Artículos (Ciencias de la Computación e Inteligencia Artificial)

URI permanente para esta colecciónhttps://hdl.handle.net/11441/11302

Examinar

Mostrando 1 - 20 de 457

PharaohFUN: phylogenomic analysis for plant protein history and function elucidation
(Oxford University Press, 2026-01-22) Ramos González, Marcos; Ramos González, Víctor; Serrano Pérez, Emma; Arvanitidou, Christina; Hernández García, Jorge; García González, Mercedes; Romero Campero, Francisco José; Ciencias de la Computación e Inteligencia Artificial; Bioquímica Vegetal y Biología Molecular; Ministerio de Ciencia, Innovación y Universidades (MICIU). España; Agencia Estatal de Investigación. España
Since DNA sequencing has become commonplace, the development of efficient methods and tools to explore gene sequences has become indispensable. In particular, despite photosynthetic eukaryotes constituting the largest percentage of terrestrial biomass, computational functional characterization of gene sequences in these organisms still predominantly relies on comparisons with Arabidopsis thaliana and other angiosperms. This paper introduces PharaohFUN, a web application designed for the evolutionary and functional analysis of protein sequences in photosynthetic eukaryotes, leveraging orthology relationships between them. PharaohFUN incorporates a homogeneous representative sampling of key species in this group, bridging clades that have traditionally been studied separately, thus establishing a comprehensive evolutionary framework to draw conclusions about sequence evolution and function. For this purpose, it incorporates modules for exploring gene tree evolutionary history, expansion and contraction events, ancestral states, domain identification, multiple sequence alignments, and diverse functional annotation. It also incorporates different search modes to facilitate its use and increase its reach within the community. Tests were performed on the whole transcription factor toolbox of A. thaliana and on CCA1 protein to assess its utility for both large-scale and fine-grained phylogenetic studies. These exemplify how PharaohFUN accurately traces the corresponding evolutionary histories of these proteins by unifying results for land plants, streptophyte and chlorophyte microalgae. Thus, PharaohFUN democratices access to these kinds of analyses in photosynthetic organisms for every user, independently of their prior training in bioinformatics.
A Genomic Surveillance Circuit for Emerging Viral Pathogens
(MDPI, 2025-04-16) Casimiro Soriguer, Carlos S.; Lara, María; Aguado, Andrea; Loucera Muñecas, Carlos; Ortuño, Francisco; Lepe, Jose A.; Dopazo, Joaquín; Pérez Florido, Javier; Ciencias de la Computación e Inteligencia Artificial
Genomic surveillance has been crucial in monitoring the evolution and spread of SARS-CoV-2. In Andalusia (Spain), a coordinated genomic surveillance circuit was established to systematically sequence and analyze viral genomes across the region. This initiative organizes sample collection through 27 hospitals, which act as regional hubs within their respective health districts. Sequencing is performed at three reference laboratories, with downstream data analysis and reporting centralized at a bioinformatics platform. From 2021 to 2025, over 42,500 SARS-CoV-2 genomes were sequenced, enabling the identification of major variants and their evolutionary dynamics. The circuit tracked the transition from Alpha and Delta to successive Omicron waves, including both recombinant and non-recombinant clades. The integration of genomic and epidemiological data facilitated rapid variant detection, outbreak investigation, and public health decision making. This surveillance framework at a regional granularity demonstrates the feasibility of large-scale sequencing within a decentralized healthcare system and has expanded to monitor other pathogens, reinforcing its value for epidemic preparedness. Continued investment in genomic surveillance is critical for tracking viral evolution, guiding interventions, and mitigating future public health threats.
