|
|
Interviews 2.0 - Using AI for oral historians
Haubert, Marek ; Hlaváček, Jiří (advisor) ; Wohlmuth Markupová, Jana (referee)
This diploma thesis explores the integration of oral history with modern information technologies (IT), especially Artificial Intelligence (AI), aiming to investigate how these technologies can enrich the practice of oral historians and make the processing of oral historical interviews more efficient. It demonstrates, through practical examples, the possibilities of integrating AI and IT services at all stages of oral historical research, from interview preparation to realization, subsequent transcription, analysis, interpretation, and up to its security, archiving, and public publication. The thesis emphasizes practical demonstrations of technology use and research on available services and tools that can facilitate recording interviews, their transcription, sentiment analysis, or metadata creation.
|
|
|
Artificial intelligence in web development
Vaň, Denis ; Štípek, Jiří (advisor) ; Procházka, Josef (referee)
This bachelor thesis deals with the use of modern artificial intelligence, specifically OpenAI's GPT-4 model, for web development and applications. The introductory section provides an overview of artificial intelligence and details the key characteristics and development of the GPT-4 model. The basic principles of its operation are explained, including the transformer architecture and technologies such as Multi-Head Attention and Positional Encoding that are essential to its performance. Furthermore, the paper explores tokenization processes, including Byte Pair Encoding, and their impact on model efficiency. Token count limits, pricing policy and token management are also considered. The broader context of the importance of GPT-4 for the future of artificial intelligence and natural language processing is also discussed. The theoretical section also shows how and where GPT-4 can be applied. The practical part of the bachelor thesis presents how the GPT-4 model can independently create web projects of varying complexity, ranging from simple HTML and CSS pages to more complex applications using JavaScript, PHP and databases. It starts with projects such as personal business cards and interactive forms that demonstrate GPT-4's basic capabilities in creating and styling web content. Gradually, more...
|
|
|
Using artificial intelligence tools in education
Budský, Dominik ; Leipert, Jiří (advisor) ; Beneš, Martin (referee)
This bachelor thesis deals with the use of artificial intelligence, especially generative predictive text models such as the GPT model, in the educational process. The aim of the thesis is to provide teachers, pupils and students with a comprehensive guide on how to use these tools effectively to enrich the learning process, foster creativity and enhance effective preparation. The work details the application of AI in education, including lesson preparation, organization and inspiration for educators, as well as the benefits for students in learning and working with information. Practical applications and prompts for chatbots are demonstrated to show how educators, pupils and students can use these tools to their advantage. The paper highlights that integrating AI into pedagogical practice offers a range of benefits, from personalising learning to improving accessibility to education, and emphasises the potential of AI to transform traditional educational methods, with an emphasis on accessibility for all educators, pupils and students.
|
|
|
Modern vibrodiagnostics of machines and evaluation of datasets by neural networks
Koníček, Tomáš ; Holoubek, Tomáš (referee) ; Hammer, Miloš (advisor)
This Master‘s thesis focuses on technical diagnostics with an emphasis on vibrodiagnostics of machines and equipment. The aim is to carry out research on vibration monitoring using modern on-line systems and to investigate the possibilities of processing the acquired data files using neural networks. Vibration monitoring from Siemens SIPLUS CMS is analyzed, including a description of individual hardware and software components. The work also focuses on machine diagnostics using a real model equipped with the SIPLUS CMS system in cooperation with the SIMATIC S7-1200 programmable automaton. The obtained data will be transferred via the FTP protocol for further processing in the Matlab program. Neural network models will be designed and used, which will be trained on the measured data. Convolutional neural network model will be used. The results will be evaluated and a conclusion will be drawn.
|
|
|
Ritterkreuz: Action Game with Artificial Intelligence
Kubala, Jan ; Vlnas, Michal (referee) ; Milet, Tomáš (advisor)
Tato práce si klade za cíl vytvořit akční počítačovou hru, která krom očekávaných herních mechanik dokáže také zajímavým způsobem poskytnout informace o historii. Hra je tvořena v herním enginu Unity a kvůli rozsahu práce využívá i placené assety pro balistiku, pathfinding a prostředí úrovně. Hra obsahuje jednu úroveň, která se snaží autenticky vyobrazit jablunkovský incident, což byla přestřelka mezi německou záškodnickou jednotkou a polskou posádkou na Česko-polském pohraničí. Je to plíživá taktická střílečka z prvního pohledu, která se zaměřuje na vylepšený pohyb hráče, umělou inteligenci nepřátel a věrné vyobrazení tamější oblasti. Pohyb hráče je řešení založené na fyzice dělané na míru s rozšířenými možnostmi pohybu, jako přikrčení s několika úrovněmi, či dynamické lezení přes překážky. Umělá inteligence nepřátel jim umožňuje se pohybovat v klidném i bojovém prostředí a stejně jako hráč používají zbraně, jejichž projektily jsou balisticky simulované. Pro co nejbližší příblížení se dané oblasti byla využita reálná cloud pointová data z dané lokality, pomocí nichž se vygeneroval terén mapy. Dále byla přidána sekce s dokumenty a popisky zkompilované z různých výpovědí, které mají za úkol hráče obeznámit s okolnostmi této přestřelky.
