The article addresses the use of multimodal psychophysiological data (eye tracking, EEG) and machine learning to predict consumer choices of sales offers. Classification models were built, key areas of interest (AOI) of offers were identified, and the significance of metrics was assessed. The highest predictive quality was achieved using Random Forest with oversampling. The most important AOIs were those related to the external visualisation of houses and the layout of rooms. The results confirm the usefulness of integrating psychophysiological data and machine learning in marketing.

The development of generative large language models (LLMs) opens up new possibilities in professional domains, including law. Tax law, in particular, poses unique challenges due to its dynamism, complexity, and susceptibility to errors (“hallucinations”). There is a need for a systematic evaluation of LLM capabilities in this context, especially for Polish tax law, and validation of tools supporting result verification. The aim of this study is a multi-faceted evaluation of the latest LLM in the analysis of Polish private tax ruling and assessment of the potential of the “LLM as a Judge” concept as a quality control tool. A two-stage experimental study was conducted. In Stage 1, four experts evaluated the quality of analyses for 100 tax interpretations performed by four LLM (Gemini 2.5 Pro/Flash, GPT-4o, DeepSeek R1) using a proprietary Legal Quality Index (LQI). In Stage 2, the model quality rankings established by experts were compared with the rankings created by the “LLM as a Judge” (based on the OpenAI 03 model), measuring concordance using Spearman’s rank correlation coefficient, Rank-Biased Overlap (RBO), and Cohen’s κ coefficient. The impact of the “critique + rerank” procedure on the quality of analyses was also examined. Stage 1 results showed varying model performance, with Gemini achieving the highest LQI. Stage 2 results showed very high concordance between expert evaluations and the “LLM as a Judge” (Spearman 0.861, RBO > 0.9 for low p, κ = 0.88). This confirms the reliability of automated evaluation, especially in identifying models from the top ranks. The “critique + rerank” procedure significantly improved the quality of the analyses. The obtained results suggest that LLM-based tools can serve as reliable support for quality control of tax law analyses, leading to process optimization and potential cost savings in law firms. Further research should focus on agent-based approaches, utilizing domain-specific knowledge bases, and analyzing the impact of AI on task completion time.

Purpose: This study aims to investigate the complex and multifaceted issue of changes in the quality of life of residents of the European Union (EU) member states from a dynamic perspective. This issue encompasses various social, economic, and political dimensions. Methodology: This study uses the vector measure construction method (VMCM) to compare the quality of life in 27 EU countries since 2004. The VMCM approach, based on vector calculus properties, uses a scalar product to analyse the actual objects of analysis. Indicators such as per capita income, housing conditions, healthcare, education, and social and environmental inequality will be identified. The aggregate measure and available data will be used to create a ranking of the quality of life in each EU country, with the top-ranked country serving as a benchmark for comparison in the second phase. Results: This study reveals that Ireland, Greece, Cyprus, and Luxembourg are the top performers in quality of life, while Hungary and Bulgaria consistently rank lower. Malta and Estonia show improvements in education, gross domestic product (GDP) per capita, income, and employment rates, while Poland and Spain experience declines. Slovenia is the top performer, followed by Malta and Lithuania, which have improved their ranking over time. Practical implications: This study underscores the dynamic nature of quality of life and provides valuable insights for policymakers and researchers alike.

Objectives The purpose of the article is to explore public awareness of knowledge autism and the phenomenon of discrimination in the school environment, their social and legal aspects. The scope of the study included the identification of problems related to the knowledge of the child's functioning, affected by autism , diagnosis and psychological-educational and medical assistance, the role of institutions and the family, the attitude towards children at school and outside school, and respect for the rights of children with autism. Material and methods A survey was conducted using a survey questionnaire. The survey was addressed to parents of students from three elementary schools witch were chosen for their variation in academic performance. The ranking was divided into a national part and a summary for eighteen provincial cities, in which 10,306 elementary schools qualified. In addition, a face-to-face interview was conducted with school principals. Results The results of the study are disturbing and indicate limited public awareness and unsatisfacto-ry understanding by the public of the occurring problem regarding people affected by autism. Studies show that society is is quite negative about the parents of children with dysfunctions. Conclusions The results of the survey indicate moderate public awareness among respondents regarding those affected by autism. The results obtained can contribute to a deeper reflection and awareness of the disorders and functioning of the child, and the implementation of measures to better understand the issues related to the functioning of a student with this condition. The results of the study may help in the decision of the Polish school to promote the discussed issues.

