ECG Biometrics: A Template Selection Approach

Electrocardiography (ECG) biometrics is emerging as a viable biometric trait. Recent developments at the sensor level have shown the feasibility of performing signal acquisition at the fingers and hand palms, using one-lead sensor technology and dry electrodes. These new locations lead to ECG signals with lower signal to noise ratio and more prone to noise artifacts; the heart rate variability is another of the major challenges of this biometric trait. In this paper we propose a novel approach to ECG biometrics, with the purpose of reducing the computational complexity and increasing the robustness of the recognition process enabling the fusion of information across sessions. Our approach is based on clustering, grouping individual heartbeats based on their morphology. We study several methods to perform automatic template selection and account for variations observed in a person's biometric data. This approach allows the identification of different template groupings, taking into account the heart rate variability, and the removal of outliers due to noise artifacts. Experimental evaluation on real world data demonstrates the advantages of our approach.

Global localization with non-quantized local image features

In the field of appearance-based robot localization, the mainstream approach uses a quantized representation of local image features. An alternative strategy is the exploitation of raw feature descriptors, thus avoiding approximations due to quantization. In this work, the quantized and non-quantized representations are compared with respect to their discriminativity, in the context of the robot global localization problem. Having demonstrated the advantages of the non-quantized representation, the paper proposes mechanisms to reduce the computational burden this approach would carry, when applied in its simplest form. This reduction is achieved through a hierarchical strategy which gradually discards candidate locations and by exploring two simplifying assumptions about the training data. The potential of the non-quantized representation is exploited by resorting to the entropy-discriminativity relation. The idea behind this approach is that the non-quantized representation facilitates the assessment of the distinctiveness of features, through the entropy measure. Building on this finding, the robustness of the localization system is enhanced by modulating the importance of features according to the entropy measure. Experimental results support the effectiveness of this approach, as well as the validity of the proposed computation reduction methods.

An unsupervised approach to feature discretization and selection

Many learning problems require handling high dimensional datasets with a relatively small number of instances. Learning algorithms are thus confronted with the curse of dimensionality, and need to address it in order to be effective. Examples of these types of data include the bag-of-words representation in text classification problems and gene expression data for tumor detection/classification. Usually, among the high number of features characterizing the instances, many may be irrelevant (or even detrimental) for the learning tasks. It is thus clear that there is a need for adequate techniques for feature representation, reduction, and selection, to improve both the classification accuracy and the memory requirements. In this paper, we propose combined unsupervised feature discretization and feature selection techniques, suitable for medium and high-dimensional datasets. The experimental results on several standard datasets, with both sparse and dense features, show the efficiency of the proposed techniques as well as improvements over previous related techniques.

Visualization of clusters in geo-referenced data using three-dimensional self-organizing maps

Dissertação apresentada como requisito parcial para obtenção do grau de Mestre em Estatística e Gestão de Informação

The Neogene of the Lower Tagus Basin (Portugal)

Revista Española de Paleontologia 19 (2), 229-242

Influence of attenuation correction in the MPI image reconstructed by the ‘Evolution for Cardiac’™

The acquisition of a Myocardial Perfusion image (MPI) is of great importance for the diagnosis of the coronary artery disease, since it allows to evaluate which areas of the heart aren’t being properly perfused, in rest and stress situations. This exam is greatly influenced by photon attenuation which creates image artifacts and affects quantification. The acquisition of a Computerized Tomography (CT) image makes it possible to get an atomic images which can be used to perform high-quality attenuation corrections of the radiopharmaceutical distribution, in the MPI image. Studies show that by using hybrid imaging to perform diagnosis of the coronary artery disease, there is an increase on the specificity when evaluating the perfusion of the right coronary artery (RCA). Using an iterative algorithm with a resolution recovery software for the reconstruction, which balances the image quality, the administered activity and the scanning time, we aim to evaluate the influence of attenuation correction on the MPI image and the outcome in perfusion quantification and imaging quality.

Performing PET/CT studies: do they create anxiety?

