Abstract
Our team previously introduced an innovative concept for an "invisible" Electrocardiography (ECG) system, incorporating electrodes and sensors into a toilet seat design to enable signal acquisition from the thighs. Building upon that work, we now present a novel dataset featuring real-world, single-lead ECG signals captured at the thighs, offering a valuable resource for advancing research on thigh-based ECG for cardiovascular disease assessment. To our knowledge, this is the first dataset of its kind. The tOLIet dataset comprises 149 ECG recordings collected from 86 individuals (50 females, 36 males) with an average age of 31.73 ± 13.11 years, a mean weight of 66.89 ± 10.70 kg, and an average height of 166.82 ± 6.07 cm. Participants were recruited through direct contact with the Principal Investigator at Centro Hospitalar Universitario de Lisboa Central (CHULC) and via clinical consultations conducted at the same institution. Each recording includes four differential signals acquired from electrode pairs embedded in the toilet seat, with reference signals obtained from a standard 12-lead hospital ECG system.

Abstract
The importance of time series forecasting drives continuous research and the development of new approaches to tackle this problem. Typically, these methods are introduced through empirical studies that frequently claim superior accuracy for the proposed approaches. Nevertheless, concerns are rising about the reliability and generalizability of these results due to limitations in experimental setups. This paper addresses a critical limitation: the number and representativeness of the datasets used. We investigate the impact of dataset selection bias, particularly the practice of cherry-picking datasets, on the performance evaluation of forecasting methods. Through empirical analysis with a diverse set of benchmark datasets, our findings reveal that cherry-picking datasets can significantly distort the perceived performance of methods, often exaggerating their effectiveness. Furthermore, our results demonstrate that by selectively choosing just four datasets - what most studies report - 46% of methods could be deemed best in class, and 77% could rank within the top three. Additionally, recent deep learning-based approaches show high sensitivity to dataset selection, whereas classical methods exhibit greater robustness. Finally, our results indicate that, when empirically validating forecasting algorithms on a subset of the benchmarks, increasing the number of datasets tested from 3 to 6 reduces the risk of incorrectly identifying an algorithm as the best one by approximately 40%. Our study highlights the critical need for comprehensive evaluation frameworks that more accurately reflect real-world scenarios. Adopting such frameworks will ensure the development of robust and reliable forecasting methods.

Abstract
Purpose – This study aims to comparatively evaluate two semantic models, ArchOnto (CIDOC CRM based) and Records in Contexts Ontology (RiC-O), for archival representation within the Linked Open Data framework. The research seeks to critically analyse their ability to represent archival documents, events, activities, and provenance through the application on a case study of historical baptism records. Design/methodology/approach – The study adopted a comparative approach, utilising the two models to represent a dataset of baptism records from a Portuguese parish spanning several centuries. This involved information extraction and conversion processes, transforming XML EAD finding aids into RDF to facilitate more explicit semantic representation and analysis. Findings – The analysis revealed distinctive strengths and limitations of each semantic model, providing nuanced insights into their respective capacities for archival description. The findings guide cultural heritage institutions in selecting and implementing the most suitable semantic model for their needs and pave the way for semantic alignment between the two models. Research limitations/implications – Although the case study explored the representation of a wide range of features, potential limitations include the specific contextual constraints of parish records and the need for broader comparative studies across diverse archival contexts. Originality/value – This paper offers original insights into semantic modelling for archival representations by providing a detailed comparative analysis of two ontological approaches. It offers valuable perspectives for archivists, digital humanities researchers, and cultural heritage professionals seeking to enhance the semantic richness of archival descriptions. © 2025 Emerald Publishing Limited

Abstract
Cancer is a leading cause of mortality worldwide, with breast and lung cancer being the most prevalent globally. Early and accurate diagnosis is crucial for successful treatment, and medical imaging techniques play a pivotal role in achieving this. This paper proposes a novel pipeline that leverages generative artificial intelligence to enhance medical images by combining synthetic image generation and super-resolution techniques. The framework is validated in two medical use cases (breast and lung cancers), demonstrating its potential to improve the quality and quantity of medical imaging data, ultimately contributing to more precise and effective cancer diagnosis and treatment. Overall, although some limitations do exist, this paper achieved satisfactory results for an image size which is conductive to specialist analysis, and further expands upon this field’s capabilities. © 2025 Elsevier B.V., All rights reserved.

Abstract
The aim of this work is to explore normalising flows to detect anomalous behaviours which is an essential task mainly for surveillance systems-related applications. To accomplish that, a series of ablation studies were performed by varying the parameters of the Spatio-Temporal Graph Normalising Flows (STG-NF) model [3] and combining it with attention mechanisms. Out of all these experiments, it was only possible to improve the state-of-the-art result for the UBnormal dataset by 3.4 percentual points (pp), for the Avenue by 4.7 pp and for the Avenue-HR by 3.2 pp. However, further research remains urgent to find a model that can give the best performance across different scenarios. The inaccuracies of the pose tracking and estimation algorithm seems to be the main factor limiting the models’ performance. The code is available at https://github.com/AnaFilipaNogueira/Abnormal-Human-Behaviour-Detection-using-Normalising-Flows-and-Attention-Mechanisms. © 2025 Elsevier B.V., All rights reserved.

Abstract