Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 32
Encontrada(s) 1 página(s)

RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

BetaGPU: Harnessing GPU power for parallelized beta distribution functions

  • Fernández-Fraga, Alejandro
  • González-Domínguez, Jorge
  • Martín, María J.
Permanent link to code/repository used for this code version: https://github.com/ElsevierSoftwareX/SOFTX-D-24-00555. Link to developer documentation/manual: https://github.com/UDC-GAC/BetaGPU, [Abstract]: The efficient computation of Beta distribution functions, particularly the Probability Density Function (PDF) and Cumulative Distribution Function (CDF), is critical in various scientific fields, including bioinformatics and data analysis. This work presents BetaGPU, a high-performance software package written in C++ and CUDA that leverages the parallel processing capabilities of Graphics Processing Units (GPUs) to significantly accelerate these computations, with an OpenMP version for multiCPU systems, and integrated seamlessly with popular statistical programming languages R and Python. This open-source package provides an accessible, accurate, and scalable solution for researchers and practitioners. By offloading intensive calculations to the GPU, this software is significantly faster than traditional single-core CPU-based methods, facilitating faster data analysis and enabling real-time applications. The software’s high performance and ease of use make it an invaluable tool for users in bioinformatics and other data-intensive domains., This work was supported by grants TED2021-130599A-I00 and PID2022-136435NB-I00, funded by MCIN/AEI/ (TED2021 also funded by “NextGenerationEU”/PRTR and PID2022 by “ERDF A way of making Europe”, EU); grant TSI-100925-2023-1, funded by Ministry for Digital Transformation and Civil Service and Next-GenerationEU/RRF; and FPU predoctoral grant of Alejandro Fernández-Fraga ref. FPU21/03408, funded by the Ministry of Science, Innovation and Universities, Spain. We gratefully thank the Galician Supercomputing Center (CESGA) for the access granted to its supercomputing resources. Funding for open access charge: Universidade da Coruña/CISUG., Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Acceleration of Cancer Detection through the Calculation of Beta Distributions on GPUs

  • Fernández-Fraga, Alejandro
  • González-Domínguez, Jorge
  • Martín, María J.
[Abstract]: DNA methylation analysis has emerged as a powerful method for non-invasive cancer detection and diagnosis. However, the statistical approaches underpinning these analyses are computationally intensive, creating a significant bottleneck for large-scale studies and clinical applications. This work addresses this challenge by presenting a high-performance, GPU-accelerated implementation of a cancer detection tool. We introduce a structured optimization methodology that leverages BetaGPU, a specialized library designed to accelerate beta distribution functions using GPU computing, to dramatically reduce the computational cost of the core statistical operations. We demonstrate how BetaGPU can be effectively integrated into a real-world bioinformatics pipeline, and introduce several optimizations to the library to further enhance performance. Our work confirms that leveraging efficient third-party GPU libraries provides a viable path to significant acceleration of methylation-based cancer detection tools, paving the way for broader adoption of accelerator technologies in bioinformatics workflows. The complete implementation of our new GPU-accelerated tool, is publicly available at https://github.com/UDC-GAC/CancerLocatorGPU., This work was supported by grant PID2022-136435NB-I00, funded by MICIU/AEI/10.13039/501100011033 and “ERDF A way of making Europe”, EU; grant TSI-100925-2023-1, funded by Ministry for Digital Transformation and Civil Service and Next-GenerationEU/RRF; FPU predoctoral grant of Alejandro Fernández-Fraga ref. FPU21/03408, funded by the Ministry of Science, Innovation and Universities, Spain ; and by Xunta de Galicia, Consolidation Program of Competitive Reference Groups, ref. ED431C 2025/33. We gratefully thank the Galician Supercomputing Center (CESGA) for the access granted to its supercomputing resources., Xunta de Galicia; ED431C 2025/33, https://github.com/UDC-GAC/CancerLocatorGPU
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Comparison of Data Set Sample Selection Algorithms for Data Science: a Systematic Review

  • Fernández Sánchez, Alberto
  • Gestal, M.
  • Bolón-Canedo, Verónica
  • Dorado, Julián
  • Pazos, A.
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG, [Abstract]: In the era of big data, selecting representative samples has become essential to mitigate overfitting, noise, and high computational cost in machine learning. This study systematically reviews the evolution of instance selection (IS) methods, highlighting the growing importance of instance hardness (IH) as a guiding criterion to improve training efficiency and model robustness. Through a comprehensive search in Scopus and Web of Science, fifty-five studies were identified and analyzed following strict inclusion and exclusion criteria. The reviewed works were classified according to their underlying rationale–error-based, geometric, heuristic, or explainability-driven–revealing that IH principles intersect these categories as a transversal perspective on data quality. Most studies focus on enhancing predictive accuracy (56%) and computational efficiency (36%), while bias reduction and privacy preservation remain secondary. Reported outcomes show significant dataset reductions (up to 97%) with minimal accuracy loss and, in some cases, notable performance gains (+32% accuracy, +67% improvement in MSE). Despite these advances, explicit references to IH are rare, though many methods implicitly rely on related metrics such as misclassification frequency or decision-boundary proximity. Overall, IS is gaining relevance across domains such as cybersecurity, biomedicine, and computer vision, yet the field still lacks standardized methodologies and benchmarking frameworks, underscoring the need for unified, IH-informed strategies for robust and generalizable instance selection., This work was supported by the Ministry for Digital Transformation and Civil Service and ’NextGenerationEU’/PRTR under Grant TSI-100925-2023-1. The author also acknowledges CITEEC, a Collaborative Center of the Galician University System, co-funded by the Xunta de Galicia and the European Union (ERDF) through the FEDER Galicia 2021-2027 program (ED431G 2023/10) under the thematic objective "A Smarter Europe: Innovative Economic Transformation., Xunta de Galicia; ED431G 2023/10
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Understanding Joint Range of Motion Development in Robotic Learning

  • Naya-Varela, M.
  • Faíña, Andrés
  • Romero, Alejandro
  • Duro, Richard J.
[Abstract] Joint Range of Motion (JROM) development has been shown to facilitate learning motor control in human beings. This developmental strategy has been applied in robotics to improve learning performance with different outcomes: sometimes it is favourable, others irrelevant, and others, even detrimental. The reasons that underpin this variability in the results are still not well understood. In this paper, we seek to better understand the principles underlying the application of JROM based morphological development to make its use more straightforward. To this end, empirical studies were carried out over two representative use cases: quadruped and bipedal robot morphologies learning to walk. Different parameters of the application of JROM development (morphological configuration, JROM developmental strategy, etc.) have been evaluated to elucidate their effects over learning. The results show that there are significant connections between the reduction of the motor space induced by JROM and the way the exploration and exploitation of the solution space is carried out by the learning algorithm, and the performance achieved. Through these connections, we have identified a set of conditions that must be satisfied for JROM development to be effective as a tool for learning improvement., This research was partially funded by the European Union’s Horizon 2020, Research and Innovation Programme, GA 101070381 (“PILLAR-Robots - Purposeful Intrinsically-motivated Lifelong Learning Autonomous Robots”), by Xunta de Galicia (EDC431C-2021/39 and M. Naya-Varela’s grant ED481B), by the Spanish Science and Education Ministry (PID2021-126220OB-I00), and the Ministry for Digital Transformation and Civil Service and Next-Generation EU/RRF (TSI-100925-2023-1), by “ERDF A way of making Europe’, Centro de Investigación de Galicia “CITIC” (ED431G 2019/01)., Xunta de Galicia; EDC431C-2021/39, Xunta de Galicia; ED481B-2022-004, Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

