Application of complex extreme learning machine to multiclass classification problems with high dimensionality: a THz spectra classification problem

We extend extreme learning machine (ELM) classifiers to complex Reproducing Kernel Hilbert Spaces (RKHS) where the input/output variables as well as the optimization variables are complex-valued. A new family of classifiers, called complex-valued ELM (CELM) suitable for complex-valued multiple-input–multiple-output processing is introduced. In the proposed method, the associated Lagrangian is computed using induced RKHS kernels, adopting a Wirtinger calculus approach formulated as a constrained optimization problem similarly to the conventional ELM classifier formulation. When training the CELM, the Karush–Khun–Tuker (KKT) theorem is used to solve the dual optimization problem that consists of satisfying simultaneously smallest training error as well as smallest norm of output weights criteria. The proposed formulation also addresses aspects of quaternary classification within a Clifford algebra context. For 2D complex-valued inputs, user-defined complex-coupled hyper-planes divide the classifier input space into four partitions. For 3D complex-valued inputs, the formulation generates three pairs of complex-coupled hyper-planes through orthogonal projections. The six hyper-planes then divide the 3D space into eight partitions. It is shown that the CELM problem formulation is equivalent to solving six real-valued ELM tasks, which are induced by projecting the chosen complex kernel across the different user-defined coordinate planes. A classification example of powdered samples on the basis of their terahertz spectral signatures is used to demonstrate the advantages of the CELM classifiers compared to their SVM counterparts. The proposed classifiers retain the advantages of their ELM counterparts, in that they can perform multiclass classification with lower computational complexity than SVM classifiers. Furthermore, because of their ability to perform classification tasks fast, the proposed formulations are of interest to real-time applications.

Can we really trust offshoring indices?

This paper argues that offshoring indices often measure something different than what we think they are. Using data from input-output tables of 21 European countries from 1995 to 2006 we decompose an offshoring index, distinguishing between a domestic (structural change) and an international component (imported inputs ratio). Regarding offshoring of business services, a large share of the index variation is driven by the domestic component. This is even more pronounced for overall service offshoring. In the case of material offshoring, by contrast, the international component drives the main variation of the indices. Our results therefore show that, regarding (business) services, the typical calculation of offshoring indices tends to over estimate the role of the imported inputs component, neglecting the role played by structural changes in the economy.

Exact Search Directions for Optimization of Linear and Nonlinear Models Based on Generalized Orthonormal Functions

A novel technique for selecting the poles of orthonormal basis functions (OBF) in Volterra models of any order is presented. It is well-known that the usual large number of parameters required to describe the Volterra kernels can be significantly reduced by representing each kernel using an appropriate basis of orthonormal functions. Such a representation results in the so-called OBF Volterra model, which has a Wiener structure consisting of a linear dynamic generated by the orthonormal basis followed by a nonlinear static mapping given by the Volterra polynomial series. Aiming at optimizing the poles that fully parameterize the orthonormal bases, the exact gradients of the outputs of the orthonormal filters with respect to their poles are computed analytically by using a back-propagation-through-time technique. The expressions relative to the Kautz basis and to generalized orthonormal bases of functions (GOBF) are addressed; the ones related to the Laguerre basis follow straightforwardly as a particular case. The main innovation here is that the dynamic nature of the OBF filters is fully considered in the gradient computations. These gradients provide exact search directions for optimizing the poles of a given orthonormal basis. Such search directions can, in turn, be used as part of an optimization procedure to locate the minimum of a cost-function that takes into account the error of estimation of the system output. The Levenberg-Marquardt algorithm is adopted here as the optimization procedure. Unlike previous related work, the proposed approach relies solely on input-output data measured from the system to be modeled, i.e., no information about the Volterra kernels is required. Examples are presented to illustrate the application of this approach to the modeling of dynamic systems, including a real magnetic levitation system with nonlinear oscillatory behavior.

Economic growth in Sweden, 2000-2010 : The dot-com bubble and the financial crisis

    Economic growth is the increase in the inflation-adjusted market value of the goods and services produced by an economy over time. The total output is the quantity of goods or servicesproduced in a given time period within a country. Sweden was affected by two crises during the period 2000-2010: a dot-com bubble and a financial crisis. How did these two crises affect the economic growth?     The changes of domestic output can be separated into four parts: changes in intermediate demand, final domestic demand, export demand and import substitution. The main purpose of this article is to analyze the economic growth during the period 2000-2010, with focus on the dot-com bubble in the beginning of the period 2000-2005, and the financial crisis at the end of the period 2005-2010. The methodology to be used is the structural decomposition method.     This investigation shows that the main contributions to the Swedish total domestic output increase in both the period 2000-2005 and the period 2005-2010 were the effect of domestic demand. In the period 2005-2010, financial crisis weakened the effect of export. The output of the primary sector went from a negative change into a positive, explained mainly by strong export expansion. In the secondary sector, export had most effect in the period 2000-2005. Nevertheless, domestic demand and import ratio had more effect during the financial crisis period. Lastly, in the tertiary sector, domestic demand can mainly explain the output growth in the whole period 2000-2010.