|
|
|
Počítačová hra s umělou inteligencí
Ludrovan, Tomáš ; Goldmann, Tomáš (referee) ; Orság, Filip (advisor)
This thesis focuses on the development of multiplayer computer game and the examination of possibilites of using artificial intelligence for implementing entities controlled by the computer. The game code is written in C++ programming language and uses SDL2 library for user input and screen output. Besides others, some of the commonly used artificial intelligence algorithms are described here, which are used by the game either directly or as a modified version.
|
|
|
Recognition of movements of an active upper limb prosthesis for modern needs.
Pelypenko, Ihor ; Mézl, Martin (referee) ; Harabiš, Vratislav (advisor)
Tato práce zkoumá oblast moderních náhrad končetin s důrazem na optimalizaci ovládání pohybových funkcí aktivních protéz. Cílem projektu je analyzovat a zpracovat data k vytvoření klasifikačního systému pro následné použití na vlastních datech. První část je věnována výsledkům průzkumu dvou skupin dobrovolníků (fyzicky zdraví a jedinci s omezením), porovnávání těchto výsledků a výběru nejrelevantnějších funkcí horní končetiny. Poté jsou studovány metody zpracování EMG, následované výběrem nejvhodnější metody. Popsán je také proces pořízení vlastní databáze a její zpracování. V poslední části jsou popsány vytvoření a testování funkcionality modelu umělé inteligence a zhodnoceno, zda dosažené výsledky jsou úspěšné.
|
|
|
Using artificial intelligence to automate trading
Čermák, František ; Hůlka, Tomáš (referee) ; Matoušek, Radomil (advisor)
This thesis deals with the use of artificial intelligence for automating stock trading. The main objective was to investigate current technologies applied in algorithmic trading and then to design and develop an automated trading system using artificial intelligence. The work focuses on various aspects of algorithmic trading, including high frequency trading, cloud solutions, machine learning, blockchain and smart contracts. It also explores the applications of AI in trading, such as predictive analytics and natural language processing, and discusses the ethical and regulatory challenges associated with this technology. The design and development of an automated trading system is described in detail, including system architecture, choice of programming languages and tools, and implementation of trading algorithms. The results show that the use of artificial intelligence can significantly increase the efficiency and accuracy of stock trading, but technological and ethical risks must be considered. This thesis makes a significant contribution to research in the field of algorithmic trading and provides a foundation for further research in optimizing trading algorithms and integrating new technologies.
|
|
|
Artificial intelligence and politeness: a small-scale experimental study
Finkevich, Dzmitryi ; Smutný, Milan (referee) ; Sučková, Magda (advisor)
Cílem této studie je ověřit hypotézu, že aplikace UI poskytuje lepší odpovědi, pokud dostává zdvořilé zadání. Na základě známých teorií zdvořilosti Brown a Levinsona (1987) a Leeche (1983, 2014), byl navržen a proveden experiment, při němž byl ChatGPT, popularní chatbot založený na konverzaci s uživateli, promptován za využití pozitivní, negativní a zdvořilostní strategie a bez nich. Vygenerované odpovědi jsou analyzovány a následně srovnány dle jejich obsahové a jazykové stránky. Na základě výsledků tohoto experimentu, tato práce stanovuje praktická doporučení pro uživatele, jak optimalizovat prompty pro UI, a dosáhnout tak přesnějších výsledků.
|
|
|
A modern approach to measuring antibiotic susceptibility of microbial cultures using machine learning
Lepík, Jakub ; Burget, Radim (referee) ; Čičatka, Michal (advisor)
The bachelor's thesis focuses on antibiotic susceptibility testing (AST), specifically enhancing and automating the assessment of the disk diffusion method using machine learning and object detection architectures. Thanks to the TensorFlow development platform and extensive dataset, on which custom detection models like EfficientDet were trained, processing a wide range of input data is enabled. This brings the possibility of using mobile devices alongside traditional laboratory equipment when evaluating this method. By employing additional image processing techniques and the OpenCV library, a custom algorithm for measuring the size of inhibitory zones was developed, which, along with the detection models, is integrated within the application module developed by Bruker Daltonics GmbH & Co. KG. This module, created using the ASP.NET platform, is a precise and valuable tool for assisting personnel in microbiological laboratories.
|
guest ::