LITHEUM. A web-based lighting and thermal urban model for city energy assessment

  • Rodríguez-Álvarez, Jorge
  • Rodríguez Luaces, Miguel
  • Varela Rodeiro, Tirso
  • Alvaredo López, Natalia
  • Lamas Sardiña, Víctor Juan
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG, [Abstract]: This study presents Litheum (LIghting and THErmal Urban Model), an online urban building energy modelling (UBEM) tool that integrates morphological sensitivity analysis with interactive scenario development. By leveraging Geographic Information Systems and open-source technologies, the model addresses the accessibility challenges of previous UBEM tools, offering an intuitive web-based application suitable for diverse users, from homeowners to planners and policymakers, without requiring prior energy modelling expertise. Litheum applies a novel algorithm to calculate solar obstruction, optimizing computational requirements while capturing the spatial and temporal dynamics of urban contexts, an area where data-driven models often fall short. The energy calculation methods follow the EN ISO 52016–1 standard, balancing precision, flexibility, and reproducibility for large-scale applications. Unlike detailed dynamic building simulation tools, Litheum is optimized for urban energy planning and policy development. Pilot studies in three Spanish cities—Pontevedra, A Coruña, and Madrid—demonstrated the model's adaptability across varying urban scales. Feedback informed enhancements, including a solar control mode functionality for warmer climates. The online platform's design enables seamless interaction and rapid deployment in diverse urban settings. Future efforts will focus on expanding the platform's deployment in additional cities, integrating artificial intelligence to infer key building characteristics, such as glazing ratios, to improve robustness and processing efficiency. Litheum exemplifies the potential of open-source UBEM tools to facilitate energy assessment, fostering widespread adoption and better informed planning decisions., The research reported in this article was funded by MCIN/ AEI/10.13039/501100011033/ and by “European Union NextGenerationEU/PRTR, with the Grant TED2021–130779A-I00 The CITIC Database Lab authors acknowledge the support by the CITIC, as a center accredited for excellence within the Galician University System and a member of the CIGUS Network, receives subsidies from the Department of Education, Science, Universities, and Vocational Training of the Xunta de Galicia. Additionally, it is co-financed by the EU through the FEDER Galicia 2021–27 operational program (Ref. ED431G 2023/01); and by MCIN/ AEI/10.13039/501100011033 ([EXTRA-Compact: PID2020–114635RB-I00]; “NextGenerationEU”/PRTR [SIGTRANS: PDC2021–120917-C21], [PLAGEMIS: TED2021–129245B-C21]; EU/ERDF A way of making Europe [EarthDL: PID2022–141027NB-C21] partially funded by MCIN/AEI/10.13039/501100011033 and EU/ERDF A way of making Europe); by GAIN/Xunta de Galicia [GRC: ED431C 2021/53]; by UE FEDER [0079_ATEMPO_6_E], [0064_GRESINT_1_E] and by INE [CIDMEFEO]. Jorge Rodríguez-Álvarez acknowledges the support of the Ministry for Digital Transformation and Civil Service and Next-GenerationEU/RRF under Grant TSI-100925–2023–1 to support the development of the model with AI techniques; and MCIN/ AEI/10.13039/501100011033/and by ERDF A way of making Europe for the assistance in the continuation of the project for the adaptation of the model to rural areas with the Grant PID2021‐123961OA‐I00. Funding for open access charge: Universidade da Coruña/CISUG.
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Improving restaurant recommendation transparency through feature selection

  • Bagué-Masanés, Roger
  • Remeseiro, Beatriz
  • Bolón-Canedo, Verónica
[Abstract]: Recommender systems are widely used to suggest items (i.e., products or services) based on user preferences. However, personalized recommender systems incorporating information beyond user ratings can provide more accurate and relevant recommendations. This paper introduces a hybrid personalized recommender system that utilizes several characteristics of items in addition to user ratings. The focus of this study is on the restaurant industry, and the dataset used is sourced from TripAdvisor, one of the most popular travel and tourism websites. The attributes include price range, cuisines, special diets, meals, and features like free WiFi and wheelchair accessibility. To improve the transparency of the recommendation process and understand the variables that influence the system’s output, we propose the use of feature selection techniques. By analyzing the impact of each variable, this study aims to help readers understand the recommendation process and identify the factors to consider when choosing to visit a restaurant., This work has been supported by the National Plan for Scientific and Technical Research and Innovation of the Spanish Government (Grants PID2023-147404OB-I00 and TED2021-130599A-I00), and by the Ministry for Digital Transformation and Civil Service and ‘Next-GenerationEU’/PRTR under Grant TSI-100925-2023-1. The Agency for Science, Business Competitiveness, and Innovation of the Principality of Asturias in Spain (SEKUENS) is also acknowledged for funding through the project GRU-GIC-24–018. CITIC, as a center accredited for excellence within the Galician University System and a member of the CIGUS Network, receives subsidies from the Department of Education, Science, Universities, and Vocational Training of the Xunta de Galicia. Additionally, it is co-financed by the EU through the FEDER Galicia 2021–27 operational program (Ref. ED431G 2023/01). Grant ED431C 2022/44 funded by, Xunta de Galicia; ED431G 2023/01, Xunta de Galicia; ED431C 2022/44, Gobierno del Principado de Asturias; GRU-GIC-24–018
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Enhancing Classification Performance on Imbalanced Datasets Through Complexity-Guided Oversampling With SMOTE

  • Morillo-Salas, José Luis
  • Bolón-Canedo, Verónica
  • Morán-Fernández, Laura
  • Alonso-Betanzos, Amparo
[Abstract]: Improving classification performance on imbalanced datasets remains a challenging problem in machine learning. Synthetic oversampling techniques such as SMOTE are widely used to address class imbalance; however, their random interpolation strategy often ignores structural data properties, which may affect classifier generalisation. This work proposes a set of SMOTE-based strategies that guide the generation of synthetic samples in order to produce structurally simpler training datasets that are easier for classifiers to learn. The first strategy generates more dispersed (outer) synthetic samples to increase class separability with minimal computational overhead. The second and main contribution, SMOTE-Complex, formulates synthetic sample selection as an explicit optimisation process that minimises measurable training dataset complexity. A clustering-based variant, SMOTE-Complex-Clustering, reduces computational cost by restricting optimisation to feature subspaces while preserving most structural and predictive benefits. The underlying hypothesis is that reducing the structural complexity of the training data can lead to improved predictive behaviour. Extensive experiments on binary and multiclass datasets, using multiple classifiers and complementary evaluation metrics, provide empirical support for this hypothesis across diverse structural conditions. The results indicate moderate but stable improvements in structurally favourable scenarios—particularly binary and moderately complex problems—without systematic degradation in imbalance-sensitive metrics, while the clustering-based refinement offers a scalable trade-off between optimisation strength and computational efficiency., This work has been supported by the National Plan for Scientific and Technical Research and Innovation of the Spanish Government (Grant PID2023-147404OB-I009), and by the Ministry for Digital Transformation and Civil Service and ‘Next-GenerationEU’/PRTR under Grant TSI-100925-2023-1. CITIC, as a center accredited for excellence within the Galician University System and a member of the CIGUS Network, receives subsidies from the Department of Education, Science, Universities, and Vocational Training of the Xunta de Galicia. Additionally, it is co-financed by the EU through the FEDER Galicia 2021-27 operational program (Ref. ED431G 2023/01). Grant ED431C 2022/44 funded by Xunta de Galicia., Xunta de Galicia; ED431G 2023/01, Xunta de Galicia; ED431C 2022/44
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Optimising Image Feature Extraction and Selection: A Comprehensive Review With Spark Case Studies

  • Figueira-Domínguez, J. Guzmán
  • Remeseiro, Beatriz
  • Bolón-Canedo, Verónica
The data that support the findings of this study are openly available inImagenet Features Extracted with VGG-19 at https://zenodo.org/records/12791398, [Abstract]: As benchmark image datasets expand in sample size and feature complexity, the challenge of managing increased dimensionality becomes apparent. Contrary to the expectation that more features equate to enhanced information and improved outcomes, the curse of dimensionality often hampers performance. This paper reviews existing literature on filter feature selection techniques applied to image features, highlighting their use in both classical and deep-learning-based feature extraction methods. Building on these findings, this study proposes a scalable approach for image feature extraction and selection using Big Data technologies, specifically Apache Spark, to efficiently process large and high-dimensional datasets. The proposed framework integrates filter-based feature selection methods within a distributed environment to evaluate their effectiveness in image analysis tasks. Several experiments were performed to compare the results using feature selection techniques with various reduction percentages. Results show that significant feature reduction can be achieved without compromising classification accuracy, demonstrating the potential of Spark-based distributed processing for large-scale image analytics., This work was supported by Xunta de Galicia (ED431C 2022/44);National Plan for Scientific and Technical Research and Innovation ofthe Spanish Government (PID2023-147404OB-I00); Ministry for DigitalTransformation and Civil Service and Next-GenerationEU/PRTR (TSI-100925-2023-1); Agency for Science, Business Competitiveness, and Innovation of the Principality of Asturias in Spain (SEKUENS) (GRU-GIC- 24-018); Department of Education, Science, Universities, andVocational Training of the Xunta de Galicia; FEDER Galicia 2021-27 op-erational program (ED431G 2023/01), Xunta de Galicia; ED431C 2022/44, Xunta de Galicia; ED431G 2023/01, Gobierno del Principado de Asturias; GRU-GIC- 24-018
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

The Kate Chopin Experiment: Comparing Generative AI and Human Creative Writing Fictional Narrative Processes

