Examinar
Envíos recientes
Publicación Deep Robust Hashing Using Self-Distillation for Remote Sensing Image Retrieval(IEEE, 2024) han,lirong; Paoletti, Mercedes Eugenia; Moreno Álvarez, Sergio; Haut, Juan Mario; Plaza, Antonio; https://orcid.org/0000-0002-8613-7037; https://orcid.org/0000-0003-1030-3729; https://orcid.org/0000-0001-6701-961X; https://orcid.org/0000-0002-9613-1659This paper presents a novel self-distillation based deep robust hash for fast remote sensing (RS) image retrieval. Specifically, there are two primary processes in our proposed model: teacher learning (TL) and student learning (SL). Two transformed samples are produced from one sample image through nuanced and signalized transformations, respectively. Transformed samples are fed into both the TL and the SL flows. To reduce discrepancies in the processed samples and guarantee a consistent hash code, the parameters are shared by the two modules during the training stage. Then, a resilient module is employed to enhance the image features in order to ensure more dependable hash code production. Lastly, a three-component loss function is developed to train the entire model. Comprehensive experiments are conducted on two common RS datasets: UCMerced and AID. The experimental results validate that the proposed method has competitive performance against other RS image hashing methods.Publicación Correlation-Aware Averaging for Federated Learning in Remote Sensing Data Classification(IEEE, 2024) Moreno Álvarez, Sergio; han, lirong; Paoletti, Mercedes Eugenia; Haut, Juan Mario; https://orcid.org/0000-0002-8613-7037; https://orcid.org/0000-0003-1030-3729; https://orcid.org/0000-0001-6701-961XThe increasing volume of remote sensing (RS) data offers substantial benefits for the extraction and interpretation of features from these scenes. Indeed, the detection of distinguishing features among captured materials and objects is crucial for classification purposes, such as in environmental monitoring applications. In these algorithms, the classes characterized by lower correlation often exhibit more distinct and discernible features, facilitating their differentiation in a straightforward manner. Nevertheless, the rise of Big Data provides a wide range of data acquired through multiple decentralized devices, where its susceptibility to be shared among various users or clients presents challenges in safeguarding privacy. Meanwhile, global features for similar classes are required to be learned for generalization purposes in the classification process. To address this, federated learning (FL) emerges as a privacy efficient decentralized solution. Firstly, in such scenarios, proprietary data is held by individual clients participating in the training of a global model. Secondly, clients may encounter challenges in identifying features that are more distinguishable within the data distributions of other clients. In this study, in order to handle these challenges, a novel methodology is proposed that considers the least correlated classes (LCCs) included in each client data distribution. This strategy exploits the distinctive features between classes, thereby enhancing performance and generalization ability in a secure and private environment.Publicación Deep Attention-Driven HSI Scene Classification Based on Inverted Dot-Product(Institute of Electrical and Electronics Engineers Inc., 2022) Paoletti, Mercedes Eugenia; Tao, Xuanwen; han, lirong; Wu, Zhaoyue; Moreno Álvarez, Sergio; Haut, Juan M.; https://orcid.org/0000-0003-1030-3729; https://orcid.org/0000-0003-1093-0079; https://orcid.org/0000-0002-8613-7037; https://orcid.org/0000-0002-6797-2440; https://orcid.org/0000-0001-6701-961XCapsule networks have been a breakthrough in the field of automatic image analysis, opening a new frontier in the art for image classification. Nevertheless, these models were initially designed for RGB images and naively applying these techniques to remote sensing hyperspectral images (HSI) may lead to sub-optimal behaviour, blowing up the number of parameters needed to train the model or not correctly modeling the spectral relations between the different layers of the scene. To overcome this drawback, this work implements a new capsule-based architecture with attention mechanism to improve the HSI data processing. The attention mechanism is applied during the concurrent iterative routing procedure through an inverted dot-product attentionPublicación Optimizing Distributed Deep Learning in Heterogeneous Computing Platforms for Remote Sensing Data Classification(IEEE, 