DSpace Coleção:
https://repositorio.ufrn.br/jspui/handle/123456789/12035
Fri, 26 Apr 2019 00:44:52 GMT2019-04-26T00:44:52ZAnálise da taxa de convergência da regra de classificação dos k-vizinhos mais próximos
https://repositorio.ufrn.br/jspui/handle/123456789/26313
Título: Análise da taxa de convergência da regra de classificação dos k-vizinhos mais próximos
Autor(es): Araújo, Juscelino Pereira de
Abstract: The main objective of this work is to analyze the velocity of convergence of k-Nearest
Neighbor (kNN) classification rule. Thus the binary classification problem is approached.
The main theoretical results are developed, overall Stone Theorem, which guarantees the
universal consistency of classification rules with some properties. Specifically the kNN
rule is analyzed, mainly its universal consistency. Then restrictive conditions which allow
uniform rates of convergence for a family of distributions are presented. Finally, under
the mentioned restrictive conditions the order of magnitude of rate of convergence of kNN
rule is obtained such that it cross out the need of a bounded space of observations.Fri, 05 Oct 2018 00:00:00 GMThttps://repositorio.ufrn.br/jspui/handle/123456789/263132018-10-05T00:00:00ZDe relações a vizinhanças: um entendimento sobre não-normalidade modal
https://repositorio.ufrn.br/jspui/handle/123456789/26312
Título: De relações a vizinhanças: um entendimento sobre não-normalidade modal
Autor(es): Dantas Neto, João Freire
Abstract: The quest for mathematical structures to represent some logical behaviors is important
for a better understanding of these logics. For example, propositional classical logic can
be characterized by Boolean Algebras. When adding modalities to classical logic, we
need other structures to represent them, as relational frames for normal modal logics, for
example in the case of non-normal modalities, we need neighborhood frames to represent
classical modal logics. In this work we investigate neighborhood frames for non-normal
modal logics, with the goal to relate frame semantics with proof systems. Moreover we
aim to understand proof systems with semantic language internalized.Thu, 18 Oct 2018 00:00:00 GMThttps://repositorio.ufrn.br/jspui/handle/123456789/263122018-10-18T00:00:00ZBidualização de espaços afins
https://repositorio.ufrn.br/jspui/handle/123456789/26153
Título: Bidualização de espaços afins
Autor(es): Silva, Josenildo Lopes da
Abstract: Main concepts on a ne space are presented. Let X be an a ne space modelled on a
vector space V and X? = A(X, R) be the a ne dual of X, that is, the vector space of all a ne
maps from X to the real line. It is well known that in the case of a nite dimensional vector
space V , the bidual V
∗∗ is isomorphic to V . We consider the vectorial bidual (X?
)
∗ of X and
an immersion of the a ne space X into its vectorial bidual. We present a discussion how to
de ne the a ne bidual X?? of X.Thu, 30 Aug 2018 00:00:00 GMThttps://repositorio.ufrn.br/jspui/handle/123456789/261532018-08-30T00:00:00ZO modelo de regressão GJS inflacionado em zero ou um
https://repositorio.ufrn.br/jspui/handle/123456789/26152
Título: O modelo de regressão GJS inflacionado em zero ou um
Autor(es): Queiroz, Francisco Felipe de
Abstract: Beta regression models are useful for modeling random variables that assume values in
the standard unit interval, such as rates and proportions. Such models cannot be used
when the data contain zeros and/or ones. In this case, usual regression models, such as
normal linear or nonlinear regression models, are not suitable. The principal aim of this
work is to propose a mixed continuous-discrete distributions to model data observed on
the intervals [0, 1) or (0, 1] and its associated regression model. The GJS distribution is
used to describe the continuous component of the model. The parameters of the mixture
distribution are modelled as functions of regression parameters. We study the performance
of the maximum likelihood estimators through Monte Carlo simulations. Also, we define
a residual for the proposed regression model to assess departures from model assumptions
as well as to detect outlying observations, and discuss some influence methods such as
the local influence. Finally, applications to real data are presented to show the usefulness
of the new regression model.Tue, 31 Jul 2018 00:00:00 GMThttps://repositorio.ufrn.br/jspui/handle/123456789/261522018-07-31T00:00:00Z