Abstract

Abstract
[No abstract available]

Abstract
Dataset complexity poses a significant challenge in classification tasks, especially in real-world applications where a combination of factors such as class overlap, data imbalance, noise, and dimensionality can jeopardize a machine learning algorithm's performance. While measures to quantify complexity have been proposed and studied in depth for tabular datasets, there is a lack of studies and toolkits focused on measuring complexity in non-structured image data. This limitation hinders our understanding of visual complexity, despite the importance of image data in fields such as healthcare, remote sensing, and autonomous navigation. To address this challenge, we introduce pycol-vis, a novel Python package that helps researchers estimate image complexity. The package implements 17 image complexity measures, specifically designed to capture complexity in real-world scenarios. This toolkit is essential for researchers dealing with complex classification problems in the vision domain, providing tools to assess difficulty and overlap in real-world image data.

Abstract
In previous work, we introduced an 'invisible' ECG system with electrodes integrated into a toilet seat, capturing signals from the thighs. Here, we present the tOLIet dataset with single-lead thigh ECGs to advance cardiovascular assessment using this novel approach. The dataset includes 149 records from 86 individuals (50 females, 36 males; mean age 31.73 +/- 13.11 years; weight 66.89 +/- 10.70 kg; height 166.82 +/- 6.07 cm). Participants were recruited via the Centro Hospitalar Universit & aacute;rio de Lisboa Central (CHULC). Each recording features four differential signals from toilet-seat electrodes alongside reference data from a hospital-grade 12-lead ECG. Beyond signal collection and quality evaluation, we conducted a gender-specific analysis comparing valid signal percentages relative to Body Mass Index (BMI). This analysis explores anatomical or physiological factors affecting thigh-based ECG acquisition, guiding system design and customization to enhance signal reliability across populations.

Abstract
Background: The increasing complexity of musculoskeletal surgical nursing education requires innovative pedagogical strategies that integrate immersive technologies with structured instructional design to enhance clinical reasoning and theory-practice integration. An: To design and develop a nursing process-structured immersive virtual reality simulation for orthopaedic nursing education and to pilot test its usability and educational appraisal among undergraduate nursing students. Design Pilot mixed-methods study. Method: The simulation, Nurse TechGames, was designed as a three-dimensional orthopaedic inpatient scenario structured sequentially according to the nursing process and incorporating gamification elements to support chnical reasoning. The intervention was implemented using Meta Quest 3 head-mounted displays. Usability was assessed using the System Usability Scale, and educational appraisal was measured uring the Serious Educational Glime in Nursing Appraisal Scale. Open-ended responses were analysed through qualitative content analysis. Participants were monitored during and after the sessions for potential cybersickness symptoma Results: The simulation achieved a mean score of 83.15 on the System Usability Scale, indicating excellent us-ability. The total mean SEGINAS score was 95.58, reflecting a very high pedagogical evaluation across the di mensions of engagement, impact on learning, and content relevance. The qualitative analysis identified eight categories, with no reports of significant cyberzickness symptoms: Perceived Learning Value, Clinical Transfer, Realism and Immersion, Engagement and Motivation, Technical Robustness, Development Potential, Minor Technical Issues, and Time Constraints. Conclusion: The inmersive simulation NurseTechGames demonstrated high usability and strong pedagogical allceptance in musculoskeletal surgical nursing education. Future controlled and longitudinal studies are required to evaluate objective and sustained impact on learning outcomes.

Abstract
With the growing adoption of machine learning systems in high-stakes domains such as healthcare, finance, and public administration, ensuring that these systems behave responsibly has become an urgent concern. Initiatives such as the EU AI Act and the broader movement toward responsible AI have highlighted fairness as a key challenge in the development and deployment of such technologies. Although existing tools support model op timization through hyperparameter tuning and algorithm selection, they often neglect the broader pipeline, overlooking how factors like data bias and model evaluation practices contribute to fairness. This paper presents Fairforge, a tool designed to support responsible ML development by guiding users through essential stages of the pipeline. These include data preprocessing with bias-awareness, fairness-informed model training, and postprocessing correction techniques. Fairforge also provides integrated interfaces for evalu ating both performance and fairness metrics. The tool aims to make state-of-the-art fairness techniques accessible to users without deep expertise in the field. To validate the effectiveness of Fairforge, we conducted a series of usability tests involving users with di verse levels of technical backgrounds. The results demonstrate that the tool helps promote fairness in model development, even among non-expert practitioners.