Sparse representation with multi-manifold analysis for texture classification from few training images

Texture classification is one of the most important tasks in computer vision field and it has been extensively investigated in the last several decades. Previous texture classification methods mainly used the template matching based methods such as Support Vector Machine and k-Nearest-Neighbour for classification. Given enough training images the state-of-the-art texture classification methods could achieve very high classification accuracies on some benchmark databases. However, when the number of training images is limited, which usually happens in real-world applications because of the high cost of obtaining labelled data, the classification accuracies of those state-of-the-art methods would deteriorate due to the overfitting effect. In this paper we aim to develop a novel framework that could correctly classify textural images with only a small number of training images. By taking into account the repetition and sparsity property of textures we propose a sparse representation based multi-manifold analysis framework for texture classification from few training images. A set of new training samples are generated from each training image by a scale and spatial pyramid, and then the training samples belonging to each class are modelled by a manifold based on sparse representation. We learn a dictionary of sparse representation and a projection matrix for each class and classify the test images based on the projected reconstruction errors. The framework provides a more compact model than the template matching based texture classification methods, and mitigates the overfitting effect. Experimental results show that the proposed method could achieve reasonably high generalization capability even with as few as 3 training images, and significantly outperforms the state-of-the-art texture classification approaches on three benchmark datasets. © 2014 Elsevier B.V. All rights reserved.

Margens de contribuição, gastos e lucro na cadeira de distribuição domiciliar de gás liquefeito de petróleo (Gás LP) : um estudo de caso do lucro na cadeia de distribuição de Gás LP domicilar no Brasil

A dissertação é um estudo de caso que tem como objetivo mapear a margem de contribuição, gastos e lucros na cadeia de distribuição do gás de cozinhas no Brasil. O trabalho focaliza o mapeamento da cadeia de valor a partir de uma das 21 distribuidoras de Gás LP e suas revendas em uma de suas áreas de atuação. Para o mapeamento dos custos e despesas fixos da distribuidora e de seus revendores foi utilizado o custeio baseado em atividade - ABC. Para o mapeamento do lucro foi utilizado o lucro antes dos juros, impostos, depreciação e amortização - Ebitda. Após o mapeamento buscou-se identificar as principais variáveis que explicam a atual configuração Ebitda da distribuidora e de suas revendas. Para isso foram geradas regressões de dados para entender o lucro unitário (reais por botijão de gás) da distribuidora e de suas mais de 500 revendas em uma das áreas de atuação. O resultado mostra uma estimativa de como a margem de contribuição, gastos e lucros na cadeia de distribuição do gás de cozinha no Brasil para o ano de 2007 se dividem entre as distribuidoras e revendedores de Gás LP domiciliar em termos percentual e unitário. Também foram explicadas quais as variáveis que mais impactam no Ebitda da distribuidora e revendas do estudo de caso. Por fim, o trabalho discute o potencial da metodologia de análise de mapeamento através do profit pool na cadeia de valor da indústria ao longo do texto e na conclusão do trabalho.

Massless DKP field in a Lyra manifold

Massless scalar and vector fields are coupled to the Lyra geometry by means of the Duffin-Kemmer-Petiau (DKP) theory. Using the Schwinger variational principle, the equations of motion, conservation laws and gauge symmetry are implemented. We find that the scalar field couples to the anholonomic part of the torsion tensor, and the gauge symmetry of the electromagnetic field does not break by the coupling with torsion.

Electromagnetic field in Lyra manifold: a first order approach

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Geometrical Lagrangian for a supersymmetric Yang-Mills theory on the group manifold

Perhaps one of the main features of Einstein's General Theory of Relativity is that spacetime is not flat itself but curved. Nowadays, however, many of the unifying theories like superstrings on even alternative gravity theories such as teleparalell geometric theories assume flat spacetime for their calculations. This article, an extended account of an earlier author's contribution, it is assumed a curved group manifold as a geometrical background from which a Lagrangian for a supersymmetric N = 2, d = 5 Yang-Mills - SYM, N = 2, d = 5 - is built up. The spacetime is a hypersurface embedded in this geometrical scenario, and the geometrical action here obtained can be readily coupled to the five-dimensional supergravity action. The essential idea that underlies this work has its roots in the Einstein-Cartan formulation of gravity and in the 'group manifold approach to gravity and supergravity theories'. The group SYM, N = 2, d = 5, turns out to be the direct product of supergravity and a general gauge group g: G = g circle times <(SU(2, 2/1))over bar>.

The Dirac equation in a non-Riemannian manifold. I. An analysis using the complex algebra

The Dirac wave equation is obtained in the non-Riemannian manifold of the Einstein-Schrödinger nonsymmetric theory. A new internal connection is determined in terms of complex vierbeins, which shows the coupling of the electromagnetic potential with gravity in the presence of a spin-1/2 field. © 1988 American Institute of Physics.

Constraints on space-time manifold in Euclidean supergravity in terms of Dirac eigenvalues

We generalize a previous work on Dirac eigenvalues as dynamical variables of Euclidean supergravity. The most general set of constraints on the curvatures of the tangent bundle and on the spinor bundle of the space-time manifold, under which space-time admits Dirac eigenvalues as observables, are derived.

Optimal conductor size selection and reconductoring in radial distribution systems using a mixed-integer LP approach

This paper presents a mixed-integer linear programming model to solve the conductor size selection and reconductoring problem in radial distribution systems. In the proposed model, the steady-state operation of the radial distribution system is modeled through linear expressions. The use of a mixed-integer linear model guarantees convergence to optimality using existing optimization software. The proposed model and a heuristic are used to obtain the Pareto front of the conductor size selection and reconductoring problem considering two different objective functions. The results of one test system and two real distribution systems are presented in order to show the accuracy as well as the efficiency of the proposed solution technique. © 1969-2012 IEEE.

A mixed-integer LP model for the reconfiguration of radial electric distribution systems considering distributed generation

The problem of reconfiguration of distribution systems considering the presence of distributed generation is modeled as a mixed-integer linear programming (MILP) problem in this paper. The demands of the electric distribution system are modeled through linear approximations in terms of real and imaginary parts of the voltage, taking into account typical operating conditions of the electric distribution system. The use of an MILP formulation has the following benefits: (a) a robust mathematical model that is equivalent to the mixed-integer non-linear programming model; (b) an efficient computational behavior with exiting MILP solvers; and (c) guarantees convergence to optimality using classical optimization techniques. Results from one test system and two real systems show the excellent performance of the proposed methodology compared with conventional methods. © 2012 Published by Elsevier B.V. All rights reserved.

A mixed-integer LP model for the optimal allocation of voltage regulators and capacitors in radial distribution systems

This paper presents a mixed-integer linear programming model to solve the problem of allocating voltage regulators and fixed or switched capacitors (VRCs) in radial distribution systems. The use of a mixed-integer linear model guarantees convergence to optimality using existing optimization software. In the proposed model, the steady-state operation of the radial distribution system is modeled through linear expressions. The results of one test system and one real distribution system are presented in order to show the accuracy as well as the efficiency of the proposed solution technique. An heuristic to obtain the Pareto front for the multiobjective VRCs allocation problem is also presented. © 2012 Elsevier Ltd. All rights reserved.

Soluções auto-similares das equações de Navier-Stokes em Lp-Fraco

Pós-graduação em Matemática - IBILCE

Unsupervised manifold learning using Reciprocal kNN Graphs in image re-ranking and rank aggregation tasks

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)