Abstract
A key feature of model finding techniques allows users to enumerate and explore alternative solutions. However, it is challenging to guarantee that the generated instances are relevant to the user, representing effectively different scenarios. This challenge is exacerbated in quantitative modelling, where one must consider both the qualitative, structural part of a model, and the quantitative data on top of it. This results in a search space of possibly infinite candidate solutions, often infinitesimally similar to one another. Thus, research on instance enumeration in qualitative model finding is not directly applicable to the quantitative context, which requires more sophisticated methods to navigate the solution space effectively. The main goal of this paper is to explore a generic approach for navigating quantitative solution spaces and showcase different iteration operations, aiming to generate instances that differ considerably from those previously seen and promote a larger coverage of the search space. Such operations are implemented in QAlloy - a quantitative extension to Alloy - on top of Max-SMT solvers, and are evaluated against several examples ranging, in particular, over the integer and fuzzy domains.

Abstract
Diabetic retinopathy (DR) is a leading cause of vision loss in working-age adults. While screening reduces the risk of blindness, traditional imaging is often costly and inaccessible. Artificial intelligence (AI) algorithms present a scalable diagnostic solution, but concerns regarding fairness and generalization persist. This work evaluates the fairness and performance of image-trained models in DR prediction, as well as the impact of disentanglement as a bias mitigation technique, using the diverse mBRSET fundus dataset. Three models, ConvNeXt V2, DINOv2, and Swin V2, were trained on macula images to predict DR and sensitive attributes (SAs) (e.g., age and gender/sex). Fairness was assessed between subgroups of SAs, and disentanglement was applied to reduce bias. All models achieved high DR prediction performance in diagnosing (up to 94% AUROC) and could reasonably predict age and gender/sex (91% and 77% AUROC, respectively). Fairness assessment suggests disparities, such as a 10% AUROC gap between age groups in DINOv2. Disentangling SAs from DR prediction had varying results, depending on the model selected. Disentanglement improved DINOv2 performance (2% AUROC gain), but led to performance drops in ConvNeXt V2 and Swin V2 (7% and 3%, respectively). These findings highlight the complexity of disentangling fine-grained features in fundus imaging and emphasize the importance of fairness in medical imaging AI to ensure equitable and reliable healthcare solutions.

Abstract
Visible-Near-Infrared (Vis-NIR) spectroscopy, spanning approximately 400 to 2500 nm, is an innovative technology with growing relevance for diagnostics performed at the point of care (POC). This review explores the potential of Vis-NIR in veterinary medicine, highlighting its advantages over complex techniques like Raman and Fourier transform infrared spectroscopy (FTIR) by being rapid, non-invasive, reagent-free, and compatible with miniaturized, portable devices. The methodology involves directing a broadband light source, often using LEDs, toward the sample (e.g., blood, urine, faeces), collecting spectral information related to molecular vibrations, which is then analyzed using chemometric methods. Successful veterinary applications include hemogram analysis in dogs, cats, and Atlantic salmon, and quantifying blood in ovine faeces for parasite detection. Key limitations include spectral interference from strong absorbers like water and hemoglobin, and the limited penetration depth of light. However, combining Vis-NIR with Self-Learning Artificial Intelligence (SLAI) is shown to isolate and mitigate these multi-scale interferences. Vis-NIR spectroscopy serves as an important complement to centralized laboratory testing, holding significant potential to accelerate clinical decisions, minimize stress on animals during assessment, and improve diagnostic capabilities for both human and animal health, aligning with the One Health concept.

Abstract
The rapid advancement of wireless technologies, particularly Wi-Fi, has spurred significant research into indoor human activity detection across various domains (e.g., healthcare, security, and industry). This work explores the non-invasive and cost-effective Wi-Fi paradigm and the application of deep learning for human activity recognition using Wi-Fi signals. Focusing on the challenges in machine interpretability, motivated by the increase in data availability and computational power, this paper uses explainable artificial intelligence to understand the inner workings of transformer-based deep neural networks designed to estimate human pose (i.e., human skeleton key points) from Wi-Fi channel state information. Using different strategies to assess the most relevant sub-carriers (i.e., rollout attention and masking attention) for the model predictions, we evaluate the performance of the model when it uses a given number of sub-carriers as input, selected randomly or by ascending (high-attention) or descending (low-attention) order. We concluded that the models trained with fewer (but relevant) sub-carriers are competitive with the baseline (trained with all sub-carriers) but better in terms of computational efficiency (i.e., processing more data per second).

Abstract
E-learning has been important in higher education, enabling people to continue their education with more flexibility. Virtual laboratories play a crucial role in Computer Science distance learning degrees, by enabling students to study at their rhythm and getting practical answers to practical problems immediately. Theoretical models such as finite automata, pushdown automata, context-free grammars, Turing machines, etc., are essential for understanding the grounds of languages and computability and are also the basis for the implementation of compilers. In this paper, a new virtual laboratory is presented, UAbALL—Automata Learning Lab, developed at Universidade Aberta (UAb), the Portuguese Open University. This virtual laboratory has already been tested in the curricular unit of Languages and Computation, with good feedback from the students. A comparison to other tools was performed showing that UAbALL is more complete in terms of tools provided.

Abstract
Green hydrogen is expected to play an important role for decarbonizing hard-to-abate sectors but faces regulatory, economic, and operational barriers. In the EU, strict renewable energy usages requirements and temporal and geographical criteria constrain green hydrogen production and complicate integration with electricity markets. Support mechanisms (SMs), such as premiums and quotas, aim to boost hydrogen production, yet their impacts on coupled electricity-hydrogen systems remain underexplored. This paper extends a previous joint electricity-hydrogen Cournot equilibrium model to represent and analyze the impact of different green hydrogen production SMs. Different SMs lead to different equilibrium models that were solved using equivalent quadratic optimization problems and applied to real-size Iberian case studies. Results reveal how different SMs influence hydrogen and electricity prices, production and emissions, highlighting trade-offs among stakeholders. The findings provide guidance for designing balanced policies that stimulate green hydrogen while minimizing unintended consequences and offer flexible tools to assess regulatory and economic interactions in emerging hydrogen markets