Artículos (Arquitectura y Tecnología de Computadores)
URI permanente para esta colecciónhttps://hdl.handle.net/11441/11292
Examinar
Envíos recientes
Artículo Review of Memristors for In-Memory Computing and Spiking Neural Networks(Wiley, 2026-03-18) Shooshtari, Mostafa; Serrano Gotarredona, María Teresa; Linares Barranco, Bernabé; Arquitectura y Tecnología de Computadores; European Union (UE); Ministerio para la Transformación Digital y de la Función Pública. EspañaThe convergence of in-memory computing (IMC) and neuromorphic architectures offers a promising path toward energy-efficient, scalable artificial intelligence, particularly for edge and real-time applications. Memristors, resistive devices with nonvolatile, analog switching, uniquely enable this convergence by serving both as computational memory units for matrix-vector multiplication and as synaptic elements for spike-based learning. This review comprehensively explores the physical mechanisms, material classes, and integration strategies of memristors tailored for IMC and spiking neural networks, with emphasis on their implementation in crossbar arrays, synapse-neuron emulation, and hybrid CMOS circuits. It discusses how memristors facilitate key biological learning rules like STDP and LTP/LTD and examine their deployment in edge artificial intelligence, adaptive robotics, and neuromorphic sensors. Despite their potential, device variability, noise, relaxation, scalability limits, and standardization remain pressing challenges. By synthesizing device-level insights with architectural innovation and emerging applications, this work outlines a roadmap toward fully integrated, low-power, and brain-inspired computing systems.Artículo A practitioner’s guide to Kolmogorov–Arnold networks(Elsevier, 2026-11) Noorizadegan, Amir; Wang, Sifan; Ling, Leevan; Domínguez Morales, Juan Pedro; Arquitectura y Tecnología de Computadores; Hong Kong Research Grants Council; TEP108: Robótica y Tecnología de ComputadoresKolmogorov–Arnold Networks (KANs), whose design is inspired—rather than dictated— by the Kolmogorov superposition theorem, have emerged as a structured alternative to MLPs. This review provides a systematic and comprehensive overview of the rapidly expanding KAN literature. The review is organized around three core themes: (i) clarifying the relationships between KANs and Kolmogorov superposition theory (KST), MLPs, and classical kernel methods; (ii) analyzing basis functions as a central design axis; and (iii) summarizing recent advances in accuracy, efficiency, regularization, and convergence. Finally, we provide a practical “Choose–Your–KAN” guide and outline open research challenges and future directions. The accompanying GitHub repository (https://github.com/AmirNoori68/kan-review) serves as a structured reference for ongoing KAN research.Artículo Concurrent validity and agreement of the HerniaCare Lab device for abdominal wall strength assessment(2026-03-10) Gil Delgado, José Luis; Rangel Cascajosa, Carlos; Sánchez Arteaga, Alejandro; Tallón Aguilar, Luis; Sañudo Corrales, Borja; Arquitectura y Tecnología de ComputadoresPurpose: Currently, no standardized, low-cost, and portable method is available for assessing abdominal wall strength in patients with incisional hernias, addressing the limitations of traditional dynamometry. Methods: This cross-sectional validation study compared the HerniaCare Lab device performance with the Activforce 2 hand-held dynamometer in92 adults diagnosed with abdominal wall hernias. Isometric trunk flexion strength was measured under identical conditions, and agreement between devices was analyzed using non-parametric tests, correlation, and concordance statistics. Results: The HerniaCare Lab showed systematically higher strength values than the Activforce 2 (mean difference = + 22.3 N, p < 0.001) but demonstrated a very strong positive correlation (ρ = 0.95, p < 0.001) and good concordance (CCC = 0.89). Bland–Altman analysis revealed a mean bias of + 24.9 N with 95% limits of agreement from − 17.7 to+ 67.5 N, and a slight proportional bias at higher force levels. Conclusion: Despite predictable overestimation, the HerniaCare Lab exhibits strong concurrent validity and good agreement with an established reference device, supporting its potential clinical utility for objective, reproducible, and accessible assessment of abdominal wall strength in surgical populations.Artículo Effectiveness of an mHealth-based impact exercise program for bone health in postmenopausal women: a randomised controlled trial protocol(Springer, 2025) Sañudo Corrales, Borja; Reverte