This paper presents the pyrepo-mcda Python package upgrade with the implementation of the Preference Vector Method (PVM) multi-criteria method. This upgrade extends the scope of multi-criteria decision analysis offered by this package. Several advantages of the PVM method, such as the reduction of the participation of decision-makers, the possibility of giving individual preference vectors, and the possibility of modification and further development, are in the interest of decision-makers in various multi-criteria decision analysis problems, particularly in the sustainability assessment.

Early school education has a very important role in the growth of young children. They get fundamental skills at this level of education, basic reading, and writing as the basis for their further development. Therefore, countries launch various types of programs supporting this process. This process is very complicated because it is influenced by many factors which exceed the educational obligations at the school level, including the very important role of state action. The success or failure of this process will depend on the State's actions in this regard. In the article, the authors attempt to use the opportunities offered by multi-criteria methods to analyze the level of development of Early School Education in Poland related to selected countries of the European Union.

Designing effective human-computer interfaces comes with significant challenges and this applies to interfaces used in e-learning as well. One way to design effective interfaces is by studying human reactions at the level of psychophysiological processes. This enables the analysis of system components' impact on cognitive and emotional human functions. The aim of this publication is to present a methodological approach for designing useful e-learning materials based on the measurement and analysis of eye movement activity and facial expression. The research results and conclusions are both methodological and applied in nature.

The TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) method is a modification of the distance reference method developed by Hwang and Yoon (Multiple Attribute Decision Making. Number 186 in Lecture Notes in Economics and Mathematical Systems. Springer, Berlin, 1981). It differs from the classical distance method by introducing an anti-pattern called the anti-ideal reference solution. The pattern is called the ideal reference solution. Between each decision variant and the ideal and anti-ideal solution, the distances are calculated, on the basis of which the value of the measure is determined.

This book presents the preference vector method (PVM) and the vector measure construction method (VMCM) for decision making with examples.

The normalized values of features are the base for calculating the measure describing a studied object. Depending on the selected variables, this measure may determine, for example, the competitiveness of an enterprise, the development of a region, investment attractiveness, etc. It is called an aggregate measure, and usually, based on the value of this measure, objects can be ordered linearly.

Making important decisions is usually a difficult and complicated task. In each enterprise, the people are responsible for its development in making a huge number of decisions regarding the economic process. Decision-making is an essential factor in many important problems at the level of an organization. Similarly, every person, regardless of the situation, must make different decisions in life. In such circumstances, the question arises about possible variants (alternatives). What could we gain and what could we lose by making these or other decisions? This question is important because each decision has its specific effects.

The selection of appropriate variables is a very important stage because it directly affects the results of the research. Inadequate selection of variables may lead to the results that misrepresent the analyzed research area. It can be considered in two aspects: their quality and reliability and compliance with the adopted research assumptions. In order for the obtained result to properly depict the research area, it is necessary to have both adequate quality data and the appropriate selection of variables representing the studied reality.

The field of resource management plays a crucial role in addressing the complex challenges of allocating resources within societal frameworks while considering ecological, legal, and practical considerations [...]

One of the decision-making problems is the problem of description, which is supposed to explain the decision-making situation by describing the alternatives and their consequences. One of the basic multi-criteria decision analysis (MCDA) tools that are used when considering the problem of description are graphical visualizations. The article presents visualizations developed for the presentation of data in the MCDA method called NEAT F-PROMETHEE. Since the NEAT F-PROMETHEE method is used to consider decision-making problems characterized by uncertainty and imprecision, it operates on fuzzy numbers. Therefore, it was important that the developed visualizations also present data in the form of fuzzy numbers and consider uncertainty. The verification of the developed graphic representations consisted in comparing the ease of processing, understanding and interpreting information presented in a visual and tabular form. As a result of the conducted research, the advantages of the graphical representation over the tabular one were noticed. Data presented in the form of numerical values included in tables, if there are a lot of them, may cause information overload of the decision-maker. Fuzzy numbers included in the tables are often difficult to read, and a big challenge for the analyst is to establish mutual relationships and compare fuzzy numbers described numerically. It is much easier to process fuzzy numbers in a graphical form, because then you can immediately observe the relationships between the numbers. • Developing a visualization of uncertain data for the NEAT F-PROMETHEE method • Comparison of clarity of graphical and tabular representation.

