{"id":105,"date":"2025-01-14T10:24:08","date_gmt":"2025-01-14T09:24:08","guid":{"rendered":"http:\/\/si2dev2"},"modified":"2026-02-23T14:29:23","modified_gmt":"2026-02-23T13:29:23","slug":"publicaciones","status":"publish","type":"page","link":"https:\/\/iafer.dasci.es\/en\/investigacion\/publicaciones\/","title":{"rendered":"Publications"},"content":{"rendered":"\n<div class=\"wp-block-media-text is-stacked-on-mobile\"><figure class=\"wp-block-media-text__media\"><img fetchpriority=\"high\" decoding=\"async\" width=\"517\" height=\"481\" src=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-123505.png\" alt=\"\" class=\"wp-image-2312 size-full\" srcset=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-123505.png 517w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-123505-300x279.png 300w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-123505-13x12.png 13w\" sizes=\"(max-width: 517px) 100vw, 517px\" \/><\/figure><div class=\"wp-block-media-text__content\">\n<p class=\"wp-block-paragraph\"><strong>T\u00edtulo<\/strong> <strong>&#8211; Evolutionary Computation for the Design and Enrichment of General-Purpose Artificial Intelligence Systems: Survey and Prospects<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Autores<\/strong> &#8211; Daniel MOLINA, Javier POYATOS, Javier Del SER, Salvador GARC\u00cdA, Hisao ISHIBUCHI, Isaac TRIGUERO, Bing XUE, <a href=\"https:\/\/scholars.ln.edu.hk\/en\/persons\/xin-yao\/\">Xin YAO<\/a>, Francisco HERRERA<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Resumen<\/strong> &#8211; In Artificial Intelligence, there is an increasing demand for adaptive models capable of dealing with a diverse spectrum of learning tasks, surpassing the limitations of systems devised to cope with a single task. The recent emergence of General-Purpose Artificial Intelligence Systems (GPAIS) poses model configuration and adaptability challenges at far greater complexity scales than the optimal design of traditional Machine Learning models. Evolutionary Computation (EC) has been a useful tool for both the design and optimization of Machine Learning models, endowing them with the capability to configure and\/or adapt themselves to the task under consideration. Therefore, their application to GPAIS is a natural choice. This paper aims to analyze the role of EC in the field of GPAIS, exploring the use of EC for their design or enrichment. We also match GPAIS properties to Machine Learning areas in which EC has had a notable contribution, highlighting recent milestones of EC for GPAIS. Furthermore, we discuss the challenges of harnessing the benefits of EC for GPAIS, presenting different strategies to both design and improve GPAIS with EC, covering tangential areas, identifying research niches, and outlining potential research directions for EC and GPAIS.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Publicado en<\/strong> &#8211; <a href=\"https:\/\/scholars.ln.edu.hk\/en\/publications\/evolutionary-computation-for-the-design-and-enrichment-of-general\/#\">IEEE Transactions on Evolutionary Computation<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>DOI<\/strong> &#8211; <a href=\"https:\/\/doi.org\/10.1109\/TEVC.2025.3530096\">10.1109\/TEVC.2025.3530096<\/a><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/scholars.ln.edu.hk\/en\/publications\/evolutionary-computation-for-the-design-and-enrichment-of-general\/\">Enlace al art\u00edculo<\/a><\/li>\n<\/ul>\n<\/div><\/div>\n\n\n\n<!--nextpage-->\n\n\n\n<div class=\"wp-block-media-text is-stacked-on-mobile\"><figure class=\"wp-block-media-text__media\"><img decoding=\"async\" width=\"351\" height=\"335\" src=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-123725.png\" alt=\"\" class=\"wp-image-2313 size-full\" srcset=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-123725.png 351w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-123725-300x286.png 300w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-123725-13x12.png 13w\" sizes=\"(max-width: 351px) 100vw, 351px\" \/><\/figure><div class=\"wp-block-media-text__content\">\n<p class=\"wp-block-paragraph\"><strong>T\u00edtulo &#8211; Directed Perturbations for Efficient Learning of Surrogate Losses<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Autores<\/strong> &#8211; <a href=\"https:\/\/ieeexplore.ieee.org\/author\/389417535887460\">T.R. Cargan<\/a>,\u00a0<a href=\"https:\/\/ieeexplore.ieee.org\/author\/38277265000\">D. Landa-Silva<\/a>,\u00a0<a href=\"https:\/\/ieeexplore.ieee.org\/author\/37590979400\">I. Triguero<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Resumen<\/strong> &#8211; Decision-Focused Learning (DFL) is a paradigm to learn neural network-based predictive models tailored to a specific optimisation problem. A key challenge for DFL methods lies in the non-differentiable nature of most optimisation problems. Recent solutions use a learned, differentiable, model to act as a surrogate loss. To learn the model, the optimisation problem is solved repeatedly using random perturbations of the predictions to calculate a regret value which can be used as a target to learn the surrogate loss. However, this necessitates numerous runs of the, potentially computationally expensive, optimiser. As such, maximising the useful information from each run of the optimizer is paramount. A sample of purely random perturbations may not yield an effective distribution to learning the surrogate from. We propose using a directed perturbation strategy to generate a set of meaningful perturbations for learning a surrogate loss model. We evaluate our approach on a resource allocation problem and real-world case study focused on a critical energy challenge: optimising solar-plus-battery systems. The results show that directed perturbations learn a stronger surrogate loss with fewer runs of the optimiser, enabling a more efficient DFL.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Publicado en<\/strong> &#8211; <a href=\"https:\/\/ieeexplore.ieee.org\/xpl\/conhome\/11227166\/proceeding\">2025 International Joint Conference on Neural Networks (IJCNN)<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>DOI<\/strong> &#8211; <a href=\"https:\/\/doi.org\/10.1109\/IJCNN64981.2025.11227956\" target=\"_blank\" rel=\"noreferrer noopener\">10.1109\/IJCNN64981.2025.11227956<\/a><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/ieeexplore.ieee.org\/document\/11227956\/authors#authors\">Enlace al art\u00edculo<\/a><\/li>\n<\/ul>\n<\/div><\/div>\n\n\n\n<!--nextpage-->\n\n\n\n<div class=\"wp-block-media-text is-stacked-on-mobile\"><figure class=\"wp-block-media-text__media\"><img decoding=\"async\" width=\"1005\" height=\"1024\" src=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-124138-1005x1024.png\" alt=\"\" class=\"wp-image-2314 size-full\" srcset=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-124138-1005x1024.png 1005w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-124138-295x300.png 295w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-124138-768x782.png 768w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-124138-12x12.png 12w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-124138.png 1031w\" sizes=\"(max-width: 1005px) 100vw, 1005px\" \/><\/figure><div class=\"wp-block-media-text__content\">\n<p class=\"wp-block-paragraph\"><strong>T\u00edtulo &#8211; Generalising Stock Detection in Retail Cabinets with Minimal Data Using a DenseNet and Vision Transformer Ensemble<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Autores<\/strong> &#8211; Babak Rahi, <a href=\"mailto:babak.rahi@unilever.com\"><\/a>Deniz Sagmanli, Felix Oppong, Direnc Pekaslan, Isaac Triguero<a href=\"mailto:triguero@decsai.ugr.es\"><\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Resumen<\/strong> &#8211; Generalising deep-learning models to perform well on unseen data domains with minimal retraining remains a significant challenge in computer vision. Even when the target task\u2014such as quantifying the number of elements in an image\u2014stays the same, data quality, shape, or form variations can deviate from the training conditions, often necessitating manual intervention. As a real-world industry problem, we aim to automate stock level estimation in retail cabinets. As technology advances, new cabinet models with varying shapes emerge alongside new camera types. This evolving scenario poses a substantial obstacle to deploying long-term, scalable solutions. To surmount the challenge of generalising to new cabinet models and cameras with minimal amounts of sample images, this research introduces a new solution. This paper proposes a novel ensemble model that combines DenseNet-201 and Vision Transformer (ViT-B\/8) architectures to achieve generalisation in stock-level classification. The novelty aspect of our solution comes from the fact that we combine a transformer with a DenseNet model in order to capture both the local, hierarchical details and the long-range dependencies within the images, improving generalisation accuracy with less data. Key contributions include (i) a novel DenseNet-201 + ViT-B\/8 feature-level fusion, (ii) an adaptation workflow that needs only two images per class, (iii) a balanced layer-unfreezing schedule, (iv) a publicly described domain-shift benchmark, and (v) a 47 pp accuracy gain over four standard few-shot baselines. Our approach leverages fine-tuning techniques to adapt two pre-trained models to the new retail cabinets (i.e., standing or horizontal) and camera types using only two images per class. Experimental results demonstrate that our method achieves high accuracy rates of 91% on new cabinets with the same camera and 89% on new cabinets with different cameras, significantly outperforming standard few-shot learning methods.