Annals of Computer Science and Information Systems, Volume 44
Position Papers of the 20th Conference on Computer Science and Intelligence Systems (FedCSIS)
Preface
Dear Reader, it is our pleasure to present to you Position Papers of the 20th Conference on Computer Science and Intelligence Systems (FedCSIS 2025), which took place on September 14–17, 2025. Kraków, Poland.
Position papers comprise two categories of contributions—challenge papers and emerging research papers. Challenge papers propose and describe research challenges in theory, or practice, of computer science and intelligence systems. Papers in this category are based on deep understanding of existing research or industrial problems. Based on such understanding and experience, they define new exciting research directions and show why these directions are crucial to the society at large. Emerging research papers present preliminary research results from work-in-progress, based on sound scientific approach but presenting work not completely validated as yet. They describe precisely the research problem and its rationale. They also define the intended future work including the expected benefits from solution to the tackled problem. Subsequently, they may be more conceptual than experimental.
FedCSIS 2025 was chaired by Jarosław Wąs. Moreover, Tomasz Hachaj was the Chair, while Marian Bubak, Marek Grzegorowski and Łukasz Rauch, were the Co-Chairs of the Organizing Committee.
This year, FedCSIS was organized by the Polish Information Processing Society (Mazovia Chapter), IEEE Poland Section Computer Society Chapter, Systems Research Institute of Polish Academy of Sciences, The Faculty of Mathematics and Information Science Warsaw University of Technology, The Faculty of Electrical and Computer Engineering of the Rzeszów University of Technology and The Faculty of Electrical Engineering, Automatics, Computer Science and Biomedical Engineering AGH in cooperation with The Faculty of Metals Engineering and Industrial Computer Science AGH, The Faculty of Materials Science and Ceramics AGH, and Centre for Computational Personalised Medicine SANO.
FedCSIS 2025 was technically co-sponsored by IEEE Poland Section, IEEE Poland Section Computer Society (Gdańsk) Chapter, IEEE Czechoslovakia Section Computer Society Chapter, IEEE Poland Section Systems, Man, and Cybernetics Society Chapter, IEEE Serbia and Montenegro Section Computational Intelligence Society Chapter, IEEE Serbia and Montenegro Section Young Professionals Affinity Group, Committee of Computer Science of the Polish Academy of Sciences and Mazovia Cluster ICT.
FedCSIS 2025 was organized in collaboration with the Strategic Partner QED Software, and sponsored by Intel+Lenovo, Jupiter as well as MDPI Electronics, MDPI Applied Sciences and MDPI AI journals. Moreover, FedCSIS 2025 has been conducted under Honorary Patronages of Professor Jerzy Lis, Rector of the AGH University of Kraków and of Aleksander Miszalski, Mayor of Krakow, as well as under patronages of the Ministry of Digital Affairs of the Republic of Poland, Polish Artificial Intelligence Society (PSSI), Forum Akademickie and Naukowe Towarzystwo Informatyki Ekonomicznej. Finally, media patronage was provided by Krakow.pl, TVP Info, TVP3 Kraków, and Kraków Convetion Bureau.
During FedCSIS 2025 four keynote speakers delivered lectures providing a broader context for the conference participants. These presentations were:
- Damaševičius, Robertas, Kaunas University of Technology, Lithuania: “AI-Driven Innovations in Brain Cancer Research”
- Dustdar, Schahram, TU Wien, Austria: “Active Inference for Distributed Intelligence in the Computing Continuum”
- Jonker, Catholijn, TU Delft (main affiliation), Leiden University, Vrije Universiteit Amsterdam, Netherlands: “Hybrid Human-AI Intelligence to Strengthen the Reflective and Learning Capacity of Organisations”
- Plank, Barbara, LMU Munich, Germany: “Human-centered LLMs for Inclusive Language Technology”
Moreover, four past FedCSIS keynote speakers have been invited to prepare special contributions, which refer to the core focus of the conference series. These were:
- Atiquzzaman, Mohammed, University of Oklahoma, USA:“Q-ID: A Reinforcement Learning Framework for Adaptive Intrusion Detection”
- Blum, Christian, Artificial Intelligence Research Institute, Spain:“Optimizing the Optimizer: An Example Showing the Power of LLM Code Generation”
- Luković, Ivan, University of Belgrade, Serbia:“New Education Challenges in Profiling Digital Experts for a Digital Economy Era”
- Skowron, Andrzej, Systems Research Institute Polish Academy of Sciences, Poland:“Interactive Granular Computing: Toward Computing Model for Complex Intelligent Systems ”
At the time, when you are reading this text, videos of the keynote presentations and of invited contributions, delivered during the FedCSIS 2025 conference, are already available on the official conference website (www.fedcsis.org). We warmly encourage you to visit the website and watch these recordings to gain additional insights and perspectives shared by distinguished speakers.