  • Williams, Paul
  • Gómez-Rodríguez, Carlos
[Abstract]: This project aims to understand the underlying process by which humans and Large Language Models (LLMs) undertake complex creative writing tasks. Using a series of semi-structured interviews with ten human writers who write a specific story, and an analysis of how four generative AI LLMs ‘create’ the same story, this project seeks to explore similarities and differences in how humans research and produce creative works, and how AI LLMs generate simulacra of creative works, in order to further understand how human creative processes and AI generative production operate. The results show that there are fundamental differences in AI and human creative writing processes, and that anthropomorphic linguistic agency is falsely attributed to LLMs. Human creative processes are varied and eclectic, sometimes illogical and non-linear, but humans could use some of the techniques used by LLMs as labor-saving shortcuts to what is sometimes a laborious and time-consuming procedure., LATCHING (PID2023-147129OB-C21) funded by MICIU/AEI/10.13039/501100011033 and ERDF, EU; and TSI-100925-2023-1 funded by Ministry for Digital Transformation and Civil Service, Spain and ‘NextGenerationEU’ PRTR; as well as funding by Xunta de Galicia (ED431C 2024/02). CITIC, as a center accredited for excellence within the Galician University System and a member of the CIGUS Network, receives subsidies from the Department of Education, Science, Universities, and Vocational Training of the Xunta de Galicia. Additionally, it is co-financed by the EU through the ERDF Galicia 2021-27 operational program (Ref. ED431G 2023/01)., Xunta de Galicia; ED431C 2024/02, Xunta de Galicia; ED431G 2023/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Low-Complexity K-Beams Clustering for Intra-Cell Pilot Reuse in Massive MIMO Communications

  • Pereira Ruisánchez, Dariel
  • Fresnedo, Óscar
  • Pérez-Adán, Darian
  • Castedo, Luis
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG, [Abstract]: Massive MIMO (mMIMO) communication systems are recognized as key enablers of next-generation wireless networks. However, the orthogonal pilot assignments typical of multiple-input multiple-output (MIMO) systems are not well suited to emerging use cases characterized by short channel coherence times and a high number of connected user equipments (UEs). In this work, we propose a novel approach for intra-cell pilot reuse that leverages the spatial features of correlated mMIMO channels to attain low pilot contamination while using a small number of pilot sequences. The first part of the proposed solution is a groundbreaking clustering algorithm termed K-beams, which splits the complex intra-cell pilot allocation into tractable problems without significant loss of optimality. Then, we introduce a heuristic approach called best-first pilot assignment (BFPA), designed to manage intra-cluster pilot assignments by minimizing interference among the most contaminating UEs. We evaluated the performance of our proposed solution (K-beams+BFPA) in terms of sum-normalized mean-squared error (NMSE) and sum-rate under various challenging network setups. The simulation results show that our approach is a robust alternative to more computationally demanding benchmarks., This work has been supported by grant ED431C 2024/18 funded by Xunta de Galicia and by grant PID2022-137099NB-C42 (MADDIE) funded by MCIN/AEI/10.13039/501100011033. This work also received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No. 101034261 and the Ministry for Digital Transformation and Civil Service and “NextGenerationEU”/PRTR under grant TSI-100925-2023-1. Additionally, this work received funding for open-access charges from the agreement Universidade da Coruña/CISUG., Xunta de Galicia; ED431C 2024/18
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Contrastive Learning for Explanation Ranking

  • Escarda Fernández, Miguel
  • Cancela, Brais
  • Eiras-Franco, Carlos
  • Guijarro-Berdiñas, Bertha
  • Alonso-Betanzos, Amparo
Financiado para publicación en acceso aberto: CRUE-CSIC, [Abstract]: Explainable recommendation systems enhance user trust and satisfaction by revealing the reasoning behind personalized recommendations. Approaching this as a post-hoc explanation-ranking problem over a fixed pool of candidate explanations, we propose Contrastive Learning for Explanation Ranking (CLER), a model that learns user, item, and explanation representations with a Normalized Temperature-scaled Binary Cross-Entropy (NT-BXent) loss. This function specifically applies a per-row reweighting strategy, preventing the vast number of negative examples from dominating the objective. We evaluate CLER on the Amazon, TripAdvisor, and Yelp datasets from the EXTRA benchmark. Across traditional ranking metrics, CLER achieves the strongest results among the compared baselines., This work was supported in part by MICIU/AEI/10.13039/501100011033 and ERDF, EU under Grant PID2023-147404OB-I00 and Grant PID2021-128045OA-I00; in part by the Ministry for Digital Transformation and Civil Service and Next-GenerationEU/PRTR under Grant TSI-100925-2023-1; in part by the Xunta de Galicia under Grant ED431C 2022/44; and in part by Consellería de Cultura, Educación e Universidade (ERDF Operational Programme Galicia 2021–2027) and Secretaría Xeral de Universidades under Grant ED431G2023/01., Xunta de Galicia; ED431C 2022/44, Xunta de Galicia; ED431G2023/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Beyond RMSE and MAE: Introducing EAUC to Unmask Hidden Bias and Unfairness in Dyadic Regression Models

  • Paz Ruza, Jorge
  • Alonso-Betanzos, Amparo
  • Guijarro-Berdiñas, Bertha
  • Cancela, Brais
  • Eiras-Franco, Carlos
[Abstract]: Dyadic regression models, which output real-valued predictions for pairs of entities, are fundamental in many domains [e.g., obtaining user-product ratings in recommender systems (RSs)] and promising and under exploration in others (e.g., tuning patient–drug dosages in precision pharmacology). In this work, we prove that nonuniform observed value distributions of individual entities lead to severe biases in state-of-the-art models, skewing predictions toward the average of observed past values for the entity and providing worse-than-random predictive power in eccentric yet crucial cases; we name this phenomenon eccentricity bias. We show that global error metrics like root-mean-squared error (RMSE) are insufficient to capture this bias, and we introduce eccentricity area under the curve (EAUC) as a novel metric that can quantify it in all studied domains and models. We prove the intuitive interpretation of EAUC by experimenting with naive post-training bias corrections and theorize other options to use EAUC to guide the construction of fair models. This work contributes a bias-aware evaluation of dyadic regression to prevent unfairness in critical real-world applications of such systems., This work was supported in part by MICIU/AEI/10.13039/501100011033 and ESF+ under Grant FPU21/05783; in part by MICIU/AEI/10.13039/501100011033 under Grant PID2019-109238GB-C22; in part by MICIU/AEI/10.13039/501100011033 and ERDF, EU under Grant PID2023-147404OB-I00 and Grant PID2021-128045OA-I00; in part by the Ministry for Digital Transformation and Civil Service and Next-Generation EU/PRTR under Grant TSI-100925-2023-1; in part by the Xunta de Galicia under Grant ED431C 2022/44; and in part by Consellería de Cultura, Educación e Universidade (ERDF Operational Programme Galicia 2021–2027) and Secretaría Xeral de Universidades under Grant ED431G 2023/01., Xunta de Galicia; ED431C 2022/44, Xunta de Galicia; ED431G 2023/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

CUDA Acceleration of MI-Based Feature Selection Methods

  • Beceiro, Bieito
  • González-Domínguez, Jorge
  • Morán-Fernández, Laura
  • Bolón-Canedo, Verónica
  • Touriño, Juan
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG, [Abstract]: Feature selection algorithms are necessary nowadays for machine learning as they are capable of removing irrelevant and redundant information to reduce the dimensionality of the data and improve the quality of subsequent analyses. The problem with current feature selection approaches is that they are computationally expensive when processing large datasets. This work presents parallel implementations for Nvidia GPUs of three highly-used feature selection methods based on the Mutual Information (MI) metric: mRMR, JMI and DISR. Publicly available code includes not only CUDA implementations of the general methods, but also an adaptation of them to work with low-precision fixed point in order to further increase their performance on GPUs. The experimental evaluation was carried out on two modern Nvidia GPUs (Turing T4 and Ampere A100) with highly satisfactory results, achieving speedups of up to 283x when compared to state-of-the-art C implementations., This work was supported by grants PID2019-104184RB-I00, PID- 2019-109238GB-C22, TED2021-130599A-I00 and PID2022-136435NB- I00, funded by MCIN/AEI/ 10.13039/501100011033 (TED2021 also funded by “NextGenerationEU”/PRTR and PID2022 by “ERDF A way of making Europe”, EU). Grant TSI-100925-2023-1, funded by Ministry for Digital Transformation and Civil Service. FPU predoctoral grant of Bieito Beceiro ref. FPU20/00997, funded by the Ministry of Sci- ence, Innovation and Universities. We gratefully thank the Galician Supercomputing Center (CESGA) for the access granted to its super- computing resources. Funding for open access charge: Universidade da Coruña/CISUG.
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

A Hybrid Metaheuristics-Bayesian Optimization Framework with Safe Transfer Learning for Continuous Spark Tuning