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Publicado en<\/strong> &#8211; <em>Mach. Learn. Knowl. Extr.<\/em>\u00a0<strong>2025<\/strong>,\u00a0<em>7<\/em>(3), 66<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>DOI<\/strong> &#8211; <a href=\"https:\/\/doi.org\/10.3390\/make7030066\">https:\/\/doi.org\/10.3390\/make7030066<\/a><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/www.mdpi.com\/2504-4990\/7\/3\/66\">Enlace al art\u00edculo<\/a><\/li>\n<\/ul>\n<\/div><\/div>\n\n\n\n<!--nextpage-->\n\n\n\n<div class=\"wp-block-media-text is-stacked-on-mobile\"><figure class=\"wp-block-media-text__media\"><img loading=\"lazy\" decoding=\"async\" width=\"527\" height=\"287\" src=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/1-s2.0-S0950705125013413-gr1.jpg\" alt=\"\" class=\"wp-image-2315 size-full\" srcset=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/1-s2.0-S0950705125013413-gr1.jpg 527w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/1-s2.0-S0950705125013413-gr1-300x163.jpg 300w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/1-s2.0-S0950705125013413-gr1-18x10.jpg 18w\" sizes=\"(max-width: 527px) 100vw, 527px\" \/><\/figure><div class=\"wp-block-media-text__content\">\n<p class=\"wp-block-paragraph\"><strong>T\u00edtulo &#8211; AutoEnergy: An automated feature engineering algorithm for energy consumption forecasting with AutoML<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Autores<\/strong> &#8211; Nasser\u00a0Alkhulaifi,\u00a0Alexander L.\u00a0Bowler,\u00a0Direnc\u00a0Pekaslan,\u00a0<a href=\"https:\/\/www.sciencedirect.com\/author\/35180596200\/nicholas-j-watson\">Nicholas J.\u00a0Watson<\/a>,\u00a0<a href=\"https:\/\/www.sciencedirect.com\/author\/36601691900\/isaac-triguero\">Isaac\u00a0Triguero<\/a><a href=\"mailto:triguero@decsai.ugr.es\"><\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Resumen<\/strong> &#8211; Feature engineering (FE) plays a crucial role in Machine Learning pipelines, yet it remains a time-consuming process requiring heavy domain expertise. While Automated Machine Learning (AutoML) has automated model selection and hyperparameter tuning, it often overlooks FE, which is particularly needed in specialised domains such as Energy Consumption Forecasting (ECF). To address this limitation, we introduce AutoEnergy, a novel, domain-aware FE algorithm tailored for ECF. AutoEnergy automatically generates interpretable features from timestamps and past consumption values through rule-based transformations, integrating them with AutoML for fully automated ECF modelling while reducing human intervention. The performance of AutoEnergy was evaluated using eighteen diverse real-world energy consumption datasets spanning residential, commercial, industrial, and grid power domains. Through extensive benchmarking against baseline AutoML without FE and established FE methods, namely TSFresh (with TSEfficient and TSMinimal configurations) and FeatureTools (FT), AutoEnergy demonstrated significant improvements in both predictive accuracy and computational efficiency. AutoEnergy achieved forecasting error reductions of 19.52 % to 84.72 % compared to benchmarking methods, with strong performance on smaller datasets and statistical validation via Friedman and Wilcoxon tests. AutoEnergy demonstrated notable computational efficiency by running 1.31 and 4.41 times faster than FT and TSEff, respectively. Although 1.58 times slower than TSMin, AutoEnergy achieved 82.38 % lower forecasting errors. Integrating AutoEnergy with the state-of-the-art Tabular Prior Data Fitted Network (TabPFN) resulted in significant forecasting error reductions across test sets. These findings highlight AutoEnergy\u2019s potential to improve AutoML performance while reducing reliance on domain expertise for FE, paving the way for fully automated ML pipelines in ECF applications.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Publicado en<\/strong> &#8211; <a href=\"https:\/\/www.sciencedirect.com\/journal\/knowledge-based-systems\">Knowledge-Based Systems<\/a> <a href=\"https:\/\/www.sciencedirect.com\/journal\/knowledge-based-systems\/vol\/329\/part\/PA\">Volume 329, Part A<\/a>,\u00a04 November 2025, 114300<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>DOI<\/strong> &#8211; <a href=\"https:\/\/doi.org\/10.1016\/j.knosys.2025.114300\">https:\/\/doi.org\/10.1016\/j.knosys.2025.114300<\/a><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0950705125013413?via%3Dihub\">Enlace al art\u00edculo<\/a><\/li>\n<\/ul>\n<\/div><\/div>\n\n\n\n<!--nextpage-->\n\n\n\n<div class=\"wp-block-media-text is-stacked-on-mobile\"><figure class=\"wp-block-media-text__media\"><img loading=\"lazy\" decoding=\"async\" width=\"651\" height=\"224\" src=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-130517.png\" alt=\"\" class=\"wp-image-2316 size-full\" srcset=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-130517.png 651w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-130517-300x103.png 300w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-130517-18x6.png 18w\" sizes=\"(max-width: 651px) 100vw, 651px\" \/><\/figure><div class=\"wp-block-media-text__content\">\n<p class=\"wp-block-paragraph\"><strong>T\u00edtulo &#8211; From Traditional Methods to GPT-based Models for 2D Video Game Level Procedural Content Generation: An Empirical Study*<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Autores<\/strong> &#8211; <a href=\"https:\/\/ieeexplore.ieee.org\/author\/705629225113282\">Daniel Cerezo<\/a>, <a href=\"https:\/\/ieeexplore.ieee.org\/author\/37590979400\">Isaac Triguero<\/a><a href=\"mailto:triguero@decsai.ugr.es\"><\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Resumen<\/strong> &#8211; Procedural level generation in video games has made significant strides, yet achieving high-quality automated level design remains a major challenge. Over the years, techniques have evolved from simple constructive algorithms to advanced Artificial Intelligence (AI) models like Generative Adversarial Networks and Large Language Models. However, the lack of a standardised evaluation framework has hindered direct numerical comparisons and the ability to gauge true progress in the field. To address this gap, we propose an evaluation methodology to benchmark key generation techniques and explore the potential of general-purpose AI models. As a case study, we present a Super Mario Bros level generator powered by ChatGPT, leveraging general-purpose natural language for design tasks. The results show the different strengths and weaknesses of existing models, indicating that traditional algorithms still outperform the most advanced AI methods in this domain, highlighting the need for further innovation to bridge the gap.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Publicado en<\/strong> &#8211; <a href=\"https:\/\/ieeexplore.ieee.org\/xpl\/conhome\/11342430\/proceeding\">2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>DOI<\/strong> &#8211; <a href=\"https:\/\/doi.org\/10.1109\/SMC58881.2025.11343196\" target=\"_blank\" rel=\"noreferrer noopener\">10.1109\/SMC58881.2025.11343196<\/a><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/ieeexplore.ieee.org\/document\/11343196\">Enlace al art\u00edculo<\/a><\/li>\n<\/ul>\n<\/div><\/div>\n\n\n\n<!