Abstract
The interaction between humans and technology has always been a key determinant factor of adoption and efficiency. This is true whether the interaction is with hardware, software or data. In the particular case of Information Retrieval (IR), recent developments in Deep Learning and Natural Language Processing (NLP) techniques opened the door to more natural and efficient IR means, no longer based on keywords or similarity metrics but on a distributed representation of meaning. In this paper we propose an agent-based architecture to serve as an interface with industrial systems, in which agents are powered by specific Large Language Models (LLMs). Its main goal is to make the interaction with such systems (e.g. data sources, production systems, machines) natural, allowing users to execute complex tasks with simple prompts. To this end, key aspects considered in the architecture are human-centricity and context-awareness. This paper provides a high-level description of this architecture, and then focuses on the development and evaluation of one of its key agents, responsible for information retrieval. For this purpose, we detail three application scenarios, and evaluate the ability of this agent to select the appropriate data sources to answer a specific prompt. Depending on the scenario and on the underlying model, results show an accuracy of up to 80%, showing that the proposed agent can be used to autonomously select from among several available data sources to answer a specific information need. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

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
Quality inspection is a critical step in ensuring the quality and efficiency of textile production processes. With the increasing complexity and scale of modern textile manufacturing systems, the need for accurate and efficient quality inspection and defect detection techniques has become paramount. This paper compares supervised and unsupervised Machine Learning techniques for defect detection in the context of industrial textile production, in terms of their respective advantages and disadvantages, and their implementation and computational costs. We explore the use of an autoencoder for the detection of defects in textiles. The goal of this preliminary work is to find out if unsupervised methods can successfully train models with good performance without the need for defect labelled data. (c) 2023 The Authors. Published by Elsevier B.V.

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 the field of Machine Learning evolves, the number of available learning algorithms and their parameters continues to grow. On the one hand, this is positive as it allows for the finding of potentially more accurate models. On the other hand, however, it also makes the process of finding the right model more complex, given the number of possible configurations. Traditionally, data scientists rely on trial-and-error or brute force procedures, which are costly, or on their own intuition or expertise, which is hard to acquire. In this paper we propose an approach for algorithm recommendation based on meta-learning. The approach can be used in real-time to predict the best n algorithms (based on a selected performance metric) and their configuration, for a given ML problem. We evaluate it through cross-validation, and by comparing it against an Auto ML approach, in terms of accuracy and time. Results show that the proposed approach recommends algorithms that are similar to those of traditional approaches, in terms of performance, in just a fraction of the time.