  • Garralda-Barrio, Mariano
  • Eiras-Franco, Carlos
  • Bolón-Canedo, Verónica
The source code and experimental resources supporting this study are openly available at Github (https://github.com/mgarralda/garralda-performance-model). They are released for academic and research use under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0)., [Abstract]: Tuning configuration parameters in distributed Big Data engines such as Apache Spark is a high-dimensional, workload-dependent problem with significant impact on performance and operational cost. We address this challenge with a hybrid optimization framework that integrates Iterated Local Search, Tabu Search, and locally embedded Bayesian Optimization guided by STL-PARN (safe transfer learning with pattern-adaptive robust neighborhoods). Historical executions are partitioned into a Nucleus of reliable neighbors and a Corona of exploratory configurations, ensuring relevance while mitigating negative transfer. The surrogate within the embedded Bayesian Optimization stage decouples performance prediction from uncertainty modeling, enabling parameter-free acquisition functions that self-adapt to diverse workloads. Experiments on a modernized HiBench suite across multiple input scales show consistent gains over state-of-the-art baselines in execution time, convergence, and cost efficiency. Overall, the results demonstrate the robustness and practical value of embedding Bayesian Optimization within a global metaheuristic loop for adaptive, cost-aware Spark tuning. All source code and datasets are publicly available, supporting reproducibility and operational efficiency in large-scale data processing., The authors extend their gratitude to Laboratorio Innovación Aplicada (LIA) at Minsait (Indra Company) for their support in this study. This work has been supported by Ministerio de Ciencia e Innovación MCIN/AEI/10.13039/501100011033/ FEDER, UE under grant PID2023-147404OB-I00, and by the Ministry for Digital Transformation and Civil Service and ‘Next-GenerationEU’ /PRTR under Grant TSI-100925-2023-1. CITIC, as a center accredited for excellence within the Galician University System and a member of the CIGUS Network, receives subsidies from the Department of Education, Science, Universities, and Vocational Training of the Xunta de Galicia. Additionally, it is co-financed by the EU through the FEDER Galicia 2021-27 operational program (Ref. ED431G 2023/01). Grant ED431C 2022/44 funded by Xunta de Galicia., Xunta de Galicia; ED431G 2023/01, Xunta de Galicia; ED431C 2022/44
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Towards Federated Feature Selection: Logarithmic Division for Resource-Conscious Methods

  • Suárez-Marcote, Samuel
  • Morán-Fernández, Laura
  • Bolón-Canedo, Verónica
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG, [Abstract]: Feature selection is a popular preprocessing step to reduce the dimensionality of the data while preserving the important information. In this paper, we propose an efficient and green feature selection method based on information theory, with the novelty of using the logarithmic division and resorting to fixed-point precision. Moreover, we extend these advancements by adapting the Mutual Information calculation for federated scenarios. The results of experiments conducted on several datasets indicate the potential of our proposal, as it does not incur significant information loss compared to the double-precision method, both in the features selected and in the subsequent classification step. Our method has shown significant potential when applied in federated scenarios, where experimentation demonstrated a lossless feature selection process and maintains classification results compared with centralised versions. These findings open up possibilities towards a new family of green feature selection methods, which would help to minimise energy consumption, lower carbon emissions and increase adaptability to Internet of Things environments., This research has been financially supported in part by the Spanish Ministerio de Ciencia e Innovación MCIN/AEI/10.13039/501100011033 and “NextGenerationEU”/PRTR, Spain under Grants [PID2019-109238GB-C22; TED2021-130599A-I00], by Ministry for Digital Transformation and Civil Service, Spain under grant TSI-100925-2023-1 and by the Xunta de Galicia, Spain (ED431C 2022/44) with the European Union ERDF funds. CITIC, as a Research Center of the University System of Galicia, is funded by Consellería de Educación, Universidade e Formación Profesional of the Xunta de Galicia, Spain through the European Regional Development Fund (ERDF) and the Secretaría Xeral de Universidades, Spain (Ref. ED431G 2023/01). It has also been supported by the Programa de axudas á etapa predoutoral of the Consellería de Cultura, Educación, Universidade e Formación Profesional, Xunta de Galicia, Spain (Ref. ED481A 2023/034). Funding for open access charge: Universidade da Coruña/CISUG., Xunta de Galicia; ED431C 2022/44, Xunta de Galicia; ED431G 2023/01, Xunta de Galicia; ED481A 2023/034
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Minimizing Redundancy in Hand Dynamic Features for Enhanced Sign Language Recognition

  • Abdullahi, Sunusi Bala
  • Bolón-Canedo, Verónica
Versión aceptada de: S. Bala Abdullahia, and V. Bolon-Canedo, "Minimizing Redundancy in Hand Dynamic Features for Enhanced Sign Language Recognition", Intelligent Data Analysis: An International Journal, Vol. 30, Issue 3. Copyright © 2025 SAGE. DOI: 10.1177/1088467X251367228., [Abstract]: This paper presents a wavelet-based framework for 3-D sign language recognition that outperforms conventional ZCA approaches by preserving critical spatiotemporal relationships in hand kinematics. We formulate hand dynamics as a wavelet exponent energy problem using Daubechies transforms, where joint coordinates, mother coefficients, and window sizes are jointly optimized, avoiding PCA’s disruptive axis rotation while maintaining interpretable feature orientations. The proposed method combines this wavelet energy representation with an ensemble deep learning feature selection layer using binary masking (λ1 = 0.10, λ2 = 0.01) and regularization to eliminate redundancy, achieving 94.09% accuracy (vs. 92.75% for PCC+ZCA (SVD)) with 4.3× faster inference on Turkish SL datasets. Statistical validation (ANOVA, p < 0.001) confirms significant improvements over ZCA-derived features (t = 24.15), with weight analysis revealing proximal arm kinematics as dominant recognition factors. The framework’s computational efficiency (0.12ms inference) and preservation of kinematic relationships demonstrate its superiority for real-life SLR applications compared to both PCC and ZCA approaches., This work has been supported by the National Plan for Scientific and Technical Research and Innovation of the Spanish Government (Grant PID2023-147404OB-I00), and by the Ministry for Digital Transformation and Civil Service and ‘Next-GenerationEU’/PRTR under Grant TSI-100925-2023-1. CITIC, as a center accredited for excellence within the Galician University System and a member of the CIGUS Network, receives subsidies from the Department of Education, Science, Universities, and Vocational Training of the Xunta de Galicia. Additionally, it is co-financed by the EU through the FEDER Galicia 2021-27 operational program (Ref. ED431G 2023/01). Grant ED431C 2022/44 funded by Xunta de Galicia., Xunta de Galicia; ED431G 2023/01, Xunta de Galicia; ED431C 2022/44
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Urbanformanalyzer: An Open-Source Workflow to Derive Orientation-Specific Building Envelope Attributes From Cadastral Data

  • García-González, Daniel
  • Rodríguez-Álvarez, Jorge
  • Rodríguez Luaces, Miguel
  • Ladra, Susana
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG The package containing the complete project, algorithm for extracting envelope descriptors for each building, and the use case for predicting glazed surfaces, is available for download at https://gitlab.lbd.udc.es/dgarcia/urbanformanalyzer., [Abstract] Detailed building-envelope information is essential for robust urban-scale energy performance analyses. However, national energy certificate databases in Spain and other countries often lack key attributes such as orientation-specific external perimeter measurements and glazing ratios. This paper introduces UrbanFormAnalyzer, an open-source Python library developed with QGIS, which automatically derives orientation-specific external perimeters and additional envelope descriptors from cadastral geometries. The workflow establishes a standard input structure to support integration with varied cadastral sources. As an example, we offer an adapter for the Spanish Cadastre that downloads and preprocesses their KML files, converting them into the required format. The spatial processing stage then calculates the perimeters by cardinal orientation, distinguishing exposed from adjacent walls. To illustrate a potential downstream application, the enhanced datasets are matched with national energy certificates to explore the estimation of orientation-specific glazing ratios, where such data are available. While predictive accuracy remains limited, the case study highlights how UrbanFormAnalyzer could support the creation of reproducible and harmonized building envelope data suitable for a range of analytical applications, including large-scale energy modeling, planning, and renovation assessment., This work was partially funded by Ministry for Digital Transformation and Civil Service and “NextGenerationEU”/PRTR under grant TSI-100925-2023-1. Moreover, CITIC, as a center accredited for excellence within the Galician University System and a member of the CIGUS Network, receives subsidies from the Department of Education, Science, Universities, and Vocational Training of the Xunta de Galicia. Additionally, it is co-financed by the EU through the FEDER Galicia 2021-27 operational program (Ref. ED431G 2023/01). Furthermore, this work was supported by GRC: ED431C 2025/34, funded by GAIN/Xunta de Galicia, and PID2022-141027NB-C21 (EarthDL): partially funded by MCIN/AEI/10.13039/501100011033 and EU/ERDF A way of making Europe. Funding for open access charge: Universidade da Coruña/CISUG., Xunta de Galicia; ED431G 2023/01, Xunta de Galicia; ED431C 2025/34, https://gitlab.lbd.udc.es/dgarcia/urbanformanalyzer
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

