Determining the number of clusters in categorical data

Cluster analysis for categorical data has been an active area of research. A well-known problem in this area is the determination of the number of clusters, which is unknown and must be inferred from the data. In order to estimate the number of clusters, one often resorts to information criteria, such as BIC (Bayesian information criterion), MML (minimum message length, proposed by Wallace and Boulton, 1968), and ICL (integrated classification likelihood). In this work, we adopt the approach developed by Figueiredo and Jain (2002) for clustering continuous data. They use an MML criterion to select the number of clusters and a variant of the EM algorithm to estimate the model parameters. This EM variant seamlessly integrates model estimation and selection in a single algorithm. For clustering categorical data, we assume a finite mixture of multinomial distributions and implement a new EM algorithm, following a previous version (Silvestre et al., 2008). Results obtained with synthetic datasets are encouraging. The main advantage of the proposed approach, when compared to the above referred criteria, is the speed of execution, which is especially relevant when dealing with large data sets.

Liderança virtuosa, comprometimento organizacional e desempenho individual

Num mundo hipercompetitivo, a afirmação da virtuosidade tem enfrentado consideráveis resistências, sendo mesmo considerada como sinónimo de fraqueza ou ingenuidade. Todavia, e perante evidências dos potenciais perigos do exercício da liderança desprovido de valores, ética e moralidade, elevam-se as vozes em defesa de uma liderança virtuosa, capaz de aportar contributos significativamente positivos às organizações e seus colaboradores. Partindo desta premissa, esta investigação teve como objetivo analisar, com base nas perceções dos liderados, o impacto da liderança virtuosa no comprometimento organizacional, assim como o contributo deste último no desempenho individual. Sustentados numa metodologia quantitativa, inquirimos, numa primeira fase, 113 liderados provenientes de organizações localizadas no território português, com vista a apurar quais as virtudes que mais valorizavam num líder. Os dados para o teste de hipóteses foram recolhidos através da aplicação de uma bateria de testes junto de 351 liderados, também a exercer funções em organizações a operar em Portugal. Os resultados sugerem que as perceções dos liderados em torno de três dimensões de virtuosidade da liderança (liderança baseada em valores, perseverança e maturidade) contribuem para o comprometimento organizacional, sobretudo nas suas vertentes afetiva e normativa e, que este último, por sua vez, é capaz de influenciar positivamente o desempenho individual.

Spatial analysis of leprosy incidence and associated socioeconomic factors

OBJECTIVE: To identify clusters of the major occurrences of leprosy and their associated socioeconomic and demographic factors. METHODS: Cases of leprosy that occurred between 1998 and 2007 in São José do Rio Preto (southeastern Brazil) were geocodified and the incidence rates were calculated by census tract. A socioeconomic classification score was obtained using principal component analysis of socioeconomic variables. Thematic maps to visualize the spatial distribution of the incidence of leprosy with respect to socioeconomic levels and demographic density were constructed using geostatistics. RESULTS: While the incidence rate for the entire city was 10.4 cases per 100,000 inhabitants annually between 1998 and 2007, the incidence rates of individual census tracts were heterogeneous, with values that ranged from 0 to 26.9 cases per 100,000 inhabitants per year. Areas with a high leprosy incidence were associated with lower socioeconomic levels. There were identified clusters of leprosy cases, however there was no association between disease incidence and demographic density. There was a disparity between the places where the majority of ill people lived and the location of healthcare services. CONCLUSIONS: The spatial analysis techniques utilized identified the poorer neighborhoods of the city as the areas with the highest risk for the disease. These data show that health departments must prioritize politico-administrative policies to minimize the effects of social inequality and improve the standards of living, hygiene, and education of the population in order to reduce the incidence of leprosy.

Do Bloco Privativo de Assinante (BPA) ao Armário de Telecomunicações Individual (ATI)

Na década de 50 do século XX foi publicado o Decreto n.º 41486 de 30 de Dezembro de 1957 que regulamentou as estações receptoras de radiodifusão, decorrentes da evolução da “caixa que mudou o mundo”, a televisão. Posteriormente, na década de 80 desse mesmo século foram fixadas as regras básicas, com o objetivo de dotar os edifícios de infraestruturas de telecomunicações, nomeadamente telefone, telex e dados, com acesso através de redes físicas, mediante a publicação do Decreto-Lei 146/87 de 24 de Março – Instalações Telefónicas de Assinante (ITA), do Decreto Regulamentar n.º 25/87, o Regulamento de Instalações Telefónicas de Assinante (RITA), que estabeleceu as condições técnicas a que deveriam obedecer os projectos, as instalações e a conservação das infraestruturas de telecomunicações, bem como os procedimentos legais a seguir para a elaboração de projetos e solicitação de vistorias às instalações executadas.