Pagola, Gonzalo; Maher, Carol; Godino, Job G; Carrasco Páez, Luis; Oviedo Caro, Miguel Ángel; Feria Madueño, Adrián; Sánchez Trigo, Horacio; Gambôa, Hugo; Domingo Molina, Raquel; Sánchez Arteaga, Alejandro; Giráldez Sánchez, Miguel Ángel; Martínez Maestre, María de los Ángeles; Cepeda, Elena; Ladrón de Guevara, Carmen; Rangel Cascajosa, Carlos; Pecci Barea, Francisco Javier; Farrahi, Vahid; Bayano-Tejero, Sergio; Arquitectura y Tecnología de Computadores; Ministerio de Ciencia e Innovación (MICIN). EspañaOsteoporosis, a major global health concern, increases fracture risk due to reduced bone mineral density (BMD), particularly in postmenopausal women. Weight-bearing and high-impact exercises are recommended for bone health, yet accurately quantifying mechanical loading outside the laboratory remains a challenge. Without precise tools, it is difficult to assess whether individuals engage in sufficient osteogenic activity. Moreover, poor adherence to structured exercise programs limits their effectiveness. Mobile health (mHealth) technologies offer a promising solution by enabling real-time mechanical loading monitoring in free-living conditions and providing personalized feedback to improve adherence. This study evaluates the effectiveness of an individualized mHealth-based intervention in optimizing exercise adherence and promoting bone health in postmenopausal women through real-time quantification of mechanical loading.Artículo Hardware Implementation of a Real-Time Adaptive Time-Series Segmentation Algorithm for Intracortical Implants(IEEE-Instutue of Electrical and Electronics Engineers, 2026) Galeote Checa, Gabriel; Panuccio, Gabriella; Linares Barranco, Bernabé; Serrano Gotarredona, María Teresa; Arquitectura y Tecnología de Computadores; Spanish National ProjectEpilepsy affects over 50 million people worldwide, posing a significant clinical challenge, particularly for patients unresponsive to conventional treatments. Advances in neural implants with on-device algorithms are revolutionizing epilepsy management by enabling precise, real-time seizure detection and reducing the technical and financial burden of data transmission. The current trend advances towards the integration of a larger number of electrodes in neural implants, enhancing spatial resolution and broadening brain coverage. Consequently, the increasing data demands necessitate highly efficient processing to minimize transmission bandwidth and power consumption, ensuring the long term viability of implantable systems. This work presents a novel approach using time-series segmentation (TSS) to extract labeled information from raw recordings. The algorithm explores multiple outlier detection methods with a heuristic low-complexity event classifier, and employs a multichannel consensus strategy to improve detection accuracy through multichannel agreement. This system enables high-performance seizure detection and segments local field potentials (LFP) into clinically relevant labels for interpretation and post-processing. Tested on microelectrode array (MEA) recordings from mouse hippocampus-cortex slices treated with 4-aminopyridine, the system demonstrated robust reliability. Implemented on a Pynq-Z2 board with a Zynq 7020 System-on-Chip, the algorithm requires minimal calibration, achieving 95% accuracy, 94% sensitivity, and a 0.03% FPR with a low power consumption of 128 mW for the best-performing outlier detector. By demonstrating the application of TSS to implantable device algorithms for ondevice processing, this work advances towards more effective, personalized epilepsy treatments.Artículo Bio-Inspired Spike-Timing-Dependent Plasticity Learning with Metal Halide Perovskites: Toward Artificial Synaptic Functionality(Amer Chemical SOC, 2026) Shooshtari, Mostafa; Kim, So Yeon; Pahlavan, Saeideh; Serrano Gotarredona, María Teresa; Bisquert, Juan; Linares Barranco, Bernabé; Arquitectura y Tecnología de Computadores; European Research Council (ERC)Recent advances in neuromorphic engineering have sparked a convergence between nanotechnology and neuroscience, where emerging devices such as memristors are being explored to replicate fundamental learning mechanisms observed in the brain. One such mechanism, spike-timing-dependent plasticity (STDP), encodes synaptic changes based on the precise timing between pre- and postsynaptic spikes, and has been widely adopted in machine intelligence and computational neuroscience. In this work, we demonstrate that a halide perovskite memristor (Cs3Bi2I6Br3) can effectively simulate biologically plausible STDP dynamics. We