A review of green artificial intelligence: Towards a more sustainable future

  • Bolón-Canedo, Verónica
  • Morán-Fernández, Laura
  • Cancela, Brais
  • Alonso-Betanzos, Amparo
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG, [Abstract]: Green artificial intelligence (AI) is more environmentally friendly and inclusive than conventional AI, as it not only produces accurate results without increasing the computational cost but also ensures that any researcher with a laptop can perform high-quality research without the need for costly cloud servers. This paper discusses green AI as a pivotal approach to enhancing the environmental sustainability of AI systems. Described are AI solutions for eco-friendly practices in other fields (green-by AI), strategies for designing energy-efficient machine learning (ML) algorithms and models (green-in AI), and tools for accurately measuring and optimizing energy consumption. Also examined are the role of regulations in promoting green AI and future directions for sustainable ML. Underscored is the importance of aligning AI practices with environmental considerations, fostering a more eco-conscious and energy-efficient future for AI systems., This work was supported by CITIC, a Research Center accredited by Galician University System, which is funded by "Consellería de Cultura, Educación e Universidade from Xunta de Galicia", supported in an 80% through ERDF Funds, ERDF Operational Programme Galicia 2014-2020, and the remaining 20% by "Secretaría Xeral de Universidades" (Grant ED431G 2019/01). It was also partially funded by Xunta de Galicia/FEDER-UE under Grant ED431C 2022/44; Ministerio de Ciencia e Innovación MCIN/AEI/10.13039/501100011033 and "NextGenerationEU"/PRTR under Grants [PID2019-109238GB-C22; PID2021-128045OA-I00; ED2021-130599A-I00] and Ministry for Digital Transformation and Civil Service under grant TSI-100925-2023-1. Funding for open access charge: Universidade da Coruña/CISUG, Xunta de Galicia; ED431G 2019/01, Xunta de Galicia; ED431C 2022/44
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Performance and sustainability of BERT derivatives in dyadic data

  • Escarda Fernández, Miguel
  • Eiras-Franco, Carlos
  • Cancela, Brais
  • Guijarro-Berdiñas, Bertha
  • Alonso-Betanzos, Amparo
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG, [Abstract]: In recent years, the Natural Language Processing (NLP) field has experienced a revolution, where numerous models – based on the Transformer architecture – have emerged to process the ever-growing volume of online text-generated data. This architecture has been the basis for the rise of Large Language Models (LLMs). Enabling their application to many diverse tasks in which they excel with just a fine-tuning process that comes right after a vast pre-training phase. However, their sustainability can often be overlooked, especially regarding computational and environmental costs. Our research aims to compare various BERT derivatives in the context of a dyadic data task while also drawing attention to the growing need for sustainable AI solutions. To this end, we utilize a selection of transformer models in an explainable recommendation setting, modeled as a multi-label classification task originating from a social network context, where users, restaurants, and reviews interact., Research funded by the Spain Ministry of Science, Innovation and Universities (MCIN/AEI/10.13039/501100011033) and ERDF “A way of making Europe” (PID2019-109238GB-C22, PID2021-128045OA-I00, PID2023-147404OB-I00), by the “Xunta de Galicia” (ED431C 2022/44) with the European Union ERDF funds, and by the Ministry for Digital Transformation and Civil Service and “Next-GenerationEU”/PRTR (Grant TSI-100925-2023-1). CITIC, as Research Center accredited by Galician University System, is funded by “Consellería de Cultura, Educación e Universidade from Xunta de Galicia ”, supported in an 80% through ERDF Operational Programme Galicia 2014-2020, and the remaining 20% by “Secretaría Xeral de Universidades” (Grant ED431G 2023/01)., Xunta de Galicia; ED431C 2022/44, Xunta de Galicia; ED431G 2023/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Fed-mRMR: A lossless federated feature selection method

  • Hermo González, Jorge
  • Bolón-Canedo, Verónica
  • Ladra, Susana
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG, Implementation can be found at: https://github.com/jorgehermo9/fed-mrmr, [Abstract]: Feature selection has become a mandatory task in data mining, due to the overwhelming amount of features in Big Data problems. To handle this high-dimensional data and avoid the well-known curse of dimensionality, we need to pre-select an optimal subset of features to reduce redundant computations. Federated learning is a machine learning technique based on training an algorithm over many decentralized edge devices holding local rather than global data on a centralized server. Application of this technique is extending to fields such as self-driving cars, medicine and health, and Industry 4.0, where data privacy is compulsory. Feature selection through federated learning is a complicated task since suboptimal features calculated by feature selection methods may be different in heterogeneous datasets from different nodes. In this paper, we propose a lossless federated version of the classic minimum redundancy maximum relevance (mRMR) feature selection algorithm, called federated mRMR (fed-mRMR), which, without losing any effectiveness of the original mRMR method, is applicable to federated learning approaches and capable of dealing with data that are not independent and identically distributed (non-IID data). Implementation can be found at: https://github.com/jorgehermo9/fed-mrmr, This work was supported by CITIC, a Research Center accredited by the Galician University System, funded by the Xunta de Galicia Consellería de Cultura, Educación e Universidade, supported 80% by ERDF/FEDER funds (Operational Programme Information Sciences 669 (2024) 120609 14 J. Hermo, V. Bolón-Canedo and S. Ladra Galicia 2014-2020) and 20% by the Xunta de Galicia Secretaría Xeral de Universidades (Grant ED431G 2019/01). It was also partially funded by the Xunta de Galicia and ERDF/FEDER (Grants ED431C 2021/53; ED431C 2022/44), the Spanish Ministerio de Ciencia e Innovación (MCIN/AEI/10.13039/501100011033) and NextGenerationEU/PRTR (Grants PDC2021-121239-C31; PID2019-105221RB-C41; PID2019-109238GB-C22; PID2022-141027NB-C2; TED2021-130599A-I00; TSI-100925-2023-1). A department collaboration grant awarded by Universidade de A Coruña also supported this research., Xunta de Galicia; ED431G 2019/01, Xunta de Galicia; ED431C 2021/53, Xunta de Galicia; ED431C 2022/44
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Statistical Procedure for Panel Block Assembly in Shipbuilding

  • Otero, Déborah
  • Cao, Ricardo
  • Blasco, Vicente
  • Brage, Álvaro
  • Tarrío-Saavedra, Javier
  • Naya, Salvador
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG, [Abstract] A statistical procedure to estimate the probability of successful sliding of transverse elements through the longitudinals in shipbuilding panel block assembly is proposed. It consists of developing a custom statistical solution to control the quality of shipbuilding block assembly process, which helps to meet the requirements of production time, cost, and resources consumption. This proposal addresses a critical shipbuilding challenge: the panel block assembly process, which involves inserting transverse pieces through panels containing longitudinal components. This statistical procedure estimates the probability of successful block assembly before the process starts, taking into account inputs such as panel dimensions, panel structure, and transverse stiffener. A comprehensive simulation study has been performed to evaluate the statistical procedure performance. In addition, an actual database obtained from Navantia shipyards has been used to obtain information about the mean values and dispersion of the block assembly parameters. Finally, a sensitivity analysis is applied in order to obtain information about the most critical inputs for process improvement. This statistical tool proposes an alternative to evaluate the proficiency of shipyards to perform panel block assembly process during the vessel construction. The identification of those critical variables in the panel assembly process and the quantification of their influence in the studied process are goals that have been also achieved., This research was supported by GAIN (Xunta de Galicia) and Navantia company (SEPI), in the framework of the UDC - Navantia joint Research Unit, with the project “Shipyard 4.0. The Shipyard of the Future” and Centro Mixto de Investigación (CEMI) Navantia-UDC, with reference IN853C 2022/01. This research has been also supported by the Ministerio de Ciencia e Innovación grant PID2020-113578RB-100 and PID2023-147127OB-I00, the Ministry for Digital Transformation and Civil Service under Grant TSI-100925-2023-1, the Xunta de Galicia (Grupos de Referencia Competitiva ED431C-2020-14 and ED431C 2024/014), and by the CITIC, also funded by the Xunta de Galicia through the collaboration agreement between the Consellería de Cultura, Educación, Formación Profesional e Universidades and the Galician universities for the reinforcement of the research centers of the Galician University System, CIGUS, with reference ED431G 2023/01. Funding for open access charge: Universidade da Coruña/CISUG., Xunta de Galicia; ED431C-2020-14, Xunta de Galicia; ED431C 2024/014, Xunta de Galicia; ED431G 2023/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Predicting lifetime of adhesive bonds for naval steel by time-temperature superposition

