Otevřená data na Zenodo

Although Body Positivity content (BoPo) has been criticized for emphasizing physical appearance and promoting self-objectification, the specific features driving these effects remain unclear. The pres…

Although Body Positivity content (BoPo) has been criticized for emphasizing physical appearance and promoting self-objectification, the specific features driving these effects remain unclear. The present study examined whether depictions of female bodies act as triggers for self-objectification in BoPo on Instagram. In a between-subjects online experiment involving 158 women aged 18-29 (M = 21.6, SD = 2.4), exposure to female bodies in BoPo posts did not heighten state self-objectification. Trait self-objectification and negative mood did not moderate these effects; however, women with negative attitudes toward BoPo reported higher levels of state self-objectification. These findings underscore the potential importance of subjective appraisals in shaping the impacts of BoPo content. Overall, the study contributes to the ongoing debate about the potentially negative effects of BoPo on Instagram, suggesting that body depictions alone may not reinforce self-objectification. Future research should examine the distinct influence of different types of body portrayals to further clarify the impact of BoPo content on body image. From a practical perspective, prevention efforts and social media campaigns should aim to raise awareness of BoPo features that continue to overemphasize appearance, helping women better protect their body image from potential adverse effects.

In this work, we consider a particular construction of IF--THEN rules and the associated inference mechanism, which coincide with the so-called quantile fuzzy transform (or L1-fuzzy transform). Given …

In this work, we consider a particular construction of IF--THEN rules and the associated inference mechanism, which coincide with the so-called quantile fuzzy transform (or L1-fuzzy transform). Given a suitable fuzzy partition of the underlying universe and a random variable defined on a probability space, the system is formulated through rules stating that if the input belongs to the $k$-th fuzzy set, then the output is modeled by a corresponding quantile function.The consequent is represented by weighted quantile functions that provide statistical estimates of the output distribution conditioned on the input's membership in the respective fuzzy set. A crucial step in the inference process is the estimation of these quantile functions from data. Traditionally, weighted quantiles are computed via linear programming. We have recently introduced an alternative and computationally efficient method for evaluating weighted quantiles based on the analysis of the right derivative of the associated convex objective function.Although classical weighted quantiles are computationally efficient, they may be inadequate for accurately capturing the local positions of output quantiles over fuzzy inputs. To overcome this limitation, we have extended the weighted quantile approach into a piecewise linear functional form. In this contribution, we propose a slight modification of this construction to enhance its applicability to forecasting tasks. We describe the modified approach, demonstrate its improved inference performance compared to scalar weighted quantiles, and highlight its relevance for forecasting applications. 

This work studies the inference mechanism of fuzzy-probabilistic inference systems (FPIS), a class of rule-based models where antecedents encode fuzzy information and consequents represent conditional…

This work studies the inference mechanism of fuzzy-probabilistic inference systems (FPIS), a class of rule-based models where antecedents encode fuzzy information and consequents represent conditional probability distributions of the output variable. A system of m rules is considered: if the input belongs to a fuzzy set A_k, then the output follows a probability distribution described by an empirical quantile function. The antecedents form a covering fuzzy partition of the universe, ensuring that every input has positive membership in at least one fuzzy set. In practice, uniform or generalized partitions are typically employed. Local quantile functions are estimated from data as weighted quantiles, with weights given by membership degrees. The inference mechanism produces an empirical quantile function for any input as a linear combination of these local quantile functions, using normalized membership weights. Fuzzy rule-based systems capture input-output relationships in a rough manner, while the inference mechanism refines this into a complete mapping usable in practice. Previous studies compared the standard weighted average of quantile functions with several alternatives on synthetic and real datasets. However, a theoretical analysis of these mechanisms, including the original weighted average and related L1-based minimization approaches, remains open. This gap motivates a deeper investigation of the foundations of the inference mechanism for FPIS. 

In this contribution, we present the multiplets algorithm for constructing and selecting optimal sets of disjoint hyperedges across multiple groups in tabular data. We describes main computational ste…

In this contribution, we present the multiplets algorithm for constructing and selecting optimal sets of disjoint hyperedges across multiple groups in tabular data. We describes main computational steps and provide a complexity analysis covering both the edge construction and optimization phases, based on the Linear Sum Assignment method and the Constraint Programming SAT-based solver. 