Introduction: Anxiety is a common problem in primary care and specialty medical settings. Treating an anxious patient takes more time and adds stress to staff. Unrecognised anxiety may lead to exam repetition, image artifacts and hinder the scan performance. Reducing patient anxiety at the onset is probably the most useful means of minimizing artifactual FDG uptake, both fat brown and skeletal muscle uptake, as well patient movement and claustrophobia. The aim of the study was to examine the effects of information giving on the anxiety levels of patients who are to undergo a PET/CT and whether the patient experience is enhanced with the creation of a guideline. Methodology: Two hundred and thirty two patients were given two questionnaires before and after the procedure to determine their prior knowledge, concerns, expectations and experiences about the study. Verbal information was given by one of the technologists after the completion of the first questionnaire. Results: Our results show that the main causes of anxiety in patients who are having a PET/CT is the fear of the procedure itself, and fear of the results. The patients who suffered from greater anxiety were those who were scanned during the initial stage of a disease. No significant differences were found between the anxiety levels pre procedural and post procedural. Findings with regard to satisfaction show us that the amount of information given before the procedure does not change the anxiety levels and therefore, does not influence patient satisfaction. Conclusions: The performance of a PET/CT scan is an important and statistically generator of anxiety. PET/CT patients are often poorly informed and present with a range of anxieties that may ultimately affect examination quality. The creation of a guideline may reduce the stress of not knowing what will happen, the anxiety created and may increase their satisfaction in the experience of having a PET/CT scan.

Guia (Algarve), gisement de vertébrés quaternaires à caractère saisonnier

A vertebrate (Mammals, Reptiles, Amphibians) fauna From Guia (Algarve) is described. The site is the only one so far known in the «Faro-Quarteira sands». The fauna is upper Pleistocene in age (may even be younger). Its stratigraphical position shows it is younger than levels in the same unit that yielded mousterian/languedocian stone artifacts. A post Riss-Wurm age is admitted. The mammalian fauna nearly exclusively comprises small mammalremains; except for a few ones, only young individuals are represented. This unusual situation, coupled with data from the study of the Squamata and even more of the Amphibia, indicates that Guia locality corresponds to sedimentation in temporary, seasonal ponds originated in depressions in this sandy area during Winter and/or early Springtime.

Paleolítico médio em Galapos (Arrábida)

Quartz (and silex) lithic artifacts collected at Galapos (Creiro), in the southern part of lhe Serra da Arrábida, Portugal, are described. These artifacts are characteristic of the Middle Paleolithic (Mousterian). This new locality reinforces lhe evidences for an important human occupation of this region at those times, as previously shown by the study of the Figueira Brava cave.

Terminology and knowledge engineering conference. New frontiers in the constructive symbiosis of terminology and knowledge engineering