Finally, as a part of official Conference Opening, a special presentation, entitled: Paths to Zero Emission Computing -- Reducing Energy Consumption, and carbon emissions in HPC and AI environments, was delivered by Tikiri Wanduragala, Technology Leader Lenovo Infrastructure Solutions Group (ISG), Lenovo UK and Ireland. An extended abstract, outlining main pints of this presentation can be found in the Position papers of FedCSIS 2025 volume, published in the Annals of Computer Science and Information Systems book series.
FedCSIS 2025 consisted of Main Track, with five Topical Areas, and 12 Thematic Sessions. Some of Thematic Sessions have been associated with the FedCSIS conference series for many years, while some of them were relatively new. The role of the Thematic Sessions is to focus and enrich discussions on selected areas, pertinent to the general scope of the conference, i.e. intelligence systems.
Each contribution, found in this volume, was refereed by at least two referees. They are presented in alphabetic order, according to the last name of the first author. The specific Topical Area or Thematic Session that given contribution was associated with is listed in the article metadata.
The delivery of FedCSIS 2025 required a dedicated effort of many people. We would like to express our warmest gratitude to all Topical Area Curators, Thematic Session organizers, members of the FedCSIS 2025 Senior Program Committee and members of the FedCSIS 2025 Program Committee (a total of more than 600 individuals), for their hard work in attracting and reviewing all submissions. We thank the authors of papers for their great contribution to the theory and practice of Computer Science and Intelligence Systems. We are grateful to Keynote and Invited Speakers for sharing their knowledge and experiences with the participants. Last, but not least, we acknowledge, one more time, Jarosław Wąs, Tomasz Hahaj, Łukasz Rauch, Anna Smyk, Anna Stolarczyk Piotrowska, Marian Bubak and Marek Grzegorowski, and their Team, Anastasiya Danilenka and Paweł Szmeja, as well as a fantastic group of student helpers. We are very grateful for your efforts!
We also hope to meet you again for the 21st Conference on Computer Science and Intelligence Systems (FedCSIS 2026) which will take place in Riga, Latvia, on August 23-26, 2026.
Co-Chairs of the FedCSIS Conference Series
Marek Bolanowski, Rzeszow University of Technology, Poland.
Maria Ganzha, Warsaw University of Technology, and Systems Research Institute Polish Academy of Sciences, Poland.
Leszek Maciaszek (Honorary Chair), Macquarie University, Australia and Wrocław University of Economics, Poland.
Marcin Paprzycki, Systems Research Institute Polish Academy of Sciences, Poland.
Dominik Ślęzak, QED Software and University of Warsaw, Poland.