Ethical and secure evidence generation from regionwide clinical data through a collaborative environment for advancing predictive care
(Frontiers Media S.A., 2025-08-08) Muñoyerro Muñiz, Dolores; Villegas, Román; Oliva, Víctor de la; Esteban Medina, Alberto; Loucera Muñecas, Carlos; Dopazo, Joaquín; Ciencias de la Computación e Inteligencia Artificial
Ensuring data protection is a major challenge in clinical research involving sensitive patient information. However, secure processing environments (SPEs) enable the ethical and compliant secondary use of real-world data (RWD) for evidence generation. This study presents a collaborative infrastructure integrating a comprehensive Health Population Database (BPS) with a legal and computational framework to facilitate secure, large-scale clinical studies. The Andalusian Platform for Medical Evidence Generation is an SPE embedded within the Andalusian healthcare network, leveraging RWD from over 15 million patients from the BPS. It supports diverse studies, including treatment efficacy, survival analyses, and predictive modeling, while ensuring alignment with the General Data Protection Regulation (GDPR) and proactively designed to meet forthcoming European Health Data Space (EHDS) requirements. Data are processed within a secure ecosystem, preventing unauthorized access and enabling legally compliant research collaborations. By combining clinical RWD with a robust ethical and legal framework, we present a scalable model for secure, data-driven region-level healthcare innovation. The platform supports cost-effective predictive models, particularly relevant for aging populations, and establishes a blueprint for regional and international adaptation. This approach strengthens the role of healthcare systems in both knowledge generation and sustainable economic growth, ensuring that patient data is leveraged for scientific and societal benefit.
AppRendo solo: Aprendizaje-servicio transversal para desarrollo de software accesible
(Asociación de Enseñantes Universitarios de la Informática (AENUI), 2023-07-07) Moyano Murillo, José María; Escobar, Juan José; García Moreno, Francisco M.; Rodríguez Fortiz, María José; Rodríguez Almendros, María Luisa; Prados Suárez, Belén; Bermúdez Edo, María; Molina Fernández, Carlos; Ciencias de la Computación e Inteligencia Artificial
En este trabajo describiremos cómo hemos aplicado la metodología educativa de Aprendizaje Como Servicio (ApS), durante varios años, en asignaturas relacionadas con la Dirección, Planificación y Gestión de Proyectos del grado y máster de Informática en la Universidad de Granada. Esta metodología conforma la planificación intencional de acciones de mejora de la realidad, la conexión de contenidos curriculares de asignaturas en actividades derivadas del servicio a la comunidad y la participación reflexiva, crítica y activa del estudiantado. Para su aplicación, planteamos proyectos realizados en equipo y enfocados intencionalmente al desarrollo de aplicaciones para la mejora de vida en personas con necesidades especiales. Dentro del contenido curricular de las asignaturas, incluimos temas relacionados con accesibilidad y habilidades blandas. Nuestros equipos de estudiantes tienen contacto con entidades colaboradoras reales durante todo el ciclo de vida del proyecto, replicando lo que ocurriría en un caso real de su futura vida profesional, lo cual es motivador y gratificante. En algunos casos, se ha conseguido financiación para completar y dejar instalada la aplicación para la entidad colaboradora. Describiremos en el artículo ejemplos de proyectos realizados hasta el momento y la estupenda experiencia del proyecto de innovación docente de este curso académico, con datos de calificaciones, cuestionarios y valoraciones de todos los implicados.
Lack of associations of microRNAs with severe NAFLD in people living with HIV: discovery case-control study
(Frontiers Media S.A., 2023-09-22) Frías, Mario; Corona Mata, D.; Camacho Espejo, Ángela; López López, Pedro; Caballero Gómez, Javier; Ruiz Cáceres, Inmaculada; Moyano Murillo, José María; Ciencias de la Computación e Inteligencia Artificial; TIC-222 Knowledge Discovery and Intelligent Systems
Background & objective: Nonalcoholic fatty liver disease (NAFLD) is highly prevalent in people living with HIV (PLWH) and the expression of some microRNAs could be useful as biomarkers for the diagnosis of NAFLD. The aim of this study was to identify patterns of differential expression of microRNAs in PLWH and assess their diagnostic value for NALFD. Methods: A discovery case-control study with PLWH was carried out. The expression of miRNAs was determined using HTG EdgeSeq technology. Cases were defined as patients with severe NAFLD and controls as patients without NAFLD, characterized using the controlled attenuation parameter (CAP). Cases and controls were matched 1:1 for age, sex, BMI, CD4+ lymphocyte count, active HCV infection, and ART regimen. Results: Serum 2,083 simultaneous microRNA transcripts were analyzed using HTG technology and compared between cases and controls. Forty-five patients, 23 cases, and 22 controls were included in the study. In the analysis of the expression pattern of the 2,083 microRNAs, no differential expression patterns were found between both groups of patients included in the study. Conclusion: Analysis of the microRNA transcriptome profile of nonobese PLWH with severe NAFLD did not appear to differ from that of patients without NAFLD. Thus, microRNA might not serve as a proper biomarker for predicting severe NALFD in this population.