To meet the increasing demands of the complex inter-organizational processes and the demand for continuous innovation and internationalization, it is evident that new forms of organisation are being adopted, fostering more intensive collaboration processes and sharing of resources, in what can be called collaborative networks (Camarinha-Matos, 2006:03). Information and knowledge are crucial resources in collaborative networks, being their management fundamental processes to optimize. Knowledge organisation and collaboration systems are thus important instruments for the success of collaborative networks of organisations having been researched in the last decade in the areas of computer science, information science, management sciences, terminology and linguistics. Nevertheless, research in this area didn’t give much attention to multilingual contexts of collaboration, which pose specific and challenging problems. It is then clear that access to and representation of knowledge will happen more and more on a multilingual setting which implies the overcoming of difficulties inherent to the presence of multiple languages, through the use of processes like localization of ontologies. Although localization, like other processes that involve multilingualism, is a rather well-developed practice and its methodologies and tools fruitfully employed by the language industry in the development and adaptation of multilingual content, it has not yet been sufficiently explored as an element of support to the development of knowledge representations - in particular ontologies - expressed in more than one language. Multilingual knowledge representation is then an open research area calling for cross-contributions from knowledge engineering, terminology, ontology engineering, cognitive sciences, computational linguistics, natural language processing, and management sciences. This workshop joined researchers interested in multilingual knowledge representation, in a multidisciplinary environment to debate the possibilities of cross-fertilization between knowledge engineering, terminology, ontology engineering, cognitive sciences, computational linguistics, natural language processing, and management sciences applied to contexts where multilingualism continuously creates new and demanding challenges to current knowledge representation methods and techniques. In this workshop six papers dealing with different approaches to multilingual knowledge representation are presented, most of them describing tools, approaches and results obtained in the development of ongoing projects. In the first case, Andrés Domínguez Burgos, Koen Kerremansa and Rita Temmerman present a software module that is part of a workbench for terminological and ontological mining, Termontospider, a wiki crawler that aims at optimally traverse Wikipedia in search of domainspecific texts for extracting terminological and ontological information. The crawler is part of a tool suite for automatically developing multilingual termontological databases, i.e. ontologicallyunderpinned multilingual terminological databases. In this paper the authors describe the basic principles behind the crawler and summarized the research setting in which the tool is currently tested. In the second paper, Fumiko Kano presents a work comparing four feature-based similarity measures derived from cognitive sciences. The purpose of the comparative analysis presented by the author is to verify the potentially most effective model that can be applied for mapping independent ontologies in a culturally influenced domain. For that, datasets based on standardized pre-defined feature dimensions and values, which are obtainable from the UNESCO Institute for Statistics (UIS) have been used for the comparative analysis of the similarity measures. The purpose of the comparison is to verify the similarity measures based on the objectively developed datasets. According to the author the results demonstrate that the Bayesian Model of Generalization provides for the most effective cognitive model for identifying the most similar corresponding concepts existing for a targeted socio-cultural community. In another presentation, Thierry Declerck, Hans-Ulrich Krieger and Dagmar Gromann present an ongoing work and propose an approach to automatic extraction of information from multilingual financial Web resources, to provide candidate terms for building ontology elements or instances of ontology concepts. The authors present a complementary approach to the direct localization/translation of ontology labels, by acquiring terminologies through the access and harvesting of multilingual Web presences of structured information providers in the field of finance, leading to both the detection of candidate terms in various multilingual sources in the financial domain that can be used not only as labels of ontology classes and properties but also for the possible generation of (multilingual) domain ontologies themselves. In the next paper, Manuel Silva, António Lucas Soares and Rute Costa claim that despite the availability of tools, resources and techniques aimed at the construction of ontological artifacts, developing a shared conceptualization of a given reality still raises questions about the principles and methods that support the initial phases of conceptualization. These questions become, according to the authors, more complex when the conceptualization occurs in a multilingual setting. To tackle these issues the authors present a collaborative platform – conceptME - where terminological and knowledge representation processes support domain experts throughout a conceptualization framework, allowing the inclusion of multilingual data as a way to promote knowledge sharing and enhance conceptualization and support a multilingual ontology specification. In another presentation Frieda Steurs and Hendrik J. Kockaert present us TermWise, a large project dealing with legal terminology and phraseology for the Belgian public services, i.e. the translation office of the ministry of justice, a project which aims at developing an advanced tool including expert knowledge in the algorithms that extract specialized language from textual data (legal documents) and whose outcome is a knowledge database including Dutch/French equivalents for legal concepts, enriched with the phraseology related to the terms under discussion. Finally, Deborah Grbac, Luca Losito, Andrea Sada and Paolo Sirito report on the preliminary results of a pilot project currently ongoing at UCSC Central Library, where they propose to adapt to subject librarians, employed in large and multilingual Academic Institutions, the model used by translators working within European Union Institutions. The authors are using User Experience (UX) Analysis in order to provide subject librarians with a visual support, by means of “ontology tables” depicting conceptual linking and connections of words with concepts presented according to their semantic and linguistic meaning. The organizers hope that the selection of papers presented here will be of interest to a broad audience, and will be a starting point for further discussion and cooperation.