fabricate and characterize the MHP-based device, and develop a dynamic physical model capturing its voltage- and history-dependent switching behavior. Using biologically inspired biphasic voltage pulses, the model replicates classic STDP characteristics including long-term potentiation (LTP), long-term depression (LTD), and the canonical asymmetric learning window. Further analysis shows that the memristor supports advanced features such as triplet-STDP and synaptic memory consolidation. Importantly, the STDP behavior remains stable across 100 independent trials with biologically realistic voltage noise, exhibiting less than 0.03% variation in synaptic weight. These results suggest that the inherent physical dynamics of halide perovskites enable bioinspired learning without external programming or algorithmic supervision. By bridging molecular-scale materials physics with spike-based computation, our findings lay the groundwork for implementing scalable, low-power, and noisetolerant synaptic learning in next-generation neuromorphic computing systemsArtículo Biomechanical behavior of a new design of dental implant: Influence of the porosity and location in the maxilla(Elsevier, 2024) Robau Porrua, Amanda; González, Jesús E.; Rodríguez Guerra, Jennifer; González Mederos, Pedro; Navarro González, Paula; de la Rosa, Julio E.; Carbonell González, Maikel; Araneda Hernández, Eugenia; Torres, Yadir; Arquitectura y Tecnología de Computadores; Ministerio de Ciencia e Innovación (MICIN). España; TEP123: Metalurgia e Ingeniería de los MaterialesThe biomechanical performance of dental implants determines their clinical success. In this work, the stress and deformation distribution of a new implant design (dense and porous) was evaluated by the Finite Element Method. Furthermore, the effect of the location of the dental implant in the maxillary zone, as well as the mechanical response in the peri-implant maxillary tissue (cortical and trabecular) is discussed in detail. Before carrying out the computational study of the dental implant, Ti6Al4V cylindrical preforms obtained by conventional powder metallurgy and space-holder technique were characterized, to choose the most appropriate porosity (percentage and size) to achieve the biomechanical and biofunctional balance of the dental implant investigated. The novel porous dental implant under investigation exhibits 40% porosity in the region in contact with the trabecular bone, featuring inclined pores at 60 and 120◦ with a diameter of 200 μm. Our findings revealed that the cortical bone experienced the highest stress values, whereas the trabecular bone exhibited the highest levels of strain. Notably, the location of dental implants in the maxilla highlighted as the most influential factor affecting the maximum values of von Mises equivalent stress and strain. Furthermore, in the second molar location, the stress and strain levels exceeded the recommended thresholds for maintaining peri-implant bone density. Additionally, the porous implants generated significantly higher levels of stress and strain in the periimplant trabecular bone than dense implants.Artículo Automated fiducial-based alignment of cryo-electron tomography tilt series in Dynamo(Cell Press, 2024) Coray, R; Navarro González, Paula; Scaramuzza, S; Stahlberg, H; Castaño Díez, D; Arquitectura y Tecnología de Computadores; Ministerio de Ciencia e Innovación (MICIN). España; TEP123: Metalurgia e Ingeniería de los MaterialesWith the advent of modern technologies for cryo-electron tomography (cryo-ET), high-quality tilt series are more rapidly acquired than processed and analyzed. Thus, a robust and fast-automated alignment for batch processing in cryo-ET is needed. While different software packages have made available several approaches for automated marker-based alignment of tilt series, manual user intervention remains necessary for many datasets, thus preventing high-throughput tomography. We have developed a MATLAB-based framework integrated into the Dynamo software package for automatic detection of fiducial markers that generates a robust alignment model with minimal input parameters. This approach allows high-throughput, unsupervised volume reconstruction. This new module extends Dynamo with a large repertory of tools for tomographic alignment and reconstruction, as well as specific visualization browsers to rapidly assess the biological relevance of the dataset. Our approach has been successfully tested on a broad range of datasets that include diverse biological samples and cryo-ET modalities.Artículo Topology-aware design of spiking