A Low-Carbon Operation Optimization Method of ETG-RIES Based on Adaptive Optimization Spiking Neural P Systems
(IEEE, 2024-09-01) Wang, Tao; Huang, Zhu; Ying, Ruixuan; Valencia Cabrera, Luis; Ciencias de la Computación e Inteligencia Artificial; TIC193: Computación Natural
To enhance multi-energy complementarity and foster a low carbon economy of energy resources, this paper proposes an innovative low-carbon operation optimization method for electric-thermal-gas regional integrated energy systems. To bolster the low-carbon operation capabilities of such systems, a coordinated operation framework is presented that integrates carbon capture devices, power to gas equipment, combined heat and power units, and a multi-energy storage system. To address the challenge of high-dimensional constraint imbalance in the optimization process, a novel low-carbon operation optimization method is then proposed. The new method is based on an adaptive single-objective continuous optimization spiking neural P system, specifically designed for this purpose. Furthermore, simulation models of four typical schemes are established and employed to test and analyze the economy and carbon environmental pollution degree of the proposed system model, as well as the performance of the operation optimization method. Finally, simulation results show that the proposed method not only considers the economic viability of the target integrated energy system, but also significantly improves the wind power utilization and carbon reduction capabilities.
Binding by the Polycomb complex component BMI1 and H2A monoubiquitination shape local and long-range interactions in the Arabidopsis genome
(Oxford Academic, 2023-04-18) Yin, Xiaochang; Romero Campero, Francisco José; Yang, Minqi; Baile, Fernando; Cao, Yuxin; Shu, Jiayue; Luo, Lingxiao; Wang, Dingyue; Sun, Shang; Yan, Peng; Gong, Zhiyun; Mo, Xiaorong; Qin, Genji; Calonje, Myriam; Zhou, Yue; Ciencias de la Computación e Inteligencia Artificial; BIO131: Biología y Biotecnología de Sistemas en Microalgas
Three-dimensional (3D) chromatin organization is highly dynamic during development and seems to play a crucial role in regulating gene expression. Self-interacting domains, commonly called topologically associating domains (TADs) or compartment domains (CDs), have been proposed as the basic structural units of chromatin organization. Surprisingly, although these units have been found in several plant species, they escaped detection in Arabidopsis (Arabidopsis thaliana). Here, we show that the Arabidopsis genome is partitioned into contiguous CDs with different epigenetic features, which are required to maintain appropriate intra-CD and long-range interactions. Consistent with this notion, the histone-modifying Polycomb group machinery is involved in 3D chromatin organization. Yet, while it is clear that Polycomb repressive complex 2 (PRC2)-mediated trimethylation of histone H3 on lysine 27 (H3K27me3) helps establish local and long-range chromatin interactions in plants, the implications of PRC1-mediated histone H2A monoubiquitination on lysine 121 (H2AK121ub) are unclear. We found that PRC1, together with PRC2, maintains intra-CD interactions, but it also hinders the formation of H3K4me3-enriched local chromatin loops when acting independently of PRC2. Moreover, the loss of PRC1 or PRC2 activity differentially affects long-range chromatin interactions, and these 3D changes differentially affect gene expression. Our results suggest that H2AK121ub helps prevent the formation of transposable element/H3K27me1-rich long loops and serves as a docking point for H3K27me3 incorporation.