2022) Moreno Álvarez, Sergio; Paoletti, Mercedes Eugenia; Rico Gallego, Juan Antonio; Cavallaro, Gabriele; Haut, Juan M.; https://orcid.org/0000-0003-1030-3729; https://orcid.org/0000-0002-4264-7473; https://orcid.org/0000-0002-3239-9904; https://orcid.org/0000-0001-6701-961XApplications from Remote Sensing (RS) unveiled unique challenges to Deep Learning (DL) due to the high volume and complexity of their data. On the one hand, deep neural network architectures have the capability to automatically ex-tract informative features from RS data. On the other hand, these models have massive amounts of tunable parameters, re-quiring high computational capabilities. Distributed DL with data parallelism on High-Performance Computing (HPC) sys-tems have proved necessary in dealing with the demands of DL models. Nevertheless, a single HPC system can be al-ready highly heterogeneous and include different computing resources with uneven processing power. In this context, a standard data parallelism strategy does not partition the data efficiently according to the available computing resources. This paper proposes an alternative approach to compute the gradient, which guarantees that the contribution to the gradi-ent calculation is proportional to the processing speed of each DL model's replica. The experimental results are obtained in a heterogeneous HPC system with RS data and demon-strate that the proposed approach provides a significant training speed up and gain in the global accuracy compared to one of the state-of-the-art distributed DL framework.Publicación El Real Cortijo de San Isidro de Aranjuez: de utopía ilustrada a poblado de colonización(CICEES, 2013-06-12) Antigüedad Del Castillo-Olivares, Mª Dolores; Martínez Pino, Joaquínel real Cortijo de san Isidro en la proximidad del real sitio y villa de aranjuez es un ejemplo de la evolución del urbanismo rural desde la utopía de Carlos III a las políticas agrarias del franquismo. el real Cortijo se convierte en poblado de colonización siguiendo los criterios del Instituto nacional de Colonización, el organismo encargado por el gobierno del general franco de colonizar las zonas regables para incrementar la producción agraria. en éste como en otros casos, el proyecto urbano del poblado se superpuso al trazado primitivo y conserva los edificios de mayor valor arquitectónico. las viviendas nuevas para los colonos y la distribución del conjunto respondieron a la aplicación de unos modelos de vivienda mínima y de equipamientos civiles que sirvieran al ideal de vida rural que el Instituto aplicó en todas las zonas en las que tuvo competencias.Publicación El abrigo de Cueva Blanca: un yacimiento de la transición al Neolítico antiguo en el campo de Hellín (Albacete)(UNIARQ WAPS, 2015) Mingo Álvarez, Alberto; Barba Rey, Jesús; Mas Cornellá, Martí; López Precioso, Francisco Javier; Benito Calvo, Alfonso; Uzquiano Ollero, Paloma; Yravedra Sainz de los Terreros, José; Galante Pérez, José Antonio; Cubas Morera, Miriam; Solís Delgado, Mónica; Avezuela, Bárbara; Martín Lerma, Ignacio; Gutiérrez Sáez, Carmen; Bellardi, Matteo; García, Soledad; Palacios, Estrella; Hernández, Javier; Urigüen López de Sandaliano, Natalia; Domínguez, JesúsEl abrigo de Cueva Blanca se localiza en el término municipal de Hellín (Albacete), en una zona con relieve serrano de altura baja, y alberga un nivel de ocupación de la transición al Neolítico antiguo. En este trabajo se presentan los resultados preliminares procedentes del análisis de los restos arqueológicos, y de los estudios geomorfológicos, antracológicos, traceológicos y de malacofauna. Su situación próxima a la estación rupestre con arte levantino de Minateda y la constatación de pinturas también prehistóricas en una pared rocosa del propio abrigo de Cueva Blanca, sin duda, incrementan la excepcionalidad de este yacimientoPublicación Paleobiodiversity versus biodiversity. Animal representations in Tamanart and Azguer rock art (Marocco)(Pan African Archeological Association, 2018) Bernáldez Sánchez, Eloísa; García Viñas, Esteban; Mas Cornellá, Martí; Lemjidi, Abdelkhalek; Solís Delgado, Mónica; Maura Mijares, Rafael; Oumouss, AhmedPublicación Evaluación de Rendimiento del Entrenamiento Distribuido de Redes Neuronales Profundas en Plataformas Heterogéneas(Universidad de Extremadura, 2019) Moreno Álvarez, Sergio; Paoletti, Mercedes Eugenia; Haut, Juan Mario; Rico Gallego, Juan Antonio; Plaza, Javier; Díaz Martín, Juan Carlos; Vega Rodriguez, Miguel ángel; Plaza Miguel, Antonio