Análise e classificação de imagens de lesões da pele por atributos de cor, forma e textura utilizando máquina de vetor de suporte

The skin cancer is the most common of all cancers and the increase of its incidence must, in part, caused by the behavior of the people in relation to the exposition to the sun. In Brazil, the non-melanoma skin cancer is the most incident in the majority of the regions. The dermatoscopy and videodermatoscopy are the main types of examinations for the diagnosis of dermatological illnesses of the skin. The field that involves the use of computational tools to help or follow medical diagnosis in dermatological injuries is seen as very recent. Some methods had been proposed for automatic classification of pathology of the skin using images. The present work has the objective to present a new intelligent methodology for analysis and classification of skin cancer images, based on the techniques of digital processing of images for extraction of color characteristics, forms and texture, using Wavelet Packet Transform (WPT) and learning techniques called Support Vector Machine (SVM). The Wavelet Packet Transform is applied for extraction of texture characteristics in the images. The WPT consists of a set of base functions that represents the image in different bands of frequency, each one with distinct resolutions corresponding to each scale. Moreover, the characteristics of color of the injury are also computed that are dependants of a visual context, influenced for the existing colors in its surround, and the attributes of form through the Fourier describers. The Support Vector Machine is used for the classification task, which is based on the minimization principles of the structural risk, coming from the statistical learning theory. The SVM has the objective to construct optimum hyperplanes that represent the separation between classes. The generated hyperplane is determined by a subset of the classes, called support vectors. For the used database in this work, the results had revealed a good performance getting a global rightness of 92,73% for melanoma, and 86% for non-melanoma and benign injuries. The extracted describers and the SVM classifier became a method capable to recognize and to classify the analyzed skin injuries

Um ambiente computacional para modelagem simbólica de sistemas físicos lineares

Este trabalho propõe um ambiente computacional aplicado ao ensino de sistemas de controle, denominado de ModSym. O software implementa uma interface gráfica para a modelagem de sistemas físicos lineares e mostra, passo a passo, o processamento necessário à obtenção de modelos matemáticos para esses sistemas. Um sistema físico pode ser representado, no software, de três formas diferentes. O sistema pode ser representado por um diagrama gráfico a partir de elementos dos domínios elétrico, mecânico translacional, mecânico rotacional e hidráulico. Pode também ser representado a partir de grafos de ligação ou de diagramas de fluxo de sinal. Uma vez representado o sistema, o ModSym possibilita o cálculo de funções de transferência do sistema na forma simbólica, utilizando a regra de Mason. O software calcula também funções de transferência na forma numérica e funções de sensibilidade paramétrica. O trabalho propõe ainda um algoritmo para obter o diagrama de fluxo de sinal de um sistema físico baseado no seu grafo de ligação. Este algoritmo e a metodologia de análise de sistemas conhecida por Network Method permitiram a utilização da regra de Mason no cálculo de funções de transferência dos sistemas modelados no software

Sobre a natureza dos processos físicos de aquecimento da atmosfera de estrelas do tipo solar

In the present work, we have studied the nature of the physical processes of the coronal heating, considering as basis significant samples of single and binary evolved stars, that have been achieved with the ROSAT satellite. In a total of 191 simple stars were studied, classified in the literature as giants with spectral type F, G and K. The results were compared with those obtained from 106 evolved stars of spectral type F, G and K, which belong to the spectroscopic binary systems. Accurate measurements on rotation and information about binarity were obtained from De Medeiros s catalog. We have analysed the behavior of the coronal activity in function of diverse stellar parameters. With the purpose to better clarify the profile of the stars evolution, the HR diagram was built for the two samples of stars, the single and the binary ones. The evolved traces added in the diagram were obtained from the Toulouse-Geneve code, Nascimento et al. (2000). The stars were segregated in this diagram not only in range of rotational speed but also in range of X-ray flux. Our analysis shows clearly that the single stars and the binary ones have coronal activity controlled by physical process independent on the rotation. Non magnetic processes seem to be strongly influencing the coronal heating. For the binary stars, we have also studied the behavior of the coronal emission as a function of orbital parameters, such as period and eccentricity, in which it was revealed the existence of a discontinuity in the emission of X-rays around an orbital period of 100 days. The study helped to conclude that circular orbits of the binary stars are presented as a necessary property for the existence of a higher level ofX-rays emission, suggesting that the effect of the gravitational tide has an important role in the coronal activity level. When applied the Kolmogorov-Smirnov test (KS test ) for the Vsini and FX parameters to the samples of single and binary stars, we could evidence very relevant aspects for the understanding of the mechanisms inherent to the coronal activity. For the Vsini parameter, the differences between the single stars and the binary ones for rotation over 6.3 km/s were really remarkable. We believe, therefore, that the existence of gravitational tide is, at least, one of the factors that most contribute for this behavior. About the X-rays flux, the KS test showed that the behavior of the single and the binary stars, regarding the coronal activity, comes from the same origin

