Buscador

Encontrado(s) 2107636 resultado(s)
Encontrada(s) 210764 página(s)

On Representation and Exploitation of Context Knowledge in a Harbor Surveillance Scenario

  • García, Jesús
  • Gómez Romero, Juan
  • Patricio Guisado, Miguel Ángel
  • Molina, José M.
  • Rogova, Gala
Proceedings of: 14th International Conference on Information Fusion (FUSION 2011) Chicago, Illinois, USA, 5-8 July 2011., Maritime surveillance involves gathering and integrating a large amount of heterogeneous information of variable quality to provide diverse decision makers with reliable knowledge about situations and threats. This requires information processing at all fusion levels while taking into account contextual information. Context is especially important for harbor surveillance, one of the most challenging maritime scenarios due to the high number of different vessel types, the coexistence of very diverse operations, the multiple agencies and countries involved, etc. Successful processing of both contextual and transient observed information requires a reusable representation of the harbor domain, as well as effective reasoning methods. This paper discusses an approach to designing a hybrid harbor surveillance system combining ontology-based context representation, deductive reasoning for detection of abnormal objects from their characteristics and behavior, and abductive reasoning under uncertainty., This research activity is supported in part by Projects CICYT TIN2008-06742-C02-02/TSI, CICYT TEC2008-06732-C02-02/TEC, CAM CONTEXTS (S2009/TIC-1485) and DPS2008-07029-C02-02.
Proyecto:


An innovative tool for intraoperative electron beam radiotherapy simulation and planning: description and initial evaluation by radiation oncologists

  • Pascau González Garzón, Javier
  • Santos Miranda, Juan Antonio
  • Calvo, Felipe A.
  • Bouché, Ana
  • Morillo, Virginia
  • González-San Segundo, Carmen
  • Ferrer, Carlos
  • López Tarjuelo, Juan
  • Desco Menéndez, Manuel
The lack of specific treatment planning tools limits the spread of Intraoperative Electron Radiation Therapy. An innovative simulation and planning tool is presented. Applicator positioning, isodose curves, and doseevolume histograms can be estimated for previously segmented regions to treat/protect. Evaluation by three radiation oncologists on 15 patients showed high parameter agreement in nine cases, demonstrating the possibilities in cases involving different anatomical locations, and identifying the importance of specialized surgical input in the preplanning process., Supported by grants PI08/90473, IPT 300000 2010 3, ARTEMIS S2009/DPI 1802(CAM), TEC2010 21619 C04 01, PI09/90568, ERD Funds., Publicado
Proyecto:


Epidermolysis bullosa simplex with mottled pigmentation: a family report and review

  • Echeverría García, Begoña
  • Vicente, Asunción
  • Hernández, Ángela
  • Mascaró, José M.
  • Colmenero, Isabel
  • Terrón, Ana
  • Escámez Toledano, María José
  • Río Nechaevsky, Marcela del
  • González Enseñat, María A.
  • Torrelo Fernández, Antonio
Epidermolysis bullosa simplex with mottled hyperpigmentation (EBS-MP) is an uncommon subtype of EBS. Its clinical features depend on the age of diagnosis, and clinical variations have been described even within family members. We present six cases from two unrelated Spanish families each with several affected members with EBS-MP and review the clinical and genetic findings in all reported patients. We highlight the changing clinical features of the disease throughout life.
Proyecto:


Aplicación de técnicas de aprendizaje máquina para la caracterización y clasificación de pacientes con trastorno obsesivo compulsivo