neural networks via modular graph architectures(Public Library of Science (PLoS), 2026) Motaghian, Farideh; Nazari, Soheila; Domínguez Morales, Juan Pedro; Jafari, Reza; Arquitectura y Tecnología de Computadores; TEP108: Robótica y Tecnología de ComputadoresSpiking Neural Networks (SNNs) offer a biologically plausible and energy-efficient alternative to traditional artificial neural networks (ANNs), yet their design remains constrained by limited architectural flexibility and slow training dynamics. In this work, we introduce a novel SNN framework that leverages modular graph-based topologies and explicit synaptic delays to significantly enhance both training efficiency and classification performance. Our architecture, TANet-Tiny, incorporates structured graph stages with up to 32 nodes and diverse community-driven connectivity patterns derived from KMeans clustering, Louvain modularity, and Watts–Strogatz small-world models. We integrate these topologies into a topology-aware search space and explore them via a Spatio-Temporal Topology Sampling (STTS) approach, enabling the discovery of high-performing networks without exhaustive search. Experimental results on MNIST, CIFAR-10, and CIFAR-100 demonstrate that our modular designs achieve state-of-the-art accuracy while requiring 6–10 × fewer training epochs, with top-1 accuracy reaching 99.57% on MNIST and over 92% on CIFAR-10, all with reduced parameter counts. We introduce an accuracy-per-epoch metric to quantify training efficiency and show that modularity, rather than network size, is the critical driver of performance. This work lays the groundwork for scalable, interpretable, and low-latency SNN architectures suitable for deployment in neuromorphic and edge computing environments.Artículo Explainable Deep Learning System for Custom Report Generation in Breast Cancer Histology(Springer, 2025) Anguita Molina, Miguel Ángel; Civit Masot, Javier; Muñoz Saavedra, Luis; Polo Rodríguez, Aurora; Domínguez Morales, Manuel Jesús; Arquitectura y Tecnología de Computadores; Universidad de Sevilla; CBUABreast cancer is the most lethal type of cancer among women, one of the causes can be due to the lack of professionals to evaluate the results of medical images in time (Sharafaddini et al. Multimed Tools Appl, 1–112 2024). This problem is even greater in developing countries. In recent years, diagnostic tools based on artificial intelligence techniques have been developed to improve diagnosis time and results. In this work, we present a system that analyzes histopathological images obtained from breast tissue biopsies to design a classification system that distinguishes between benign and malignant tissue. To demonstrate that the proposed work is robust, multiple alternatives and combinations are studied to obtain the best cases. Finally, we compare the proposed approach with previous works. Furthermore, the developed system integrates explainable artificial intelligence techniques to produce a report to the physician, including a heat map with the areas the system has determined to be essential for classification.Artículo Convolutional Neural Networks for Segmenting Cerebellar Fissures from Magnetic Resonance Imaging(MDPI, 2022) Cabeza Ruiz, Robin; Velázquez Pérez, Luis; Linares Barranco, Alejandro; Pérez-Rodríguez, Roberto; Arquitectura y Tecnología de Computadores; TEP108: Robótica y Tecnología de ComputadoresThe human cerebellum plays an important role in coordination tasks. Diseases such as spinocerebellar ataxias tend to cause severe damage to the cerebellum, leading patients to a progressive loss of motor coordination. The detection of such damages can help specialists to approximate the state of the disease, as well as to perform statistical analysis, in order to propose treatment therapies for the patients. Manual segmentation of such patterns from magnetic resonance imaging is a very difficult and time-consuming task, and is not a viable solution if the number of images to process is relatively large. In recent years, deep learning techniques such as convolutional neural networks (CNNs or convnets) have experienced an increased development, and many researchers have used them to automatically segment medical images. In this research, we propose the use of convolutional neural networks for automatically segmenting the cerebellar fissures from brain magnetic resonance imaging. Three models are presented, based on the same CNN architecture, for obtaining three different binary masks: fissures, cerebellum with fissures, and cerebellum without fissures. The models perform well in terms