Všechny publikace

This article examines the role of digital skills in the health sector, where healthcare social workers perform their professional work, using the Delphi method in two rounds: 2020 (pre-Covid-19 contex…

This article examines the role of digital skills in the health sector, where healthcare social workers perform their professional work, using the Delphi method in two rounds: 2020 (pre-Covid-19 context) and 2021 (Covid-19 context). Experts point out three major transformations in organisations resulting from digitalisation: (i) the growing importance of digital skills; (ii) the relevance of developing a leadership adapted to a digitalisated context, and (iii) the key role of health managers and their organisations. Based on the results obtained, a conceptual approach based on the Shaw et al. (2017) model is proposed to face the challenges of e-Health, explicitly centred on fostering both organisational and individual wellbeing. This leadership model aims to improve the wellbeing of workers in the healthcare sector, including healthcare social workers.

DXAlyzer is a desktop tool for extracting, reviewing, validating, and exporting DXA measurement data from Hologic DXA PDF reports and OCR text exports. The application runs locally, stores data in a l…

DXAlyzer is a desktop tool for extracting, reviewing, validating, and exporting DXA measurement data from Hologic DXA PDF reports and OCR text exports. The application runs locally, stores data in a local SQLite database, and prepares cohort-level CSV tables and SVG figures for research and publication workflows. Features Import DXA reports from .pdf, .txt, .text, and .ocr files. Extract patient identifiers, scan dates, BMD, BMC, T-score, Z-score, fat mass, lean mass, and total mass values. Review and edit extracted records before saving them. Validate measurements with QC status and notes. Compare repeated measurements for the same patient. Export full measurement data to CSV. Generate publication summary tables and subject-level change tables. Export cohort figures as SVG. Manage parser templates for different report formats. Requirements For running from source: Python 3.11 or newer Windows, macOS, or Linux with Tkinter support Python dependencies are listed in requirements.txt. Run From Source python -m pip install -r requirements.txt python main.py   Application data is stored locally in: ~/DXAlyzer/dxa.db ~/DXAlyzer/templates/   Windows Executable The Windows executable is built with PyInstaller and published through GitHub Actions. To download it: Open the repository on GitHub. Go to Releases. Download DXAlyzer.exe from the latest release. If there is no release yet, open Actions, run the Windows Release workflow manually, and download the windows-DXAlyzer artifact. Build On Windows From a Windows command prompt in the project folder: build.bat Expected output: dist\DXAlyzer.exe   More release and code-signing details are documented in WINDOWS_RELEASE.md. Basic Workflow Import PDF reports or OCR text exports. Review extracted records before saving. Check measurement quality in the QC tab. Run cohort analysis. Export CSV tables and SVG figures.   Acknowledgements This software was developed as part of the project Research of Excellence on Digital Technologies and Wellbeing, CZ.02.01.01/00/22_008/0004583, co-funded by the European Union. License This project is licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0). 

Abstract Digital Behaviour Change Interventions (DBCIs) aim at improving individual health by engaging various means of Information and Communication Technology (ICT), including mobile apps and weara…

Abstract Digital Behaviour Change Interventions (DBCIs) aim at improving individual health by engaging various means of Information and Communication Technology (ICT), including mobile apps and wearables. Participant intervention fatigue may happen when DBCIs become too frequent, repetitive, demanding, or lack perceived relevance, and this may result in participants’ reduced motivation and adherence over time. Advancing technology-supported engagement mechanisms is therefore of utmost importance. To address this problem, we present a reference and solution architecture based on open-source technologies and open Application Programming Interfaces (Open APIs). First, we integrated a Large Language Model (LLM) component into the DBCI design. Second, to support context-awareness, we enhanced this integration by adding a Geographic Information Systems (GIS) element. Our pilot implemented AI4Motion platform targets both personalization and contextualization aspects of DBCIs. Our work contributes to the emerging discussion on LLM/GIS-related system design patterns for digital platforms supporting Ecological Momentary Assessment (EMA), Experience Sampling Method (ESM), and Just-in-Time Adaptive Interventions (JITAIs).  

ABSTRACT This study illustrates how organizations reconcile their information processing capabilities with uncertainty within the supply chain (SC) through generative artificial intelligence (GAI) to…

ABSTRACT This study illustrates how organizations reconcile their information processing capabilities with uncertainty within the supply chain (SC) through generative artificial intelligence (GAI) to achieve carbon performance (CP). A quantitative research methodology is applied, and 155 responses from manufacturing firms are analyzed through structural equation modeling (SEM) for hypothesis testing. The findings suggest that GAI for process automation and cognitive engagement has a positive influence on business intelligence (BI), whereas end-of-life (EOL) product management mediates the relationship between green product innovation (GPI) and CP. This study contributes to the SC context, focusing on GAI and BI in mitigating uncertainties within SCs to foster GPI and improve CP. This study highlights actionable frameworks for leveraging digital technologies in sustainable SCs by addressing technological challenges and integrating green innovation practices

