Abstract
Obstructive sleep apnea is a heterogeneous sleep disorder with varying phenotypes. Several studies have already performed cluster analyses to discover various obstructive sleep apnea phenotypic clusters. However, the selection of the clustering method might affect the outputs. Consequently, it is unclear whether similar obstructive sleep apnea clusters can be reproduced using different clustering methods. In this study, we applied four well-known clustering methods: Agglomerative Hierarchical Clustering; K-means; Fuzzy C-means; and Gaussian Mixture Model to a population of 865 suspected obstructive sleep apnea patients. By creating five clusters with each method, we examined the effect of clustering methods on forming obstructive sleep apnea clusters and the differences in their physiological characteristics. We utilized a visualization technique to indicate the cluster formations, Cohen's kappa statistics to find the similarity and agreement between clustering methods, and performance evaluation to compare the clustering performance. As a result, two out of five clusters were distinctly different with all four methods, while three other clusters exhibited overlapping features across all methods. In terms of agreement, Fuzzy C-means and K-means had the strongest (kappa = 0.87), and Agglomerative hierarchical clustering and Gaussian Mixture Model had the weakest agreement (kappa = 0.51) between each other. The K-means showed the best clustering performance, followed by the Fuzzy C-means in most evaluation criteria. Moreover, Fuzzy C-means showed the greatest potential in handling overlapping clusters compared with other methods. In conclusion, we revealed a direct impact of clustering method selection on the formation and physiological characteristics of obstructive sleep apnea clusters. In addition, we highlighted the capability of soft clustering methods, particularly Fuzzy C-means, in the application of obstructive sleep apnea phenotyping.

Abstract
This paper presents the preliminary findings from the initial research phase of a PhD project that explores the relationship between performative arts and technology. This art-based research critically examines concepts of autonomy, control, and theatricality in puppets empowered by autonomous systems. The project is organized into a three-phase methodological framework, of which the first phase involved conducting interviews with professional puppeteers from diverse cultural backgrounds. This methodological framework was designed to address the first of two research questions, which address the dynamics between the puppeteer and the puppet. After the qualitative analysis of the interviews, the overall findings display not only the current use of technological elements and devices in puppetry practices but also the puppeteers ´ perspectives on enhancing the puppet autonomy for their performances. Moreover, the results reveal the artists ´ concerns about technological applicability, specifically about the role of human presence and its subsequent replacement, and the preservation of puppetry principles. Conclusively, these preliminary results present a framework where the intertwining between puppetry and robotics offers groundbreaking perspectives for mutual growth. © 2025 Copyright held by the owner/author(s).

Abstract
This study explores a novel approach for nonintrusive stress assessment based on Heart Rate Variability (HRV) features extracted from Electrocardiogram (ECG) signals acquired through a toilet seat-embedded sensor system. Building upon previous work by our group, we developed a framework for real-time Stress Index (SI) computation and evaluated its physiological relevance by analyzing the correlation with classical HRV parameters (SDNN, RMSSD, and LF/HF ratio) across subjects with and without cardiovascular disease. Results showed moderate negative correlations between SI and both SDNN and RMSSD, and a positive correlation with LF/HF ratio, supporting the validity of SI as a marker of autonomic stress. The system successfully differentiated autonomic stress responses between groups, with pathological participants exhibiting higher SI values, likely influenced by underlying cardiac conditions and the inherently stressful hospital environment. In contrast, individuals in contexts without cardiovascular disease exhibited lower SI values, consistent with parasympathetic predominance. These findings highlight the potential of ambient physiological monitoring using everyday objects for continuous and passive health assessment. The system's unobtrusive nature and capability to detect subclinical autonomic dysregulation support its application in personalised digital health, stress prevention, and early detection of autonomic dysfunction. © 2025 IEEE.

Abstract
Telecommunications and computer vision solutions have evolved significantly in recent years, allowing a huge advance in the functionalities and applications offered. However, these two fields have been making their way as separate areas, not exploring the potential benefits of merging the innovations brought from each of them. In challenging environments, for example, combining radio sensing and computer vision can strongly contribute to solving problems such as those introduced by obstructions or limited lighting. Machine learning algorithms, able to fuse heterogeneous and multi-modal data, are also a key element for understanding and inferring additional knowledge from raw and low-level data, able to create a new abstracting level that can significantly enhance many applications. This paper introduces the CONVERGE vision-radio concept, a new paradigm that explores the benefits of integrating two fields of knowledge towards the vision of View-to-Communicate, Communicate-to-View. The main concepts behind this vision, including supporting use cases and the proposed architecture, are presented. CONVERGE introduces a set of tools integrating wireless communications and computer vision to create a novel experimental infrastructure that will provide open datasets to the scientific community of both experimental and simulated data, enabling new research addressing various 6 G verticals, including telecommunications, automotive, manufacturing, media, and health.

Abstract
This chapter examines how Artificial Intelligence (AI) and Learning Analytics (LA) are transformingdistanceeducation, accelerated by the COVID-19 shift toe-learning. By using data from Learning Management Systems (LMS), these technologies can personalize learning, improve student retention, and automate tasks. AI, particularly machine learning, enables dynamic adaptation to student needs, while LA provides valuable insights for informed instructional decisions. However, ethical concerns, including data privacy and algorithmic bias, must be addressed to ensure equitable access and fair learning outcomes. The future of distance learning lies in responsible integration of AI and LA, creating immersive and inclusive educational experiences. © 2025 by IGI Global Scientific Publishing. All rights reserved.

Abstract