of precision and efficiency. Evaluation results show that convnets can be trained for such purposes, and could be considered as additional tools in the diagnosis and characterization of neurodegenerative diseases.Artículo Towards neuromorphic FPGA-based infrastructures for a robotic arm(Springer, 2023) Canas Moreno, Salvador; Piñero Fuentes, Enrique; Ríos Navarro, José Antonio; Cascado Caballero, Daniel; Pérez Peña, Fernando; Linares Barranco, Alejandro; Arquitectura y Tecnología de Computadores; Agencia Estatal de Investigación. España; TEP108: Robótica y Tecnología de ComputadoresMuscles are stretched with bursts of spikes that come frommotor neurons connected to the cerebellum through the spinal cord. Then, alpha motor neurons directly innervate the muscles to complete the motor command coming from upper biological structures. Nevertheless, classical robotic systems usually require complex computational capabilities and relative highpower consumption to process their control algorithm, which requires information from the robot’s proprioceptive sensors. The way in which the information is encoded and transmitted is an important difference between biological systems and robotic machines. Neuromorphic engineering mimics these behaviors found in biology into engineering solutions to produce more efficient systems and for a better understanding of neural systems. This paper presents the application of a Spike-based Proportional-Integral-Derivative controller to a 6-DoF Scorbot ER-VII robotic arm, feeding themotorswith Pulse-Frequency-Modulation instead of Pulse-Width-Modulation, mimicking the way in which motor neurons act over muscles. The presented frameworks allow the robot to be commanded and monitored locally or remotely from both a Python software running on a computer or from a spike-based neuromorphic hardware. Multi-FPGA and single-PSoC solutions are compared. These frameworks are intended for experimental use of the neuromorphic community as a testbed platform and for dataset recording for machine learning purposes.Artículo Predictive Maintenance Edge Artificial Intelligence Application Study Using Recurrent Neural Networks for Early Aging Detection in Peristaltic Pumps(IEEE-Inst Electrical Electronics Engineers INC, 2024) Montes-Sánchez, Juan Manuel; Uwate, Yoko; Nishio, Yoshifumi; Vicente Díaz, Saturnino; Jiménez Fernández, Ángel Francisco; Arquitectura y Tecnología de Computadores; TEP108: Robótica y Tecnología de ComputadoresPeristaltic pumps are widely used in many industrial applications, especially in medical devices. Their reliability depends on proper maintenance, which includes the total replacement of tubes regularly due to the aging of the materials. The proper use of predictive maintenance techniques could potentially improve the efficiency of maintenance interventions and prevent failures by having a way to determine when the tube has passed its replacement time. We recorded a dataset using six different sensors (three accelerometers, one gyroscope, one magnetometer, and one microphone) using several cassettes (three new units and three units with expired life span). The recording was done at the highest possible frequency (100–6667 Hz, different for each sensor) and then downsampled several times to obtain frequencies as low as 12 Hz. This dataset is now publicly available. We trained 939 different models, which were the result of combining all different sensors as inputs but the microphone, and four basic architectures of recurrent neural network: One or two layers of either gated recurrent unit or long short-term memory with different number of nodes per layer (from 2 to 64). Among all trained models, we selected the ten best performing networks interms of both accuracy and complexity. All of them reached an F1 score of 0.99 or 1 with holdout cross-validation. Those models were deployed on four different edge AI devices. For all combinations of model and edge AI devices we obtained metrics of memory size (from 0.3% to 160.6% RAM, and from 0.9% to 21.3% flash), inference time (from 0.39 to 1463.91 ms), and average consumption (from 0.15 to 5.30 mA). Nine out of ten models were proven viable for deployment. We concluded that the four models based on magnetometer data were significantly better in terms of consumption and inference time. To the best of our knowledge, the use of magnetometer data is a very uncommon approach to failure detection inpredictive maintenance applications, and this is probably the first time it has been used for peristaltic pump aging detection, so our results are very promising for future