<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom" xmlns:dc="http://purl.org/dc/elements/1.1/">
  <title>DSpace Coleção:</title>
  <link rel="alternate" href="https://repositorio.ufpb.br/jspui/handle/123456789/13467" />
  <subtitle />
  <id>https://repositorio.ufpb.br/jspui/handle/123456789/13467</id>
  <updated>2026-03-12T04:39:28Z</updated>
  <dc:date>2026-03-12T04:39:28Z</dc:date>
  <entry>
    <title>Classificação de regiões favoráveis a concentração de hidrocarbonetos em imagens sísmicas utilizando redes neurais artificiais</title>
    <link rel="alternate" href="https://repositorio.ufpb.br/jspui/handle/123456789/16076" />
    <author>
      <name>Melo Neto, Edvaldo Francisco de</name>
    </author>
    <id>https://repositorio.ufpb.br/jspui/handle/123456789/16076</id>
    <updated>2019-10-19T06:01:08Z</updated>
    <published>2018-10-31T00:00:00Z</published>
    <summary type="text">Título: Classificação de regiões favoráveis a concentração de hidrocarbonetos em imagens sísmicas utilizando redes neurais artificiais
Autor(es): Melo Neto, Edvaldo Francisco de
Orientador: Santos, Moisés Dantas dos
Abstract: Identifying regions favorable to the concentration of hydrocarbons (regions of interest) in seismic data is an important task, performed subjectively by geologists and geophysicists, which requires considerable time and experience. In this work an automatic process was developed to detect the regions of interest in seismic images using the Haralick descriptors and the geostatistical functions. This method is based on the use of artificial neural networks for the pattern recognition in conjunction with these descriptors. To evaluate the performance of the network, statistical metrics were used for accuracy, sensitivity, specificity, precision and F1score. The network achieved a performance of up to 98,3% accuracy and F1score, 96,7% sensitivity and 100% specificity and precision.
Editor: Universidade Federal da Paraíba
Tipo: TCC</summary>
    <dc:date>2018-10-31T00:00:00Z</dc:date>
  </entry>
  <entry>
    <title>Soluções de referência para a equação da onda unidimensional</title>
    <link rel="alternate" href="https://repositorio.ufpb.br/jspui/handle/123456789/15694" />
    <author>
      <name>Sá, Raul Renner Martins de</name>
    </author>
    <id>https://repositorio.ufpb.br/jspui/handle/123456789/15694</id>
    <updated>2019-09-14T06:07:41Z</updated>
    <published>2017-06-14T00:00:00Z</published>
    <summary type="text">Título: Soluções de referência para a equação da onda unidimensional
Autor(es): Sá, Raul Renner Martins de
Orientador: Torii, André Jacomel
Abstract: The development of numerical methods for Di erential Equations is of great importance for the comprehension of several phenomenons, since, in general, the exact solution of these equations is not known. On the other hand, these methods turned to be pretty effective along the years, di culting the comparison between them in terms of precision. In this work, it is presented, as a support to comparison of parameter adjustment based numerical methods, the exact solution of the unidimensional Wave Equation applied to vibration of a string submitted to determined initial and boundary conditions. For the utility veri cation of the obtained solution, this work also approximates the analytical solution using the Galerkin Method, considering other numerical methods that makes time related comparisons, also presenting a study about the function sets used in the Galerkin Method.
Editor: Universidade Federal da Paraíba
Tipo: TCC</summary>
    <dc:date>2017-06-14T00:00:00Z</dc:date>
  </entry>
  <entry>
    <title>Soluções de referência para a equação da onda bidimensional</title>
    <link rel="alternate" href="https://repositorio.ufpb.br/jspui/handle/123456789/15693" />
    <author>
      <name>Lima, Rômulo da Silva</name>
    </author>
    <id>https://repositorio.ufpb.br/jspui/handle/123456789/15693</id>
    <updated>2019-09-14T06:08:00Z</updated>
    <published>2017-06-14T00:00:00Z</published>
    <summary type="text">Título: Soluções de referência para a equação da onda bidimensional
Autor(es): Lima, Rômulo da Silva
Orientador: Torii, André Jacomel
Abstract: The modellin gthrough Differential Equations(DE) has been of great importance for the study of the behavior and comprehension of several phenomena, as well as for the developing of technics for obtaining solutions for these differential equations. The exact solution of a DE is not always possible to be found,and,in this case,the use of numerical methods to obtain approximate solutions is necessary. However, the precision of numerical methods has improved along the years, what makes it difficult to compare them, since the difference in terms of precision of the methods is generally small. In order to provide a support to make comparisons&#xD;
between high precision numerical methods, this work presents two benchmark solutions for two initial value and boundary problems, modeled by the Bidimensional Wave Equation, that includes an adjustment parameter, defi ned as the membrane's frequency of excitation. The parameter, presentin the benchmark solutions, will be used as an arti fice to difficult the approximation of the exact solution, making viable the comparison between highly precise methods. This work also provides the approximation of the solutions of the proposed problem susing the Finite Difference Method, with an analysis about its precisio ntakingin consideration the adjustment parameter.
Editor: Universidade Federal da Paraíba
Tipo: TCC</summary>
    <dc:date>2017-06-14T00:00:00Z</dc:date>
  </entry>
  <entry>
    <title>Análise da amostragem por ponto mais distante para a aproximação geodésica em um grafo: o estado da arte</title>
    <link rel="alternate" href="https://repositorio.ufpb.br/jspui/handle/123456789/15691" />
    <author>
      <name>Meira, Diego Albertim</name>
    </author>
    <id>https://repositorio.ufpb.br/jspui/handle/123456789/15691</id>
    <updated>2019-09-14T06:07:51Z</updated>
    <published>2017-06-14T00:00:00Z</published>
    <summary type="text">Título: Análise da amostragem por ponto mais distante para a aproximação geodésica em um grafo: o estado da arte
Autor(es): Meira, Diego Albertim
Orientador: Bezerra, Sérgio de Carvalho
Abstract: The farthest point sampling algorithm has been vastly used in various applications involving image processing, surface mapping, among other purposes. A recent work, proposed by the team of prof. Sylvain Lazard, applies this algorithm to approximate geodesic distances in graphs associated to isometry-invariant surfaces, being that some points in the publishing showed to be a little nebulous. In this present work, will be offered a bibliographic complementation to Lazard et al’s project, intending to clarify some questions about the farthest point sampling method and other concepts used on the proposed application. Moreover, it’s intended to offer a satisfactory translation of the ideas in the referred work.
Editor: Universidade Federal da Paraíba
Tipo: TCC</summary>
    <dc:date>2017-06-14T00:00:00Z</dc:date>
  </entry>
</feed>