Saúde mental, qualidade de vida e acesso aos cuidados de saúde na comunidade brasileira de Lisboa

Introdução: A utilização de serviços de saúde tem implicações importantes para o estado de saúde das populações. As políticas de imigração adoptadas nos países de destino têm influência no estado de saúde das comunidades imigrantes. Políticas que limitam o acesso de imigrantes aos cuidados de saúde aumentarão a vulnerabilidade e os riscos na saúde. Apesar da imigração promover uma série de rupturas na vida do sujeito, migrar, por si só, não pode ser considerado como factor de risco no âmbito da saúde e da saúde mental. O peso dos determinantes socioeconómicos tem ganho relevância no estudo das migrações, estado de saúde geral e mental. Isto porque, em geral, os imigrantes estão em situação mais precária do que a população autóctone. O estatuto socioeconómico baixo, as condições precárias de habitação e de trabalho, a falta de suporte social e a irregularidade jurídica são indicadores de risco acrescido para a saúde mental. Neste sentido é um desafio de monta os governos estabelecerem medidas sustentadas e, simultaneamente, integradoras dos imigrantes. Em Portugal, considera-se que há escassez de estudos relacionados com a área das migrações e da saúde.Metodologia: Estudo exploratório, descritivo e transversal. A finalidade foi a de identificar o estado de saúde, saúde mental e qualidade de vida da comunidade brasileira residente em Lisboa e o seu acesso aos serviços de saúde. Este estudo teve como principais objectivos a caracterização sociodemográfica, a identificação de variáveis inerentes ao processo migratório, a identificação da auto-apreciação do estado de saúde, a caracterização do acesso aos cuidados de saúde, a identificação do grupo em provável sofrimento psicológico, a comparação entre os resultados dos imigrantes juridicamente regulares e irregulares e a comparação entre a população imigrante e a população portuguesa. Inicialmente, foi prevista a utilização da técnica de amostragem de propagação geométrica ou snowball, pois a amostra tornar-se-ia maior à medida que os próprios inquiridos identificam outros potenciais respondentes. Ao longo do estudo, a metodologia inicial mostrou-se insuficiente para estabelecer uma amostra mais representativa dos imigrantes juridicamente irregulares. Para este feito, foi utilizada a metodologia de amostragem por conveniência e o local escolhido para a recolha da amostra foi o Consulado do Brasil em Lisboa. O instrumento de recolha de dados empregue baseou-se no questionário utilizado no 4º Inquérito Nacional de Saúde. O MHI-5 (Mental Health Index 5) é um instrumento de saúde mental e é parte integrante do inquérito, sendo recomendado pela Organização Mundial de Saúde. Consta de cinco itens relativos à saúde mental e os resultados são classificados através de um indicador que mede a existência de provável sofrimento psicológico. Foram incluídos no estudo 213 brasileiros. De seguida, procedeu-se ao tratamento estatístico dos dados. Resultados: A população inquirida é jovem, a maior parte tem entre 18 e 44 anos. As mulheres representam mais de metade da amostra. A taxa de actividade é elevada e a taxa de desemprego é similar à nacional. A inserção laboral prioritária é nos segmentos pouco qualificados ou de semi-qualificação. Aproximadamente um terço dos inquiridos afirmou ser beneficiário do Sistema Nacional de Saúde. A autoapreciação do estado de saúde é classificada como bastante positiva, assim como a qualidade de vida. O provável sofrimento psicológico, definido no MHI-5 pelo ponto de corte no score 52, atinge 23,3% dos participantes. Os homens apresentam melhores resultados do que as mulheres. Além disso, para os valores mais baixos no MHI-5 foram encontradas relações com as longas jornadas de trabalho e o diagnóstico de doença crónica.Discussão: O presente estudo apresenta limitações em relação à dimensão da amostra e à provável existência de enviesamento pela ausência de aleatorização. Apesar da legislação portuguesa garantir o acesso aos serviços de saúde e garantir a equidade no caso dos imigrantes que fazem descontos para a Segurança Social, apenas um terço referiu ser beneficiário do Sistema Nacional de Saúde. Este dado pode ser justificado por factores como o cumprimento da lei por alguns serviços e, também, pela falta de conhecimento da legislação e da forma de funcionamento do Serviço Nacional de Saúde por parte dos imigrantes. O facto das mulheres representarem o maior grupo em provável sofrimento psicológico é consistente com a literatura. As hipóteses levantadas para explicar este resultado podem ser agrupadas em: artefactos metodológicos, causalidade biológica e determinação social. Em relação ao instrumento, é possível que o MHI-5 se comporte de forma diferente no que diz respeito ao género.