Diferenciação entre cisto simples e hemangioma hepático utilizando seqüência de ressonância magnética ponderada em T2 com técnica gradiente-eco (B-FFE)

OBJETIVO: Estabelecer o valor das seqüências ponderadas em T2 para diferenciar cistos simples de hemangiomas hepáticos. MATERIAIS E MÉTODOS: Estudo prospectivo, observacional, transversal e duplo-cego em 52 pacientes com 91 lesões hepáticas (34 cistos simples e 57 hemangiomas) submetidos a ressonância magnética de abdome. A análise conjunta de todas as seqüências realizadas foi considerada o padrão-ouro. Dois observadores independentes avaliaram, subjetivamente, as seqüências TSE com TE longo e B-FFE, procurando diferenciar cistos de hemangiomas. Foram calculadas a eficácia das seqüências e a concordância interobservador e intra-observador por meio do teste kappa (κ) (p < 0,05*). RESULTADOS: As dimensões dos cistos variaram entre 0,5 e 6,5 cm (média de 1,89 cm) e as dos hemangiomas, entre 0,8 e 11 cm (média de 2,62 cm). A concordância entre a avaliação da seqüência com TE longo e o padrão-ouro foi insignificante (κ: 0,00-0,10). A concordância entre a avaliação da seqüência B-FFE e o padrão-ouro variou de substancial (κ: 0,62-0,71) a quase perfeita (κ: 0,86) para ambos os examinadores. A concordância interobservador e intra-observador para a seqüência B-FFE variou entre substancial (κ: 0,62-0,70) e quase perfeita (κ: 0,85-0,91). CONCLUSÃO: A técnica B-FFE apresenta eficácia e reprodutibilidade elevadas na diferenciação de cistos e hemangiomas.

Generalization transitions in Hidden-Layer neural networks for third-order feature discrimination

Stochastic learning processes for a specific feature detector are studied. This technique is applied to nonsmooth multilayer neural networks requested to perform a discrimination task of order 3 based on the ssT-block¿ssC-block problem. Our system proves to be capable of achieving perfect generalization, after presenting finite numbers of examples, by undergoing a phase transition. The corresponding annealed theory, which involves the Ising model under external field, shows good agreement with Monte Carlo simulations.

Resurrecting Disney: Tracing Walt Disney‘s ever-present spirit in feature animated films of the Michael Eisner era (1984-2004)

El treball Ressuscitant a Disney: Rastrejant el sempre present esperit de Walt Disney en els llargmetratges animats de l'era Michael Eisner (1984-2004) pretén definir i analitzar les característiques, tant respecte al procés creatiu com en la definició de contingut, integrades en els clàssics originals de Disney per, a continuació, demostrar que aquestes van ser recuperades i implementades de nou després de la mort de Walt Disney -amb lleus adaptacions- per donar lloc a una segona edat d'or de l'animació

Complex patterns of global spread in invasive insects: eco-evolutionary and management consequences

The advent of simple and affordable tools for molecular identification of novel insect invaders and assessment of population diversity has changed the face of invasion biology in recent years. The widespread application of these tools has brought with it an emerging understanding that patterns in biogeography, introduction history and subsequent movement and spread of many invasive alien insects are far more complex than previously thought. We reviewed the literature and found that for a number of invasive insects, there is strong and growing evidence that multiple introductions, complex global movement, and population admixture in the invaded range are commonplace. Additionally, historical paradigms related to species and strain identities and origins of common invaders are in many cases being challenged. This has major consequences for our understanding of basic biology and ecology of invasive insects and impacts quarantine, management and biocontrol programs. In addition, we found that founder effects rarely limit fitness in invasive insects and may benefit populations (by purging harmful alleles or increasing additive genetic variance). Also, while phenotypic plasticity appears important post-establishment, genetic diversity in invasive insects is often higher than expected and increases over time via multiple introductions. Further, connectivity among disjunct regions of global invasive ranges is generally far higher than expected and is often asymmetric, with some populations contributing disproportionately to global spread. We argue that the role of connectivity in driving the ecology and evolution of introduced species with multiple invasive ranges has been historically underestimated and that such species are often best understood in a global context.