A multi-scale spatiotemporal spiking neural model for power load forecasting considering extreme weather impact
(Elsevier, 2026-01-21) Guo, Yuanshuo; Wang, Jun; Peng, Hong; Wang, Tao; Hu, Hongping; Ramírez de Arellano Marreiro, Antonio; Ciencias de la Computación e Inteligencia Artificial; TIC193: Computación Natural
The increasing frequency of extreme weather events has brought about significant mutation in the distribution characteristics of power load, while traditional models are unable to handle such sudden changes in load and adequately characterize the coupling effects across various scales. To address this problem, this study proposes a bidirectional nonlinear spiking neural P (NSNP) model with weather-aware multi-scale fusion, which represents an enhanced NSNP framework that integrates multi-scale adaptive feature extraction network (MAFEN) and multiple encoders based on bidirectional NSNP (BiNSNP) variants, termed multi-scale spatiotemporal BiNSNP attention fusion network (MSBAF-Net). Inspired by nonlinear spiking mechanisms, this architecture captures complex nonlinear load dynamics. Moreover, this multi-source data parallel fusion network effectively achieves dynamic weighting of features across both spatial and temporal dimensions, thereby capturing local patterns at critical time steps in load sequences and cross-channel feature correlations under extreme weather. Specifically, MSBAF-Net performs channel separation, isolating the abrupt components of the load into the residual channel. Based on the characteristics of different channels, MSBAF-Net incorporates a targeted bidirectional modeling strategy alongside differentiated feature extraction pathways, implemented through two lightweight NSNP-like convolutional models. Additionally, feature fusion network (FFN) maintains the interaction of multi-scale load features in time and space. Finally, comparison study using three real-world datasets and 25 baseline prediction models is performed. Experimental results demonstrate that MSBAF-Net achieves the best comprehensive performance across all extreme weather scenarios. Notably, under the low-temperature cold wave scenario, MSBAF-Net achieves average forecasting accuracies of 97.51% and 97.38% for Lines 1–10 at the power station A and Lines 1–7 at the power station B, respectively. Our codes and datasets have been released at https://github.com/hssinne/MSBAF-Net.
Design of novel intelligent electronic trap for early detection and monitoring of tomato crops pest Tuta Absoluta using Deep learning
(Elsevier, 2025-07-08) Alasady, Yaser M. Abid; Pérez Perdomo, Eduardo; Ventura, Sebastián; Ciencias de la Computación e Inteligencia Artificial
To control insect pests and reduce the destruction of agricultural crops, the process of detection and monitoring of pests is an urgent need at present time. Due to the tremendous development in technology, the traditional methods used in laboratories considered a waste of time and human efforts. In this research, a new data set collected and published for the first time, novel electronic trap designed with intelligent system to detect pests in tomato crop, and monitor the spread of the pest periodically and continuously based on the collected dataset. As the designed intelligent system firstly consists of a novel trap designed in a way that contains six colored sticky traps to catch insects continuously, controlled by L293D IC to rotate the motor, a digital camera used to provide the system with real images at periodic intervals. To detect pest, the (YOLOv11, YOLOv9, YOLOv8 and YOLOv5) used for this purpose. The Tuta Absoluta pest used for the detection and monitoring process of the designed novel intelligent system. The results used in the system; the precision was 95.9%, recall was 92.5%, Mean Average Precision (mAP 0.5) was 94% and F1 score was 94% and the results were promising. As compared to other models of (YOLOv11, YOLOv9, YOLOv8 and YOLOv5), the YOLOv5x shows that its higher results than other models. This system is easy to use and accurate in providing the information required monitoring the spread of the insect pest, therefore it could use in modern agricultural applications.
Indoor UAV navigation using event cameras and intermediate frame reconstruction
(Academic Press Inc Elsevier Science, 2026-01-10) Tejero Ruiz, David; Solís Martín, David; Pérez Grau, Francisco J.; Borrego Díaz, Joaquín; Ciencias de la Computación e Inteligencia Artificial; TIC137: Lógica, Computación e Ingeniería del Conocimiento
Indoor UAV navigation faces significant challenges due to GPS signal absence and limitations of conventional visual-inertial systems under challenging lighting and motion conditions. This paper presents an event-based visual-inertial odometry system that addresses these limitations through intermediate frame reconstruction from event streams combined with established odometry algorithms. The approach leverages event cameras’ unique characteristics — microsecond temporal resolution, high dynamic range (120 dB), and motion blur immunity — to maintain stable navigation performance under conditions that cause conventional systems to fail. The system achieves real-time operation at 30 Hz frame reconstruction and 20 Hz pose estimation on embedded hardware, consuming 15 W power while adding only 50 g to the UAV platform. Experimental validation in controlled indoor environments demonstrates mean absolute pose errors of 26–42 cm across different operational conditions, comparable to conventional visual-inertial systems. Critically, the system maintains stable performance during rapid lighting transitions, showing only 59% performance degradation compared to baseline conditions, while conventional cameras typically experience complete tracking failure. The results establish event-based visual-inertial odometry as a viable alternative for indoor UAV navigation, particularly in applications requiring environmental robustness over marginal accuracy improvements under optimal conditions.