--nextpage-->\n\n\n\n<div class=\"wp-block-media-text is-stacked-on-mobile\"><figure class=\"wp-block-media-text__media\"><img loading=\"lazy\" decoding=\"async\" width=\"255\" height=\"237\" src=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-130835.png\" alt=\"\" class=\"wp-image-2317 size-full\" srcset=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-130835.png 255w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-130835-13x12.png 13w\" sizes=\"(max-width: 255px) 100vw, 255px\" \/><\/figure><div class=\"wp-block-media-text__content\">\n<p class=\"wp-block-paragraph\"><strong>T\u00edtulo &#8211; CUBIC: Concept Embeddings for Unsupervised Bias Identification using VLMs<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Autores<\/strong> &#8211; <a href=\"https:\/\/arxiv.org\/search\/cs?searchtype=author&amp;query=M%C3%A9ndez,+D\">David M\u00e9ndez<\/a>,\u00a0<a href=\"https:\/\/arxiv.org\/search\/cs?searchtype=author&amp;query=Bontempo,+G\">Gianpaolo Bontempo<\/a>,\u00a0<a href=\"https:\/\/arxiv.org\/search\/cs?searchtype=author&amp;query=Ficarra,+E\">Elisa Ficarra<\/a>,\u00a0<a href=\"https:\/\/arxiv.org\/search\/cs?searchtype=author&amp;query=Confalonieri,+R\">Roberto Confalonieri<\/a>,\u00a0<a href=\"https:\/\/arxiv.org\/search\/cs?searchtype=author&amp;query=D%C3%ADaz-Rodr%C3%ADguez,+N\">Natalia D\u00edaz-Rodr\u00edguez<\/a><a href=\"mailto:triguero@decsai.ugr.es\"><\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Resumen<\/strong> &#8211; Deep vision models often rely on biases learned from spurious correlations in datasets. To identify these biases, methods that interpret high-level, human-understandable concepts are more effective than those relying primarily on low-level features like heatmaps. A major challenge for these concept-based methods is the lack of image annotations indicating potentially bias-inducing concepts, since creating such annotations requires detailed labeling for each dataset and concept, which is highly labor-intensive. We present CUBIC (Concept embeddings for Unsupervised Bias IdentifiCation), a novel method that automatically discovers interpretable concepts that may bias classifier behavior. Unlike existing approaches, CUBIC does not rely on predefined bias candidates or examples of model failures tied to specific biases, as such information is not always available. Instead, it leverages image-text latent space and linear classifier probes to examine how the latent representation of a superclass label &#8211; shared by all instances in the dataset &#8211; is influenced by the presence of a given concept. By measuring these shifts against the normal vector to the classifier&#8217;s decision boundary, CUBIC identifies concepts that significantly influence model predictions. Our experiments demonstrate that CUBIC effectively uncovers previously unknown biases using Vision-Language Models (VLMs) without requiring the samples in the dataset where the classifier underperforms or prior knowledge of potential biases.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Publicado en<\/strong> &#8211; <strong><a href=\"https:\/\/arxiv.org\/abs\/2505.11060\">arXiv:2505.11060<\/a>\u00a0[cs.CV]<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>DOI<\/strong> &#8211; <a href=\"https:\/\/doi.org\/10.48550\/arXiv.2505.11060\">https:\/\/doi.org\/10.48550\/arXiv.2505.11060<\/a><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/arxiv.org\/abs\/2505.11060\">Enlace al art\u00edculo<\/a><\/li>\n<\/ul>\n<\/div><\/div>\n\n\n\n<!--nextpage-->\n\n\n\n<div class=\"wp-block-media-text is-stacked-on-mobile\"><figure class=\"wp-block-media-text__media\"><img loading=\"lazy\" decoding=\"async\" width=\"416\" height=\"175\" src=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-131105.png\" alt=\"\" class=\"wp-image-2319 size-full\" srcset=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-131105.png 416w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-131105-300x126.png 300w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-131105-18x8.png 18w\" sizes=\"(max-width: 416px) 100vw, 416px\" \/><\/figure><div class=\"wp-block-media-text__content\">\n<p class=\"wp-block-paragraph\"><strong>T\u00edtulo &#8211; STOOD-X methodology: using statistical nonparametric test for OOD Detection Large-Scale datasets enhanced with explainability<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Autores<\/strong> &#8211; <a href=\"https:\/\/arxiv.org\/search\/cs?searchtype=author&amp;query=Sevillano-Garc%C3%ADa,+I\">Iv\u00e1n Sevillano-Garc\u00eda<\/a>,\u00a0<a href=\"https:\/\/arxiv.org\/search\/cs?searchtype=author&amp;query=Luengo,+J\">Juli\u00e1n Luengo<\/a>,\u00a0<a href=\"https:\/\/arxiv.org\/search\/cs?searchtype=author&amp;query=Herrera,+F\">Francisco Herrera<\/a><a href=\"mailto:triguero@decsai.ugr.es\"><\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Resumen<\/strong> &#8211; Out-of-Distribution (OOD) detection is a critical task in machine learning, particularly in safety-sensitive applications where model failures can have serious consequences. However, current OOD detection methods often suffer from restrictive distributional assumptions, limited scalability, and a lack of interpretability. To address these challenges, we propose STOOD-X, a two-stage methodology that combines a Statistical nonparametric Test for OOD Detection with eXplainability enhancements. In the first stage, STOOD-X uses feature-space distances and a Wilcoxon-Mann-Whitney test to identify OOD samples without assuming a specific feature distribution. In the second stage, it generates user-friendly, concept-based visual explanations that reveal the features driving each decision, aligning with the BLUE XAI paradigm. Through extensive experiments on benchmark datasets and multiple architectures, STOOD-X achieves competitive performance against state-of-the-art post hoc OOD detectors, particularly in high-dimensional and complex settings. In addition, its explainability framework enables human oversight, bias detection, and model debugging, fostering trust and collaboration between humans and AI systems. The STOOD-X methodology therefore offers a robust, explainable, and scalable solution for real-world OOD detection tasks.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Publicado en<\/strong> &#8211; <strong><a href=\"https:\/\/arxiv.org\/abs\/2504.02685\">arXiv:2504.02685<\/a>\u00a0[cs.LG]<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>DOI<\/strong> &#8211; <a href=\"https:\/\/doi.org\/10.48550\/arXiv.2504.02685\">https:\/\/doi.org\/10.48550\/arXiv.2504.02685<\/a><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/arxiv.org\/abs\/2504.02685\">Enlace al art\u00edculo<\/a><\/li>\n<\/ul>\n<\/div><\/div>\n\n\n\n<!--nextpage-->\n\n\n\n<div class=\"wp-block-media-text is-stacked-on-mobile\"><figure class=\"wp-block-media-text__media\"><img loading=\"lazy\" decoding=\"async\" width=\"338\" height=\"500\" src=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/images_medium_pr5c00534_0007.gif\" alt=\"\" class=\"wp-image-2320 size-full\"\/><\/figure><div class=\"wp-block-media-text__content\">\n<p class=\"wp-block-paragraph\"><strong>T\u00edtulo &#8211; Toward Robust Machine Learning Models for MALDI-TOF MS: Novel Approaches for\u00a0<em>Mycobacterium abscessus<\/em>\u00a0Subspecies Identification<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Autores<\/strong> &#8211; <a href=\"https:\/\/pubmed.ncbi.nlm.nih.gov\/?term=Padial-Fuillerat+E&amp;cauthor_id=41662266\">Erica Padial-Fuillerat<\/a>,\u00a0<a href=\"https:\/\/pubmed.ncbi.nlm.nih.gov\/?term=Mart%C3%ADnez-Manj%C3%B3n+JE&amp;cauthor_id=41662266\">Juan E Mart\u00ednez-Manj\u00f3n<\/a>,\u00a0<a href=\"https:\/\/pubmed.ncbi.nlm.nih.gov\/?term=Zwir+I&amp;cauthor_id=41662266\">Igor Zwir<\/a>,\u00a0<a href=\"https:\/\/pubmed.ncbi.nlm.nih.gov\/?term=Arroyo+MJ&amp;cauthor_id=41662266\">Manuel J Arroyo<\/a>,\u00a0<a href=\"https:\/\/pubmed.ncbi.nlm.nih.gov\/?term=Bl%C3%A1zquez-S%C3%A1nchez+M&amp;cauthor_id=41662266\">Mario Bl\u00e1zquez-S\u00e1nchez<\/a>,\u00a0<a href=\"https:\/\/pubmed.ncbi.nlm.nih.gov\/?term=Rodr%C3%ADguez-Temporal+D&amp;cauthor_id=41662266\">David Rodr\u00edguez-Temporal<\/a>,\u00a0<a href=\"https:\/\/pubmed.ncbi.nlm.nih.gov\/?term=Rodr%C3%ADguez+B&amp;cauthor_id=41662266\">Bel\u00e9n Rodr\u00edguez<\/a>,\u00a0<a href=\"https:\/\/pubmed.ncbi.nlm.nih.gov\/?term=Mancera+L&amp;cauthor_id=41662266\">Luis Mancera<\/a>,\u00a0<a href=\"https:\/\/pubmed.ncbi.nlm.nih.gov\/?term=Del+Val+C&amp;cauthor_id=41662266\">Coral Del Val<\/a><a href=\"mailto:triguero@decsai.ugr.es\"><\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Resumen<\/strong> &#8211; Distinguishing\u00a0<em>Mycobacterium abscessus<\/em>\u00a0subspecies presents significant diagnostic challenges due to their genetic homogeneity and variability in analytical platforms. Our research combines matrix-assisted laser desorption\/ionization time-of-flight (MALDI-TOF) mass spectrometry with machine learning (ML) approaches to enhance discrimination accuracy, utilizing 325 spectra profiles from diverse European hospitals. The analytical pipeline incorporates specialized techniques for geographical data harmonization, feature selection, and balancing class representation. The best model employs support vector machines (SVMs) with ComBat correction, Boruta feature selection, and centroid clustering for class imbalance, achieving a discrimination performance of 97% F1 score and 97.17% AUC-ROC on test samples. Noteworthily, most tested models improved their discrimination performance with the approach and demonstrated consistent performance metrics with high geometric mean (GEO) and index balanced accuracy (IBA) metrics (>0.90), ensuring consistent sensitivity and specificity across all subspecies. SHAP (SHapley Additive exPlanations) validated the biological relevance of selected spectral features, particularly improving discrimination of the diagnostically challenging\u00a0<em>M. abscessus<\/em>\u00a0subsp.\u00a0<em>bolletii.