applications. Also, since most trained models use little resources, we have proved that our approach is perfectly compatible with running other communication and control algorithms on the same device, which is ideal for easy integration and scalability in industrial systems. Some limitations for real deployment include facing environmental factors (noise) and long-term monitoring, so wealso proposed a protocol that should reduce the impact of those factors by taking measurements in a controlled way.Artículo Exploring Virtual Reality-Induced Anxiety in Iatrophobia: A Pilot Study for Future Exposure Therapy(IEEE Access, 2025) Revelo Aguilar, Fabian; Miró Amarante, María Lourdes; Gómez Rodríguez, Francisco de Asís; Arquitectura y Tecnología de Computadores; Ministerio de Ciencia e Innovación (MICIN). España; TEP108: Robótica y Tecnología de ComputadoresThis pilot study explores the feasibility of using Virtual Reality (VR) to simulate medically related environments that elicit anxiety responses in individuals with iatrophobia—a specific phobia characterized by an intense fear of medical professionals and procedures. Rather than providing a therapeutic intervention, the aim is to validate the capacity of VR-based scenarios to induce physiological and emotional reactions associated with medical anxiety, thereby laying the groundwork for future therapeutic applications. Ten participants—five with self-reported iatrophobia and five without—were exposed to a series of VR scenarios simulating clinical settings, including a waiting room, a medical consultation, and a diagnostic procedure. The study was conducted at the Ecuadorian Institute of Social Security (IESS), Ambato Hospital, Ecuador. Physiological responses, including heart rate and electrodermal activity, were measured and analyzed using statistical methods. The results demonstrate significant differences between the experimental and control groups, with individuals with Iatrophobia exhibiting heightened anxiety responses in VR environments. Furthermore, correlation analysis reveals a strong positive association between heart rate and electrodermal response, indicating the reliability of these physiological indicators in assessing anxiety levels. The study also discusses the implications of these findings for phobia treatment and highlights future research directions, including the integration of advanced VR technologies and exploring VR’s applicability in treating other specific phobias and anxiety disorders. These findings support the use of VR for eliciting controlled emotional responses in medical contexts, which may inform the design of future exposure-based interventions for iatrophobia and other medical-related phobias.Artículo Characterization of a Spiking Convolutional Processor for FPGA(MDPI, 2026) Curra Sosa, Dagnier Antonio; Gómez Rodríguez, Francisco de Asís; Linares Barranco, Alejandro; Arquitectura y Tecnología de Computadores; TEP108: Robótica y Tecnología de ComputadoresIn event-based neuromorphic processing, computer vision finds an efficient alternative capable of optimizing computational and energy resources, inspired by the dynamics of biological neural systems. In the development of real-time processing systems, it is crucial to visually represent the information captured by sensors and to explore its content with precision. Thus, machine learning models are implemented with the capability of being deployed on hardware devices with limited capabilities, depending on the intended purpose, ensuring savings in computational resources. The aim of this work was to evaluate the limits of the implemented neuron model, leaky-integrate and fire (LIF), for fitting convolutional layers of a neural network. To this end, the characteristics of the LIF neuron model used are summarized, as well as the details of its implementation in a hardware design, using configurable parameters. The experimental phase considered two convolution approaches to compare performance, Matlab R2022a software and a spiking convolutional processor for an FPGA, using sample recordings from the MNIST-DVS dataset and Sobel kernels for edge detection. The results reflect that the number of spikes generated by both approaches is very similar and their distribution by frame addresses is directly proportional.Artículo Práctica de desarrollo de un dispositivo de accesibilidad controlado mediante extremidades distales superiores basado en la plataforma Leap Motion(Actas de las Jenui, 2023) Ayuso Martínez, Álvaro; Casanueva Morato, Daniel; Marrón Esquivel, José Manuel; Durán López, Lourdes; Domínguez Morales, Juan