  • Rodríguez-Dopico, Francisco J.
  • Álvarez García, Ana
  • Tarrío-Saavedra, Javier
  • Meneses Freire, Antonio
  • Naya, Salvador
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG, [Abstract] There is a lack of knowledge about the long-term behaviour of adhesive joints in the marine environment, and for hence, its reliability. The life cycle expected for a ship is twenty-five years and conduct duration tests would last decades. The importance and originality of this study are that it provides a methodology for predicting the durability of adhesive bonds. For this purpose, three adhesives for bonding naval steel were tested at several temperatures for determination of their shear strength on standard single-lap-joint specimens. Subsequently, using the time temperature superposition principle, these results were combined into one master curve for each adhesive that can be considered as a prediction method of the durability in a long-term period. The usual parametric models of Arrhenius and Williams-Landel-Ferry were used to obtain the master curve for each adhesive by manual shifting. The results were compared with those obtained applying an open-source software developed by the authors in R language, which specifically implements a non-parametric methodology based on the shift of the first derivative curves, following parameters of Explainable Artificial Intelligence. It was found a good correlation between both methodologies, supporting the durability lifetime obtained and therefore the applicability on ships of this adhesive technology., The authors wish to acknowledge and thank the support provided by Krafft S.L.U. Spain (ITW Performance Polymers), Sarsch Adhesives, S.L. Spain (Engineered Bonding Solutions, LLC, Florida, United States) and Masterbond Inc. United States. The research of Javier Tarrío Saavedra and Salvador Naya has been supported by the Ministerio de Ciencia e Innovación grant PID2020-113578RB-100 and PID2023-147127OB-I00, the Ministry for Digital Transformation and Civil Service under Grant TSI-100925-2023-1, the Xunta de Galicia (Grupos de Referencia Competitiva ED431C-2020-14 and ED431C 2024/014), and by the CITIC, also funded by the Xunta de Galicia through the collaboration agreement between the Consellería de Cultura, Educación, Formación Profesional e Universidades and the Galician universities for the reinforcement of the research centers of the Galician University System, CIGUS, with reference ED431G 2023/01., Xunta de Galicia; ED431C-2020-14, Xunta de Galicia; ED431C 2024/014, Xunta de Galicia; ED431G 2023/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Breaking Boundaries: Low-Precision Conditional Mutual Information for Efficient Feature Selection

  • Morán-Fernández, Laura
  • Blanco-Mallo, Eva
  • Sechidis, Konstantinos
  • Bolón-Canedo, Verónica
[Abstract] As internet-of-things (IoT) devices proliferate, the need for efficient data processing at the network edge becomes increasingly critical due to the vast amounts of data generated. This paper presents a groundbreaking approach that leverages edge computing to address these challenges, using low-precision conditional mutual information (CMI) for feature selection. Our novel methodology improves the efficiency of edge computing systems by significantly reducing memory and energy consumption while maintaining high accuracy. We adapt this approach to feature selection algorithms, specifically, conditional mutual information maximization (CMIM) and incremental association Markov blanket (IAMB), and demonstrate its effectiveness for diverse datasets, including complex DNA microarrays. Our results show that low-precision methods not only compare competitively with traditional 64-bit implementations, but also yield significant performance and resource savings. For IoT and other machine learning applications, this work represents a significant advance in the development of more sustainable and efficient algorithms that can optimize computational resources and reduce their environmental impact., This work was supported in part by Xunta de Galicia/FEDER-UE under Grant ED431G 2023/01; Ministerio de Ciencia e Innovacion MCIN/AEI/10.13039/501100011033 and ‘Next-GenerationEU’/PRTR under Grants [PID2019-109238GB-C22; TED2021-130599A-I00; PID2023-147404OB-I00] and Ministry for Digital Transformation and Civil Service and ‘Next-GenerationEU’/PRTR under grant TSI-100925-2023-1. CITIC, as a Research Center of the University System of Galicia, is funded by Consellería de Educacion, Universidade e Formación Profesional of the Xunta de Galicia, Spain through the European Regional Development Fund (ERDF/FEDER) and the Secretaría Xeral de Universidades (ED431G 2023/01)., Xunta de Galicia; ED431G 2023/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Efficient Single-Step Framework for Incremental Class Learning in Neural Networks

  • Dopico Castro, Alejandro
[Abstract]: Incremental learning continues to present a significant challenge in deep learning, particularly in environments where resources are limited. While existing methods have been shown to achieve high levels of accuracy, they often require substantial computational resources and storage capacity. This work proposes CIFNet, an efficient approach to class incremental learning that matches comparable accuracy to state-of-the-art methods while significantly reducing training time and energy consumption through a single-step optimisation process. CIFNet incorporates a novel compressed buffer mechanism that stores condensed representations of previous data samples instead of full raw data, substantially reducing memory requirements. In contrast to conventional approaches that necessitate multiple iterations of weight optimisation, our method achieves optimal performance in a single training step, with no need for iterations, leading to a significant decrease in computational overhead. Experimental results on standard benchmark datasets have shown that our approach inherently mitigates catastrophic forgetting without the need for complex regularization schemes. CIFNet achieves accuracy comparable to current state-of-the-art approaches while significantly reducing training time and energy consumption. This work represents a step forward in making class incremental learning more accessible for resource-constrained environments while maintaining robust performance., This work was partially funded by Horizon Europe, GA 101070381 (‘PILLAR-Robots - Purposeful Intrinsically motivated Lifelong Learning Autonomous Robots’); Project PID2023-147404OB-I00 funded by MCIN/AEI/10.13039/501100011033/ ERDF, UE; Ministry for Digital Trans- formation and Civil Service and ‘Next-GenerationEU’/PRTR under Grant TSI-100925-2023-1; and Xunta de Galicia/FEDER-UE under Grant ED431C 2022/44. CITIC, as Research Center accredited by Galician University System, is funded by “Consellería de Cultura, Educación e Universidade from Xunta de Galicia”, supported in an 80% through ERDF Operational Programme Galicia 2014-2020, and the remaining 20% by “Secretaría Xeral de Universidades” (Grant ED431G 2023/01)., Xunta de Galicia; ED431C 2022/44, Xunta de Galicia; ED431G 2023/01, Traballo fin de mestrado (UDC.FIC). Intelixencia Artificial. Curso 2024/2025
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Characterization of Epoxy Adhesive for Marine Applications

  • Rodríguez-Dopico, Francisco J.
  • Álvarez García, Ana
  • Tarrío-Saavedra, Javier
[Abstract] The shipping industry faces the challenge of expanding its capabilities and mitigating its environmental impact. The utilization of adhesive bonding techniques has the potential to facilitate the construction of lighter ships with a reduced carbon footprint. In this work, a complete methodology has been established to study the properties of an adhesive bond between naval steel and the behavior of the bulk adhesive when introduced into seawater. Thermogravimetric analysis (TGA) has been used to determine the thermal properties. Single-lap-joint and tensile tests have been performed showing the negative influence of temperature on the mechanical properties. Seawater absorption has been studied by gravimetric tests. Differential scanning calorimetry (DSC), Fourier transform infrared spectroscopy (FTIR), and mechanical bulk tests have been carried out before and after aging. The water absorption is Fickian, and when a constant load is applied, the absorption occurs faster and in greater quantity, decreasing the stiffness and strength. An increase in the glass transition temperature was observed in the absence of a load, with no discernible change upon the application of load condition. Also, aged specimens with constant load exhibited a reduction in water content. These phenomena may be attributed to several diffusion processes., This research was made possible by the support of the Campus Industrial de Ferrol (CIF) and the Centro de Investigación en Tecnologías Navales e Industriales (CITENI) of the University of A Coruña. The authors wish to acknowledge and thank Masterbond Inc., United States, for their support. The research of Javier Tarrío Saavedra has been supported by the Ministerio de Ciencia e Innovación grant PID2020-113578RB-100 and PID2023-147127OB-I00, the Ministry for Digital Transformation and Civil Service under Grant TSI-100925-2023-1, the Xunta de Galicia (Grupos de Referencia Competitiva ED431C-2020-14 and ED431C 2024/014), and by the CITIC, also funded by the Xunta de Galicia through the collaboration agreement between the Consellería de Cultura, Educación, Formación Profesional e Universidades and the Galician universities for the reinforcement of the research centers of the Galician University System, CIGUS, with reference ED431G 2023/01., Xunta de Galicia; ED431C-2020-14, Xunta de Galicia; ED431C 2024/014, Xunta de Galicia; ED431G 2023/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