Tato práce aplikuje grafové neuronové sítě na predikci podcílů ve hře s názvem Ricochet Robots, NP-úplné logické hře. Herní stavy …

Tato práce aplikuje grafové neuronové sítě na predikci podcílů ve hře s názvem Ricochet Robots, NP-úplné logické hře. Herní stavy jsou reprezentovány jako orientované grafy, kde uzly odpovídají políčkům mřížky a hrany reprezentují pohyby robotů. Rekurentní architektura Graph Attention Network je trénována k napodobení hierarchické vyhledávací heuristiky, která identifikuje slibné pozice (podcíle), kterých by cílový robot měl dosáhnout. Vyhodnoceny jsou dva klasifikační úkoly: identifikace políček, ze kterých je cíl nezávisle dosažitelný, a predikce optimálních podcílů. Model dosahuje téměř dokonalého výkonu u jednoduššího úkolu dosažitelnosti a prokazuje významné učení u komplexnějšího úkolu predikce optimálních podcílů. Výsledky potvrzují, že grafové neuronové sítě dokážou zachytit prostorové uvažování potřebné pro identifikaci podcílů ve výpočetně náročných problémových doménách, čímž vytvářejí základ pro autonomní objevování podcílů v komplexních stavových prostorech. 

In this work, we pose the question of how to assess the dissimilarity of pairs of information granules that may be exemplified with I1 and I2. We focus on two representative types of information granu…

In this work, we pose the question of how to assess the dissimilarity of pairs of information granules that may be exemplified with I1 and I2. We focus on two representative types of information granules, namely fuzzy association rules (FAR) and fuzzy linguistic summaries, and aim to (1) propose a unified notation for the construction and selection of the most meaningful fuzzy information granules, and (2) analyze and discuss the assessment of dissimilarity across the considered types. 

This contribution builds upon previous achievements in the theories of generalized and intermediate quantifiers, and the evaluative linguistic expressions. In this work, we study the antonym property …

This contribution builds upon previous achievements in the theories of generalized and intermediate quantifiers, and the evaluative linguistic expressions. In this work, we study the antonym property of fuzzy linguistic summaries with absolute linguistic expressions. First, we briefly review qualitative evaluation criteria with a particular focus on the degree of truth (as baseline) and the degrees of imprecision and specificity. Next, we consider the property of antonym and investigate its adequacy for the selected criteria. 

This paper reports on the empirical performance of few-shot learning (FSL) for visualdefect classification using confidential industrial datasets. We evaluate 16 combinations offour backbone models (P…

This paper reports on the empirical performance of few-shot learning (FSL) for visualdefect classification using confidential industrial datasets. We evaluate 16 combinations offour backbone models (Perception Encoder, DINOv2, DINOv3, ConvNeXt-v2) and fourFSL classifiers (Prototypical Networks, Neighborhood Component Analysis, Relation Networks,Linear Adapter). The evaluation covers three conditions: a baseline comparison,deterministic support set augmentation, and a learnable attention preprocessor. Resultsdemonstrate that support set augmentation is a highly effective strategy, improving performancein nearly all configurations. Furthermore, the DINOv2 and ConvNeXt-V2-T backbonesemerged as top performers, achieving the most competitive and highest-accuracyresults, respectively. These findings suggest that for industrial FSL applications, combininga strong, pre-trained backbone with a simple augmentation strategy is a practicalapproach for building data-efficient classification systems. 

This paper examines the application of fuzzy natural logic in the analysis of scientific data and their representation through special linguistic expressions. We use the theory of evaluative linguisti…

This paper examines the application of fuzzy natural logic in the analysis of scientific data and their representation through special linguistic expressions. We use the theory of evaluative linguistic expressions, which makes it possible to describe quantitative data using imprecise expressions such as ``very small'', ``medium'', ``large'', and similar. They occur in the definition of the so-called intermediate quantifiers, using which we characterize given data. 

In this article, we will examine the validity of selected forms of logical syllogisms with intermediate quantifiers. We will focus in particular on forms related to the graded Peterson's cube of oppos…

In this article, we will examine the validity of selected forms of logical syllogisms with intermediate quantifiers. We will focus in particular on forms related to the graded Peterson's cube of opposition. Our verification will be based on the application of graded Peterson's rules using the distribution index.