Pedro; Arquitectura y Tecnología de Computadores; Ministerio de Educación, Cultura y Deporte (MECD). España; TEP108: Robótica y Tecnología de ComputadoresEste artículo presenta una práctica de laboratorio impartida en el contexto de la asignatura Sistemas de Rehabilitación y Ayuda a la Discapacidad, la cual se imparte como optativa en el Grado en Ingeniería de la Salud– Mención en Ingeniería Biomédica. El objetivo principal de dicha práctica es la de adquirir la capacidad de desarrollar un dispositivo enfocado a la accesibilidad, el cual permita controlar el ratón del ordenador únicamente mediante gestos realizados con las manos. Los dispositivos y herramientas empleados para dicho fin son el hardware Leap Motion, que recoge los movimientos de las manos y los dedos gracias a los sensores de los que se compone, junto con el entorno de desarrollo Visual Studio, en el que se desarrolla una aplicación de escritorio mediante Windows Forms, .NET y C#. El proceso de desarrollo está guiado y documentado, aportando al alumno todo un entorno base sobre el que construir e ir aprendiendo mientras se avanza en el desarrollo. El proyecto a desarrollar por el alumno abarca competencias clave propias del grado en el que se lleva a cabo, incluyendo la resolución de problemas de carácter multidisciplinar, además de la programación orientada al desarrollo de dispositivos asistenciales.Artículo Towards the automation of sports scouting using artificial intelligence(Elsevier, 2026-07-15) Canas Moreno, Salvador; Cerezuela Escudero, Elena; Ríos Navarro, José Antonio; Arquitectura y Tecnología de Computadores; TEP108: Robótica y Tecnología de ComputadoresIn the realms of professional and semi-professional sports across various major leagues, the role of a scouter, scout, or talent scout is pivotal. This individual attends games to analyze and collect comprehensive data about the events unfolding during the match. Traditionally, scouters rely on scouting software where they input match data, which then generates extensive statistics, conclusions, and recommendations. These insights are subsequently utilized by sports clubs for purposes such as player recruitment and devising strategies against specific rivals. This research introduces a novel line of inquiry, harnessing AI/ML (Artificial Intelligence/Machine Learning) techniques, predominantly convolutional neural networks, to automate the collection of data from physical sports events. This includes tracking the movement of the ball, the positioning of players, the arm used for hitting the ball, and more. The objective is to advance current sports scouting systems, which predominantly depend on manual data collection, towards a more automated, accurate, and efficient methodology. Utilizing nine tennis match videos from YouTube covering three different court surfaces (hard court, grass court, and clay court), this study has achieved high effectiveness in detecting players (99.3%), their body joints (100%), the tennis ball (94.13%), the segments of the tennis court ( ~100%), and identifying the type of stroke (forehand or backhand) (100%). Moreover, it successfully extracts detailed statistics, such as the number of points played, stroke effectiveness, and efficiency, all categorized by specific court areas, culminating in the creation of a heat map. This advancement not only streamlines the scouting process but also offers richer, data-driven insights into player performance and game dynamics.Artículo Characterization of a Spiking Convolutional Processor for FPGA(MDPI, 2026-03-12) Curra Sosa, Dagnier Antonio; Gómez Rodríguez, Francisco de Asís; Linares Barranco, Alejandro; Arquitectura y Tecnología de Computadores; Junta de Andalucía; TEP108: Robótica y Tecnología de ComputadoresIn event-based neuromorphic processing, computer vision finds an efficient alternative capable of optimizing computational and energy resources, inspired by the dynamics of biological neural systems. In the development of real-time processing systems, it is crucial to visually represent the information captured by sensors and to explore its content with precision. Thus, machine learning models are implemented with the capability of being deployed on hardware devices with limited capabilities, depending on the intended purpose, ensuring savings in computational resources. The aim of this work was to evaluate the limits of the implemented neuron model, leaky-integrate and fire (LIF), for fitting convolutional layers of a neural network. To this end, the characteristics of the LIF neuron model used are summarized, as well as the