<\/em>\u00a0This work advances the state-of-the-art in\u00a0<em>M. abscessus<\/em>\u00a0classification, providing a scalable analytical framework for enhanced microbial diagnostics and targeted antimicrobial therapy selection.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Publicado en<\/strong> &#8211; J Proteome Res. 2026 Feb 9. doi: 10.1021\/acs.jproteome.5c00534. Epub ahead of print. PMID: 41662266.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>DOI<\/strong> &#8211; <a href=\"https:\/\/doi.org\/10.1021\/acs.jproteome.5c00534\" target=\"_blank\" rel=\"noreferrer noopener\">10.1021\/acs.jproteome.5c00534<\/a><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/pubmed.ncbi.nlm.nih.gov\/41662266\/\">Enlace al art\u00edculo<\/a><\/li>\n<\/ul>\n<\/div><\/div>\n\n\n\n<!--nextpage-->\n\n\n\n<div class=\"wp-block-media-text is-stacked-on-mobile\"><figure class=\"wp-block-media-text__media\"><img loading=\"lazy\" decoding=\"async\" width=\"339\" height=\"109\" src=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/1-s2.0-S1566253525002064-gr1.jpg\" alt=\"\" class=\"wp-image-2321 size-full\" srcset=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/1-s2.0-S1566253525002064-gr1.jpg 339w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/1-s2.0-S1566253525002064-gr1-300x96.jpg 300w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/1-s2.0-S1566253525002064-gr1-18x6.jpg 18w\" sizes=\"(max-width: 339px) 100vw, 339px\" \/><\/figure><div class=\"wp-block-media-text__content\">\n<p class=\"wp-block-paragraph\"><strong>T\u00edtulo &#8211; Reflections and attentiveness on eXplainable Artificial Intelligence (XAI). The journey ahead from criticisms to human\u2013AI collaboration<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Autores<\/strong> &#8211; Francisco Herrera<a href=\"mailto:triguero@decsai.ugr.es\"><\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Resumen<\/strong> &#8211; The emergence of\u00a0<a href=\"https:\/\/www.sciencedirect.com\/topics\/computer-science\/deep-learning\">deep learning<\/a>\u00a0over the past decade has driven the development of increasingly complex\u00a0<a href=\"https:\/\/www.sciencedirect.com\/topics\/computer-science\/artificial-intelligence-model\">AI models<\/a>, amplifying the need for Explainable Artificial Intelligence (XAI). As\u00a0<a href=\"https:\/\/www.sciencedirect.com\/topics\/computer-science\/artificial-intelligence\">AI<\/a>\u00a0systems grow in size and complexity, ensuring\u00a0<a href=\"https:\/\/www.sciencedirect.com\/topics\/computer-science\/interpretability\">interpretability<\/a>\u00a0and transparency becomes essential, especially in high-stakes applications. With the rapid expansion of XAI research, addressing emerging debates and criticisms requires a comprehensive examination. This paper explores the complexities of XAI from multiple perspectives, proposing six key axes that shed light on its role in human\u2013AI interaction and collaboration. First, it examines the imperative of XAI under the dominance of black-box AI models. Given the lack of definitional cohesion, the paper argues that XAI must be framed through the lens of audience and understanding, highlighting its different uses in AI\u2013human interaction. The recent BLUE vs. RED XAI distinction is analyzed through this perspective. The study then addresses the criticisms of XAI, evaluating its maturity, current trajectory, and limitations in handling complex problems. The discussion then shifts to explanations as a bridge between AI models and human understanding, emphasizing the importance of usability of explanations in human\u2013AI\u00a0<a href=\"https:\/\/www.sciencedirect.com\/topics\/psychology\/decision-making\">decision making<\/a>. Key aspects such as AI reliance, human intuition, and emerging collaboration theories \u2014 including the human-algorithm centaur and co-intelligence paradigms \u2014 are explored in connection with XAI. The medical field is considered as a\u00a0<a href=\"https:\/\/www.sciencedirect.com\/topics\/computer-science\/case-study\">case study<\/a>, given its extensive research on collaboration between doctors and AI through explainability. The paper proposes a framework to evaluate the maturity of XAI using three dimensions: practicality, auditability, and AI governance. Provide the final lessons learned focused on trends and questions to tackle in the near future. This is an in-depth exploration of the impact and urgency of XAI in the era of pervasive expansion of AI. Three Key reflections from this study include: (a) XAI must enhance cognitive engagement with explanations, (b) it must evolve to fully address why, what, and for what purpose explanations are needed, and (c) it plays a crucial role in building societal trust in AI. By advancing XAI in these directions, we can ensure that AI remains transparent, auditable, and accountable, and aligned with human needs.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Publicado en<\/strong> &#8211; <a href=\"https:\/\/www.sciencedirect.com\/journal\/information-fusion\">Information Fusion<\/a>, <a href=\"https:\/\/www.sciencedirect.com\/journal\/information-fusion\/vol\/121\/suppl\/C\">Volume 121<\/a>,\u00a0September 2025, 103133<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>DOI<\/strong> &#8211; <a href=\"https:\/\/doi.org\/10.1016\/j.inffus.2025.103133\">https:\/\/doi.org\/10.1016\/j.inffus.2025.103133<\/a><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1566253525002064\">Enlace al art\u00edculo<\/a><\/li>\n<\/ul>\n<\/div><\/div>\n\n\n\n<!--nextpage-->\n\n\n\n<div class=\"wp-block-media-text is-stacked-on-mobile\"><figure class=\"wp-block-media-text__media\"><img loading=\"lazy\" decoding=\"async\" width=\"449\" height=\"388\" src=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-132633.png\" alt=\"\" class=\"wp-image-2322 size-full\" srcset=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-132633.png 449w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-132633-300x259.png 300w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-132633-14x12.png 14w\" sizes=\"(max-width: 449px) 100vw, 449px\" \/><\/figure><div class=\"wp-block-media-text__content\">\n<p class=\"wp-block-paragraph\"><strong>T\u00edtulo &#8211; Aligning Trustworthy AI with Democracy: A Dual Taxonomy of Opportunities and Risks<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Autores<\/strong> &#8211; <a href=\"https:\/\/arxiv.org\/search\/cs?searchtype=author&amp;query=Mentxaka,+O\">Oier Mentxaka<\/a>,\u00a0<a href=\"https:\/\/arxiv.org\/search\/cs?searchtype=author&amp;query=D%C3%ADaz-Rodr%C3%ADguez,+N\">Natalia D\u00edaz-Rodr\u00edguez<\/a>,\u00a0<a href=\"https:\/\/arxiv.org\/search\/cs?searchtype=author&amp;query=Coeckelbergh,+M\">Mark Coeckelbergh<\/a>,\u00a0<a href=\"https:\/\/arxiv.org\/search\/cs?searchtype=author&amp;query=de+Prado,+M+L\">Marcos L\u00f3pez de Prado<\/a>,\u00a0<a href=\"https:\/\/arxiv.org\/search\/cs?searchtype=author&amp;query=G%C3%B3mez,+E\">Emilia G\u00f3mez<\/a>,\u00a0<a href=\"https:\/\/arxiv.org\/search\/cs?searchtype=author&amp;query=Llorca,+D+F\">David Fern\u00e1ndez Llorca<\/a>,\u00a0<a href=\"https:\/\/arxiv.org\/search\/cs?searchtype=author&amp;query=Herrera-Viedma,+E\">Enrique Herrera-Viedma<\/a>,\u00a0<a href=\"https:\/\/arxiv.org\/search\/cs?searchtype=author&amp;query=Herrera,+F\">Francisco Herrera<\/a><a href=\"mailto:triguero@decsai.ugr.es\"><\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Resumen<\/strong> &#8211; Artificial Intelligence (AI) poses both significant risks and valuable opportunities for democratic governance. This paper introduces a dual taxonomy to evaluate AI&#8217;s complex relationship with democracy: the AI Risks to Democracy (AIRD) taxonomy, which identifies how AI can undermine core democratic principles such as autonomy, fairness, and trust; and the AI&#8217;s Positive Contributions to Democracy (AIPD) taxonomy, which highlights AI&#8217;s potential to enhance transparency, participation, efficiency, and evidence-based policymaking.<br>Grounded in the European Union&#8217;s approach to ethical AI governance, and particularly the seven Trustworthy AI requirements proposed by the European Commission&#8217;s High-Level Expert Group on AI, each identified risk is aligned with mitigation strategies based on EU regulatory and normative frameworks. Our analysis underscores the transversal importance of transparency and societal well-being across all risk categories and offers a structured lens for aligning AI systems with democratic values.<br>By integrating democratic theory with practical governance tools, this paper offers a normative and actionable framework to guide research, regulation, and institutional design to support trustworthy, democratic AI. It provides scholars with a conceptual foundation to evaluate the democratic implications of AI, equips policymakers with structured criteria for ethical oversight, and helps technologists align system design with democratic principles. In doing so, it bridges the gap between ethical aspirations and operational realities, laying the groundwork for more inclusive, accountable, and resilient democratic systems in the algorithmic age.