Data mining framework for fatty liver disease classification in ultrasound: a hybrid feature extraction paradigm

PURPOSE: Fatty liver disease (FLD) is an increasing prevalent disease that can be reversed if detected early. Ultrasound is the safest and ubiquitous method for identifying FLD. Since expert sonographers are required to accurately interpret the liver ultrasound images, lack of the same will result in interobserver variability. For more objective interpretation, high accuracy, and quick second opinions, computer aided diagnostic (CAD) techniques may be exploited. The purpose of this work is to develop one such CAD technique for accurate classification of normal livers and abnormal livers affected by FLD. METHODS: In this paper, the authors present a CAD technique (called Symtosis) that uses a novel combination of significant features based on the texture, wavelet transform, and higher order spectra of the liver ultrasound images in various supervised learning-based classifiers in order to determine parameters that classify normal and FLD-affected abnormal livers. RESULTS: On evaluating the proposed technique on a database of 58 abnormal and 42 normal liver ultrasound images, the authors were able to achieve a high classification accuracy of 93.3% using the decision tree classifier. CONCLUSIONS: This high accuracy added to the completely automated classification procedure makes the authors' proposed technique highly suitable for clinical deployment and usage.

Sistema de visão para percepção e navegação de um UAV Quadrotor

Mestrado em Engenharia Electrotécnica e de Computadores

Harvesting dynamic aspects from a real rational map : the bulb of period 5

This journal provides immediate open access to its content on the principle that making research freely available to the public supports a greater global exchange of knowledge.

A loucura e o cinema: representações cinematográficas de personalidade limite

Dissertação apresentada à Escola Superior de Comunicação Social como parte dos requisitos para obtenção de grau de mestre em Audiovisual e Multimédia.

Reabilitação de edifícios: enquadramento e estudo da reabilitação num grupo empresarial

Dissertação para obtenção do grau de Mestre em Engenharia Civil na Área de Especialização em Edificações

Mapping non-suicidal self-injury in adolescence: Development and confirmatory factor analysis of the impulse, self-harm and sucidal ideation questionnaire for adolescents (ISSIQ-A)

Non-suicidal self-injury (NSSI) is the deliberate, self-inflicted destruction of body tissue without suicidal intent and an important clinical phenomenon. Rates of NSSI appear to be disproportionately high in adolescents and young adults, and is a risk factor for suicidal ideation and behavior. The present study reports the psychometric properties of the Impulse, Self-harm and Suicide Ideation Questionnaire for Adolescents (ISSIQ-A), a measure designed to comprehensively assess the impulsivity, NSSI behaviors and suicide ideation. An additional module of this questionnaire assesses the functions of NSSI. Results of Confirmatory Factor Analysis (CFA) of the scale on 1722 youths showed items' suitability and confirmed a model of four different dimensions (Impulse, Self-harm, Risk-behavior and Suicide ideation) with good fit and validity. Further analysis showed that youth׳s engagement in self-harm may exert two different functions: to create or alleviate emotional states, and to influence social relationships. Our findings contribute to research and assessment on non-suicidal self-injury, suggesting that the ISSIQ-A is a valid and reliable measure to assess impulse, self-harm and suicidal thoughts, in adolescence.

Leis de potência em sistemas naturais e artificiais

A Lei de Potência é uma particularidade de um sistema não linear, revelando um sistema complexo próximo da auto-organização. Algumas características de sistemas naturais e artificiais, tais como dimensão populacional das cidades, valor dos rendimentos pessoais, frequência de ocorrência de palavras em textos e magnitude de sismos, seguem distribuições do tipo Lei de Potência. Estas distribuições indicam que pequenas ocorrências são muito comuns e grandes ocorrências são raras, podendo porém verificar-se com razoável probabilidade. A finalidade deste trabalho visa a identificação de fenómenos associados às Leis de Potência. Mostra-se o comportamento típico destes fenómenos, com os dados retirados dos vários casos de estudo e com a ajuda de uma meta-análise. As Leis de Potência em sistemas naturais e artificiais apresentam uma proximidade a um padrão, quando os valores são normalizados (frequências relativas) para dar origem a um meta-gráfico.

Indexação e pesquisa de informação com base em ontologias interligadas

Tecnologias da Web Semântica como RDF, OWL e SPARQL sofreram nos últimos anos um forte crescimento e aceitação. Projectos como a DBPedia e Open Street Map começam a evidenciar o verdadeiro potencial da Linked Open Data. No entanto os motores de pesquisa semânticos ainda estão atrasados neste crescendo de tecnologias semânticas. As soluções disponíveis baseiam-se mais em recursos de processamento de linguagem natural. Ferramentas poderosas da Web Semântica como ontologias, motores de inferência e linguagens de pesquisa semântica não são ainda comuns. Adicionalmente a esta realidade, existem certas dificuldades na implementação de um Motor de Pesquisa Semântico. Conforme demonstrado nesta dissertação, é necessária uma arquitectura federada de forma a aproveitar todo o potencial da Linked Open Data. No entanto um sistema federado nesse ambiente apresenta problemas de performance que devem ser resolvidos através de cooperação entre fontes de dados. O standard actual de linguagem de pesquisa na Web Semântica, o SPARQL, não oferece um mecanismo para cooperação entre fontes de dados. Esta dissertação propõe uma arquitectura federada que contém mecanismos que permitem cooperação entre fontes de dados. Aborda o problema da performance propondo um índice gerido de forma centralizada assim como mapeamentos entre os modelos de dados de cada fonte de dados. A arquitectura proposta é modular, permitindo um crescimento de repositórios e funcionalidades simples e de forma descentralizada, à semelhança da Linked Open Data e da própria World Wide Web. Esta arquitectura trabalha com pesquisas por termos em linguagem natural e também com inquéritos formais em linguagem SPARQL. No entanto os repositórios considerados contêm apenas dados em formato RDF. Esta dissertação baseia-se em múltiplas ontologias partilhadas e interligadas.