Enhancing Mathematical Knowledge Graphs with Large Language Models
(MDPI, 2025-06-24) Lobo Santos, Antonio; Borrego Díaz, Joaquín; Ciencias de la Computación e Inteligencia Artificial; TIC137: Lógica, Computación e Ingeniería del Conocimiento
The rapid growth in scientific knowledge has created a critical need for advanced systems capable of managing mathematical knowledge at scale. This study presents a novel approach that integrates ontology-based knowledge representation with large language models (LLMs) to automate the extraction, organization, and reasoning of mathematical knowledge from LaTeX documents. The proposed system enhances Mathematical Knowledge Management (MKM) by enabling structured storage, semantic querying, and logical validation of mathematical statements. The key innovations include a lightweight ontology for modeling hypotheses, conclusions, and proofs, and algorithms for optimizing assumptions and generating pseudo- demonstrations. A user-friendly web interface supports visualization and interaction with the knowledge graph, facilitating tasks such as curriculum validation and intelligent tutoring. The results demonstrate high accuracy in mathematical statement extraction and ontology population, with potential scalability for handling large datasets. This work bridges the gap between symbolic knowledge and data-driven reasoning, offering a robust solution for scalable, interpretable, and precise MKM.
Pearclustering: a novel clustering algorithm with an application to bike mobility
(Springer, 2026-06-25) Márquez Saldaña, Francisco; Aranda Corral, Gonzalo A.; Borrego Díaz, Joaquín; Ciencias de la Computación e Inteligencia Artificial; TIC137: Lógica, Computación e Ingeniería del Conocimiento
Bike Sharing Systems (BSS) have become a key solution for urban mobility, reducing traffic-related CO2 emissions. However, managing BSS poses challenges that require data-driven solutions, particularly for understanding their global behavior and forecasting their evolution. These dynamics arise from the interaction among users, companies, dock stations, and city policies, influenced by sociological and infrastructure-based factors. This paper proposes a novel clustering methodology to analyze BSS data across multiple cities. By clustering station-day tuples instead of aggregating statistics, our approach captures seasonal patterns, special events, and weekday/weekend differences. Using Pearson Correlation as a distance metric, it remains robust across different station sizes and system scales. Trained on three European BSS and evaluated across six cities from 4 different countries, our model uncovers meaningful patterns such as work, residential, and leisure areas, as well as seasonal changes even in systems not used in the training process. These insights enhance BSS management, expansion, and decision-making, with applications in monitoring, anomaly detection, and demand prediction.
Remb: regularized embedding memory book to extend metric learning in fault diagnosis
(Springer, 2025-10-11) Solís Martín, David; Fuentes Morono, Martina; Galán Páez, Juan; Borrego Díaz, Joaquín; Ciencias de la Computación e Inteligencia Artificial; TIC137: Lógica, Computación e Ingeniería del Conocimiento
Few-Shot Learning (FSL) has gained significant attention in fault diagnosis due to its ability to classify faults with limited labeled data. Metric learning-based approaches, such as prototypical networks, have demonstrated effectiveness in this domain by computing class prototypes from support examples. However, these methods often rely on high-dimensional embeddings, which can lead to computational inefficiencies and overfitting, particularly in low-data regimes. This work introduces the Regularized Embedding Memory Book (REMB), a novel module designed to improve prototype estimation and enhance classification accuracy in FSL for fault diagnosis. The REMB module constructs a memory book of embeddings for each class and refines prototype computation by selecting the most representative embeddings. Additionally, we incorporate a set of regularization techniques to improve generalization and robustness, particularly in noisy environments. We evaluate REMB on four benchmark datasets commonly used in fault diagnosis: CWRU, JNU, PU, and an additional dataset with varying training sample sizes. The experimental results demonstrate that REMB improves classification performance, particularly in low-data scenarios, and enhances model calibration. Furthermore, we analyze the impact of noise adaptation and the contribution of different regularization terms through an ablation study. Our findings suggest that the proposed approach provides a robust and efficient solution for few-shot fault diagnosis, outperforming conventional metric learning methods. Few-Shot Learning (FSL) has gained significant attention in fault diagnosis due to its ability to classify faults with limited labeled data. Metric learning-based approaches, such as prototypical networks, have demonstrated effectiveness in this domain by computing class prototypes from support examples. However, these methods often rely on high-dimensional embeddings, which can lead to computational inefficiencies and overfitting, particularly in low-data regimes. This work introduces the Regularized Embedding Memory Book (REMB), a novel module designed to improve prototype estimation and enhance classification accuracy in FSL for fault diagnosis. The REMB module constructs a memory book of embeddings for each class and refines prototype computation by selecting the most representative embeddings. Additionally, we incorporate a set of regularization techniques to improve generalization and robustness, particularly in noisy environments. We evaluate REMB on four benchmark datasets commonly used in fault diagnosis: CWRU, JNU, PU, and an additional dataset with varying training sample sizes. The experimental results demonstrate that REMB improves classification performance, particularly in low-data scenarios, and enhances model calibration. Furthermore, we analyze the impact of noise adaptation and the contribution of different regularization terms through an ablation study. Our findings suggest that the proposed approach provides a robust and efficient solution for few-shot fault diagnosis, outperforming conventional metric learning methods.