J.; https://orcid.org/0000-0003-1030-3729; https://orcid.org/0000-0001-6701-961X; https://orcid.org/0000-0002-4264-7473; https://orcid.org/0000-0002-8908-1606; https://orcid.org/0000-0002-8435-3844Asynchronous stochastic gradient descent es una tecnica de optimizacion comunmente utilizada en el entrenamiento distribuido de redes neuronales profundas. En distribuciones basadas en particionamiento de datos, se entrena una replica del modelo en cada unidad de procesamiento de la plataforma, utilizando conjuntos de muestras denominados mini-batches. Este es un proceso iterativo en el que al nal de cada mini-batch, las replicas combinan los gradientes calculados para actualizar su copia local de los parametros. Sin embargo, al utilizar asincronismo, las diferencias en el tiempo de entrenamiento por iteracion entre replicas provocan la aparicion del staleness, esto es, las replicas progresan a diferente velocidad y en el entrenamiento de cada replica se utiliza una vers on no actualizada de los parametros. Un alto gradde staleness tiene un impacto negativo en la precision del modelo resultante. Ademas, las plataformas de computacion de alto rendimiento suelen ser heterogeneas, compuestas por CPUs y GPUs de diferentes capacidades, lo que agrava el problema de staleness. En este trabajo, se propone aplicar t ecnicas de equilibrio de carga computacional, bien conocidas en el campo de la Computaci on de Altas Prestaciones, al entrenamiento distribuido de modelos profundos. A cada r eplica se asignar a un n umero de mini-batches en proporci on a su velocidad relativa. Los resultados experimentales obtenidos en una plataforma hete-rog enea muestran que, si bien la precisi on se mantiene constante, el rendimiento del entrenamiento aumenta considerablemente, o desde otro punto de vista, en el mismo tiempo de entrenamiento, se alcanza una mayor precisi on en las estimaciones del modelo. Discutimos las causas de tal incremento en el rendimiento y proponemos los pr oximos pasos para futuras investigaciones.Publicación Estimación Automática del Coste de Comunicación de Aplicaciones Paralelas en Plataformas Heterogéneas(Universidad Extremadura, 2018) Moreno Álvarez, Sergio; Rico Gallego, Juan A.; Díaz Martín, Juan Carlos; https://orcid.org/0000-0002-4264-7473; https://orcid.org/0000-0002-8435-3844Optimizar el tiempo de ejecución de aplicaciones paralelas en plataformas heterogéneas de altas prestaciones es un problema complejo. Estas aplicaciones cient´ıficas normalmente se componen de kernels que implementan algoritmos como la multiplicación de matrices, ecuaciones en derivadas parciales o Transformadas de Fourier. Los kernels son ejecutados por los procesos desplegados en los diferentes recursos de cómputo de una plataforma, por ejemplo, en procesadores multi-core o aceleradores (GPUs, Xeon PHIs, etc.). El volumen de datos del kernel se distribuye entre los procesos de forma proporcional a su capacidad de cómputo, de forma que se equilibra la carga computacional global. Este equilibrado de carga no homogéneo tiene un impacto importante en el coste de las comunicaciones. La optimización del coste de las comunicaciones de éstas aplicaciones se aborda habitualmente mediante pruebas exhaustivas en la plataforma destino. Sin embargo, estas pruebas consumen recursos y tiempo, y a menudo se basan en la extrapolación de los resultados obtenidos con la ejecución de una versión reducida de la aplicación en la plataforma. Los Modelos Anal´ıticos de Rendimiento de Comunicaciones ofrecen una alternativa factible y prometedora en este sentido. Estos modelos representan el coste de las comunicaciones de un kernel en una plataforma heterogénea, ofreciendo una estimación precisa de su tiempo de comunicación de forma no invasiva, esto es, sin utilizar recursos de cómputo HPC en la estimación. Este trabajo contribuye ofreciendo una herramienta de estimación que permite representar y evaluar expresiones de coste de comunicaciones que siguen el modelo t- Lop. Adem´as, permite incluir el c´alculo de coste de las comunicaciones de forma autom´atica en algoritmos de particionamiento y optimización de comunicaciones. En este documento se proporcionan ejemplos tanto de uso b´asico como avanzado. Se incluyen tres casos de ejemplo de modelado de comunicaciones en kernels representativos utilizando la herramienta: la solución de una ecuación diferencial utilizando la técnica de elementos finitos, un algoritmo paralelo de multiplicación de matrices densas, y una simulación N-Body. Estos kernels utilizan diferentes patrones de comunicación y particionamiento del espacio de datos.Publicación