Teoria cinética não extensiva: efeitos físicos em gases e plasmas

The standard kinetic theory for a nonrelativistic diluted gas is generalized in the spirit of the nonextensive statistic distribution introduced by Tsallis. The new formalism depends on an arbitrary q parameter measuring the degree of nonextensivity. In the limit q = 1, the extensive Maxwell-Boltzmann theory is recovered. Starting from a purely kinetic deduction of the velocity q-distribution function, the Boltzmann H-teorem is generalized for including the possibility of nonextensive out of equilibrium effects. Based on this investigation, it is proved that Tsallis' distribution is the necessary and sufficient condition defining a thermodynamic equilibrium state in the nonextensive context. This result follows naturally from the generalized transport equation and also from the extended H-theorem. Two physical applications of the nonextensive effects have been considered. Closed analytic expressions were obtained for the Doppler broadening of spectral lines from an excited gas, as well as, for the dispersion relations describing the eletrostatic oscillations in a diluted electronic plasma. In the later case, a comparison with the experimental results strongly suggests a Tsallis distribution with the q parameter smaller than unity. A complementary study is related to the thermodynamic behavior of a relativistic imperfect simple fluid. Using nonequilibrium thermodynamics, we show how the basic primary variables, namely: the energy momentum tensor, the particle and entropy fluxes depend on the several dissipative processes present in the fluid. The temperature variation law for this moving imperfect fluid is also obtained, and the Eckart and Landau-Lifshitz formulations are recovered as particular cases

Influência de fatores individuais e sociais sobre as respostas endócrina e comportamental de callithrix jacchus a desafios ambientais físicos e sociais

Regarding the growing number of human beings with physical and mental pathologies associated to different stressor agents, attempts are being made to validate animal models with a close phylogenetic resemblance to man, to study stress response. Callithrix jacchus has been widely used in biomedical research, including on stress, but there is scarce information in the literature about how individual and social factors modulate stressor response in this species. This study uses 4 approaches to investigate the response of male and female adult C. jacchus, under situations of stress, and in the first we show evidence of the importance of this animal as an experimental model in research involving the hypothalamus-pituitary-adrenal axis. And we investigate if sex and baseline cortisol levels modulate the behavioral and hormonal response to separation. In two additional approaches investigate if type of social support (co-specific parent or non-parent) and social rank interfere in behavioral and hormonal when the animal are exposure to a new environment, paired with a co-specific (F2), exposure of the animal to a new environment, isolated (F3) or during reunion (F4). Finally, we also investigated the androgen levels in the males, with a focus on the challenge hypothesis, referring to environmental responsiveness and male-male exposure to relatives and non-relatives of C. jacchus. It was observed that: (1) the baseline cortisol of the animal is predictive of cortisol reactivity at separation; (2) males and females do not show dimorphism in the response of cortisol to stressors, although the females have higher baseline levels of this hormone and exhibit higher frequencies of anxiety-related behaviors; (3) only social support provided by relatives proved to be effective in buffering the cortisol response. In behavioral terms this response was dimorphic, showing that only the male dyads displayed an attenuated response to stress; (4) the males showed differences in cortisol levels as a function of social rank and study phases, whereas in the females no such alterations were observed. The males with indefinite dominance hierarchy (IDH) had reduced cortisol in F2 and F4, while the IDH females showed an increase in F3 and F4; (5) the males of relative and non-relative dyads did not exhibit variations in androgen levels as a function of a new environment. These results, taken together, (a) corroborate the use of C. jacchus as a good animal model for stress-related studies, given that they exhibit similar behavioral and physiological alterations to those of human beings in response to stressor agents; (b) point to the importance of considering individual and social modulating factors during experiments with stressors; (c) provide more reliable comparison parameters in studies where these primates are used as animal models, and (d) show that androgens vary as a function of genetic proximity (relative or non-relative) when the animals are faced with physical and social environmental challenges, thus providing important information for studying the challenge hypothesis in this species

Otimização em comitês de classificadores: uma abordagem baseada em filtro para seleção de subconjuntos de atributos

Traditional applications of feature selection in areas such as data mining, machine learning and pattern recognition aim to improve the accuracy and to reduce the computational cost of the model. It is done through the removal of redundant, irrelevant or noisy data, finding a representative subset of data that reduces its dimensionality without loss of performance. With the development of research in ensemble of classifiers and the verification that this type of model has better performance than the individual models, if the base classifiers are diverse, comes a new field of application to the research of feature selection. In this new field, it is desired to find diverse subsets of features for the construction of base classifiers for the ensemble systems. This work proposes an approach that maximizes the diversity of the ensembles by selecting subsets of features using a model independent of the learning algorithm and with low computational cost. This is done using bio-inspired metaheuristics with evaluation filter-based criteria