-------------------------------------------Introduction: The utilization of health services has important implications for the health state of the populations. The immigration policies adopted in the destiny countries are going to influence the health state of immigrant communities. Policies that limit the access of immigrants to health care are going to increase the vulnerability and the risk factor in health. Although immigration promotes several disruptive actions in ones life, migrating, on its own, cannot be considered as a risk factor for health and mental health. The preponderance of the socioeconomic factors has gained relevance in the study of migrations and also in the study of general health state and mental health. This happens because, in general, immigrants are in a more unfavorable situation compared with the destiny country population. The low socioeconomic status, the poor working and housing conditions, the lack of social support and the juridical irregularity are indicators of the incremented risk to mental health. Therefore, it is a major challenge for governments to find sustainable, and simultaneously, integrative measures for the immigrants. The studies related with the migrations and health in Portugal were considered to be few.Methods: It is an exploratory, descriptive and transversal study. The purpose is to identify the health state, mental health, quality of life and the access to health care of the Brazilian community resident in Lisbon. In addition, this study has as main goals the sociodemographic characterization, the variables identification inherent to the migrating process, the identification of the self-appreciation of health state, the characterization of the access to health care, the identification of the group in probable psychological suffer, the comparison between the results of regular and irregular immigrants and the comparison between the immigrant population and the Portuguese population. Initially it was predicted the utilization of the geometric propagation or “snowball”, as sampling technique, because the sample becomes larger as one answerer identify other potential answering persons. Along with the study, the methodology has shown insufficient to establish a more representative sample of the irregular immigrants. For this latter case, it was used a convenient sample methodology and the place chosen for the sample gathering was the “Consulate of Brazil in Lisbon”. The instrument was based in the questionnaire used in the “4th National Health Inquiry”. The MHI-5 (Mental Health Index 5) is a mental health instrument which is part of the enquiry and it is recommended by the World Health Organization. There are five items related to mental health and the results are classified through an indicator which measures the existence of a probable psychological suffer. It were included 213 Brazilian in the study. After, the statistical treatment of the data took place.Results: The answering population is young and the majority is between the 18 and 44 years of age. The women represent more than one half of the sample. The activity rate is high and the unemployment rate is similar to the national one. The priority labor insertion is in the few qualified or of semi-qualification segments. Approximately, one third of the answering people has stated to be beneficiary of the National Health System. The self-appreciation of the health state as well as the quality of life are classified as fairly positive ones. The probable psychological suffer, as defined in the MHI-5 through the cut point in the score below or equal to 52, reaches 23,3% of the sample population. Men show the better results than women. Further, for the lower values of MHI-5 it was found a relation with the long work periods and chronic disease diagnostic. Discussion: The present study evidences limitations in relation to the sample dimension and in relation to the existence of biases due to the lack of randomness. Although the Portuguese legislation guarantees the access to health services and the equality in the cases of the immigrants that do their Social Security discounts, only one third has mentioned to be beneficiary of the National Health System. This can be justified by several facts such as the non-fulfillment of law by some national services or the lack of knowledge of the legislation or the functioning process of the National Health System. Women representing the bigger group in probable psychological suffer has been coherent with the literature review. The hypothesis set to explain this result might be grouped in: methodological artifacts, biologic cause and social determination. In relation to the instrument used, it may be that MHI-5 behaves in a different way in respect to gender.

