DeustoTeka
DeustoTeka recoge la producción científica del personal docente e investigador de la Universidad de Deusto. Su propósito es reunir, archivar, preservar y aumentar la visibilidad en acceso abierto de los resultados de investigación.
Comunidades en DSpace
Selecciona una comunidad para explorar sus colecciones.
Envíos recientes
A new multi-agent feature wrapper machine learning approach for heart disease diagnosis
(Tech Science Press, 2021-01-12) Elhoseny, Mohamed; Abed Mohammed, Mazin; Mostafa, Salama A.; Abdulkareem, Karrar Hameed; Maashi, Mashael S.; García-Zapirain, Begoña; Mutlag, Ammar Awad; Maashi, Marwah Suliman
Heart disease (HD) is a serious widespread life-threatening disease. The heart of patients with HD fails to pump sufficient amounts of blood to the entire body. Diagnosing the occurrence of HD early and efficiently may prevent the manifestation of the debilitating effects of this disease and aid in its effective treatment. Classical methods for diagnosing HD are sometimes unreliable and insufficient in analyzing the related symptoms. As an alternative, noninvasive medical procedures based on machine learning (ML) methods provide reliable HD diagnosis and efficient prediction of HD conditions. However, the existing models of automated ML-based HD diagnostic methods cannot satisfy clinical evaluation criteria because of their inability to recognize anomalies in extracted symptoms represented as classification features from patients with HD. In this study, we propose an automated heart disease diagnosis (AHDD) system that integrates a binary convolutional neural network (CNN) with a new multi-agent feature wrapper (MAFW) model. The MAFW model consists of four software agents that operate a genetic algorithm (GA), a support vector machine (SVM), and Naïve Bayes (NB). The agents instruct the GA to perform a global search on HD features and adjust the weights of SVM and BN during initial classification. A final tuning to CNN is then performed to ensure that the best set of features are included in HD identification. The CNN consists of five layers that categorize patients as healthy or with HD according to the analysis of optimized HD features. We evaluate the classification performance of the proposed AHDD system via 12 common ML techniques and conventional CNN models by using a cross-validation technique and by assessing six evaluation criteria. The AHDD system achieves the highest accuracy of 90.1%, whereas the other ML and conventional CNN models attain only 72.3%-83.8% accuracy on average. Therefore, the AHDD system proposed herein has the highest capability to identify patients with HD. This system can be used by medical practitioners to diagnose HD efficiently.
Novel artificial intelligence approach for nsLTP early detection using NIRs data
(Springer, 2025-07-29) Rodríguez Alonso, Alex; Barrio, Itxasne del; Bernardo Seisdedos, Ganeko; Osa Sánchez, Ainhoa; García-Zapirain, Begoña
Food allergies have become a significant public health issue, particularly lipid transfer protein (LTP) allergies, which are highly stable allergens and can cause severe allergic reactions. This research aims to develop and validate an AI-driven solution for detecting LTPs in food using near-infrared spectroscopy (NIRS), exploring the feasibility of non-invasive allergen identification using AI-assisted spectroscopy. The methodology involves collecting spectral data from various food samples, building a machine learning model, and optimizing it iteratively to improve detection accuracy. The results show that the AI model achieved an accuracy of 87% and an F1-score of 89.91%, indicating its potential for enhancing food safety. In conclusion, this solution demonstrates the viability of using NIRS and AI for allergen detection, with promising future applications in healthcare.
Orientación deportiva sin balizas físicas ni códigos QR: análisis de la app GPS Orienteering
(Universidad de Murcia, Servicio de Publicaciones, 2025-07-31) Fraile, Juan; Orgaz Rincón, Daniel; Ruiz Bravo, Patricia; Baena Extremera, Antonio; Fuentesal García, Julio; Zamorano Sande, David
La orientación es un deporte en auge dentro de las actividades físicas en el medio natural y está incluida en el currículo de la asignatura de Educación Física (EF). Es una actividad excelente desde el punto de vista didáctico, ya que no necesita ser competitiva, resulta desafiante, cooperativa, inclusiva, accesible y ofrece posibilidades de éxito para todos los participantes. Aunque la orientación es el contenido más impartido dentro de estas actividades, el profesorado identifica barreras que dificultan su implementación o la mejora de su práctica. Este estudio analizó la aplicación GPS Orienteering, cuya característica principal es que no requiere la colocación de balizas físicas ni códigos QR. Un total de 85 estudiantes del grado en Ciencias de la Actividad Física y del Deporte, en la asignatura relacionada con las actividades físicas en el medio natural, experimentaron una progresión de aprendizaje en orientación, incluyendo el uso de esta aplicación, sobre la cual se exploraron sus percepciones y su uso. En conclusión, la aplicación es fácil de usar y práctica, organiza eficazmente una carrera y genera datos valiosos sin necesidad de utilizar balizas ni códigos QR.