Gold electrode modified by self-assembled monolayers of thiols to determine DNA sequences hybridization

The process of immobilization of biological molecules is one of the most important steps in the construction of a biosensor. In the case of DNA, the way it exposes its bases can result in electrochemical signals to acceptable levels. The use of self-assembled monolayer that allows a connection to the gold thiol group and DNA binding to an aldehydic ligand resulted in the possibility of determining DNA hybridization. Immobilized single strand of DNA (ssDNA) from calf thymus pre-formed from alkanethiol film was formed by incubating a solution of 2-aminoethanothiol (Cys) followed by glutaraldehyde (Glu). Cyclic voltammetry (CV) was used to characterize the self-assembled monolayer on the gold electrode and, also, to study the immobilization of ssDNA probe and hybridization with the complementary sequence (target ssDNA). The ssDNA probe presents a well-defined oxidation peak at +0.158 V. When the hybridization occurs, this peak disappears which confirms the efficacy of the annealing and the DNA double helix performing without the presence of electroactive indicators. The use of SAM resulted in a stable immobilization of the ssDNA probe, enabling the hybridization detection without labels. This study represents a promising approach for molecular biosensor with sensible and reproducible results.

Self-assembly in chains, rings, and branches: a single component system with two critical points

Agências financiadoras: FCT - PEstOE/FIS/UI0618/2011; PTDC/FIS/098254/2008 ERC-PATCHYCOLLOIDS e MIUR-PRIN

An Evaluation of Local Feature Combiners for Robot Visual Localization

In the last decade, local image features have been widely used in robot visual localization. To assess image similarity, a strategy exploiting these features compares raw descriptors extracted from the current image to those in the models of places. This paper addresses the ensuing step in this process, where a combining function must be used to aggregate results and assign each place a score. Casting the problem in the multiple classifier systems framework, we compare several candidate combiners with respect to their performance in the visual localization task. A deeper insight into the potential of the sum and product combiners is provided by testing two extensions of these algebraic rules: threshold and weighted modifications. In addition, a voting method, previously used in robot visual localization, is assessed. All combiners are tested on a visual localization task, carried out on a public dataset. It is experimentally demonstrated that the sum rule extensions globally achieve the best performance. The voting method, whilst competitive to the algebraic rules in their standard form, is shown to be outperformed by both their modified versions.

Implementação das medidas de autoproteção em edifícios escolares

Mestrado em Segurança e Higiene no Trabalho

Gestão de comportamentos sociais adequados à sala de aula no 1.º ciclo do ensino básico

Relatório de Estágio apresentado à Escola Superior de Educação de Lisboa para obtenção de grau de mestre em Ensino do 1.º e 2.º Ciclo do Ensino Básico

Feature selection for clustering categorical data with an embedded modelling approach

Research on the problem of feature selection for clustering continues to develop. This is a challenging task, mainly due to the absence of class labels to guide the search for relevant features. Categorical feature selection for clustering has rarely been addressed in the literature, with most of the proposed approaches having focused on numerical data. In this work, we propose an approach to simultaneously cluster categorical data and select a subset of relevant features. Our approach is based on a modification of a finite mixture model (of multinomial distributions), where a set of latent variables indicate the relevance of each feature. To estimate the model parameters, we implement a variant of the expectation-maximization algorithm that simultaneously selects the subset of relevant features, using a minimum message length criterion. The proposed approach compares favourably with two baseline methods: a filter based on an entropy measure and a wrapper based on mutual information. The results obtained on synthetic data illustrate the ability of the proposed expectation-maximization method to recover ground truth. An application to real data, referred to official statistics, shows its usefulness.

East of Suez and the imaginary tangles of space and self

Drawing on postcolonial studies and the theorization on imperial gothic, this paper centres on three texts: The Hosts of the Lord (1900) by Flora Annie Steel; East of Suez (1901) by Alice Perrin, and The Way of an Eagle (1912)by Ethel Dell. These three texts highlight in different ways the discursive mediation of the Other and its destabilizing effects on the identity of the European-minded colonizer, thus foregrounding the multifarious nature of the British imaginative engagement with India. In this context, it is particularly relevant to examine the political and ideological implications of representing anywhere East of Suez as a locus of primitivism and chaos vis-à-vis the colonizer’s ambivalent reactions. Thus we seek to demonstrate the power of two distinct practices or modes of representation – namely, the power of a metaphorical discourse versus metonymic discourse- within the proces of constructing the East for a vast Western readership.