The Chair of Artificial Intelligence conducts research on new methods of data mining, also such as lack sufficient precision of description, which take into account incomplete cases and various causes of incompleteness. We develop methods of multi-strategic modeling of knowledge, its arithmetic and interrelational analysis of dependencies. We create unique solutions in the field of biomedical image processing and analysis algorithms which support effective diagnosis of malignant melanoma.
Contact: tmroczek@wsiz.edu.pl
Research teams
Integration of Psychology and Artificial Intelligence in Preventing Occupational Burnout
Occupational burnout is a complex syndrome resulting from prolonged and poorly managed stress in the workplace, leading to the gradual depletion of an employee’s emotional, psychological, and physical resources. This phenomenon has been officially recognized by the World Health Organization (WHO) and included in the International Classification of Diseases (ICD-11) as a work-related condition.
Burnout has a significant impact on both mental and physical health. It may lead to anxiety disorders, depression, sleep disturbances, reduced immunity, and cardiovascular diseases. At the social and organizational level, it results in decreased work efficiency, increased absenteeism, and higher employee turnover.
Due to the growing prevalence of occupational burnout and its serious consequences for individuals and institutions, the phenomenon has become the subject of intensive psychological, sociological, and medical research. However, there is still a lack of a comprehensive IT system that would enable the automatic detection of burnout symptoms and the generation of context-aware health-promoting recommendations tailored to individual user needs. The application of artificial intelligence in this area creates an opportunity to develop modern tools that support mental well-being monitoring, enable early detection of burnout risk, and facilitate the implementation of personalized preventive measures.
Research Team:
Agnieszka Jastrzębska PhD, DSc., Assoc. Prof. (KUL)
Małgorzata Przybyła-Kasperek, PhD, DSc., Assoc. Prof. (UŚ)
Dorota Pyrsak, PhD (UŚ)
Zofia Matusiewcz, PhD UITM
Teresa Mroczek PhD, DSc., Assoc. Prof. UITM
Aphasia – A Recovered Language
A new perspective, in which aphasic speech is treated as a distinct, new linguistic system (“a new language”), opens the way to a deeper understanding of the brain’s adaptive mechanisms and human linguistic creativity. This approach makes it possible to recognize the semiotic and expressive value of communication by people with aphasia, rather than viewing it solely as a disorder.
AI-based systems can serve as interactive communication assistants that learn an individual’s way of speaking and support them in everyday communication—for example, by predicting intentions, completing utterances, or translating the “new language” into forms more understandable to others.
From a broader perspective, the use of AI in this area encourages a shift in the paradigm of thinking about aphasia—from a medical (deficit-based) model to a linguistic-humanistic and inclusive one. It allows us to treat the speech of people with aphasia as a fully valid form of communication that can be studied, described, and technologically supported, rather than something that must be “fixed.”
Such an approach also has ethical and social implications, as it promotes a subject-centered view of people with aphasia, recognizing their language as an authentic means of expression rather than an “error” requiring correction. Consequently, it may contribute to changing the social perception of aphasia—from a disease and limitation to a form of human linguistic and communicative diversity.
Research Team:
Jakub Rezler, MSc. ITTI Poznań
Leszek Gajecki, PhD, UITM
Regina Waszut, MSc. Neurologopedist
Zofia Matusiewicz, PhD, UITM
Teresa Mroczek, PhD, DSc., Assoc. Prof. UITM
Intelligent Fuzzy Models in Identifying Key Features of Communication Systems
Discovering relationships between attributes and decisions using relational fuzzy equations and inequalities is particularly important in the analysis of contemporary datasets characterized by high complexity, a large number of features, as well as uncertainty and imprecision of information. Traditional analytical methods often fail to fully capture hidden relationships or identify the most significant decision variables, which limits the accuracy of classification and predictive models.
The application of fuzzy methods enables precise modeling of relationships between features and decisions while accounting for data ambiguity, which is crucial in the context of large, diverse, and multidimensional datasets. This makes it possible to identify relevant attributes, eliminate redundant ones, and increase the efficiency of analysis, classification, and modeling processes.
