покращення вихідної моделі. Реалізовано алгоритм “крокуючі куби” для отримання 3D-моделі на мові С++ з використанням бібліотеки OpenCV.
3D-візуалізація об’єктів на основі медичних зображень
(2022) Першута, П.; Бучко, Олена
Метою даної курсової роботи є дослідження роботи алгоритмів побудови 3D-моделей на основі зрізів, отриманих в результаті томографії голови. Проведено аналіз актуальності теми та проаналізовано два алгоритми побудови 3D-зображень, а саме "крокуючі куби" та "крокуючі тетраедри". Також було розглянуто алгоритми сегментації для покращення вихідної моделі. Реалізовано алгоритм "крокуючі куби" для отримання 3D-моделі на мові С++ з використанням бібліотеки OpenCV.
Architectural approach in Software development. Research and technology stack decision
(2021) Кузьменко, Дмитро; Корнійчук, Максим
The topic of architectural approach in software engineering is chosen for the research in this work. The topic is undoubtedly relevant at the moment. The further we progress technologically, the more requirements are set for new projects centered around the software. Also, more projects are being created, more products are being designed, and more diversified approaches can be assessed and chosen for many different tasks. Domain research and technology stack decisions do play a vital role in the potential risk avoidance and success of the project. This work will comprise of different segments, such as the theoretical part of software development architectural approach - architectural patterns, different methodologies to the development itself, server and client sides of the application as necessary parts of any product, core solutions to the set tasks, and solutions to continuous integration and delivery - are to be explored, assessed, compared and explained; the practical part - in which the team project is evaluated, the development process inside the team is shown, and the general structure of the project, as well as the decision per every point mentioned in the theoretical part, is explained; the demo part - involves demonstration snapshots
Astronomical images quality assessment
(2025) Цвєткова, Анна; Швай, Надія
У цій кваліфікаційній роботі проведено комплексне дослідження сучасних методів безреференсної (NR-IQA) оцінки якості астрономічних зображень у контексті задачі автоматичного виявлення гравітаційних лінз. На відміну від традиційних підходів, що базуються на наявності ідеального еталонного зображення, зосереджено увагу на моделях, здатних відображати наукову значущість зображення без зразків — що є критично важливим у контексті реальних астрономічних спостережень, зокрема отриманих через open source проєкти. У першій частині роботи наведено теоретичні засади Image Quality Assessment (IQA) методів, включно з оглядом сучасних моделей: як класичних, так і глибоких нейронних мереж, з адаптацією до специфіки астрономічних даних (PSF, шум, FWHM, фонові варіації). Окрему увагу приділено методології трансферного навчання та використанню попередньо тренованих за допомогою Full Reference (FR) метрик моделей для оцінки зображень у реальному часі. Друга частина містить опис проведених експериментів: від побудови адаптивної системи зважування метрик (FWHM, SNR, ellipticity) до кореляційного аналізу між результатами моделей NR-IQA та ефективністю виявлення гравітаційних лінз. Також запропоновано власну гібридну метрику для оцінки якості, що узгоджується з візуальною експертизою астрономів, та показано її переваги у задачах відбору пріоритетних кандидатів для подальшого моделювання лінз. Результати роботи демонструють, що навіть за відсутності точної ground truth NR-IQA моделі можуть забезпечувати релевантні оцінки якості, корисні для автоматизованого аналізу великих масивів астрономічних зображень. Запропонований підхід дозволяє не лише фільтрувати спотворені дані, але й підвищити recall систем гравітаційного лінзування за рахунок покращення вхідної якості даних.
Binary relations between binary operations
(2021) Bilyi, Illia; Козеренко, Сергій
Let Bin(X) be a collection of all groupoids on some non-empty set X. De ne the operation : Bin2(X) ! Bin(X) so that x( )y = (x y) (y x) for all x; y 2 X and (X; ); (X; ) 2 Bin(X). Let lz denote left-zero operation (8x; y 2 X : x lz y = x) on X. Then, (X; lz) is an identity of (Bin(X); ). Similarly, de ne right-zero rz 2 Bin(X) (8x; y 2 X : x rz y = y). We consider the center of (Bin(X); ) and represent its elements as graphs. Furthermore, we investigate distributivity from the left in Bin(X) and its interaction with -product. We show that the only operation that is left- distributive over all possible 2 Bin(X) is rz 2 Bin(X) and that any 2 Bin(X) is left-distributive over lz; rz 2 Bin(X).