Feature Discretization with Relevance and Mutual Information Criteria

Feature discretization (FD) techniques often yield adequate and compact representations of the data, suitable for machine learning and pattern recognition problems. These representations usually decrease the training time, yielding higher classification accuracy while allowing for humans to better understand and visualize the data, as compared to the use of the original features. This paper proposes two new FD techniques. The first one is based on the well-known Linde-Buzo-Gray quantization algorithm, coupled with a relevance criterion, being able perform unsupervised, supervised, or semi-supervised discretization. The second technique works in supervised mode, being based on the maximization of the mutual information between each discrete feature and the class label. Our experimental results on standard benchmark datasets show that these techniques scale up to high-dimensional data, attaining in many cases better accuracy than existing unsupervised and supervised FD approaches, while using fewer discretization intervals.

Realidade Imersiva Aplicada a Espaços Culturais

Informação é o conceito genérico de tudo que possa representar, conhecimento ou comunicação. Trata-se de conhecimento registado de forma impressa ou digital, oral ou audiovisual, mas ainda pode ser registada em suporte físico. Desde o início da civilização que o Ser Humano tenta criar novas formas de transmitir informação, antes da invenção da forma escrita era utilizado o método do desenho para descrever a realidade, este método ao longo do tempo foi evoluindo, ganhando mais qualidade, pormenor e suportes mais evoluídos. Mas sempre com a mesma intenção, a de conseguir transmitir de forma mais direta e percetível informação a qualquer individuo. Dado isto, o Ser Humano sempre produziu arte e a foi preservando para mostrar aos vindouros. Neste processo, os museus em conjunto com espaços culturais e artísticos, foram assumindo um papel de relevo na sociedade. Mas inicialmente o objetivo principal dos museus era o de preservar e expor artefactos históricos e culturais. A grande evolução tecnológica dos últimos anos veio dotar o Ser Humano com formas de aceder à informação tão simples e diversificadas, que no passado eram completamente impensáveis e certamente que no futuro irão ser descobertas ainda mais formas de registar e propagar a informação. Assim o presente trabalho descreve a investigação realizada, através de uma recolha de bibliografia, levantamento do estado-da-arte, que pretende descobrir se a construção de visitas virtuais imersivas é uma boa forma para mostrar um espaço cultural ao público, que está cada vez mais exigente e disperso geograficamente. Além do levantamento são estudados alguns exemplos de visitas virtuais existentes, de modo a detetar boas praticas e formas mais usuais para a criação de uma visita. Finalmente foi descrito todo o processo desde a recolha de informação até à própria implementação, construção de um protótipo para apresentar ao utilizador o espaço de uma fundação, a do escultor José Rodrigues. Este protótipo tem por objetivo mostrar ao utilizador a fundação o mais aproximado do real possível.

Adaptive filtering for high quality HMM based speech synthesis

In this work an adaptive filtering scheme based on a dual Discrete Kalman Filtering (DKF) is proposed for Hidden Markov Model (HMM) based speech synthesis quality enhancement. The objective is to improve signal smoothness across HMMs and their related states and to reduce artifacts due to acoustic model's limitations. Both speech and artifacts are modelled by an autoregressive structure which provides an underlying time frame dependency and improves time-frequency resolution. Themodel parameters are arranged to obtain a combined state-space model and are also used to calculate instantaneous power spectral density estimates. The quality enhancement is performed by a dual discrete Kalman filter that simultaneously gives estimates for the models and the signals. The system's performance has been evaluated using mean opinion score tests and the proposed technique has led to improved results.

Initial dilemmas in IST research: design science and design research, a clarification of concepts

The inter-disciplinarity of information systems, applied discipline and activity of design, and the study from different paradigms perspectives explains the diversity of problems addressed. The context is broad and includes important issues beyond technology, as the application, use, effectiveness, efficiency and their organizational and social impacts. In design science, the research interest is in contributing to the improvement of the processes of the design activity itself. The relevance of research in design science is associated with the result obtained for the improvement of living conditions in organizational, inter-organizational and Society contexts. In the research whose results are artifacts, the adoption of design research as a process of research is crucial to ensure discipline, rigor and transparency. Based on a literature review, this paper clarifies the terms of design science and design research. This is the main motivation for presenting this paper, determinant for the phase in research in technologies and information systems which are the three research projects presented. As a result the three projects are discussed in relation to the concepts of design science and design research.