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Publicado en<\/strong> &#8211; <strong><a href=\"https:\/\/arxiv.org\/abs\/2505.13565\">arXiv:2505.13565<\/a>\u00a0[cs.CY]<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>DOI<\/strong> &#8211; <a href=\"https:\/\/doi.org\/10.48550\/arXiv.2505.13565\">https:\/\/doi.org\/10.48550\/arXiv.2505.13565<\/a><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/arxiv.org\/abs\/2505.13565\">Enlace al art\u00edculo<\/a><\/li>\n<\/ul>\n<\/div><\/div>\n\n\n\n<!--nextpage-->\n\n\n\n<div class=\"wp-block-media-text is-stacked-on-mobile\"><figure class=\"wp-block-media-text__media\"><img loading=\"lazy\" decoding=\"async\" width=\"685\" height=\"687\" src=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/10796_2025_10668_Fig1_HTML.png\" alt=\"\" class=\"wp-image-2323 size-full\" srcset=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/10796_2025_10668_Fig1_HTML.png 685w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/10796_2025_10668_Fig1_HTML-300x300.png 300w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/10796_2025_10668_Fig1_HTML-150x150.png 150w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/10796_2025_10668_Fig1_HTML-12x12.png 12w\" sizes=\"(max-width: 685px) 100vw, 685px\" \/><\/figure><div class=\"wp-block-media-text__content\">\n<p class=\"wp-block-paragraph\"><strong>T\u00edtulo &#8211; A Three-level Framework for LLM-enhanced Explainable AI: From Technical Explanations to Natural Language<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Autores<\/strong> &#8211; <a href=\"https:\/\/link.springer.com\/article\/10.1007\/s10796-025-10668-1#auth-Marilyn-Bello-Aff1\">Marilyn Bello<\/a>,\u00a0<a href=\"https:\/\/link.springer.com\/article\/10.1007\/s10796-025-10668-1#auth-Rafael-Bello-Aff2\">Rafael Bello<\/a>,\u00a0<a href=\"https:\/\/link.springer.com\/article\/10.1007\/s10796-025-10668-1#auth-Mar_a_Matilde-Garc_a-Aff2\">Mar\u00eda-Matilde Garc\u00eda<\/a>,\u00a0<a href=\"https:\/\/link.springer.com\/article\/10.1007\/s10796-025-10668-1#auth-Ann-Now_-Aff3\">Ann Now\u00e9<\/a>,\u00a0<a href=\"https:\/\/link.springer.com\/article\/10.1007\/s10796-025-10668-1#auth-Iv_n-Sevillano_Garc_a-Aff1\">Iv\u00e1n Sevillano-Garc\u00eda<\/a>, <a href=\"https:\/\/link.springer.com\/article\/10.1007\/s10796-025-10668-1#auth-Francisco-Herrera-Aff1\">Francisco Herrera<\/a>\u00a0<a href=\"mailto:triguero@decsai.ugr.es\"><\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Resumen<\/strong> &#8211; The growing application of artificial intelligence in sensitive domains has intensified the demand for systems that are not only accurate but also explainable and trustworthy. Although explainable AI (XAI) methods have proliferated, many do not consider the diverse audiences that interact with AI systems: from developers and domain experts to end-users and society. This paper addresses how trust in AI is influenced by the design and delivery of explanations and proposes a multilevel framework that aligns explanations with the epistemic, contextual, and ethical expectations of different stakeholders. The framework consists of three layers: algorithmic and domain-based, human-centered, and social explainability, with Large Language Models serving as crucial mediators that transform technical outputs of AI explanations into accessible, contextual narratives across all levels. We show how LLMs enable dynamic, conversational explanations that bridge the gap between complex model behavior and human understanding, facilitating interactive dialogue and enhancing societal transparency. Through comprehensive case studies, we show how this LLM-enhanced approach achieves technical fidelity, user engagement, and societal accountability, reframing XAI as a dynamic, trust-building process that leverages natural language capabilities to democratize AI explainability.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Publicado en<\/strong> &#8211; <em>Inf Syst Front<\/em>\u00a0(2025).<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>DOI<\/strong> &#8211; <a href=\"https:\/\/doi.org\/10.1007\/s10796-025-10668-1\">https:\/\/doi.org\/10.1007\/s10796-025-10668-1<\/a><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/link.springer.com\/article\/10.1007\/s10796-025-10668-1\">Enlace al art\u00edculo<\/a><\/li>\n<\/ul>\n<\/div><\/div>\n\n\n\n<!--nextpage-->\n\n\n\n<div class=\"wp-block-media-text is-stacked-on-mobile\"><figure class=\"wp-block-media-text__media\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"776\" src=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/applsci-15-06465-g001-1024x776.png\" alt=\"\" class=\"wp-image-2324 size-full\" srcset=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/applsci-15-06465-g001-1024x776.png 1024w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/applsci-15-06465-g001-300x227.png 300w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/applsci-15-06465-g001-768x582.png 768w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/applsci-15-06465-g001-1536x1164.png 1536w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/applsci-15-06465-g001-2048x1552.png 2048w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/applsci-15-06465-g001-16x12.png 16w\" sizes=\"(max-width: 1024px) 100vw, 1024px\" \/><\/figure><div class=\"wp-block-media-text__content\">\n<p class=\"wp-block-paragraph\"><strong>T\u00edtulo &#8211; Artificial Intelligence Adoption in SMEs: Survey Based on TOE\u2013DOI Framework, Primary Methodology and Challenges<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Autores<\/strong> &#8211; Esther S\u00e1nchez, Reyes Calder\u00f3n, Francisco Herrera<a href=\"mailto:triguero@decsai.ugr.es\"><\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Resumen<\/strong> &#8211; Despite the transformative potential of artificial intelligence (AI), small and medium-sized enterprises (SMEs) continue to face significant challenges in its effective adoption. While prior studies have emphasized strategic benefits and readiness models, there remains a lack of operational guidance tailored to SME realities\u2014particularly regarding implementation barriers, resource constraints, and emerging demands for responsible AI use. This study presents an analysis of AI adoption in SMEs by integrating the technology\u2013organization\u2013environment (TOE) framework with selected attributes from the diffusion of innovations (DOI) theory to examine adoption dynamics through a dual structural and perceptual lens. Empirical insights from sectoral and regional contexts are also incorporated. Ten critical challenges are identified and analyzed across the TOE dimensions, ranging from data access and skill shortages to cultural resistance, infrastructure limitations, and weak governance practices. Notably, the framework is expanded to incorporate responsible AI governance and democratized access to generative AI\u2014particularly open-weight large language models (LLMs) such as LLaMA, DeepSeek-R1, Mistral, and FALCON\u2014as emerging technological and ethical imperatives. Each challenge is paired with actionable, context-sensitive solutions. The paper is a structured, literature-based conceptual analysis enriched by empirical case study insights. As a key contribution, it introduces a structured, six-phase roadmap methodology to guide SMEs through AI adoption\u2014offering step-by-step recommendations aligned with technological, organizational, and strategic readiness. While this roadmap is conceptual and has yet to be validated through field data, it sets a foundation for future diagnostic tools and practical assessments. The resulting study bridges theoretical insight and implementation strategy\u2014empowering inclusive, responsible, and scalable AI transformation in SMEs. By offering both analytical clarity and practical relevance, this study contributes to a more grounded understanding of AI integration and calls for policies, ecosystems, and leadership models that support SMEs in adopting AI not merely as a tool, but as a strategic enabler of sustainable and inclusive innovation.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Publicado en<\/strong> &#8211; <em>Appl. Sci.<\/em>\u00a0<strong>2025<\/strong>,\u00a0<em>15<\/em>(12), 6465<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>DOI<\/strong> &#8211; <a href=\"https:\/\/doi.org\/10.3390\/app15126465\">https:\/\/doi.org\/10.3390\/app15126465<\/a><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/www.mdpi.com\/2076-3417\/15\/12\/6465\">Enlace al art\u00edculo<\/a><\/li>\n<\/ul>\n<\/div><\/div>\n\n\n\n<!