Abstract
Many of today’s domains of application of Machine Learning (ML) are dynamic in the sense that data and their patterns change over time. This has a significant impact in the ML lifecycle and operations, requiring frequent model (re-)training, or other strategies to deal with outdated models and data. This need for dynamic and responsive solutions also has an impact on the use of computational resources and, consequently, on sustainability indicators. This paper proposes an approach in line with the concept of Frugal AI, whose main aim is to minimize the resources and time spent on training models by re-using models from a pool of past models, when appropriate. Specifically, we present and validate a methodology for similarity-based model selection in data streaming environments with concept drift. Rather than training a new model for each new block of data, this methodology considers a pool with only a subset of the models and, for each new block of data, will select the best model from the pool. The best model is determined based on the distance between its training data and the current block of data. Distance is calculated based on a set of meta-features that characterizes the data, and on the Bray-Curtis distance. We show that it is possible to reuse previous models using this methodology, leading to potentially significant saving of resources and time, while maintaining predictive quality. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

Abstract
As LLMs gain an increasingly relevant role and agency, their alignment with human values, principles and goals is crucial for their responsible deployment and acceptance. The main goal of this study is to assess the alignment of different LLMs regarding the relative importance of AI Ethics principles across different domains. To this end, human experts in different domains were asked, through a questionnaire, to rate the relative importance of six AI Ethics principles in their respective domains, totaling 6 domains. Then, five publicly available LLMs were asked to rate the same Ethics principles in different domains. Multiple prompts were used multiple times, to also evaluate consistency, totaling 90 runs per LLM. Model alignment was measured through the correlation with human experts, and consistency was evaluated through the standard deviation. Results show varying degrees of alignment and consistency, with a couple of models showing satisfactory results. This makes it possible to envisage the use of such models to automatically configure and adapt data pipeline ecosystems and architectures across different domains, selecting processes, dashboard elements or monitored KPIs according to the target domain or the goals of the system.

Abstract
The high rates of mortality provoked by cardiovascular disorders (CVDs) have been rated by the OMS in the top among non-communicable diseases, killing about 18 million people annually. It is crucial to detect arrhythmias or cardiovascular events in an early way. For that purpose, novel portable acquisition devices have allowed long-term electrocardiographic (ECG) recording, being the most common way to discover arrhythmias of a random nature such as atrial fibrillation (AF). Nonetheless, the acquisition environment can distort or even destroy the ECG recordings, hindering the proper diagnosis of CVDs. Thus, it is necessary to assess the ECG signal quality in an automatic way. The proposed approach exploits the feature and meta-feature extraction of 5-s ECG segments with the ability of machine learning classifiers to discern between high- and low-quality ECG segments. Three different approaches were tested, reaching values of accuracy close to 83% using the original feature set and improving up to 90% when all the available meta-features were utilized. Moreover, within the high-quality group, the segments belonging to the AF class outperformed around 7% until a rate over 85% when the meta-features set was used. The extraction of meta-features improves the accuracy even when a subset of meta-features is selected from the whole set.

Abstract
As distributed and multi-organization Machine Learning emerges, new challenges must be solved, such as diverse and low-quality data or real-time delivery. In this paper, we use a distributed learning environment to analyze the relationship between block size, parallelism, and predictor quality. Specifically, the goal is to find the optimum block size and the best heuristic to create distributed Ensembles. We evaluated three different heuristics and five block sizes on four publicly available datasets. Results show that using fewer but better base models matches or outperforms a standard Random Forest, and that 32 MB is the best block size.

Abstract
To address the increasing complexity of product characteristics, demand fluctuations, and higher costs of raw materials, along with pressures for fast-er integration of decarbonized energy resources, manufacturing companies require flexible production systems. These systems should minimize waste, achieve faster cycle times, and deliver high-quality products to stay competitive. In this regard, Product Design-for-Excellence (DfX) principles have gained significant importance in recent years. DfX enables all management levels to perform quick and comprehensive design inputs and performance evaluations, leveraging product lifecycle management platforms. LeanDfX, a dedicated Lean approach for product development performance assessment, has been previously proposed. This work builds upon LeanDfX by presenting a multi-dimensional approach to support design and performance assessment of production systems throughout its lifecycle. This approach coherently integrates different production knowledge areas and strategic foundations (e.g., Lean Manufacturing, Strategic Aspects, Sustainability, and Circular Economy) for the effectiveness and efficiency evaluation of production systems. The research hypothesis revolves around the translational strategy of extending and transforming the LeanDfX methodology for application in production system design within factory operations. This new architecture is presented in the context of the European project RENEE, devoted to designing and deploying remanufacturing processes for a more sustainable, circular, and competitive industry.

Abstract
As the need for enhanced material performance continues to escalate in several sectors, addressing complex parameters such as economic feasibility, ease of manufacturing, and production volume, rises the need for multidomain decision-making tools. In order to explore and streamline this process, this study employed the novel Material Design-for-eXcellence methodology to investigate polymer material selection in aeronautical and power transformer components, using additive manufacturing. The study assessed the X's selected (mechanical, thermal, physical, cost, dielectric, and environmental) by assigning weights to these factors, and identifying the optimal materials for each application. In the aeronautical context, PEI+GF30 was chosen as the best solution, attaining an overall effectiveness of 79 %, primarily due to its exceptional mechanical characteristics. The use of a thermoplastic can lead to lighter components while ensuring the same technical performance, enabling longer flight duration. Conversely, in the energy sector for power transformers, PSU obtained a 78 % score, largely attributable to its outstanding dielectric properties. The application of additive methods on transformers' insulating parts leads to optimized channels for the mineral oil, enhancing its thermal and dielectric performance. The obtained results underscored the importance of tailored material selection approaches, adjusted to specific application requirements. The importance of comprehending and adapting to diverse contexts for effective material design and implementation is also highlighted.