Uma Análise de métodos de distriubuição de atributos em comitês de classificadores

The objective of the researches in artificial intelligence is to qualify the computer to execute functions that are performed by humans using knowledge and reasoning. This work was developed in the area of machine learning, that it s the study branch of artificial intelligence, being related to the project and development of algorithms and techniques capable to allow the computational learning. The objective of this work is analyzing a feature selection method for ensemble systems. The proposed method is inserted into the filter approach of feature selection method, it s using the variance and Spearman correlation to rank the feature and using the reward and punishment strategies to measure the feature importance for the identification of the classes. For each ensemble, several different configuration were used, which varied from hybrid (homogeneous) to non-hybrid (heterogeneous) structures of ensemble. They were submitted to five combining methods (voting, sum, sum weight, multiLayer Perceptron and naïve Bayes) which were applied in six distinct database (real and artificial). The classifiers applied during the experiments were k- nearest neighbor, multiLayer Perceptron, naïve Bayes and decision tree. Finally, the performance of ensemble was analyzed comparatively, using none feature selection method, using a filter approach (original) feature selection method and the proposed method. To do this comparison, a statistical test was applied, which demonstrate that there was a significant improvement in the precision of the ensembles

Seleção de atributos em comitês de classificadores utilizando algoritmos genéticos

Classifier ensembles are systems composed of a set of individual classifiers and a combination module, which is responsible for providing the final output of the system. In the design of these systems, diversity is considered as one of the main aspects to be taken into account since there is no gain in combining identical classification methods. The ideal situation is a set of individual classifiers with uncorrelated errors. In other words, the individual classifiers should be diverse among themselves. One way of increasing diversity is to provide different datasets (patterns and/or attributes) for the individual classifiers. The diversity is increased because the individual classifiers will perform the same task (classification of the same input patterns) but they will be built using different subsets of patterns and/or attributes. The majority of the papers using feature selection for ensembles address the homogenous structures of ensemble, i.e., ensembles composed only of the same type of classifiers. In this investigation, two approaches of genetic algorithms (single and multi-objective) will be used to guide the distribution of the features among the classifiers in the context of homogenous and heterogeneous ensembles. The experiments will be divided into two phases that use a filter approach of feature selection guided by genetic algorithm

Competitividade de destinos turísticos e o imperativo sustentável: avaliação de dimensões e atributos condicionantes no Pólo Costa das Dunas, RN, Brasil

Being available as a tourist destination is a necessary condition but not enough for the expansion and success of tourism activity. To be successful, tourism requires investment, inputs, appropriate planning and management, like any other economic activity. A fundamental goal of the destination management is to understand how the competitiveness of a tourist destination can be improved and sustained. Competitive position of tourism can be measured and assessed by various models. Evaluating the indicators of competitiveness of a tourist destination involves a multivariate analysis, ranging from issues directly related to tourism activity itself to the indirect factors. These are elements that are interrelated and that together will point out the competitive condition of this destination. From the definition and characterization of competitiveness, sustainability and management in the context of tourist destinations, understood as the main concepts of this study, we present the main theoretical and methodological models of assessment of competitiveness of tourist destinations in the literature and represent the state of the issue in the scientific treatment of the subject. These models, designed by researchers from several countries and applied in different tourist destinations, are confronted about their structure, indicators considered and localities in which they were applied. The aim of this study was to know and evaluate the condition of tourist competitiveness of the destination Pólo Costa das Dunas, from the constraints attributes of superior performance of the evaluation model of tourist competitiveness of destinations Competenible, suggested by Mazaro, and that suit the requirements of international market aware of the strength and importance of sustainability. The condition of competitiveness of tourist destination in Rio Grande do Norte Pólo Costa das Dunas was moderate. The competitive strengths and weaknesses of the destination Pólo Costa das Dunas revealed through the dozens of sustainable attributes of the model Competenible showed guidelines and initiatives that can be taken to guide strategic decisions related to their planning and management. Thus, this study should serve as support for strategic planning and long-term management of the sector and as a crucial tool for making decisions related to public policies, sectoral investments, monitor processes, strategic planning, direction and control of the local and regional tourism development of destinations

Interpretação sísmica e análise de atributos - área do levantamento sísmico 3D de siririzinho (Bacia Sergipe-Alagoas, NE do Brasil)