Dynamical behaviour of multi-particle large-scale systems

Collective behaviours can be observed in both natural and man-made systems composed of a large number of elemental subsystems. Typically, each elemental subsystem has its own dynamics but, whenever interaction between individuals occurs, the individual behaviours tend to be relaxed, and collective behaviours emerge. In this paper, the collective behaviour of a large-scale system composed of several coupled elemental particles is analysed. The dynamics of the particles are governed by the same type of equations but having different parameter values and initial conditions. Coupling between particles is based on statistical feedback, which means that each particle is affected by the average behaviour of its neighbours. It is shown that the global system may unveil several types of collective behaviours, corresponding to partial synchronisation, characterised by the existence of several clusters of synchronised subsystems, and global synchronisation between particles, where all the elemental particles synchronise completely.

Optimal virtual cluster-based multiprocessor scheduling

Scheduling of constrained deadline sporadic task systems on multiprocessor platforms is an area which has received much attention in the recent past. It is widely believed that finding an optimal scheduler is hard, and therefore most studies have focused on developing algorithms with good processor utilization bounds. These algorithms can be broadly classified into two categories: partitioned scheduling in which tasks are statically assigned to individual processors, and global scheduling in which each task is allowed to execute on any processor in the platform. In this paper we consider a third, more general, approach called cluster-based scheduling. In this approach each task is statically assigned to a processor cluster, tasks in each cluster are globally scheduled among themselves, and clusters in turn are scheduled on the multiprocessor platform. We develop techniques to support such cluster-based scheduling algorithms, and also consider properties that minimize total processor utilization of individual clusters. In the last part of this paper, we develop new virtual cluster-based scheduling algorithms. For implicit deadline sporadic task systems, we develop an optimal scheduling algorithm that is neither Pfair nor ERfair. We also show that the processor utilization bound of us-edf{m/(2m−1)} can be improved by using virtual clustering. Since neither partitioned nor global strategies dominate over the other, cluster-based scheduling is a natural direction for research towards achieving improved processor utilization bounds.

Contextual and individual indicators associated with the presence of teeth in adults

OBJECTIVE The objective of this study was to analyze whether socioeconomic conditions and the period of availability of fluoridated water are associated with the number of teeth present.METHODSThis cross-sectional study analyzed data from 1,720 adults between 20 and 59 years of age who resided in Florianópolis, SC, Southern Brazil, in 2009. The outcome investigated was the self-reported number of teeth present. The individual independent variables included gender, age range, skin color, number of years of schooling, and per capita household income. The duration of residence was used as a control variable. The contextual exposures included the period of availability of fluoridated water to the households and the socioeconomic variable for the census tracts, which was created from factor analysis of the tract’s mean income, education level, and percentage of households with treated water. Multilevel logistic regression was performed and inter-level interactions were tested.RESULTS Residents in intermediate and poorer areas and those with fluoridated water available for less time exhibited the presence of fewer teeth compared with those in better socioeconomic conditions and who had fluoridated water available for a longer period (OR = 1.02; 95%CI 1.01;1.02). There was an association between the period of availability of fluoridated water, per capita household income and number of years of education. The proportion of individuals in the poorer and less-educated stratum, which had fewer teeth present, was higher in regions where fluoridated water had been available for less time.CONCLUSIONS Poor socioeconomic conditions and a shorter period of availability of fluoridated water were associated with the probability of having fewer teeth in adulthood. Public policies aimed at reducing socioeconomic inequalities and increasing access to health services such as fluoridation of the water supply may help to reduce tooth loss in the future.

