Intelligent Systems for IT

Intelligent systems do not represent a single, unified discipline but rather a set of approaches, methods, and technologies that combine elements of artificial intelligence, machine learning, data analytics, adaptive control, and interactive interfaces. This broad framework enables the integration of knowledge from multiple fields and supports the development of solutions capable of independent analysis, decision-making, and adaptation to changing environments. The evolution of intelligent systems is characterized by the close interconnection between theoretical foundations, computational methods, and practical IT applications.

Intelligent systems focus on solving complex problems that require learning, adaptation, and reasoning under uncertainty or incomplete information. They employ advanced algorithms of machine learning, neural networks, fuzzy logic, evolutionary computation, expert systems, and various hybrid methods. The goal is to design systems capable of understanding data, optimizing their own behavior, and supporting human decision-making.

In the field of information technology, intelligent systems have a wide range of applications — from data analysis and prediction, process optimization, automation, and service personalization to the development of adaptive information systems, intelligent agents, and virtual environments. Their importance continues to grow with the expansion of artificial intelligence, virtual reality, the Internet of Things (IoT), cyber systems, and Big Data, where efficient real-time information processing is crucial.

Current research focuses on the integration of intelligent systems into modern IT architectures, such as cloud computing, edge computing, and hybrid AI platforms. Particular emphasis is placed on explainability, transparency, and reliability, which are essential for deployment in areas such as healthcare, Industry 4.0, cybersecurity, and autonomous systems.

Thus, intelligent systems represent a key research direction that connects informatics, artificial intelligence, and modern technologies. Their objective is not only to automate traditional tasks but also to enable new forms of adaptive and context-aware information processing, pushing the boundaries of what is possible in contemporary information technology.

Research Teams and Staff Involved:

  • doc. RNDr. Martin Kotyrba, Ph.D. – Research Team Coordinator
  • prof. RNDr. PaedDr. Eva Volná, PhD.
  • doc. RNDr. PaedDr. Hashim Habiballa, Ph.D., PhD.
  • doc. RNDr. Petr Bujok, Ph.D.
  • Mgr. Rostislav Fojtík, Ph.D.
  • RNDr. Michal Janošek, Ph.D.
  • Mgr. Robert Jarušek, Ph.D.
  • Mgr. Alexej Kolcun, CSc.
  • Mgr. Marek Malina, Ph.D.
  • Ing. Pavel Smolka, Ph.D.
  • Ing. Zdeňka Telnarová, Ph.D.
  • RNDr. Marek Vajgl, Ph.D.
  • RNDr. Bogdan Walek, Ph.D.
  • RNDr. Matej Zuzčák, Ph.D.
  • RNDr. Jaroslav Žáček, Ph.D.
  • PhDr. RNDr. Martin Žáček, Ph.D.

Major projects over the last five years:

OP TAK CZ.01.01.01/01/24_062/0007501 Anafra Global Web 2026-2027
OP TAK CZ.01.01.01/01/22_002/0000497 24 VISION a.s. – Application 1 – Automation of Quality Control with Elements of Artificial Intelligence in a Hybrid Environment 2024-2026
OP VVV NPO_OSU_MSMT-16610/2022 Preparation of the Accreditation of the Doctoral Study Programme in Applied Informatics 2022-2024
Visegrad Fund 22210032 V4 Educational Academic Portal for Integrating IT into Education 2022-2023
EU ERASMUS +KA2 Active Education for Seniors without Barriers (ASEB) 2020-2023
TAČR TL02000313 Smart Neurorehabilitation System for Patients with Acquired Brain Injury in the Early Stages of Treatment 2019-2023
GAČR GA18-06915S New Approaches to Aggregation Operators in Data Analysis and Processing 2018-2020

Significant publications:

  1. Walek, B., & Müller, P. (2025). A text-based recommender system for recommending relevant news articles. Expert Systems with Applications, 266, 125816.
  2. Walek, B., & Fajmon, P. (2023). A hybrid recommender system for an online store using a fuzzy expert system. Expert Systems with Applications, 212, 118565.
  3. Kotyrba, M., Habiballa, H., Volna, E., Jarusek, R., Smolka, P., Prasek, M., ... & Jaremova, V. (2023). Proposal of neural network model for neurocognitive rehabilitation and its comparison with fuzzy expert system model. BMC Medical Informatics and Decision Making, 23(1), 221.
  4. Silva, P., Gonçalves, C., Antunes, N., Curado, M., & Walek, B. (2022). Privacy risk assessment and privacy-preserving data monitoring. Expert Systems with Applications, 200, 116867.
  5. Jarusek, R., Volna, E., & Kotyrba, M. (2022). FOREX rate prediction improved by Elliott waves patterns based on neural networks. Neural Networks, 145, 342-355.
  6. Hurtik, P., Molek, V., Hula, J., Vajgl, M., Vlasanek, P., & Nejezchleba, T. (2022). Poly-YOLO: higher speed, more precise detection and instance segmentation for YOLOv3. Neural Computing and Applications, 34(10), 8275-8290
  7. Barton, A., Volna, E., Kotyrba, M., & Jarusek, R. (2021). Proposal of a control algorithm for multiagent cooperation using spiking neural networks. IEEE Transactions on Neural Networks and Learning Systems, 34(4), 2016-2027.
  8. Kotyrba, M., Volna, E., Jarusek, R., & Smolka, P. (2021). The use of conventional clustering methods combined with SOM to increase the efficiency. Neural Computing and Applications, 33(23), 16519-16531.
  9. Volna, E., Jarusek, R., Kotyrba, M., & Zacek, J. (2021). Training set fuzzification based on histogram to increase the performance of a neural network. Applied Mathematics and Computation, 398, 125994.
  10. Zuzčák, M., & Bujok, P. (2021). Using honeynet data and a time series to predict the number of cyber attacks. Computer Science and Information Systems, 18(4), 1197-1217.

Updated: 01. 06. 2026