--nextpage-->\n\n\n\n<div class=\"wp-block-media-text is-stacked-on-mobile\"><figure class=\"wp-block-media-text__media\"><img loading=\"lazy\" decoding=\"async\" width=\"912\" height=\"777\" src=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-133701.png\" alt=\"\" class=\"wp-image-2325 size-full\" srcset=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-133701.png 912w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-133701-300x256.png 300w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-133701-768x654.png 768w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-133701-14x12.png 14w\" sizes=\"(max-width: 912px) 100vw, 912px\" \/><\/figure><div class=\"wp-block-media-text__content\">\n<p class=\"wp-block-paragraph\"><strong>T\u00edtulo &#8211; A Maturity Model for Practical Explainability in Artificial Intelligence-Based Applications: Integrating Analysis and Evaluation (MM4XAI-AE) Models<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Autores<\/strong> &#8211; <a href=\"https:\/\/onlinelibrary.wiley.com\/authored-by\/Mu%C3%B1oz-Ord%C3%B3%C3%B1ez\/Juli%C3%A1n\">Juli\u00e1n Mu\u00f1oz-Ord\u00f3\u00f1ez<\/a>,\u00a0<a href=\"https:\/\/onlinelibrary.wiley.com\/authored-by\/Cobos\/Carlos\">Carlos Cobos<\/a>,\u00a0<a href=\"https:\/\/onlinelibrary.wiley.com\/authored-by\/Vidal-Rojas\/Juan+C.\">Juan C. Vidal-Rojas<\/a>,\u00a0<a href=\"https:\/\/onlinelibrary.wiley.com\/authored-by\/Herrera\/Francisco\">Francisco Herrera<\/a><a href=\"mailto:triguero@decsai.ugr.es\"><\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Resumen<\/strong> &#8211; The increasing adoption of artificial intelligence (AI) in critical domains such as healthcare, law, and defense demands robust mechanisms to ensure transparency and explainability in decision-making processes. While machine learning and deep learning algorithms have advanced significantly, their growing complexity presents persistent interpretability challenges. Existing maturity frameworks, such as Capability Maturity Model Integration, fall short in addressing the distinct requirements of explainability in AI systems, particularly where ethical compliance and public trust are paramount. To address this gap, we propose the Maturity Model for eXplainable Artificial Intelligence: Analysis and Evaluation (MM4XAI-AE), a domain-agnostic maturity model tailored to assess and guide the practical deployment of explainability in AI-based applications. The model integrates two complementary components: an analysis model and an evaluation model, structured across four maturity levels\u2014operational, justified, formalized, and managed. It evaluates explainability across three critical dimensions: technical foundations, structured design, and human-centered explainability. MM4XAI-AE is grounded in the PAG-XAI framework, emphasizing the interrelated dimensions of practicality, auditability, and governance, thereby aligning with current reflections on responsible and trustworthy AI. The MM4XAI-AE model is empirically validated through a structured evaluation of thirteen published AI applications from diverse sectors, analyzing their design and deployment practices. The results show a wide distribution across maturity levels, underscoring the model\u2019s capacity to identify strengths, gaps, and actionable pathways for improving explainability. This work offers a structured and scalable framework to standardize explainability practices and supports researchers, developers, and policymakers in fostering more transparent, ethical, and trustworthy AI systems.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Publicado en<\/strong> &#8211; International Journal of Intelligent SystemsVolume 2025, Article ID 4934696, 18 pages<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>DOI<\/strong> &#8211; <a href=\"https:\/\/doi.org\/10.1155\/int\/4934696\">https:\/\/doi.org\/10.1155\/int\/4934696<\/a><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/onlinelibrary.wiley.com\/doi\/full\/10.1155\/int\/4934696\">Enlace al art\u00edculo<\/a><\/li>\n<\/ul>\n<\/div><\/div>\n\n\n\n<!--nextpage-->\n\n\n\n<div class=\"wp-block-media-text is-stacked-on-mobile\"><figure class=\"wp-block-media-text__media\"><img loading=\"lazy\" decoding=\"async\" width=\"639\" height=\"422\" src=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-134002.png\" alt=\"\" class=\"wp-image-2326 size-full\" srcset=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-134002.png 639w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-134002-300x198.png 300w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-134002-18x12.png 18w\" sizes=\"(max-width: 639px) 100vw, 639px\" \/><\/figure><div class=\"wp-block-media-text__content\">\n<p class=\"wp-block-paragraph\"><strong>T\u00edtulo &#8211; <em>In silico<\/em>\u00a0prediction of the impact of genomic variations in the small conductance calcium activated potassium channel SK3 structure and function<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Autores<\/strong> &#8211; Lucia Padilla, Coral Del Val, Daria B. Neidre, Agust\u00edn S. Kokenge, Juan E. Martinez, Antonio L. Teixeira, Igor Zwir, Gabriel A. de Erausquin<a href=\"mailto:triguero@decsai.ugr.es\"><\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Resumen<\/strong> &#8211; The small-conductance calcium-activated potassium channel SK3, encoded by the KCNN3 gene, plays a critical role in regulating dopaminergic neuron (DN) firing patterns by modulating after hyperpolarization currents. SK3 dysfunction has been implicated in neuropsychiatric and neurodegenerative disorders. We analyzed structural and functional consequences of KCNN3 splicing and genetic variation. Alternative splicing variants of the KCNN3 gene were retrieved from the Ensembl database and aligned using T-Coffee, manually inspected and curated. Protein domains were identified with Pfam 35.0, SMART 9.0, and InterPro 98.0, and visualized. An AlphaFold2 model of SK3 full-length protein (UniProt: Q9UGI6) used as reference and structural models of its splicing variants were predicted with ColabFold. Functional domains (S1\u2013S6 transmembrane helices, H5 pore loop, and calmodulin-binding) were defined and superimposed onto the AlphaFold2 reference. Domain integrity was assessed based on completeness of all expected residue indices within each functional region. SNPs and CNVs across all coding KCNN3 splicing variants were analyzed, classified, and filtered to isolate pathogenic variants prioritizing non-synonymous amino acid substitutions. Differential variant impacts across splicing isoforms were assessed by mapping variant positions to individual transcript protein sequences and used to predict functional consequences. Two long and two short splicing variants are known. Short variants lack the motif required for potassium channels. Pathogenic variants result from missense mutations resulting in amino acid substitutions. In all cases, the consequential effects depend on the specific location and role of the amino acid being changed.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Publicado en<\/strong> &#8211; Front. Neurosci. 19:1631536.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>DOI<\/strong> &#8211; <a href=\"https:\/\/doi.org\/10.3389\/fnins.2025.1631536\">https:\/\/doi.org\/10.3389\/fnins.2025.1631536<\/a><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/www.frontiersin.org\/journals\/neuroscience\/articles\/10.3389\/fnins.2025.1631536\/full\">Enlace al art\u00edculo<\/a><\/li>\n<\/ul>\n<\/div><\/div>\n\n\n\n<!--nextpage-->\n\n\n\n<div class=\"wp-block-media-text is-stacked-on-mobile\"><figure class=\"wp-block-media-text__media\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"359\" src=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/make-08-00007-g001-1024x359.png\" alt=\"\" class=\"wp-image-2327 size-full\" srcset=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/make-08-00007-g001-1024x359.png 1024w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/make-08-00007-g001-300x105.png 300w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/make-08-00007-g001-768x269.png 768w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/make-08-00007-g001-1536x539.png 1536w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/make-08-00007-g001-2048x718.png 2048w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/make-08-00007-g001-18x6.png 18w\" sizes=\"(max-width: 1024px) 100vw, 1024px\" \/><\/figure><div class=\"wp-block-media-text__content\">\n<p class=\"wp-block-paragraph\"><strong>T\u00edtulo &#8211; WinStat: A Family of Trainable Positional Encodings for Transformers in Time Series Forecasting<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Autores<\/strong> &#8211; Cristhian Moya-Mota, <a href=\"mailto:cris190402@correo.ugr.es\"><\/a>Ignacio Aguilera-Martos, <a href=\"mailto:nacheteam@ugr.es\"><\/a>Diego Garc\u00eda-Gil, <a href=\"mailto:djgarcia@ugr.es\"><\/a>Juli\u00e1n Luengo<a href=\"mailto:julianlm@decsai.ugr.es\"><\/a><a href=\"mailto:triguero@decsai.ugr.es\"><\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Resumen<\/strong> &#8211; Transformers for time series forecasting rely on positional encoding to inject temporal order into the permutation-invariant self-attention mechanism. Classical sinusoidal absolute encodings are fixed and purely geometric; learnable absolute encodings often overfit and