Estudo comparativo de três câmaras de ionização para medição directa do equivalente de dose individual, a 10 mm de profundidade, Hp(10)

Dissertação apresentada na Faculdade de Ciências e Tecnologia da Universidade Nova de Lisboa para obtenção do grau de Mestre em Engenharia Biomédica

Data analytics in the cloud with flexible mapreduced workflows

Data analytic applications are characterized by large data sets that are subject to a series of processing phases. Some of these phases are executed sequentially but others can be executed concurrently or in parallel on clusters, grids or clouds. The MapReduce programming model has been applied to process large data sets in cluster and cloud environments. For developing an application using MapReduce there is a need to install/configure/access specific frameworks such as Apache Hadoop or Elastic MapReduce in Amazon Cloud. It would be desirable to provide more flexibility in adjusting such configurations according to the application characteristics. Furthermore the composition of the multiple phases of a data analytic application requires the specification of all the phases and their orchestration. The original MapReduce model and environment lacks flexible support for such configuration and composition. Recognizing that scientific workflows have been successfully applied to modeling complex applications, this paper describes our experiments on implementing MapReduce as subworkflows in the AWARD framework (Autonomic Workflow Activities Reconfigurable and Dynamic). A text mining data analytic application is modeled as a complex workflow with multiple phases, where individual workflow nodes support MapReduce computations. As in typical MapReduce environments, the end user only needs to define the application algorithms for input data processing and for the map and reduce functions. In the paper we present experimental results when using the AWARD framework to execute MapReduce workflows deployed over multiple Amazon EC2 (Elastic Compute Cloud) instances.

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 effect of Schistosoma mansoni infection on child morbidity in the State in Bahia, Brazil: II — Analysis at the individual level

The present investigation was carried out on a sample of 840 children (5 to 16 years old) from ten small towns of the State of Bahia in northeastern Brazil. The objetive was to study, by using a cross sectional methodology, the evolution of schistosomiasis morbidity (hepatic and splenic enlargement) in children, and the role of the intensity of S. mansoni infection in this process. The children were analised in three age groups (5 to 8, to 12 and 13 to 16 years old) and classified as uninfected, mildly infected, moderately infected and heavily infected according to the number of eggs in the stool. In children aged 5 to 8 years, increasing egg counts were not associated with increasing frequencies of hepatic or splenic enlargement. In the 9 to 12 years old group and association was observed with the prevalence of hepatic enlargement, but not with the prevalence of spleen enlargement. In the oldest group, 13 to 16 years old, an association was observed with the prevalence of enlargement of both organs. It was evident that in this population schistosomiasis morbidity develops in the early period of life as a gradual process starting with liver enlargement and followed by spleen enlargement some years later. It was found that the intensity of infection has a fundamental role in this process, although there is a latent period of some years before clinical splenomegaly appears in moderate-heavily infected children. The Authors suggest that the prevalence of splenomegaly in the 13 to 16 years old group is a good measure of the community level of schistosomiasis morbidity and could be used to measure the impact of control programs.

O trabalho individual e o trabalho de grupo no processo de ensino-aprendizagem do estudo do meio no 1º Ciclo

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

Catálise de hydrocraking baseado em zeólitos

Trabalho Final de Mestrado para obtenção do grau de Mestre em Engenharia Química

Malária humana: padronização e optimização de testes sorológicos para diagnóstico individual e inquéritos soroepidemiológicos

O teste de imunofluorescência indireta (IFI) é considerado teste de referência na soroiogia da malária. Neste trabalho procuramos optimizar o teste empregando P. falciparum obtido de sangue humano e de cultura e P. vivax obtido de sangue de paciente como antígenos, para pesquisa de anticorpos IgG e IgM. Das variáveis técnicas estudadas melhores resultados foram obtidos quando os soros foram diluidos ern PBS contendo 1% de Tween 80 e as lâminas contendo a suspensão antigênica foram estabilizadas em dessecadores ou fixadas com acetona. Foi também padronizado o teste imunoenzimático ELISA com antigenos de P. falciparum obtidos em cultura. O estudo comparativo com o teste de imunofluorescência indireta para pesquisa de anticorpos IgG mostrou: a) nos pacientes primo infectados por P. falciparum a sensibilidade para ambos os testes foi de 71%; b) nos pacientes primo infectados pelo P. vivax a sensibilidade foi de 40% para ambos os testes; c) nos pacientes não primo infectados e com malária atual pelo P. falciparum a sensibilidade para ambos os testes foi de 100%; d) nos pacientes não primo infectados e com malária atual pelo P. vivax a sensibilidade foi de 85% para o teste ELISA e de 92% para a IFI; e) nos pacientes com malária mista a sensibilidade para ambos os testes foi de 100%. A especificidade da IFI foi de 100% e do teste ELISA 95% nos casos de indivíduos não maláricos. Os resultados obtidos sugerem ser o teste ELISA, uma boa alternativa para o teste de IFI, para a pesquisa de anticorpos IgG anti P. falciparum, na soroiogia da malária.