Ing. Magda Friedjungová, Ph.D.

2021 - 2023

Hlavním cílem projektu je vytvoření postupů pro analýzu tematických klastrů na materiálu uměleckého textu novočeské literatury a jejich následná aplikace na konkrétní digitalizovaně zpracované texty. Smyslem projektu je za využití softwarových nástrojů materiál uměleckého textu roztřídit podle stanovených kulturně-společenských kategorií, jež i dnes vnímáme jako společensky závažná a aktuální, do tematických hnízd, s nimiž bude moci uživatel pracovat, třídit je a kombinovat, což mu umožní nalezení nečekaných souvislostí v textech novočeského básnictví. Výstup výzkumu se následně promítne do prezentační aplikace, která bude zpřístupňovat takto zpracovaný materiál pomocí definovaných modulů podle cílového uživatele (čtenářská veřejnost; student středoškolák a vysokoškolák, resp. pedagog; badatel; vydavatel). Tato prezentační aplikace bude přístupná on-line a přinese nejvýznamnější knihy česky psané poezie 19. a počátku 20. století ve fulltextu s rozsáhlým rejstříkem nástrojů. Proponovaná aplikace má potenciál zásadním způsobem ovlivnit způsob výuky literatury, bude moderní didaktickou pomůckou a bude mít též dopad v oblasti výzkumu společenských věd.

2016

The project is focused on data mining of non-structured data from large-scale sources. The data are represented by textual and image/video information. To porcess the data, selected methods of artificial intelligence such as neural networks/deep learning, evolutionary algorithms and methods of image processing will be used. The need of these topics is evident from the fact that each year, the volume of data is doubling. At the same time, only 20 % of the available data are processed.

2022 - 2025

The project researches new methods of effective protection against cyber threats that misuse secured communication for cyber attacks against servers and computers in the environment of high-speed networks. Based on available metadata, the project will investigate Machine learning methods suitable for determining the characteristics of the encrypted network flows and associated risks. The system will be implemented using a hardware-accelerated traffic monitor and a software prototype for high-speed detection of security incidents, which will be reported to the SIEM tool. Further, a plug-in to the QRadar system for the incident analysis will be developed. The project outcomes will also include reference data sets of network traffic and a system for their collection and annotation.

2020 - 2022

The project focuses on research of modern algorithms and techniques in knowledge engineering in a broader sense. The topic of the project represents a promising and constantly expanding area both in terms of theoretical research and in terms of potential for practical applications. In particular, the project will focus on methods in data processing, extraction of information-intensive knowledge from data, and automatic search for explanations for phenomena occurring in the data. The important issue of contemporary artificial intelligence focused on knowledge processing is the limited ability or inability to give explanations leading to a certain decision, and thus often the decision cannot be formally supported and justified. The whole project through all sub-themes will therefore reflect this question. This is a doctoral project covering the diverse research interests of PhD students, but providing a general underlying question that encompasses all sub-themes. The project specifically aims to develop algorithms and techniques in neural networks, evolutionary algorithms, image and text processing, and motion information processing. The project is a direct continuation of a finishing SGS project from data processing area.

2017 - 2019

The project focuses on perspective and ever-expanding field of data processing and extraction of information of valuable content from the data. The methods for information extraction are increasingly using selected methods of artificial intelligence such as neural networks and evolutionary algorithms. Combined models or algorithms for text processing (text mining) come to the fore. The need of these topics is evident from the fact that each year, the volume of data is doubling. At the same time, only 20 % of the available data are processed.