A Multi-Backend Autotuning Study of Feature Selection on GPUs

  • Beceiro, Bieito
  • González-Domínguez, Jorge
  • Pérez Diéguez, Adrián
  • Ibrahim, Khaled Z.
  • Touriño, Juan
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG The code for the CUDA, HIP, and SYCL backends for mRMR used in the experimental evaluation is available at https://gitlab.com/bieito/gpufs. The datasets analyzed in this study are available in the LIBSVM repository, https://www.csie.ntu.edu.twcjlin/libsvmtools/datasets/, [Abstract]: Feature selection is an important step in machine learning that can benefit from GPU acceleration. As the number of GPU vendors increases, it is imperative to adapt algorithms such as the minimum Redundancy Maximum Relevance (mRMR) feature selection method to different backends that support several GPU architectures. This work presents a multi-backend implementation of mRMR across CUDA, HIP, and SYCL, and studies its performance when combined with Bayesian optimization and transfer learning to automatically tune execution parameters for different platforms and datasets. Our experimental results show that when tuned, CUDA and HIP achieve comparable performance on NVIDIA architectures, while SYCL exhibits a moderate performance gap. Overall, this work highlights the impact of backend choice and autotuning on GPU-accelerated feature selection and provides insights into deploying mRMR across heterogeneous environments., Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. This work was supported by grants PID2022-136435NB-I00 and PID2025-167767NB-I00, funded by MICIU/AEI/10.13039/501100011033 and “ERDF A way of making Europe”, EU; grant TSI-100925-2023-1, funded by the Ministry for Digital Transformation and Civil Service and Next-GenerationEU/RRF; FPU predoctoral grant of Bieito Beceiro ref. FPU20/00997, funded by the Ministry of Science, Innovation and Universities; and INDITEX-UDC Predoctoral Research Stay Grants Program 2024. In addition, this material is based upon work supported by the U.S. Department of Energy, Office of Science, Office of Advanced Scientific Computing Research, Scientific Discovery through Advanced Computing (SciDAC) program under Award Number DE-AC02-05CH11231. Funding for open access charge: Universidade da Coruña/CISUG., United States. Department of Energy; DE-AC02-05CH11231, https://gitlab.com/bieito/gpufs
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

SynNER: Syntax-infused Named Entity Recognition in the Biomedical Domain

  • Imran, Muhammad
  • Zamaraeva, Olga
  • Gómez-Rodríguez, Carlos
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG The code and other resources developed for this work are available in our GitHub repository at: https://github.com/chimran135/SynNER. The datasets used in this study are publicly available from third-party sources. The MTSamples and VAERS datasets can be downloaded from: https://github.com/BIDS-Xu-Lab/Clinical_Entity_Recognition_Using_GPT_models. The NCBI-Disease, BC2GM, and JNLPBA datasets can be downloaded from: https://github.com/cambridgeltl/MTL-Bioinformatics-2016. Supplementary material is available at JAMIA Open online, [Abstract]: Named Entity Recognition (NER) is a technology that helps computers automatically find and classify important terms in text, such as names of diseases, drugs, or medical procedures. This is especially valuable in the biomedical field, where researchers and clinicians need to process large volumes of text from scientific articles, clinical notes, or patient records. In this work, we present SynNER, a system that improves the accuracy of NER by teaching computers to pay attention not only to the words themselves, but also to syntax, ie, the internal structure of sentences. For example, recognizing how words are connected in a sentence (which parts of the sentence are subjects, objects or modifiers) can make it easier to correctly identify medical terms, even when they appear in complex contexts. We tested our method on five different collections of biomedical texts. The results showed that incorporating grammatical knowledge significantly boosted accuracy. Our SynNER system outperformed previous state-of-the-art methods on three of the five datasets. Our results show that using syntax can help researchers and healthcare professionals more reliably and quickly extract vital information from a vast amount of text, which could ultimately help improve biomedical research and clinical decision support tools., We acknowledge the European Research Council (ERC), which has funded this research under the Horizon Europe research and innovation programme (SALSA, grant agreement No 101100615), SCANNER-UDC (PID2020-113230RB-C21) funded by MICIU/AEI/10.13039/501100011033, LATCHING (PID2023-147129OB-C21) funded by MICIU/AEI/10.13039/501100011033 and ERDF (EU), Ministry for Digital Transformation and Civil Service and “NextGenerationEU” PRTR under grant TSI-100925-2023-1, Xunta de Galicia (ED431C 2024/02), and Galician Research Center “CITIC”, funded by Xunta de Galicia through the collaboration agreement between the Consellería de Cultura, Educación, Formación Profesional e Universidades and the Galician universities for the reinforcement of the research centres of the Galician University System (CIGUS). Furthermore, this research was supported by the International, Interdisciplinary and Intersectoral Information and Communications Technology PhD programme (3-i ICT) granted to CITIC and supported by the European Union through the Horizon 2020 research and innovation programme under a Marie Skłodowska-Curie agreement (H2020-MSCA-COFUND), GA 101034261. Funding for open access charge: Universidade da Coruña/CISUG., Xunta de Galicia; ED431C 2024/02
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

CUDA Acceleration of Feature Selection Methods Based on Conditional Mutual Information

  • Beceiro, Bieito
  • González-Domínguez, Jorge
  • Touriño, Juan
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG, [Abstract]: Feature Selection (FS) is a fundamental data mining technique that improves machine learning models by eliminating irrelevant or redundant data, especially as dataset dimensions continue to grow. However, greedy FS methods can be com¬putationally intensive, particularly for large datasets. This work focuses on the development of CUDA implementations for FS methods that use Conditional Mutual Information (CMI). Specifically, we address the Interaction Capping (ICAP) method and the family of algorithms that can be included in the BetaGamma space. The proposed implementations lever¬age memory hierarchy, asynchronous computation, and a reduced-precision approach to efficiently exploit the hardware of NVIDIA GPUs to achieve high performance with relatively low energy costs. The experimental evaluation has been carried out in two systems with different types and numbers of CPUs and GPUs using four publicly available datasets from different fields. We first provide insight into the performance impact of each optimization technique, and also into the combination of configuration parameters that best exploits the GPU architecture. Finally, the novel GPU implementa¬tions are compared to their fastest available counterparts (parallel implementations for multi-CPU systems), proving that the GPU versions are significantly faster than these multithreaded approaches in all scenarios using 32 or 64 CPU cores., Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. This work was sup¬ported by grant PID2022-136435NB-I00, funded by MICIU/ AEI/10.13039/501100011033 and “ERDF A way of making Europe” (EU), grant TSI-100925-2023-1, funded by the Ministry for Digital Transformation and Civil Service, and FPU predoctoral grant of Bieito Beceiro ref. FPU20/00997, funded by the Ministry of Science, Inno¬vation and Universities. It was also supported by the Consolidation Program of Competitive Reference Groups of Xunta de Galicia (ref. ED431C 2025/33). Funding for open access charge: Universidade da Coruña/CISUG, Xunta de Galicia; ED431C 2025/33
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

A Syntax-Injected Approach for Faster and More Accurate Sentiment Analysis

  • Imran, Muhammad
  • Kellert, Olga
  • Gómez-Rodríguez, Carlos
The following information was supplied regarding data availability: The OpeNERen, OpeNERes, UD_English-EWT and UD_Spanish-AnCora datasets are available at Zenodo: Muhammad Imran. (2025). chimran135/syntax-injected-sentimentanalysis: Syntax-injected Sentiment Analysis (1.0.0). Zenodo. https://doi.org/10.5281/zenodo.15323755. The Rest-Mex 2023 shared task website provides access to the training data for registered participants. The data are held privately for assessment purposes and can be obtained from Rest-Mex 2023 organizers https://sites.google.com/cimat.mx/rest-mex2023 by contacting Miguel Ángel Álvarez Carmona at miguel.alvarez@cimat.mx. The Rest-Mex 2023 dataset was used under license for this study., [Abstract]: Sentiment Analysis (SA) is a crucial aspect of Natural Language Processing (NLP), focusing on identifying and interpreting subjective assessments in textual content. Syntactic parsing is useful in SA as it improves accuracy and provides explainability; however, it often becomes a computational bottleneck due to slow parsing algorithms. This article proposes a solution to this bottleneck by using a Sequence Labeling Syntactic Parser (SELSP) to integrate syntactic information into SA via a rule-based sentiment analysis pipeline. By reformulating dependency parsing as a sequence labeling task, we significantly improve the efficiency of syntax-based SA. SELSP is trained and evaluated on a ternary polarity classification task, demonstrating greater speed and accuracy compared to conventional parsers like Stanza and heuristic approaches such as Valence Aware Dictionary and sEntiment Reasoner (VADER). The combination of speed and accuracy makes SELSP especially attractive for sentiment analysis applications in both academic and industrial contexts. Moreover, we compare SELSP with Transformer-based models trained on a 5-label classification task. In addition, we evaluate multiple sentiment dictionaries with SELSP to determine which yields the best performance in polarity prediction. The results show that dictionaries accounting for polarity judgment variation outperform those that ignore it. Furthermore, we show that SELSP outperforms Transformer-based models in terms of speed for polarity prediction., The European Research Council (ERC) funded this research under the Horizon Europe research and innovation programme (SALSA, grant agreement No. 101100615), SCANNER-UDC (PID2020-113230RB-C21) funded by MICIU/AEI/10.13039/501100011033, LATCHING (PID2023-147129OB-C21) funded by MICIU/AEI/10.13039/501100011033 and ERDF (EU), project GAP (PID2022-139308OA-I00) funded by MICIU/AEI/10.13039/501100011033/ and ERDF (EU), Ministry for Digital Transformation and Civil Service and “NextGenerationEU” PRTR under grant TSI-100925-2023-1, Xunta de Galicia (ED431C 2024/02), and Galician Research Center “CITIC”, funded by Xunta de Galicia through the collaboration agreement between the Consellería de Cultura, Educación, Formación Profesional e Universidades and the Galician universities for the reinforcement of the research centres of the Galician University System (CIGUS). Furthermore, this research was supported by the International, Interdisciplinary and Intersectoral Information and Communications Technology PhD programme (3-i ICT) granted to CITIC and supported by the European Union through the Horizon 2020 research and innovation programme under a Marie Skłodowska-Curie agreement (H2020-MSCA-COFUND), GA 101034261. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript., Xunta de Galicia; ED431C 2024/02
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