During the COVID-19 pandemic, the demand for systems supporting remote education increased significantly, and after the pandemic this form of education remained in place to supplement the stationary education. Among the tools that comprehensively support remote learning, there are two most popular systems, i.e. Google Workspace for Education and Microsoft Office 365, available in several different variants, differing in the functionalities offered. The aim of the article is to analyse the functionality, as well as to compare and evaluate this software. Since the assessment of e-learning systems is based on the subjective judgements of experts, and the assessment criteria are qualitative in nature, a new MCGDM (Multi-Criteria Group Decision Making) method called NEAT F-PROMETHEE GDSS (New Easy Approach To Fuzzy PROMETHEE – Group Decision Support System) was developed for the purposes of the study. This method captures the uncertain and imprecise qualitative assessments expressed by many experts and aggregates them into an overall quantitative assessment. As a result of the assessment, it was found that all variants of Google Workspace for Education and Microsoft Office 365 meet the basic requirements for tools for conducting remote learning. In addition, the use of the NEAT F-PROMETHEE GDSS method made it possible to create a ranking of individual software variants. Based on the group evaluation, it was determined that the best system in terms of the relationship between the offered capabilities and the cost of use is Google Workspace for Education Plus, with other variants of Google Workspace for Education taking subsequent positions in the ranking. In turn, Microsoft Office 365 solutions received a worse group rating, largely due to the higher cost of use and slightly less ability to control student work.

The pandemic period has made remote work a reality in many organizations. Despite the possible negative aspects of this form of work, many employers and employees appreciate its flexibility and effectiveness. Therefore, employers are looking for the most optimal tools to support this form of work. However, this may be difficult due to their complexity, different functionality, or different conditions of the company's operations. Decisions on the choice of a given solution are usually made in a group of decision makers. Often their subjective assessments differ from each other, making it even more difficult to make a decision. The aim of this article is to propose a methodological solution supporting the assessment of the most popular teleconferencing systems and generating their ranking. The feature of this solutions is the combination of two important methodological aspects facilitating the selection process. The first one concerns the possibility of taking into account quantitative and qualitative criteria expressed linguistically and of an uncertain nature in the assessment (NEAT F-PROMETHEE method). The second one is related to the possibility of taking into account the assessments of many experts, including the consensus study between them (PROSA GDSS method). The use of these combined methods to assess teleconferencing platforms made it possible to create their ranking and indicate the solution that best meets the adopted criteria (based on experts' opinions). The Microsoft Teams system turned out to be this solution, whose functionality, usability, multi-platform aspect and other elements turned out to be crucial in the context of the overall assessment. The results obtained may be a guideline for managers and decision makers facing the choice of a tool supporting remote work.

Microsoft Common Objects in Context (COCO) is a huge image dataset that has over 300 k images belonging to more than ninety-one classes. COCO has valuable information in the field of detection, segmentation, classification, and tagging; but the COCO dataset suffers from being unorganized, and classes in COCO interfere with each other. Dealing with it gives very low and unsatisfying results whether when calculating accuracy or intersection over the union in classification and segmentation algorithms. A simple method is proposed to create a customized subset from the COCO dataset by determining the class or class numbers. The suggested method is very useful as preprocessing step for any detection or segmentation algorithms such as YOLO, SSPNET, RCNN, etc. The proposed method was validated using the link net architecture for semantic segmentation. The results after applying the preprocessing were presented and compared to the state of art methods. The comparison demonstrates the exceptional effectiveness of transfer learning with our preprocessing model. Index Terms— COCO JSON files, Object detection, object tracking, semantic segmentation.

Decision-making is directly related to the preferences of a decision-maker. Most often, one can come across two models of aggregating preferences, namely the model based on the utility function (classical decision-making theory) and the one using the outranking relationship Słowiński (Podejście regresji porządkowej do wielokryterialnego porządkowania wariantów decyzyjnych. In P. Kulczycki, O. Hryniewicz, & J. Kacprzyk (eds.), Techniki informacyjne w badaniach systemowych (pp. 315–338). WNT, Warszawa, 2007). Both approaches have their supporters and critics. The first model assumes the existence of a utility function by means of which the assessment of individual decision variants is made. Variants may be equivalent or prevalence to each other (Kobryń (Wielokryterialne wspomaganie decyzji w gospodarowaniu przestrzenią. Difin SA, Warszawa, 2014)). Such a concept, along with the characteristics of selected methods based on the utility function, is described in Chap. 5 .

The studies on complex business issues in management described by multiple characteristics (indicators), use a variety of methodological approaches. Diverse decision support methods are used to solve problems in this area (depending on the situation considered). These methods include TOPSIS and VMCM. There are methodological similarities between them, but there are also several differences. VMCM eliminates some limitations of TOPSIS regarding, inter alia, the inclusion of non-typical objects, real-world patterns, and time-varying dynamics. Methodological considerations supplemented with an exemplary application are presented in this paper.