Boolean network optimization by stochastic rewiring
(2024) Черевко, Крiстiна; Олійник, Богдана
This bachelor thesis introduces novel algorithms for the area minimization of Multi-Input And-Inverter Graphs (MAIGs) within the field of logic synthesis. The primary focus is on the implementation of a new method named "Boolean network optimization by stochastic rewiring". This approach significantly diverges from traditional techniques like algebraic factoring and AIG rewriting by adopting a global strategy to add and remove wires at various locations within the circuit. The method relies on a simple randomization strategy to produce structural variations in the AIGs. Additionally, the thesis formulates and proves a new criterion for acceptable fanins, which ensures valid insertions and deletions without compromising the functionality of the circuit. Experimental results validate the effectiveness of the proposed algorithm in optimizing benchmark circuits. This work is important as it addresses the growing demand for smaller, more efficient circuits in modern electronics, potentially reducing manufacturing costs and enhancing performance.
Coherence in the coupled oscillators for the case of financial time series
(2020) Марченко, Анастасія; Щестюк, Наталія
The analysis in natural science leads to spreading the ideas of chaos theory and non- linear dynamics to nancial mathematics and creating the new researches to consider similar models and procedures for nancial time series. Also, the irregular uctuations in these series are sometimes considered as an outcome from chaotic systems.[1] This can be used, for example, to forecast the value of an investment portfolio, which is the combination of di erent nancial assets, for example, stocks, bonds, cash. One of the ways to think about a successful portfolio is when the chosen equities have the high expected returns and synchronized in time for bottom moments.[2] Then the dynamics of these nancial assets can be described as oscillators connected in the network.
Comparative Analysis of Development Environments for UAV Software Development
(2025) Budilova, Sofiia; Kurochkin, Andrew
Unmanned aerial vehicles are in demand nowadays due to their ability to perform various tasks, both military and civilian, without the involvement of humans. The UAV simulators (UAV algorithm development environments) have a great value at the present day since they present a way to test all the new UAV algorithms that are spreading more and more finding real-world applications across various disciplines. A plethora of simulators already exist. All of them have their own advantages and disadvantages. This presents difficulties for developers to opt for the most suitable one to meet their requirements. This paper reviews the most popular UAV simulators. It also provides statistics regarding the amount of papers in general and throughout the years related to simulators and also to flight control software (e.g., ArduPilot). This provides the opportunity to observe tendencies in UAV simulation technologies. Subsequently, research was conducted to analyze scenes (usually called worlds) of the most popular and robust simulator, namely Gazebo, that are available open-source online. тA list of them is provided in this thesis. Eventually, a research gap was found, namely a shortage of Gazebo worlds containing moving objects. A new world with a moving car was created and might be used, for example, for the testing of the UAV object-tracking algorithms.
Creation and distribution of the commercial project
(2020) Гончар, Андрій; Ющенко, Юрій
In this coursework the basic lifespan of a startup or a regular project are described. Specific situations, which come up during building and managing the team are explained. There is also a description of the work done to create the app “Quarantine” . The idea of this app is just a fun for the users and money income for the developers from the adds banners inside the app. The preparations done before launching the app are also described below. All the paragraphs describe the real experience gained by the author during the “Quarantine” project.
Creation of an atomic cross-chain escrow, which supports EVM, Solana and TON
(2025) Rastiehaiev, Volodymyr; Gorokhovskyi, Kyrylo
This paper presents the design, development, and evaluation of an atomic cross-chain escrow system facilitating secure, trustless asset transfers between Ethereum Virtual Machine compatible blockchains, Solana, and The Open Network. Driven by the increasing fragmentation of the blockchain ecosystem and the demand for seamless cross-chain interoperability, this work addresses the limitations of centralized intermediaries and existing bridge solutions. The research involved identifying key challenges in atomic cross-chain escrow development, including differing blockchain architectures and HTLC concept and its core principles. As a core contribution, three distinct smart contracts were engineered, one for each target blockchain (EVM, Solana, and TON), to enable a hash-time-locked escrow mechanism. The developed contracts were evaluated for security and efficiency, demonstrating the feasibility of achieving guaranteed fund delivery or refund across these disparate networks without reliance on a trusted third party.
Decoding Speech from ECoG with Machine Translation Models
(2023) Burakov, Roman; Shvai, Nadyia; Wang, Bo
This paper explores the use and improvement of brain-computer interface (BCI)- based speech neuroprostheses, devices designed to enhance communication for individuals with speech disorders. Focusing on the machine learning aspect, we address the existing challenges associated with these systems, such as the limited vocabulary and simple algorithms of previous research and the individual variances in electrode implantation sites. Our approach reframes the decoding of speech from BCI as a machine translation problem and employs existing language models for semantic knowledge transfer. This research provides an extensive analysis of current neural speech decoding and multilingual neural machine translation methods, adapts the pre-existing M2M100 neural machine translation model for decoding ECoG data into text, and introduces a state-of-the-art model for neural speech decoding that improves upon current methods in semantic text reconstructions.