Progress and future directions in machine learning through control theory
(Universidad de Oviedo, Servicio de Publicaciones, 2024) Zuazua, Enrique
This paper presents our recent advancements at the intersection of machine learning and control theory. We focus specifically on utilizing control theoretical tools to elucidate the underlying mechanisms driving the success of machine learning algorithms. By enhancing the explainability of these algorithms, we aim to contribute to their ongoing improvement and more effective application. Our research explores several critical areas: Firstly, we investigate the memorization, representation, classification, and approximation properties of residual neural networks (ResNets). By framing these tasks as simultaneous or ensemble control problems, we have developed nonlinear and constructive algorithms for training. Our work provides insights into the parameter complexity and computational requirements of ResNets. Similarly, we delve into the properties of neural ODEs (NODEs). We demonstrate that autonomous NODEs of sufficient width can ensure approximate memorization properties. Furthermore, we prove that by allowing biases to be time-dependent, NODEs can track dynamic data. This showcases their potential for synthetic model generation and helps elucidate the success of methodologies such as Reservoir Computing. Next, we analyze the optimal architectures of multilayer perceptrons (MLPs). Our findings offer guidelines for designing MLPs with minimal complexity, ensuring efficiency and effectiveness for supervised learning tasks. The generalization and prediction capacity of trained networks plays a crucial role. To address these properties, we present two nonconvex optimization problems related to shallow neural networks, capturing the ”sparsity” of parameters and robustness of representation. We introduce a ”mean-field” model, proving, via representer theorems, the absence of a relaxation gap. This aids in designing an optimal tolerance strategy for robustness and, through convexification, efficient algorithms for training. In the context of large language models (LLMs), we explore the integration of residual networks with self-attention layers for context capture. We treat ”attention” as a dynamical system acting on a collection of points and characterize their asymptotic dynamics, identifying convergence towards special points called leaders. These theoretical insights have led to the development of an interpretable model for sentiment analysis of movie reviews, among other possible applications. Lastly, we address federated learning, which enables multiple clients to collaboratively train models without sharing private data, thus addressing data collection and privacy challenges. We examine training efficiency, incentive mechanisms, and privacy concerns within this framework, proposing solutions to enhance the effectiveness and security of federated learning methods. Our work underscores the potential of applying control theory principles to improve machine learning models, resulting in more interpretable and efficient algorithms. This interdisciplinary approach opens up a fertile ground for future research, raising profound mathematical questions and application-oriented challenges and opportunities
Barriers to the digital transformation of cultural and creative industry MSMEs: the case of the Basque country
(Emerald Publishing, 2025-11-24) Eguia Aguirre, Ibone; Wilson, James Ralph; Cuenca Cabeza, Manuel; Mosquera López, Stephanía; Bohórquez Correa, Santiago
Purpose – This research aims to study the barriers to digital transformation (DT) faced by micro, small and medium-sized enterprises (MSMEs) within the Cultural and Creative Industries (CCIs) in the Basque Country. It identifies key obstacles and explores how public policy can support overcoming these barriers to enhance organizations’ competitiveness. Design/methodology/approach – This research uses a quantitative approach, surveying 268 CCI MSMEs in the Basque Country using a standardized online questionnaire. The authors analyzed the response through descriptive statistics, correlation analysis and multiple regression to assess the impact of various barriers and organizational characteristics on organizational DT level. Findings – The findings highlight that organizations with lower DT levels perceive barriers more acutely, specifically knowledge-related barriers, such as the lack of information about appropriate technologies and qualified staff, and organizational culture barriers, including the low prioritization of DT within organizations. Moreover, certain organizational characteristics and collaboration with other organizations and public administration assistance enhance the perceived level of DT and reduce the perception of the barriers. Originality/value – This research fills a gap in the literature by focusing on DT in CCI MSMEs, a sector with unique structural characteristics and significant economic importance. It provides policymakers with actionable insights to design targeted interventions that address specific barriers, thereby fostering competitiveness in CCIs.