details of its implementation in a hardware design, using configurable parameters. The experimental phase considered two convolution approaches to compare performance, Matlab R2022a software and a spiking convolutional processor for an FPGA, using sample recordings from the MNIST-DVS dataset and Sobel kernels for edge detection. The results reflect that the number of spikes generated by both approaches is very similar and their distribution by frame addresses is directly proportional.Artículo Neuromorphic hardware based on memristive nanodevices for seizure detection and recovery(IOP Publishing, 2026-02-11) Díez-De-los-Ríos, Iván; Farsani, Javad; Ricci, Saverio; Bridarolli, Davide; Camuñas Mesa, Luis Alejandro; Subramaniyam, Narayan; Tanskanen, Jarno; Hyttinen, Jari; Ielmini, Daniele; Serrano Gotarredona, María Teresa; Linares Barranco, Bernabé; Arquitectura y Tecnología de Computadores; Instituto de Microelectrónica de Sevilla (IMSE-CNM)During the last decades, neuromorphic engineers have developed specific hardware designed to build efficient computing systems inspired by the structure of the human brain. The emergence of nanoscale memristors provided these systems with a new component which can approximately emulate the behavior of synaptic connections, improving the capability to implement in-situ learning algorithms like spike-timing-dependent plasticity. Meanwhile, neuro-inspired biomimetic platforms have been developed to directly interface with biological neurons, allowing to record and process neural signals like local field potentials (LFP). Combining both technologies, it would be possible to implant intracraneal electroencephalography electrodes with a neuromorphic chip which could sense signals from epileptic tissues and provide stimulation to prevent seizures in a closed-loop setup. In this work, we use a neuromorphic hardware platform with memristors to process LFP activity generated by an artificial neural mass model (ANMM) of the hippocampal loop implemented on a microcontroller for real-time operation, showing that the memristor system can learn correlations between neurons to detect seizures and eventually prevent them. This closed-loop ANMM-memristor crossbar interaction demonstration paves the way for trying a similar setup, replacing the ANMM with biological epileptic tissues.Artículo BAM-SLDK: biologically inspired attention mechanism with spiking learnable delayed kernel synapses(IOP Publishing, 2025-06-13) Chacón Falcón, Mario; Patiño Saucedo, Alberto; Camuñas Mesa, Luis Alejandro; Serrano Gotarredona, María Teresa; Linares Barranco, Bernabé; Arquitectura y Tecnología de Computadores; Instituto de Microelectrónica de Sevilla (IMSE-CNM); Ministerio para la Transformación Digital y de la Función Pública; European Commission (EC); Ministerio de Ciencia, Innovación y Universidades (MICIU). EspañaSpiking neural networks are emerging as an alternative neural network model due to their biological plausibility, energy efficiency, and built-in ability to learn from temporal dynamics. However, in order to effectively process data with rich spatial and temporal dependencies, the usual static projections (feedforward and recurrent) among layers of spiking neurons fail to represent all the information needed. Inspired by how synaptic delays affect the learning process in biological neurons, in this paper, we propose a biologically inspired attention mechanism based on spiking convolutions with learnable delayed kernel synapses. The proposed model increases temporal learning ability, attending simultaneously to spatial and temporal dynamics with few parameters required. More precisely, our main technical contributions are: (1) we add kernels to the temporal dimension to enlarge the receptive field of the convolution; (2) we time kernels activations to mimic multiple delayed times; and (3) we introduce three different pruning techniques to optimize the number of delays and parameters used. Experiments show that our method surpasses conventional spiking convolutional modules and achieves state-of-the-art results. When pruning, we show that, for some datasets or pruning techniques, removing up to 80% of the initially trained delays results in minimal performance loss, effectively reducing memory consumption and parameters required. To the best of our knowledge, this is the first time that learnable delayed synapses have been included in spiking convolutional layers for neuromorphic datasets classification, unlocking a new biologically inspired attention mechanism and achieving superior performance on high temporal demanding tasks.