Dependent Types for Formal Theorem Proving: A Case Study of Hall’s Theorem
(2023) Власенко, Павло; Жежерун, Олександр
This thesis investigates the role of dependent types and Curry-Howard isomorphism in formal theorem proving and programming. First, we highlight the connection between formal logic and type theory and demonstrate how dependent types allow us to encode complex properties like proofs or programs. Next, we introduce Lean, a language utilizing dependent types, and show practical examples to check that the program will never fail and be correct at compile time without needing tests. Finally, we will show an example of a more complex theorem defined in Lean – Hall’s graph theorem and how to use its proof to write the verified program.
Developing a Hybrid AI model for Financial Market Prediction
(2025) Войтішин, Микита; Кузьменко, Дмитро
Over the recent years, financial time series modeling has presented a significant challenge due to market stochasticity and volatility. The stock market is influenced not only by market data such as price and volume but also by a wide range of additional external factors, including macroeconomic indicators, seasonality, fundamentals, and market sentiment. The increasing availability of diverse financial data, combined with the rapid advances in artificial intelligence (AI), has opened up new possibilities for analyzing and understanding how stock markets behave. These technologies have the potential to capture more complex nonlinear patterns that traditional statistical and machine learning models often fail to detect. This research examines how combining various model architectures and feature sets with domain - specific knowledge from the financial sector can enhance uncertainty quantification, a crucial aspect of making informed decisions and investments in financial markets.
Developing a Trip Planning Application with a Focus on People with Disabilities
(2025) Орлов, Станіслав; Андрощук, Максим
Ця робота демонструє етапи розробки організаційної системи для планування подорожей, що враховує потреби людей з інвалідністю, у вигляді Android-застосунку. Описано аналіз наявних подібних рішень на предмет інклюзивності, виявлено та категоризовано їхні бар’єри у забезпеченні інклюзивності, викладено функціонал створеної системи, а також обґрунтовано вибір програмних засобів та технологій, використаних у роботі.
Development and Implementation of a Military Technology Trends Monitoring System
(2025) Prokhorov, Oleksandr; Kurochkin, Andrew
This work presents the design and implementation of a system for monitoring technological trends in the military sector using Telegram as a data source. The system automatically collects, processes, and analyzes both historical and real-time posts from selected Telegram channels, focusing on the emergence and dissemination of key terminology such as "реб" (eng.: "electronic warfare") in our evaluation case study. A modular architecture was developed, combining Go-based data scraping, Python-based aggregation and keyword analysis, and a Grafana dashboard for visualization. The system supports both local Docker-based deployment and cloud-based deployment via Terraform on AWS. Evaluation included performance benchmarks, peak resident-set size (RSS) profiling, and a case study comparing our system’s findings against professional media and Google Trends. Results indicate that a Telegram-based pipeline can detect rising interest in electronic-warfare topics earlier than traditional information channels.
Development of a proprietary game engine
(2025) Burliai, Danylo; Gorohovskyi, S.
The present study focuses on the development of crossplatform game engines. It reveals how technologies like reflection systems and game editors can streamline the development of games. The project developed for this study is a cross-platform game engine, featuring a built-in reflection system and an editor application, supporting both Windows and MacOS.
Development of the auditoriums’ occupation management system called “KMAuditoriums”
(2020) Леськів, Олександр; Глибовець, Андрій
In the modern world, most applications are built using software as a service (SaaS), client-server approach. With server-rendering is no longer being a common nor recommended practice for most scenarios, Frontend development became separated from the Backend one. They might be built using different languages and technologies and will usually be hosted on two different servers, one for web’s static files serving and another for the application programming interface (also known as API) server. The only thing that ties those two is the HTTP protocol. With that, the whole application development becomes more flexible as frontend and backend teams can work independently of each other and even test their code using mock data (for frontend) and an API development tools like Postman (for backend) to be completely separate.
Diffusion models for music generation
(2024) Савкін, Гліб; Крюкова, Галина
In this work, we aim to research the possibility of applications of diffusion models for the task of symbolic audio generation. We will implement and train a diffusion model, comparing its performance against other popular models for music generation. By providing results and analysis, this study aims to demonstrate the advantages of DDPMs for music generation and to create a foundation for future research in the use of generative models in music generation.
Dropout for Neural Networks Pruning
(2025) Семенець, Дарина; Швай, Надія
In this study, the hypothesis is examined whether Dropout masks can be used for structural pruning without further evaluating the importance of individual filters or weight. It was decided to compare a Dropout-based approach, which is based on the utilization of binary Dropout masks, with a classical L2-Norm-based pruning method. For this task, we manually designed an architecture of a convolutional neural network with a custom Dropout. The research undergoes the following phases: designing a mask generation mechanism, preprocessing data, training of model, implementing of pruning algorithms, and conducting experiments using the Imagenette2 dataset. Our idea is to determine whether Dropout pruning can offer a reliable alternative to traditional methods, especially under different levels of sparsity and stochasticity.

Browse

Browsing Факультет інформатики by Title

Results Per Page

Sort Options