Introducción a la inferencia causal
(2025) Baeza Ruiz-Henestrosa, Juan; Sancho Caparrini, Fernando; Ciencias de la Computación e Inteligencia Artificial; TIC137: Lógica, Computación e Ingeniería del Conocimiento
La capacidad de establecer relaciones causales entre eventos y de emplear este conocimiento para hacer inferencias constituye una característica fundamental del proceso cognitivo humano y juega un papel central en la toma de decisiones y en la búsqueda de explicaciones en numerosas áreas de conocimiento. En este contexto, el marco de los modelos causales basados en grafos permite dotar de una formalización matemática rigurosa al concepto de causalidad desde una perspectiva computacional, permitiendo explicitar las relaciones causales entre las variables de un sistema por medio de grafos dirigidos acíclicos (DAGs). El presente trabajo fin de máster constituye una introducción integral a la inferencia causal desde el marco de los modelos causales basados en grafos. Partiendo de las motivaciones y los supuestos de este enfoque, se desarrollan sus fundamentos teóricos a partir del concepto de modelo causal estructural (SCM), formalizando las nociones de intervención y contrafactual. Se aborda el problema del descubrimiento causal, resaltando las hipótesis en las que se sustenta y sus limitaciones, y se presentan algunos de los algoritmos más representativos. Asimismo, se analiza cómo tratar la presencia de variables no observadas en el sistema. Finalmente, el trabajo concluye destacando el potencial transformador de este marco de inferencia dentro de las ciencias empíricas y del campo de la inteligencia artificial.
Inteligencia colectiva emergente sobre enjambres de minirrobots
(2024) García Barragán, Lidia; Borrego Díaz, Joaquín; Ciencias de la Computación e Inteligencia Artificial; TIC137: Lógica, Computación e Ingeniería del Conocimiento
Esta memoria se centra en el estudio, diseño, implementación y prueba de tres comportamientos emergentes sobre un enjambre de minirobots Thymio. El diseño de dichos comportamientos deberá ser adaptado a las capacidades de nuestra tecnología. Para conseguirlo, haremos uso de la inteligencia reactiva,la creación de patrones geométricos, el comportamiento enjambre, el comportamiento hormiga y la Teleo-Reactividad, con vistas a poder implementarlos en nuestra tecnología. Se justificará el tema elegido y se hará una breve introducción a las tecnologías utilizadas así como una explicación de su hardaware y software, se guiará al lector a lo largo del diseño, adaptación e implementación y se presentarán unos resultados y unas conclusiones del rendimiento para cada comportamiento.
Spiking Neural P Systems with Extended Channel Rules
(World Scientific, 2021) Lv, Zeqiong; Bao, Tingting; Zhou, Nan; Peng, Hong; Huang, Xiangnian; Riscos Núñez, Agustín; Pérez Jiménez, Mario de Jesús; Ciencias de la Computación e Inteligencia Artificial
This paper discusses a new variant of spiking neural P systems (in short, SNP systems), spiking neural P systems with extended channel rules (in short, SNP–ECR systems). SNP–ECR systems are a class of distributed parallel computing models. In SNP–ECR systems, a new type of spiking rule is introduced, called ECR. With an ECR, a neuron can send the different numbers of spikes to its subsequent neurons. Therefore, SNP–ECR systems can provide a stronger firing control mechanism compared with SNP systems and the variant with multiple channels. We discuss the Turing universality of SNP–ECR systems. It is proven that SNP–ECR systems as number generating/accepting devices are Turing universal. Moreover, we provide a small universal SNP–ECR system as function computing devices.