fail to extrapolate, while relative or advanced schemes can impose substantial computational overhead without being sufficiently tailored to temporal data. This work introduces a family of window-statistics positional encodings that explicitly incorporate local temporal semantics into the representation of each timestamp. The base variant (WinStat) augments inputs with statistics computed over a sliding window; WinStatLag adds explicit lag-difference features; and hybrid variants (WinStatFlex, WinStatTPE, WinStatSPE) learn soft mixtures of window statistics with absolute, learnable, and semantic positional signals, preserving the simplicity of additive encodings while adapting to local structure and informative lags. We evaluate proposed encodings on four heterogeneous benchmarks against state-of-the-art proposals: Electricity Transformer Temperature (hourly variants), Individual Household Electric Power Consumption, New York City Yellow Taxi Trip Records, and a large-scale industrial time series from heavy machinery. All experiments use a controlled Transformer backbone with full self-attention to isolate the effect of positional information. Across datasets, the proposed methods consistently reduce mean squared error and mean absolute error relative to a strong Transformer baseline with sinusoidal positional encoding and state-of-the-art encodings for time series, with WinStatFlex and WinStatTPE emerging as the most effective variants. Ablation studies that randomly shuffle decoder inputs markedly degrade the proposed methods, supporting the conclusion that their gains arise from learned order-aware locality and semantic structure rather than incidental artifacts. A simple and reproducible heuristic for setting the sliding-window length\u2014roughly one quarter to one third of the input sequence length\u2014provides robust performance without the need for exhaustive tuning.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Publicado en<\/strong> &#8211; <em>Mach. Learn. Knowl. Extr.<\/em>\u00a0<strong>2026<\/strong>,\u00a0<em>8<\/em>(1), 7;<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>DOI<\/strong> &#8211; <a href=\"https:\/\/doi.org\/10.3390\/make8010007\">https:\/\/doi.org\/10.3390\/make8010007<\/a><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/www.mdpi.com\/2504-4990\/8\/1\/7\">Enlace al art\u00edculo<\/a><\/li>\n<\/ul>\n<\/div><\/div>\n\n\n\n<!--nextpage-->\n\n\n\n<div class=\"wp-block-media-text is-stacked-on-mobile\"><figure class=\"wp-block-media-text__media\"><img loading=\"lazy\" decoding=\"async\" width=\"660\" height=\"413\" src=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-135940.png\" alt=\"\" class=\"wp-image-2328 size-full\" srcset=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-135940.png 660w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-135940-300x188.png 300w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-135940-18x12.png 18w\" sizes=\"(max-width: 660px) 100vw, 660px\" \/><\/figure><div class=\"wp-block-media-text__content\">\n<p class=\"wp-block-paragraph\"><strong>T\u00edtulo &#8211; Decision-Focused Learning Enhanced by Automated Feature Engineering for Energy Storage Optimisation<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Autores<\/strong> &#8211; Nasser\u00a0Alkhulaifi,\u00a0Ismail\u00a0Gokay Dogan,\u00a0Timothy R.\u00a0Cargan,\u00a0Alexander L.\u00a0Bowler,\u00a0Direnc\u00a0Pekaslan,\u00a0Nicholas J.\u00a0Watson,\u00a0Isaac\u00a0Triguero<a href=\"mailto:triguero@decsai.ugr.es\"><\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Resumen<\/strong> &#8211; Decision-making under uncertainty in energy management is complicated by unknown parameters hindering optimal strategies, particularly in Battery Energy Storage System (BESS) operations. Predict-Then-Optimise (PTO) approaches treat forecasting and optimisation as separate processes, allowing prediction errors to cascade into suboptimal decisions as models minimise forecasting errors rather than optimising downstream tasks. The emerging Decision-Focused Learning (DFL) methods overcome this limitation by integrating prediction and optimisation; however, they are relatively new and have been tested primarily on synthetic datasets with limited evidence of their practical viability. Real-world BESS applications present additional challenges, including greater variability and data scarcity due to collection constraints. Because of these challenges, this work leverages Automated Feature Engineering (AFE) to improve the nascent approach of DFL. This AFE\u2013DFL integration automatically extracts decision-relevant features from limited energy data without requiring domain expertise, while ensuring features directly enhance BESS operational decisions rather than merely improving prediction accuracy metrics. We propose an AFE\u2013DFL framework suitable for small datasets that forecasts electricity prices and demand while optimising BESS operations to minimise costs. We validate the framework\u2019s effectiveness on a novel real-world UK property dataset. The evaluation compares DFL methods against PTO, with and without AFE. Results show that DFL yields lower operating costs than PTO, and adding AFE further improves DFL performance by 22.9\u201356.5 % compared to models without AFE. These findings provide empirical evidence for DFL\u2019s practical viability, demonstrating that AFE-DFL integration reduces reliance on domain expertise while achieving superior economic outcomes for BESS optimisation.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Publicado en<\/strong> &#8211; <a href=\"https:\/\/www.sciencedirect.com\/journal\/expert-systems-with-applications\">Expert Systems with Applications<\/a>, <a href=\"https:\/\/www.sciencedirect.com\/journal\/expert-systems-with-applications\/vol\/302\/suppl\/C\">Volume 302<\/a>,\u00a015 March 2026, 130554<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>DOI<\/strong> &#8211; <a href=\"https:\/\/doi.org\/10.1016\/j.eswa.2025.130554\">https:\/\/doi.org\/10.1016\/j.eswa.2025.130554<\/a><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0957417425041697?via%3Dihub\">Enlace al art\u00edculo<\/a><\/li>\n<\/ul>\n<\/div><\/div>\n\n\n\n<!--nextpage-->\n\n\n\n<div class=\"wp-block-media-text is-stacked-on-mobile\"><figure class=\"wp-block-media-text__media\"><img loading=\"lazy\" decoding=\"async\" width=\"678\" height=\"255\" src=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-140321.png\" alt=\"\" class=\"wp-image-2329 size-full\" srcset=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-140321.png 678w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-140321-300x113.png 300w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-140321-18x7.png 18w\" sizes=\"(max-width: 678px) 100vw, 678px\" \/><\/figure><div class=\"wp-block-media-text__content\">\n<p class=\"wp-block-paragraph\"><strong>T\u00edtulo &#8211; A Case for the Use of Chroma Cartesian Colour Representations for Image<br>Classification on Plant-Based Domains<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Autores<\/strong> &#8211; Alexis J S Payne, Gail Hopkins, Shreyank N Gowda, Isaac Triguero, Michael P Pound<a href=\"mailto:triguero@decsai.ugr.es\"><\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Resumen<\/strong> &#8211; The primary approach in computer vision across all domains is to work with the Red, Green, Blue (RGB) colour representation. This is most clear in the use of transfer learning, where leveraging known good weights for a model, pretrained on large datasets in RGB, is commonplace. Despite the dominance of RGB, alternative colour representations, such as Hue, Saturation, Value (HSV), have seen use in plant-based domain specific tasks, or with models that are trained from the ground up. In this paper we have explored a wide array of known colour representations, across a variety of plant and plant disease identification datasets. These show that there is not just several colour representations that consistently outperform RGB in training from scratch, but a common construction of the representations that do: an isolated Luminosity channel, similar to a black and white version of the image;combined with a Cartesian representation of the Chroma component, the colour information. We propose a new and effective addition to this class, H2SV, which derives from the relatively widely used HSV representation, improving upon its polar representation of colour information and limited effectiveness when used with neural networks. We conduct extensive experiments that show the effectiveness of these colour representations over RGB is not limited to a single architecture, and this trend is seen across almost all plant datasets. We also show that these benefits can be combined with appropriately pretrained weights so both the computer vision norm of transfer learning, and these alternative colour representations can be leveraged at once. Relevant code tooling is available via PyPI.