Promoción de la Igualdad de trato y la no discriminación(Laborum ediciones, 2024) Nieto Rojas, PatriciaPublicación A Rule-Learning Approach for Detecting Faults in Highly Configurable Software Systems from Uniform Random Samples(2022) Heradio Gil, Rubén; Fernández Amoros, David José; Ruiz Parrado, Victoria; Cobo, Manuel J.; https://orcid.org/0000-0003-2993-7705; http://orcid.org/ 0000-0001-6575-803XSoftware systems tend to become more and more configurable to satisfy the demands of their increasingly varied customers. Exhaustively testing the correctness of highly configurable software is infeasible in most cases because the space of possible configurations is typically colossal. This paper proposes addressing this challenge by (i) working with a representative sample of the configurations, i.e., a ``uniform'' random sample, and (ii) processing the results of testing the sample with a rule induction system that extracts the faults that cause the tests to fail. The paper (i) gives a concrete implementation of the approach, (ii) compares the performance of the rule learning algorithms AQ, CN2, LEM2, PART, and RIPPER, and (iii) provides empirical evidence supporting our procedurePublicación Circuit Testing Based on Fuzzy Sampling with BDD Bases(University of Hawaiʻi at Mānoa, 2023) Pinilla, Elena; Fernández Amoros, David José; Heradio Gil, RubénFuzzy testing of integrated circuits is an established technique. Current approaches generate an approximately uniform random sample from a translation of the circuit to Boolean logic. These approaches have serious scalability issues, which become more pressing with the ever-increasing size of circuits. We propose using a base of binary decision diagrams to sample the translations as a soft computing approach. Uniformity is guaranteed by design and scalability is greatly improved. We test our approach against five other state-of-the-art tools and find our tool to outperform all of them, both in terms of performance and scalability.Publicación Pragmatic Random Sampling of the Linux Kernel: Enhancing the Randomness and Correctness of the conf Tool(Association for Computing Machinery, New York, 2024-09-02) Fernández Amoros, David José; Heradio Gil, Rubén; Horcas Aguilera, Jose Miguel; Galindo, José A.; Benavides, David; Fuentes, Lidia; https://orcid.org/0000-0003-3758-0195; https://orcid.org/0000-0002-5677-7156; https://orcid.org/0000-0002-8449-3273; https://orcid.org/0000-0001-9293-9784The configuration space of some systems is so large that it cannot be computed. This is the case with the Linux Kernel, which provides almost 19,000 configurable options described across more than 1,600 files in the Kconfig language. As a result, many analyses of the Kernel rely on sampling its configuration space (e.g., debugging compilation errors, predicting configuration performance, finding the configuration that optimizes specific performance metrics, etc.). The Kernel can be sampled pragmatically, with its built-in tool conf, or idealistically, translating the Kconfig files into logic formulas. The pros of the idealistic approach are that it provides statistical guarantees for the sampled configurations, but the cons are that it sets out many challenging problems that have not been solved yet, such as scalability issues. This paper introduces a new version of conf called randconfig+, which incorporates a series of improvements that increase the randomness and correctness of pragmatic sampling and also help validate the Boolean translation required for the idealistic approach. randconfig+ has been tested on 20,000 configurations generated for 10 different Kernel versions from 2003 to the present day. The experimental results show that randconfig+ is compatible with all tested Kernel versions, guarantees the correctness of the generated configurations, and increases conf’s randomness for numeric and string options.Publicación An Object-Oriented Library for Process Control Simulations in MATLAB(ELSEVIER, 2017) Rodríguez, Carlos; Guinaldo Losada, María; Aranda Escolástico, Ernesto; Guzmán, José L.This paper presents a library of MATLAB classes developed to provide a framework to allow performing easy and scalable process control simulations. The proposed object-oriented tool features the basic components of a control loop including: processes, controllers, sensors, actuators and connection links. The simulator can be configured to carry out simulations with continuous and/or discrete elements, and/or include event-triggered capabilities in a straightforward manner. The benefits