From a broader perspective, this research has not only methodological but also practical significance: it enables the development of more precise decision-support tools, particularly in fields where data are uncertain, fuzzy, or difficult to interpret using standard methods.
Research Team:
Zofia Matusiewicz, PhD, UITM
Teresa Mroczek, PhD, DSc., Assoc. Prof. UITM
Scientific research projects financed from external sources:
VISUAL – VERSATILE INFRARED LIGHT SOURCE FOR ADVANCED ILLUMINATION
Project manager: Łukasz Piątek , Ph.D lpiatek@wsiz.edu.pl
Medical and consumer electronics markets drive an ever-growing demand for powerful, compact, high quality and cost-effective femtosecond (fs) sources. Ophthalmic surgery and stent manufacturing in the medical field, post-processing of OLED panels defective pixels and smartphones machining in the consumer electronic field are examples of maturing processes where Ultrafast Lasers (UL) are key enablers. In the global scientific instrumentation market, non-linear multimodal optical microscopy (multiphoton absorption fluorescence or coherent Raman microscopy), high energy photon coherent radiation via high harmonic generation processes, high energy particle beam generation, time-resolved dynamic charge transfer studies in materials are in increasing use in research laboratories. Such increasing business perspectives fuel a worldwide competition for UL manufacturers.The VISUAL project aims to strengthen the leadership of the industrial UL manufacturing partners in the scientific, medical and industrial application fields, based upon a novel design-to-cost and innovative UL platform providing an unprecedented technical versatility. This high-average-power platform will deliver ultrashort optical pulses with pulse-on-demand capability at very high repetition rates (60 MHz) and with extremely broad wavelength tuning ability. The numerous benefits of this platform, designed for multi-purpose applications cases, will be assessed, within the framework of VISUAL, in label-free bio-imaging and medical diagnosis, in “on-chip” particle acceleration for electron-beam therapy, and in advanced fiber and glass microstructuration.
Period of implementation: 01.01.2024 – 12.2027
Funding: Horyzont Europe Program
Digital solutions for automatic skin cancer diagnosis
Project manager for the Polish team: Prof. J. W. Grzymała-Busse, for the German team: Prof. Jens Haueisen
The aim of the project is to develop methods and algorithms for image processing that will support the diagnosis of malignant melanoma performed by dermatologists and general practitioners, providing objective and reliable results. It will be implemented in cooperation with Technische Universität Ilmenau and the JensLab company.
Period of implementation: 05.2019–04.2022
Financing: National Center for Research and Development (NCBiR)
Contact: lpiatek@wsiz.edu.pl
Scientific research projects financed from the Ministry:
Exploration of incomplete data and biomedical imaging
Project manager: Teresa Mroczek, Ph.D tmroczek@wsiz.edu.pl
As part of this research, two separate goals are proposed: 1) creating new methods for analyzing incomplete data sets and moving away from the commonly used approach in incomplete data mining, i.e. imputing missing attribute values before the mining process for the development of incompleteness interpretation methods and set indicators, and 2) development of new methods enabling quantitative assessment of biomedical images, including mainly the development of a method for automatic classification of digital images of melanocytic skin
nevi using deep learning networks.
Period of implementation: 2023-2025
Hybrid models using fuzzy and approximate set theories and their application in medicine
Project menager: Barbara Pękala, Ph.D., Assoc. Prof. bpekala@wsiz.edu.pl
Development of Rough-Fuzzy models for image processing and analysis in the problem of “Optimization of physiotherapy offices” and development of an optimal hybrid rule system based on expert knowledge and machine learning.
Period of implementation: 2023-2024
Models of fuzzy and rough sets theory used for posture detection
Project leader: Barbara Pękala, Ph.D., Assoc. Prof. bpekala@wsiz.edu.pl
The aim of the research is to develop new methods of computational intelligence constructed for uncertain data requiring non-classical methods of representation and modelling. In particular, sets of fuzzy and approximate inference algorithms for detecting body posture will be identified, which demonstrate effectiveness at a given level of accuracy and quality of individual classification methods.
Implementation period: 2021-2023