Gated Spiking Neural P Systems for Time Series Forecasting
(2023) Liu, Qian; Long, Lifan; Peng, Hong; Wang, Jun; Yang, Qian; Song, Xiaoxiao; Riscos Núñez, Agustín; Pérez Jiménez, Mario de Jesús; Ciencias de la Computación e Inteligencia Artificial
Spiking neural P (SNP) systems are a class of neural-like computing models, abstracted by the mechanism of spiking neurons. This article proposes a new variant of SNP systems, called gated spiking neural P (GSNP) systems, which are composed of gated neurons. Two gated mechanisms are introduced in the nonlinear spiking mechanism of GSNP systems, consisting of a reset gate and a consumption gate. The two gates are used to control the updating of states in neurons. Based on gated neurons, a prediction model for time series is developed, known as the GSNP model. Several benchmark univariate and multivariate time series are used to evaluate the proposed GSNP model and to compare several state-of-the-art prediction models. The comparison results demonstrate the availability and effectiveness of GSNP for time series forecasting.
Medical image fusion method based on coupled neural P systems in nonsubsampled shearlet transform domain
(World Scientific, 2021) Li, Bo; Peng, Hong; Luo, Xiaohui; Wang, Jun; Song, Xiaoxiao; Pérez Jiménez, Mario de Jesús; Riscos Núñez, Agustín; Ciencias de la Computación e Inteligencia Artificial
Coupled neural P (CNP) systems are a recently developed Turing-universal, distributed and parallel computing model, combining the spiking and coupled mechanisms of neurons. This paper focuses on how to apply CNP systems to handle the fusion of multi-modality medical images and proposes a novel image fusion method. Based on two CNP systems with local topology, an image fusion framework in nonsubsampled shearlet transform (NSST) domain is designed, where the two CNP systems are used to control the fusion of low-frequency NSST coefficients. The proposed fusion method is evaluated on 20 pairs of multi-modality medical images and compared with seven previous fusion methods and two deep-learning-based fusion methods. Quantitative and qualitative experimental results demonstrate the advantage of the proposed fusion method in terms of visual quality and fusion performance.
PFUS1: Premier pelvic floor ultrasound segmentation dataset. A resource for advancing research
(Elsevier, 2025-12-01) Solís Martín, David; Sáinz Bueno, José Antonio; Borrego Díaz, Joaquín; Cirugía; Ciencias de la Computación e Inteligencia Artificial; TIC137: Lógica, Computación e Ingeniería del Conocimiento
This article presents a curated dataset of transperineal pelvic floor ultrasound videos collected from 111 patients in a clinical setting using a Canon i700 Aplio® ultrasound system with a PVT-675 MV 3D probe. Each video captures the midsagittal view of pelvic floor organs at rest and during the Valsalva maneuver. Eight anatomical structures were manually annotated by an expert sonographer using the CVAT platform, resulting in pixel-level segmentation masks. The dataset is intended to support research in automated pelvic floor assessment, medical image segmentation, and dynamic organ tracking. To facilitate reuse, a public source code repository is provided with scripts for data loading, mask generation, and training of baseline deep learning models, including Feature Pyramid Networks (FPNs). This dataset represents the first annotated ultrasound video resources focused on pelvic floor anatomy and is designed to enable benchmarking, reproducibility, and methodological innovation in computer-assisted diagnosis and medical image analysis.
Uniform solution to Subset Sum by means of virus machines
(Springer Nature, 2025-06-25) Ramírez de Arellano, Antonio; Orellana Martín, David; Cabarle, Francis George C.; Pérez Jiménez, Mario de Jesús; Ciencias de la Computación e Inteligencia Artificial
Unconventional computing plays an important role in computational complexity theory, providing unconventional computing paradigms to tighten the gap between tractable and presumable intractable problems; however, most unconventional paradigms reach similar gaps and their perspective may become stagnant. In this work, we develop a new outlook by a young natural computing paradigm called virus machines (VMs) which takes inspiration from the biological virus life cycle. A new computational complexity theory through VM is developed by attacking a classical NP-complete problem, the Subset Sum problem. It has been uniformly solved by means of deterministic VM. The uniform construction consists of three different modules: one module B for selecting the possible subset; another module that encodes the selection, adds it or not to the final sum, and compares the result; and one last module END to reach the halting configuration and make the output consistent. This design provides a new perspective for solving presumably hard problems by means of families of VMs, opening new research lines in this framework.

Examinar

Envíos recientes