  • López Bautista, María
El siguiente Trabajo Fin de Grado se basa en el cada vez más habitual empleo de métodos de aprendizaje máquina con el fin de clasificar y caracterizar trastornos psiquiátricos. Concretamente, el sistema diseñado pretende acercarse al diagnóstico de TOC (‘Trastorno Obsesivo Compulsivo’) a través del análisis de imágenes de resonancia magnética (MRI). El sistema diseñado tiene como objetivo plantear un algoritmo capaz de diagnosticar pacientes con TOC y, principalmente, capaz de caracterizar la enfermedad, detectando de manera automática las regiones neuroanatómicas relacionadas con el trastorno. Para ello, se empleará una arquitectura modular creada a partir de dos premisas fundamentales. 1. Análisis por áreas funcionales y/o neuroanatómicas. Cada imagen de resonancia magnética se divide en, aproximadamente, una centena de subconjuntos compuestos por vóxeles asociados a un área funcional o región neuroanatómica del cerebro. Así pues, el objetivo es aplicar un clasificador que facilite la selección de los conjuntos de vóxeles relevantes para la detección de la enfermedad. 2. Caracterización y fusión de áreas funcionales. El sistema utilizará métodos de selección de características sobre las salidas de los clasificadores el objetivo de obtener una selección automática de las áreas relevantes para el diagnóstico de la patología que estamos tratando. Asimismo, el último paso será el estudio de la relación que tienen las áreas entre sí mediante el uso de clasificadores, tanto lineales como no lineales. Una vez desarrollado y aplicado el algoritmo, se aprovecharán los resultados tanto para comparar la clasificación de pacientes con los resultados previos obtenidos mediante métodos tradicionales [1], [2], como para analizar el patrón de áreas neuroanatómicas responsables del trastorno. -------------------------------------------------------, This work is based on increasingly common use of machine learning methods in order to classify and characterize psychiatric disorders. Specifically, the designed system tries to be able to diagnose OCD (Obsessive-Compulsive Disorder) though the MRI (Magnetic Resonance Imaging) analysis. The main system's goal is to construct an algorithm able to detect OCD patients and characterize the disease, detecting automatically neuroanatomical regions related to the disorder, supported on a modular arquitecture process with two fundamental principles. 1. Analysis of functional and/or neuroanatomical areas. Each MRI is divided into one hundred subsets composed of voxels associated to a functional area. Thus, the goal is to apply a classifier which facilitates the selection of the relevant voxels sets for the diagnosis of the disease. 2. Characterization and combination of functional areas. The system will use feature selection methods with the outputs of the first classifiers in order to get an automatic selection of the relevant areas for diagnosis of the pathology. The last step will use linear and no liner classifiers to analyze whether the different areas are interrelated. Having the algorithm developed, we will use the results to compare the classifications of patients with previous results got by traditional methods [1], [2], and to analyze the pattern of neuroanatomical areas responsible for the disorder., Ingeniería de Sistemas Audiovisuales
Proyecto:


Recessive dystrophic epidermolysis bullosa: the origin of the c.6527insC mutation in the Spanish population

  • Sánchez-Jimeno, C.
  • Cuadrado-Corrales, N.
  • Aller, E.
  • García Díez, Marta
  • Escámez Toledano, María José
  • Illera, Nuria
  • Trujillo-Tiebas, M.J.
  • Ayuso, C.
  • Millán, J.M.
  • Río Nechaevsky, Marcela del
This work was supported by grants from the Spanish Ministry of Science and Innovation (MICINN) (SAF2007-61019 and SAF 2010-16976), INTRA ⁄08 ⁄714.1 and INTRA ⁄09 ⁄758 from the Biomedical Network Research Centre on Rare Diseases (CIBERER) and S2010 ⁄BMD-2420 (CELLCAM) from Comunidad de Madrid.
Proyecto:


The regenerative potential of fibroblasts in a new diabetes-induced delayed humanised wound healing model

  • Martínez-Santamaría, L.
  • Conti, Claudio J.
  • Llames, Sara
  • García, Eva
  • Retamosa, Luisa
  • Holguín, Almudena
  • Illera, Nuria
  • Duarte, Blanca
  • Camblor, Lina
  • Llaneza, José M.
  • Jorcano, José L.
  • Larcher Laguzzi, Fernando
  • Meana, Álvaro
  • Escámez Toledano, María José
  • Río Nechaevsky, Marcela del
Cutaneous diabetic wounds greatly affect the quality of life of patients, causing a substantial economic impact on the healthcare system. The limited clinical success of conventional treatments is mainly attributed to the lack of knowledge of the pathogenic mechanisms related to chronic ulceration. Therefore, management of diabetic ulcers remains a challenging clinical issue. Within this context, reliable animal models that recapitulate situations of impaired wound healing have become essential. In this study, we established a new in vivo humanised model of delayed wound healing in a diabetic context that reproduces the main features of the human disease. Diabetes was induced by multiple low doses of streptozotocin in bioengineered human-skin-engrafted immunodeficient mice. The significant delay in wound closure exhibited in diabetic wounds was mainly attributed to alterations in the granulation tissue formation and resolution, involving defects in wound bed maturation, vascularisation, inflammatory response and collagen deposition. In the new model, a cell-based wound therapy consisting of the application of plasma-derived fibrin dermal scaffolds containing fibroblasts consistently improved the healing response by triggering granulation tissue maturation and further providing a suitable matrix for migrating keratinocytes during wound re-epithelialisation. The present preclinical wound healing model was able to shed light on the biological processes responsible for the improvement achieved, and these findings can be extended for designing new therapeutic approaches with clinical relevance., This work was supported by grants from the Science and Innovation Ministry of Spain (SAF2010-16976), from the European VI Framework Programme (LSHB-CT-512102), from Comunidad de Madrid (S2010/BMD-2420; CELLCAM) and from Fundacion Ramon Areces (CIVP16A1864).
Proyecto:


MIJ2K Optimization using evolutionary multiobjective optimization algorithms

  • Luis Bustamante, Álvaro
  • Molina, José M.
  • Patricio Guisado, Miguel Ángel
This paper deals with the multiobjective definition of video compression and its optimization. The optimization will be done using NSGA-II, a well-tested and highly accurate algorithm with a high convergence speed developed for solving multiobjective problems. Video compression is defined as a problem including two competing objectives. We try to find a set of optimal, so-called Pareto-optimal solutions, instead of a single optimal solution. The two competing objectives are quality and compression ratio maximization. The optimization will be achieved using a new patent pending codec, called MIJ2K, also outlined in this paper. Video will be compressed with the MIJ2K codec applied to some classical videos used for performance measurement, selected from the Xiph.org Foundation repository. The result of the optimization will be a set of near-optimal encoder parameters. We also present the convergence of NSGA-II with different encoder parameters and discuss the suitability of MOEAs as opposed to classical search-based techniques in this field., This work was supported in part by Projects CICYT TIN2008- 06742-C02-02/TSI, CICYT TEC2008-06732-C02-02/TEC, SINPROB, CAM MADRINET S-0505/TIC/0255 and DPS2008-07029-C02-02., publicado
Proyecto:


A behaviour-based control architecture for heterogeneous modular, multi-configurable, chained micro-robots

  • Brunete González, Alberto
  • Hernando, M.
  • Gambao, E.
  • Torres, José Emilio
This article presents a new control architecture designed for heterogeneous modular, multi-configurable, chained micro-robots. This architecture attempts to fill the gap that exists in heterogeneous modular robotics research, in which little work has been conducted compared to that in homogeneous modular robotics studies. The architecture proposes a three-layer structure with a behaviour-based, low-level embedded layer, a half-deliberative half-behaviour-based high layer for the central control, and a heterogeneous middle layer acting as a bridge between these two layers. This middle layer is very important because it allows the central control to treat all modules in the same manner, facilitating the control of the robot. A communication protocol and a module description language were also developed for the control architecture to facilitate communication and information flow between the heterogeneous modules and the central control. Owing to the heterogeneous behaviour of the architecture, the system can automatically reconfigure its actions to adapt to unpredicted events (such as actuator failure). Several behaviours (at low and high levels) are also presented here., The research leading to these results has received funding from RoboCity2030-II-CM (S2009/DPI-1559), funded by Programas de Actividades I+D en la Comunidad de Madrid and cofunded by Structural Funds os the EU, Publicado
Proyecto:


Clinical outcomes after the use of complete autologous oral mucosa equivalents: preliminary cases

  • Peña, Ignacio
  • Junquera, Luis Manuel
  • Llorente, Santiago
  • Villalaín, Lucas de
  • Vicente, Juan Carlos de
  • Llames, Sara
Objective. Previously, we reported how to obtain complete autologous oral mucosa equivalents (CAOMEs) composed of an autologous plasma scaffold and fibroblasts together with immature keratinocytes able to build an oral epithelium with a structure similar to that of the oral mucosa. In this study, we present the clinical outcomes after applying our CAOMEs as grafts. Study Design. Four patients who needed a CAOME to restore a defect of oral mucosa were selected. Two of the patients suffered from ankyloglossia, and the other 2 required a restoration of the keratinized gum of the alveolar rim. To assess the outcomes, the scale designed by Ewers et al. was used., Supported by a grant from Sanity Institute Carlos III (Spanish Government)
Proyecto:


Fuzzy region assignment for visual tracking

  • García, Jesús
  • Patricio Guisado, Miguel Ángel
  • Berlanga de Jesús, Antonio
  • Molina López, José Manuel
In this work we propose a new approach based on fuzzy concepts and heuristic reasoning to deal with the visual data association problem in real time, considering the particular conditions of the visual data segmented from images, and the integration of higher-level information in the tracking process such as trajectory smoothness, consistency of information, and protection against predictable interactions such as overlap/occlusion, etc. The objects' features are estimated from the segmented images using a Bayesian formulation, and the regions assigned to update the tracks are computed through a fuzzy system to integrate all the information. The algorithm is scalable, requiring linear computing resources with respect to the complexity of scenarios, and shows competitive performance with respect to other classical methods in which the number of evaluated alternatives grows exponentially with the number of objects., Research supported by projects CICYT TIN2008-06742-C02-02/TSI, CICYT TEC2008-06732-C02-02/TEC, SINPROB and CAM MADRINET S-0505/TIC/0255., publicado
Proyecto:


Buscador avanzado