The main objective of the present thesis was the seismic interpretation and seismic attribute analysis of the 3D seismic data from the Siririzinho high, located in the Sergipe Sub-basin (southern portion of Sergipe-Alagoas Basin). This study has enabled a better understanding of the stratigraphy and structure that the Siririzinho high experienced during its development. In a first analysis, we used two types of filters: the dip-steered median filter, was used to remove random noise and increase the lateral continuity of reflections, and fault-enhancement filter was applied to enhance the reflection discontinuities. After this filtering step similarity and curvature attributes were applied in order to identify and enhance the distribution of faults and fractures. The use of attributes and filtering greatly contributed to the identification and enhancement of continuity of faults. Besides the application of typical attributes (similarity and curvature) neural network and fingerprint techniques were also used, which generate meta-attributes, also aiming to highlight the faults; however, the results were not satisfactory. In a subsequent step, well log and seismic data analysis were performed, which allowed the understanding of the distribution and arrangement of sequences that occur in the Siririzinho high, as well as an understanding of how these units are affected by main structures in the region. The Siririzinho high comprises an elongated structure elongated in the NS direction, capped by four seismo-sequences (informally named, from bottom to top, the sequences I to IV, plus the top of the basement). It was possible to recognize the main NS-oriented faults, which especially affect the sequences I and II, and faults oriented NE-SW, that reach the younger sequences, III and IV. Finally, with the interpretation of seismic horizons corresponding to each of these sequences, it was possible to define a better understanding of geometry, deposition and structural relations in the area.

Detecção de áreas degradadas na sub-bacia hidrográfica do rio taperoá/pb, utilizando parâmetros físicos dos sensores modis/terra e tm/landsat

This study includes the results of the analysis of areas susceptible to degradation by remote sensing in semi-arid region, which is a matter of concern and affects the whole population and the catalyst of this process occurs by the deforestation of the savanna and improper practices by the use of soil. The objective of this research is to use biophysical parameters of the MODIS / Terra and images TM/Landsat-5 to determine areas susceptible to degradation in semi-arid Paraiba. The study area is located in the central interior of Paraíba, in the sub-basin of the River Taperoá, with average annual rainfall below 400 mm and average annual temperature of 28 ° C. To draw up the map of vegetation were used TM/Landsat-5 images, specifically, the composition 5R4G3B colored, commonly used for mapping land use. This map was produced by unsupervised classification by maximum likelihood. The legend corresponds to the following targets: savanna vegetation sparse and dense, riparian vegetation and exposed soil. The biophysical parameters used in the MODIS were emissivity, albedo and vegetation index for NDVI (NDVI). The GIS computer programs used were Modis Reprojections Tools and System Information Processing Georeferenced (SPRING), which was set up and worked the bank of information from sensors MODIS and TM and ArcGIS software for making maps more customizable. Initially, we evaluated the behavior of the vegetation emissivity by adapting equation Bastiaanssen on NDVI for spatialize emissivity and observe changes during the year 2006. The albedo was used to view your percentage of increase in the periods December 2003 and 2004. The image sensor of Landsat TM were used for the month of December 2005, according to the availability of images and in periods of low emissivity. For these applications were made in language programs for GIS Algebraic Space (LEGAL), which is a routine programming SPRING, which allows you to perform various types of algebras of spatial data and maps. For the detection of areas susceptible to environmental degradation took into account the behavior of the emissivity of the savanna that showed seasonal coinciding with the rainy season, reaching a maximum emissivity in the months April to July and in the remaining months of a low emissivity . With the images of the albedo of December 2003 and 2004, it was verified the percentage increase, which allowed the generation of two distinct classes: areas with increased variation percentage of 1 to 11.6% and the percentage change in areas with less than 1 % albedo. It was then possible to generate the map of susceptibility to environmental degradation, with the intersection of the class of exposed soil with varying percentage of the albedo, resulting in classes susceptibility to environmental degradation

Percepção dos usuários nos espaços públicos: avaliação pós-ocupação em três praças de Natal-RN

The research investigates the acting and the importance for the users of the public squares located predominantly in residential areas. It presents the results of the posoccupation evaluations accomplished in three squares, whose physical, environmental characteristics, equipments and fumitures are different in its qualities and amounts, taking in consideration aspects related to the users' physical and psychological comfort and of the inhabitants of the I spill. The collection of data involved physical risings and of files, observations behavious, application of questionnaires and interviews, analyzed qualitative as quantitatively so much for a larger precision and validity of the investigation. The results were obtained through the relationship among the users' perception the environmental attributes and the different levels of apropriation/use of the studied places. They indicate that the aspects composicionais of physical order of the space affects the type and the intensity of use of the squares intimately, contributing positive or negatively for its valor. It is evidenced like this, that the low freqüentation of the public squares of Natal, is due mainly to referring aspects to the physical quality and the amount of the fumitures and urban equipments. It is ended that the investments and the physical planning of these public spaces should be based in the real knowledge of the aspirations of the population objective, in way to allow its largest use and valor