Position Papers
-
Enhancing Arabic ASR in Noisy and Transcoding EVS Conditions: A Multimodal Deep Learning Study
2032 Audio transcoding, Noise, Arabic speech, NMF, CNN LSTM, LSTM, DNN, SNR Lallouani Bouchakour, Khaled Lounnas, Ahmed Krobba, pages 1–8. NSA -
Examining the Increasing Use of Artificial Intelligence in Education, A step Closer to Personalized Learning
7856 AI, ML, EdTech Matteo Ciaschi, Marco Barone, pages 9–14. SL-SAS -
Enhancing Socio-Emotional Skills in Children with Autism through AI-Powered Serious Games: A Narrative Review
7538 Serious Games, Artificial Intelligence, Autism Spectrum Disorder Enza Curcio, Fabrizio Stasolla, Antonio Zullo, Mariacarla Di Gioia, Anna Passaro, pages 15–21. SL-SAS -
Practical security of evidence for regulated artificial intelligence modules
4971 artificial intelligence, functional identification, legal metrology Marko Esche, Levin Ho, Martin Nischwitz, Sabine Glesner, pages 23–30. AAIA -
SIG Denúncia - Web GIS of Popular Participation in the Public administration
6762 Web Geographic Information System (Web GIS) Geographic, Database, SIG Denúncia, Public Services, Public Administration, Popular Participation Henrique Pereira de Freitas Filho, Thiago Oliveira de Freitas, Johnny Evangelista Figueiredo, pages 31–36. ITBS -
Constructive genetic algorithm with penalty function for a concurrent real-time optimization in embedded system design process
5892 Genetic Programming, Concurrent Real-Time Optimization, Embedded Systems, Artificial Intelligence Adam Górski, Maciej Ogorzalek, pages 37–40. CO -
RAG⁴-Unet: An Approach for Recognition and Segmentation of Brain Tumor in MRI Scans
7399 Tumor Segmentation, Residual Attention Gated, Unet, Yolo11, Attention Maps Ameer Hamza, Robertas Damaševičius, pages 41–48. AAIA -
Evaluating Depression and Stress Among Young Adults Using DASS-21: Towards Personalized Intervention Strategies
7347 depression, stress, personalized intervention, dass-21, reinforcement learning, UCB Umamah Bint Khalid, Mario Fiorino, Madiha Haider S., Musarat Abbas, pages 49–54. SL-SAS -
Detecting Spatial Ordering of Nanoparticles with Geometric Deep Learning
8934 heterogeneous catalysts, graph neural networks, deep learning, scanning electron microscopy Jan Krupiński, Kazimierz Kiełkowicz, pages 55–60. AAIA -
Utilization of Large Language Models for conformity assessment: Chances, Threats, and Mitigations
7772 conformity assessment, large language models, confidentiality, metrology János Litzinger, Daniel Peters, Florian Thiel, Florian Tschorsch, pages 61–68. NEMESIS -
Integrating Real-ESRGAN with CNN Models for UAV Image Based Plant Disease Detection
2775 Crop Monitoring, Enhanced Super Resolution GAN, Deep Learning, UAV imagery, Precision Agriculture, Disease Detection Sravya Malladi, Pranav Kulkarni, pages 69–73. AgriAI -
Interpreting NAS-Optimized Transformer Models for Remaining Useful Life Prediction Using Gradient Explainer
8176 Remaining Useful Life (RUL), Transformers, Neural Architecture Search (NAS), Explainable AI (XAI), Gradient Explainer, C-MAPSS, Interpretability Messaouda Nekkaa, Mohamed Abdouni, Dalila Boughaci, pages 75–80. AAIA -
Adapting CycleGAN architecture for Unpaired Diachronic Text Style Transfer
4661 natural language processing, CycleGAN, text transformation, diachronic language changes, unpaired data Adrian Niedziółka-Domański, Jarosław Bylina, pages 81–86. CNLPS -
Towards Human-Robot Interaction in Agriculture Using Large
Language Models
0373 Large Language Models, AI, HRI, NLP, Precision farming, digital agriculture Lavanyan Rathy, Håvard Pedersen Brandal, Weria Khaksar, pages 87–92. AgriAI -
Multitask Learning for Six-Pack Toxicity Prediction
1171 multitask learning, biological readacross, six-pack toxicity, distinct chemical space, MTForestNet Chun-Wei Tung, Chia-Chi Wang, Run-Hsin Lin, Shan-Shan Wang, pages 93–97. AAIA -
Exploring Multi-Agent Reinforcement Learning for Cell Mechanics
4886 Multi-Agent Reinforcement Learning, Cell Mechanics, Cell Aggregation Muhammad Waris, Arsenio Cutolo Cutolo, Musarat Abbas, Mustafa Shah, pages 99–106. SL-SAS -
Paths to Zero Emission Computing—Reducing Energy Consumption, and carbon emissions in HPC and AI environments
9634 data center, zero emission, HPC Tikiri Wanduragala, pages 107–107. CSS -
DBRow: A Density-Based algorithm for autonomous navigation within crop rows
7442 Robotics, Navigation, Agriculture, Farming, crop, autonomous Peder Ormen Bukaasen, Weria Khaksar, pages 109–117. AgriAI -
Detection and Classification of Rumex Weeds in Grasslands Using YOLOv11
9629 Weed detection, AI, YOLO, Precision farming, digital agriculture Jorid Holmen, Weria Khaksar, pages 119–129. AgriAI
E-mail:
Phone/fax: +48-89-5246089