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Publicado en<\/strong> &#8211; Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) Workshops, 2025, pp. 7128-7137<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>DOI<\/strong> &#8211; <\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/openaccess.thecvf.com\/content\/ICCV2025W\/CVPPA\/html\/Payne_A_Case_for_the_Use_of_Chroma_Cartesian_Colour_Representations_ICCVW_2025_paper.html\">Enlace al art\u00edculo<\/a><\/li>\n<\/ul>\n<\/div><\/div>\n\n\n\n<!--nextpage-->\n\n\n\n<div class=\"wp-block-media-text is-stacked-on-mobile\"><figure class=\"wp-block-media-text__media\"><img loading=\"lazy\" decoding=\"async\" width=\"242\" height=\"139\" src=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-141458.png\" alt=\"\" class=\"wp-image-2330 size-full\" srcset=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-141458.png 242w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/Captura-de-pantalla-2026-02-23-141458-18x10.png 18w\" sizes=\"(max-width: 242px) 100vw, 242px\" \/><\/figure><div class=\"wp-block-media-text__content\">\n<p class=\"wp-block-paragraph\"><strong>T\u00edtulo &#8211; Exploring TabPFNv2 as a Novel Baseline for ADMET Prediction in Drug Discovery<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Autores<\/strong> &#8211; <a href=\"https:\/\/zenodo.org\/search?q=metadata.creators.person_or_org.name:%22Ipas,+Oroel%22\">Ipas, Oroel<\/a>, <a href=\"https:\/\/zenodo.org\/search?q=metadata.creators.person_or_org.name:%22Su%C3%A1rez+Mart%C3%ADn,+Ignacio%22\">Su\u00e1rez Mart\u00edn, Ignacio<\/a>, <a href=\"https:\/\/zenodo.org\/search?q=metadata.creators.person_or_org.name:%22Gomez-Trenado,+Guillermo%22\">Gomez-Trenado, Guillermo<\/a>, <a href=\"https:\/\/zenodo.org\/search?q=metadata.creators.person_or_org.name:%22Triguero,+Isaac%22\">Triguero, Isaac<\/a>, <a href=\"https:\/\/zenodo.org\/search?q=metadata.creators.person_or_org.name:%22Romero-Zaliz,+Rocio%22\">Romero-Zaliz, Rocio<\/a><a href=\"mailto:triguero@decsai.ugr.es\"><\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Resumen<\/strong> &#8211; Tabular data is one of the most widely used formats in bioinformatics research. Therefore,<br>improving algorithmic baselines for such data has important implications for a wide range of<br>applications. One of these critical applications is the prediction of Absorption, Distribution,<br>Metabolism, Excretion, and Toxicity (ADMET) properties of drugs, a key step in the early<br>stages of drug development. Failures due to poor pharmacokinetic profiles remain a leading<br>cause of attrition in clinical trials, highlighting the need for reliable predictive tools. In recent<br>years, machine learning has emerged as a powerful approach to model complex ADMET<br>behaviors, enabling faster, more cost-effective, and more ethical drug screening pipelines.<br>While some current state-of-the-art pproaches, such as MiniMol or MolE, leverage especialized models pretrained on millions of drug-like molecules, Gradient Boosted Decision Trees algorithms like XGBoost continue to serve as strong baselines for many general-purpose tasks.<br>The objective of this study is to explore the use of novel tabular foundation models as a new<br>baseline for tabular data in bioinformatics, with a focus on ADMET drug prediction. To this<br>end, we used TabPFNv2, an In-Context Learning model based on transformers that was<br>pretrained on synthetic data. For evaluation, we employed the Therapeutic Data Commons<br>benchmark, comprising 22 datasets that include both regression and classification tasks,<br>and extracted the widely used set of 217 RDKit molecular descriptors.<br>This generic algorithm outperforms XGBoost in 19 out of 22 datasets and surpasses MiniMol<br>in 9 out of 22, despite not relying on any prior, drug-specific knowledge. Notably, TabPFNv2<br>achieves the top rank in 3 tasks, surpassing specialized methods in the field. These results<br>suggest that TabPFNv2 is a promising baseline for drug prediction, with potential<br>applications in other bioinformatics tasks, including clinical and small omics datasets that<br>meet TabPFNv2\u2019s size constraints. Furthermore, its independence from domain-specific<br>pretraining and hyperparameter tuning enhances its applicability for non-expert practitioners.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Publicado en<\/strong> &#8211; Presented poster in the XVIII Brazilian&nbsp;Symposium&nbsp;on Bioinformatics (BSB) 2025.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>DOI<\/strong> &#8211; <a href=\"https:\/\/doi.org\/10.5281\/zenodo.17468021\">10.5281\/zenodo.17468021<\/a>.<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/zenodo.org\/records\/17468022\">Enlace al art\u00edculo<\/a><\/li>\n<\/ul>\n<\/div><\/div>\n\n\n\n<!--nextpage-->\n\n\n\n<div class=\"wp-block-media-text is-stacked-on-mobile\"><figure class=\"wp-block-media-text__media\"><img loading=\"lazy\" decoding=\"async\" width=\"470\" height=\"270\" src=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/1-s2.0-S1566253526001156-gr1.jpg\" alt=\"\" class=\"wp-image-2331 size-full\" srcset=\"https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/1-s2.0-S1566253526001156-gr1.jpg 470w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/1-s2.0-S1566253526001156-gr1-300x172.jpg 300w, https:\/\/iafer.dasci.es\/wp-content\/uploads\/2026\/02\/1-s2.0-S1566253526001156-gr1-18x10.jpg 18w\" sizes=\"(max-width: 470px) 100vw, 470px\" \/><\/figure><div class=\"wp-block-media-text__content\">\n<p class=\"wp-block-paragraph\"><strong>T\u00edtulo &#8211; From privacy to trust in the agentic era: a taxonomy of challenges in trustworthy federated learning through the lens of trust report 2.0<\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Autores<\/strong> &#8211; Nuria\u00a0Rodr\u00edguez-Barroso,\u00a0Mario\u00a0Garc\u00eda-M\u00e1rquez, M. Victoria\u00a0Luz\u00f3n, Francisco\u00a0Herrera<a href=\"mailto:triguero@decsai.ugr.es\"><\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Resumen<\/strong> &#8211; Federated Learning (FL) enables privacy-preserving collaborative learning, yet deployments increasingly show that privacy guarantees alone do not sustain trust in high-risk settings. As FL systems move toward agentic AI, large language model\u2013enabled, and dynamically adaptive architectures, trustworthiness becomes a system-level problem shaped by autonomous decision-making, non-stationary environments, and multi-stakeholder governance. We argue for Trustworthy FL (TFL), treating trust as a continuously maintained operating condition rather than a static model property.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Through the lens of Trust Report 2.0, we propose a requirement-driven taxonomy of challenges grounded in TAI and explicitly extended to account for control-plane decisions, agency, and system dynamics across the federated lifecycle. Building on this diagnosis, we introduce a coordination blueprint that structures cross-requirement trade-offs, decision justification, and governance alignment in TFL systems. To operationalize assurance, Trust Report 2.0 is instantiated as a lightweight, privacy-preserving artifact that surfaces decision-centric trust evidence without centralizing raw data. We illustrate applicability via healthcare as a stress-test domain, focusing on oncology FL under regulatory pressure and clinical risk.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>Publicado en<\/strong> &#8211; <a href=\"https:\/\/www.sciencedirect.com\/journal\/information-fusion\">Information Fusion<\/a>, <a href=\"https:\/\/www.sciencedirect.com\/journal\/information-fusion\/vol\/132\/suppl\/C\">Volume 132<\/a>,\u00a0August 2026, 104236<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>DOI<\/strong> &#8211; <a href=\"https:\/\/doi.org\/10.1016\/j.inffus.2026.104236\">https:\/\/doi.org\/10.1016\/j.inffus.2026.104236<\/a><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1566253526001156?dgcid=rss_sd_all\">Enlace al art\u00edculo<\/a><\/li>\n<\/ul>\n<\/div><\/div>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"parent":89,"menu_order":30,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-105","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/iafer.dasci.es\/en\/wp-json\/wp\/v2\/pages\/105","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/iafer.dasci.es\/en\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/iafer.dasci.es\/en\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/iafer.dasci.es\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/iafer.dasci.es\/en\/wp-json\/wp\/v2\/comments?post=105"}],"version-history":[{"count":3,"href":"https:\/\/iafer.dasci.es\/en\/wp-json\/wp\/v2\/pages\/105\/revisions"}],"predecessor-version":[{"id":2333,"href":"https:\/\/iafer.dasci.es\/en\/wp-json\/wp\/v2\/pages\/105\/revisions\/2333"}],"up":[{"embeddable":true,"href":"https:\/\/iafer.dasci.es\/en\/wp-json\/wp\/v2\/pages\/89"}],"wp:attachment":[{"href":"https:\/\/iafer.dasci.es\/en\/wp-json\/wp\/v2\/media?parent=105"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}