of the proposed library are shown with the rapid development and simulation of a quadruple-tank system that is controlled by means of a PI controller.Publicación Stability of output event-based control systems through quadratic trigger functions(IEEE, 2015-10) Aranda Escolástico, Ernesto; Guinaldo Losada, María; Dormido Canto, SebastiánThe design of event-based controllers for systems with unknown states is investigated in this paper. The case of general quadratic triggering conditions that depend on the estimated state given by a Luenberger observer is studied. Novel frameworks are proposed for continuous and periodic event-based control providing criteria for asymptotic stability with the form of Linear Matrix Inequalities (LMIs). The frameworks are tested in simulation through a challenging system, such as the double rotary inverted pendulum.Publicación Underwater coverage with a mobile robot of limited control authority(IEEE, 2018) Aranda Escolástico, Ernesto; Cortes, Jorge; Guinaldo Losada, María; Dormido Canto, Sebastián; https://orcid.org/0000-0001-9582-5184This work considers the coverage of underwater areas with a mobile robot with constrained control and communication capabilities. While underwater, the robot can control its depth but it is subject to flow in the other directions. While on the surface, it can move (essentially) freely. The aim of the work is the coverage of the areas with the minimum waste of resources. For that, we propose a two-part algorithm, where one part is a genetic algorithm and the other part is an algorithm based on Netwton's method. Numerical simulations are provided to illustrate the efficiency of the algorithm.Publicación Distributed targeted distance-based formation control for mechanical systems(IEEE Xplore, 2020-07-20) Aranda Escolástico, Ernesto; Colombo, Leonardo J.; Guinaldo Losada, MaríaThis paper studies the problem of distributed targeted distance-based formation control for mechanical systems. The problem consists on finding a distributed control law such that if each agent observes a convex set as a targeted set, and also the relative position of their nearest neighbors, then the agents must achieve the desired formation in these sets while its velocities are driven to zero. We study the problem for agents with a time-delay communication in the measurements of the relative positions and where the motion of each agent is determined by a Lagrangian function. Simulation are given to validate the theoretical result.Publicación Fuzzy logic vs analytic controllers on a non-linear system(World Scientific, 2014) Aranda Escolástico, Ernesto; Guinaldo Losada, María; Dormido Canto, Sebastián; Santos, M.In this paper, an intelligent control of the rotary inverted pendulum by fuzzy logic is presented. Specifically, the design consists of a Takagi-Sugeno fuzzy model to approximate the non-linear system to a succession of points where a linear system is described. A feedback gain is obtained that allows the stabilization of the inverted pendulum in a higher attractor than in the case of analytic Full State Feedback controller or Linear Quadratic Regulator.Publicación A novel approach for periodic event-triggering based on general quadratic functions(IEEE, 2015) Aranda Escolástico, Ernesto; Guinaldo Losada, María; Dormido Canto, SebastiánThis paper is concerned with periodic event-triggered control, which avoids the continuous monitoring of the state of the system while reducing the number of control updates. A new form of quadratic event-triggering condition is proposed to enlarge the inter-event times. The asymptotic stability criteria is analyzed by means of Lyapunov-Krasovskii functionals and the stability condition is expressed in terms of linear matrix inequalities. Simulation and experimental results are given to show the effectiveness of the proposed method.Publicación Periodic Event-Triggered Swing-Up Control of the Inverted Pendulum(Springer, 2016) Aranda Escolástico, Ernesto; Gordillo, F.; Guinaldo Losada, María; Dormido Canto, Sebastián; Garrido, Paulo; Soares, Filomena; Moreira, António PauloIn this paper, a novel strategy for swinging up an inverted pendulum is proposed. The strategy combines an energy-based control law with an event triggering condition to minimize transmissions, protect actuators and save energy. In addition, the strategy is periodic event-triggered, which provides two main advantages: An analytical way to determine a priori the sampling period to guarantee the appropriate behavior and an easy implementation in real prototypes.