Shared feature extraction for nearest neighbor face recognition

In this paper, we propose a new supervised linearfeature extraction technique for multiclass classification problemsthat is specially suited to the nearest neighbor classifier (NN).The problem of finding the optimal linear projection matrix isdefined as a classification problem and the Adaboost algorithmis used to compute it in an iterative way. This strategy allowsthe introduction of a multitask learning (MTL) criterion in themethod and results in a solution that makes no assumptions aboutthe data distribution and that is specially appropriated to solvethe small sample size problem. The performance of the methodis illustrated by an application to the face recognition problem.The experiments show that the representation obtained followingthe multitask approach improves the classic feature extractionalgorithms when using the NN classifier, especially when we havea few examples from each class

A Sparse Bayesian Approach for Joint Feature Selection and Classifier Learning

Peer-reviewed

Feature-based matching of underwater images

This work investigates performance of recent feature-based matching techniques when applied to registration of underwater images. Matching methods are tested versus different contrast enhancing pre-processing of images. As a result of the performed experiments for various dominating in images underwater artifacts and present deformation, the outperforming preprocessing, detection and description methods are proposed

Feature selection for automatic analysis of emotional response based on nonlinear speech modeling suitable for diagnosis of Alzheimer׳s disease

Alzheimer׳s disease (AD) is the most common type of dementia among the elderly. This work is part of a larger study that aims to identify novel technologies and biomarkers or features for the early detection of AD and its degree of severity. The diagnosis is made by analyzing several biomarkers and conducting a variety of tests (although only a post-mortem examination of the patients’ brain tissue is considered to provide definitive confirmation). Non-invasive intelligent diagnosis techniques would be a very valuable diagnostic aid. This paper concerns the Automatic Analysis of Emotional Response (AAER) in spontaneous speech based on classical and new emotional speech features: Emotional Temperature (ET) and fractal dimension (FD). This is a pre-clinical study aiming to validate tests and biomarkers for future diagnostic use. The method has the great advantage of being non-invasive, low cost, and without any side effects. The AAER shows very promising results for the definition of features useful in the early diagnosis of AD.

Python y OpenCV aplicados a un caso de estudio real

Este trabajo se centra en el uso del lenguaje Python y la librería OpenCV de visión por computador para el seguimiento de crustáceos marinos en condiciones experimentales y determinar su comportamiento en un entorno social.

Plug-in de procesado visual (OpenCV) en OpenDomo OS

Este proyecto consiste en el diseño y desarrollo de un plug-in que permita usar el sistema de procesado de imagen OpenCV desde el sistema operativo OpenDomo OS.

A hybrid feature selection approach for the early diagnosis of Alzheimer's disease

Objective. Recently, significant advances have been made in the early diagnosis of Alzheimer’s disease from EEG. However, choosing suitable measures is a challenging task. Among other measures, frequency Relative Power and loss of complexity have been used with promising results. In the present study we investigate the early diagnosis of AD using synchrony measures and frequency Relative Power on EEG signals, examining the changes found in different frequency ranges. Approach. We first explore the use of a single feature for computing the classification rate, looking for the best frequency range. Then, we present a multiple feature classification system that outperforms all previous results using a feature selection strategy. These two approaches are tested in two different databases, one containing MCI and healthy subjects (patients age: 71.9 ± 10.2, healthy subjects age: 71.7 ± 8.3), and the other containing Mild AD and healthy subjects (patients age: 77.6 ± 10.0; healthy subjects age: 69.4± 11.5). Main Results. Using a single feature to compute classification rates we achieve a performance of 78.33% for the MCI data set and of 97.56 % for Mild AD. Results are clearly improved using the multiple feature classification, where a classification rate of 95% is found for the MCI data set using 11 features, and 100% for the Mild AD data set using 4 features. Significance. The new features selection method described in this work may be a reliable tool that could help to design a realistic system that does not require prior knowledge of a patient's status. With that aim, we explore the standardization of features for MCI and Mild AD data sets with promising results.

Pabellón Eco 2014

Bajo el concepto de "Cuando el muro dejó de ser sólo un muro", se propone la construcción de un muro que se va transformado en el mobiliario del patio del Museo Experimental el Eco para el Pabellón del Eco 2014.Esta proyecto finalista dirige las posibles actividades al centro del espacio vacío; y por otro lado plantea cubrir la estela y el muro de colindancia del museo con un material reflejante para multiplicar el horizonte perceptible desde el patio.

De parallelismo membrorum Hebraeis usitato

Arkit: 1 arkintunnukseton lehti, A-D4 E2.

Comparison of Local Feature Detectors and Descriptors for Visual Object Categorization

Local features are used in many computer vision tasks including visual object categorization, content-based image retrieval and object recognition to mention a few. Local features are points, blobs or regions in images that are extracted using a local feature detector. To make use of extracted local features the localized interest points are described using a local feature descriptor. A descriptor histogram vector is a compact representation of an image and can be used for searching and matching images in databases. In this thesis the performance of local feature detectors and descriptors is evaluated for object class detection task. Features are extracted from image samples belonging to several object classes. Matching features are then searched using random image pairs of a same class. The goal of this thesis is to find out what are the best detector and descriptor methods for such task in terms of detector repeatability and descriptor matching rate.