This directory contains R scripts, data files, and analysis reports relatedto the analysis of adherence. FILE OVERVIEW DATA FILES* data.xlsx  Main subject-level dataset. * data-fitbit.xlsx  …

This directory contains R scripts, data files, and analysis reports relatedto the analysis of adherence. FILE OVERVIEW DATA FILES* data.xlsx  Main subject-level dataset. * data-fitbit.xlsx  Dataset with detailed Fitbit-derived measures. DATA LOADING AND PREPROCESSING* data.R  R script for loading and preprocessing the main dataset. * data-fitbit.R  R script for loading and preprocessing the detailed Fitbit dataset. DESCRIPTIVE AND BASELINE ANALYSES* summary.Rmd  R Markdown document providing a basic description of the datasets. * baseline.Rmd  R Markdown document with baseline characteristics and missing-value  analysis, including evaluation and imputation of missing values in SWL  (new variable SWLlm.predicted). * baseline-by-burst.Rmd  R Markdown document with baseline characteristics stratified by burst  number. MODELING AND VARIABLE IMPORTANCE* importance.Rmd  R Markdown analysis template for evaluating variable importance using  stepwise regression and random forest models. PROJECT CONFIGURATION AND BUILD SYSTEM* Makefile.R  Project definition for the rmake package; generates the GNU Makefile. * Makefile  File dependencies and compilation commands used by GNU Make to generate  all project results. * Rproject.Rproj  RStudio project file. ------------------------------------------------------------------------------REQUIREMENTS------------------------------------------------------------------------------ 1) INSTALL REQUIRED R PACKAGES Run the following commands in R:   install.packages(c(    "tidyverse", "knitr", "rmake", "caret", "randomForest",    "fastDummies", "broom", "devtools"  ))  devtools::install_github("beerda/hammer")  devtools::install_github("beerda/mbrtools") 2) GENERATE PROJECT ANALYSES Run the analysis pipeline using rmake:   make() This command generates all results defined in the project Makefile.------------------------------------------------------------------------------  

Abstract This paper presents a structured overview and novel insights into the universal approximation property offeedforward neural networks. We categorize existing results based on the characteristi…

Abstract This paper presents a structured overview and novel insights into the universal approximation property offeedforward neural networks. We categorize existing results based on the characteristics of activation functions— ranging from strictly monotonic to weakly monotonic and continuous almost everywhere — and examinetheir implications under architectural constraints such as bounded depth and width. Building on classical resultsby Cybenko [1], Hornik [2], and Maiorov [3], we introduce new activation functions that enable even simplerneural network architectures to retain universal approximation capabilities. Notably, we demonstrate thatsingle-layer networks with only two neurons and fixed weights can approximate any continuous univariatefunction, and that two-layer networks can extend this capability to multivariate functions. These findings refinethe known lower bounds of neural network complexity and offer constructive approaches that preserve strictmonotonicity, improving upon prior work that relied on relaxed monotonicity conditions. Our results contributeto the theoretical foundation of neural networks and open pathways for designing minimal yet expressivearchitectures.

Abstract In this paper, we explore the use of General Unary Hypotheses Automaton quantifiers and provide representations for their specific subclasses. Furthermore, we focus explicitly on implication…

Abstract In this paper, we explore the use of General Unary Hypotheses Automaton quantifiers and provide representations for their specific subclasses. Furthermore, we focus explicitly on implicational quantifiers for analyzing specific relational dependencies. We discuss their suitability in fuzzy modeling and demonstrate their integration with appropriate fuzzy rules to create a new class of weighted fuzzy rules. This study contributes to the advancement of fuzzy modeling and offers a framework for further research and practical applications.  

Abstract This paper investigates the use of fuzzy set theory in approximating solutions to differential equations under uncertainty. By defining lower and upper bounds, a robust framework is develope…

Abstract This paper investigates the use of fuzzy set theory in approximating solutions to differential equations under uncertainty. By defining lower and upper bounds, a robust framework is developed for modeling transitions between function extrema, extending classical methods to fuzzy initial value problems. The study demonstrates universal approximation properties and proposes numerical techniques that ensure stability and convergence. Applications highlight the practical utility of this approach in engineering and computational mathematics, solidifying fuzzy set theory as a powerful tool for addressing uncertainty in mathematical modeling.  

Abstract This paper introduces an enhanced framework for performing division operations on interactive fuzzy numbers characterized by complete correlation. Unlike traditional methods reliant on the i…

Abstract This paper introduces an enhanced framework for performing division operations on interactive fuzzy numbers characterized by complete correlation. Unlike traditional methods reliant on the independence assumption, we build on the sup-J extension framework to support correlated input fuzzy values. The proposed method establishes precise conditions under which the result aligns with, diverges from, or subsumes conventional divisions such as Zadeh’s and the generalized Hukuhara division. Additionally, we investigate invertibility conditions for the proposed division with respect to multiplication. These refinements offer valuable theoretical insights and have implications for models involving uncertainty, including difference equations.