AI Driven TTS Procedure to Predict Sailcloth Mechanical Behaviour for Wind Assisted Propulsion in Marine Navigation

  • Baamonde-González, J.
  • Álvarez García, Ana
  • Tarrío-Saavedra, Javier
  • González Taboada, María
  • López-Beceiro, Jorge
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG, [Abstract]: The shipping industry is transitioning towards more sustainable propulsion strategies due to increasingly stringent greenhouse gas regulations, with wind-assisted propulsion emerging as a viable near-term solution to improve energy efficiency, reduce emissions and boost blue economy. However, the long-term mechanical performance of sail materials under combined environmental and mechanical degradation remains insufficiently understood. This study investigates the effects of marine exposure and mechanical abrasion on the dynamic and creep behaviour of Dacron sailcloth. Dynamic Mechanical Analysis (DMA) shows that marine ageing reduces the storage modulus by up to 17.7% (weft) and 11.2% (warp), while abrasion causes a reduction of 8.1%, with no significant changes in glass transition temperature. Short-term creep tests (30–100 °C) are extended using the Time–Temperature Superposition (TTS) principle to construct creep compliance master curves at 30 °C, revealing a clear increase in compliance for aged materials. A Generalised Additive Model (GAM) is applied to capture nonlinear behaviour and quantify the influence of predictors, showing excellent agreement (R² > 0.99 for individual curves; R² = 0.933 for the global model). The results indicate that creep compliance increases significantly with ageing, with marine exposure producing a vertical shift of the master curve and abrasion inducing a horizontal shift, suggesting increased chain mobility. Time (83.41%) and ageing level (10.63%) are identified as the dominant factors governing deformation, while fabric orientation confirms orthotropic behaviour, with lower compliance in the weft direction. The combination of TTS and GAM provides a robust framework for predicting long-term sailcloth performance within the validated time domain (∼10⁸ s), although extrapolation beyond this range should be treated with caution., Financing the Open Access Fee: Universidade da Coruña/CISUG. The following sail makers provided the Dacron sailcloth used in this paper free of charge: North Sails, Cuntis and Tartaruga Mar, Baiona (Spain). The research of Javier Tarrío-Saavedra has been supported by the Ministerio de Ciencia e Innovación grant PID2023-147127OB-I00, the Ministry for Digital Transformation and Civil Service under Grant TSI-100925-2023-1, the Xunta de Galicia (Grupos de Referencia Competitiva ED4[]C-2020-14 and ED431C 2024/014), and by the CITIC (Centro de Investigación en Tecnologías de la Información y Comunicación), also funded by the Xunta de Galicia through the collaboration agreement between the Consellería de Cultura, Educación, Formación Profesional e Universidades and the Galician universities for the reinforcement of the research centers of the Galician University System, CIGUS, with reference ED431G 2023/01., Xunta de Galicia; ED4[]C-2020-14, Xunta de Galicia; ED431C 2024/014, Xunta de Galicia; ED431G 2023/01
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Optimising resource use through low-precision feature selection: a performance analysis of logarithmic division and stochastic rounding

  • Suárez-Marcote, Samuel
  • Morán-Fernández, Laura
  • Bolón-Canedo, Verónica
This is the peer reviewed version of the article which has been published in final form at https://doi.org/10.1111/exsy.70012., [Abstract]: The growth in the number of wearable devices has increased the amount of data produced daily. Simultaneously, the limitations of such devices has also led to a growing interest in the implementation of machine learning algorithms with low-precision computation. We propose green and efficient modifications of state-of-the-art feature selection methods based on information theory and fixed-point representation. We tested two potential improvements: stochastic rounding to prevent information loss, and logarithmic division to improve computational and energy efficiency. Experiments with several datasets showed comparable results to baseline methods, with minimal information loss in both feature selection and subsequent classification steps. Our low-precision approach proved viable even for complex datasets like microarrays, making it suitable for energy-efficient internet-of-things (IoT) devices. While further investigation into stochastic rounding did not yield significant improvements, the use of logarithmic division for probability approximation showed promising results without compromising classification performance. Our findings offer valuable insights into resource-efficient feature selection that contribute to IoT device performance and sustainability., This work was supported by CITIC, a Research Center accredited by Galician University System, which is funded by ‘Consellería de Cultura, Educación e Universidade from Xunta de Galicia’, supported in an 80% through ERDF Funds, ERDF Operational Programme Galicia 2014–2020, and the remaining 20% by ‘Secretaría Xeral de Universidades, Xunta de Galicia’ (Grant ED431G 2023/01). It was also partially funded by Xunta de Galicia/FEDER-UE under Grant ED431C 2022/44; Ministerio de Ciencia, Innovación y Universidades MCIN/AEI/10.13039/501100011033 and ‘Next-GenerationEU’/PRTR under Grants (PID2023-147404OB-I00; TED2021-130599A-I00) and Ministry for Digital Transformation and Civil Service under grant TSI-100925-2023-1. It was also supported by the Programa de axudas á etapa predoutoral of the Consellería de Cultura, Educación, Universidade e Formación Profesional, Xunta de Galicia, Spain (Ref. ED481A 2023/034)., Xunta de Galicia; ED431G 2023/01, Xunta de Galicia; ED431C 2022/44, Xunta de Galicia; ED481A 2023/034
RUC. Repositorio da Universidade da Coruña
Publicación Artículo científico (JournalArticle)

Fatigue Behavior of Joule-cured and Oven-cured Carbon/Epoxy Laminates: a Generalized Additive Model Analysis

  • Vázquez, Laura
  • Naya, Salvador
  • Tarrío-Saavedra, Javier
  • Álvarez García, Ana
  • López-Beceiro, Jorge
  • Pereira, Mercedes
  • Francisco-Fernández, Mario
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG, [Abstract]: Joule (resistive) heating is a promising alternative to conventional oven curing for carbon/epoxy composites because it provides fiber interior heating and can reduce cycle time and energy consumption. From a fatigue perspective, however, the influence of the curing route on long-term mechanical performance is less understood. Here we compare the fatigue response (three-point bending load versus cycle count) of [90/0/90] laminates manufactured by Joule heating and by oven cure. Using a data-driven framework based on generalized additive models (GAMs), we analyze the effects of curing route, isothermal temperature and dwell time, ramp rate, displacement-controlled testing, and specimen orientation. Nonlinear degradation trends are captured by semiparametric GAMs fitted to 27 coupons, totaling 365,059 observations. The curing route emerges as the dominant driver of fatigue degradation: Oven-cured coupons start at higher load but lose capacity more rapidly, whereas Joule-cured coupons exhibit a smoother and more stable decline with cycling. Vertical orientation consistently yields higher loads, while within the explored Joule design space (110–130, 3–12 min) the effects of isothermal temperature, dwell time, and ramp rate are comparatively modest. These results support the viability of Joule heating as an alternative to conventional curing from the standpoint of fatigue behavior, in addition to its known gains in processing efficiency. The GAM approach identifies the key design parameters, quantifies their relative importance, and provides an interpretable tool for comparing curing programs and guiding the optimization of electrically cured composite structures., Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. Funding for open access charge: Universidade da Coruña / CISUG. This research was made possible by the support of the Campus Industrial de Ferrol (CIF) and the Centro de Investigación en Tecnoloxías Navais e Industriais (CITENI) of the University of A Coruña. The research of Laura S. Vázquez has been supported by the Axencia Galega de Innovación (Xunta de Galicia) through a Doutoramento Industrial grant (2022). This work has also been supported by grant PID2023-147127OB-I00 (“ERDF/EU”), funded by MCIN/AEI/10.13039/501100011033, by the Ministry for Digital Transformation and Civil Service under grant TSI-100925-2023-1, by the Xunta de Galicia through the “Grupos de Referencia Competitiva” program (grant ED431C-2024/14), and by CITIC, a center accredited for excellence within the Galician University System and a member of the CIGUS Network. CITIC receives support from the Department of Education, Science, Universities, and Vocational Training of the Xunta de Galicia and is co-financed by the European Union through the FEDER Galicia 2021-27 operational program (Ref. ED431G 2023/01)., Xunta de Galicia; ED431C-2024/14