Aspectos do comércio entre China e Brasil e seus impactos

O presente trabalho tem como objetivo clarificar alguns pontos da relação comercial entre Brasil e China. Em grande parte é um trabalho descritivo, que utiliza diferentes agregações de produtos (Sistema harmônico; Broad Economic Categories), a fim de construir um cenário completo desta relação. Efeitos totais na produção brasileira, oriundos da demanda Chinesa por produtos Brasileiros também são analisados. Para tal utilizamos o ferramental de Matriz de Insumo Produto. Este efeito também é construído para o comércio do Brasil com os outros países do Mundo, e uma comparação é estabelecida. No fim do trabalho temos um estudo sobre possibilidades de comércio que ainda não foram exploradas entre esses dois países.

Controle de estoques de sal: uma inovação da quantificação e no gerenciamento dos recursos naturais da indústria mineral

The strengthening of the domestic industry in Brazil required the modernization, mechanization and expansion of salt production. Thereafter the production of sea salt started to be made in a process of continuous flow, where the product is constantly stored in yards, with daily movements in and out of salt. Thus far, the major bottleneck found in this production process is the control of production, because due to the large amount produced and variety of losses existing in the various stages of production there are not a regulated and safe way to control inventories with accuracy and speed demanded. In a typical case with a salt marsh company of Rio Grande do Norte state, salt produced is stored in two open courtyards and inventory control of salt made by carrying input / output relationship of salt in each storage yard. This work developed a conceptual model of inventory control, based on topography, adopting surveys into one of the courtyards of the company. There were 25 biweekly survey measurements over a year book to generate digital models representing the stock. For each measurement, results were compared with the values of inventory accounting provided by the salt marsh in order to identify existing losses and mark out the sales department on the actual stock available at each measurement date. Inventories calculated by the model indicated losses of 6,349 tonnes for the period of one year book and 3,279 tonnes for the period between harvests, when compared to the accounting control

Identificação em tempo real de modelo dinâmico de robô móvel com acionamento diferencial e zona morta

Several mobile robots show non-linear behavior, mainly due friction phenomena between the mechanical parts of the robot or between the robot and the ground. Linear models are efficient in some cases, but it is necessary take the robot non-linearity in consideration when precise displacement and positioning are desired. In this work a parametric model identification procedure for a mobile robot with differential drive that considers the dead-zone in the robot actuators is proposed. The method consists in dividing the system into Hammerstein systems and then uses the key-term separation principle to present the input-output relations which shows the parameters from both linear and non-linear blocks. The parameters are then simultaneously estimated through a recursive least squares algorithm. The results shows that is possible to identify the dead-zone thresholds together with the linear parameters

Efficient procedure to evaluate electromagnetic transients on three-phase transmission lines

This paper presents a hybrid way mixing time and frequency domain for transmission lines modelling. The proposed methodology handles steady fundamental signal mixed with fast and slow transients, including impulsive and oscillatory behaviour. A transmission line model is developed based on lumped elements representation and state-space techniques. The proposed methodology represents an easy and practical procedure to model a three-phase transmission line directly in time domain, without the explicit use of inverse transforms. The proposed methodology takes into account the frequency-dependent parameters of the line, considering the soil and skin effects. In order to include this effect in the state matrices, a fitting method is applied. Furthermore the accuracy of proposed the developed model is verified, in frequency domain, by a simple methodology based on line distributed parameters and transfer function related to the input/output signals of the lumped parameters representation. In addition, this article proposes the use of a fast and robust analytic integration procedure to solve the state equations, enabling transient and steady-state simulations. The results are compared with those obtained by the commercial software Microtran (EMTP), taking into account a three-phase transmission line, typical in the Brazilian transmission system.

Hartman-Grobman decomposition when in presence of jumps in the relative degree of the dynamics in an energy harvesting device

This work deals with the nonlinear piezoelectric coupling in vibration-based energy harvesting, done by A. Triplett and D.D. Quinn in J. of Intelligent Material Syst. and Structures (2009). In that paper the first order nonlinear fundamental equation has a three dimensional state variable. Introducing both observable and control variables in such a way the controlled system became a SISO system, we can obtain as a corollary that for a particular choice of the observable variable it is possible to present an explicit functional relation between this variable one, and the variable representing the charge harvested. After-by observing that the structure in the Input-Output decomposition essentially changes depending on the relative degree changes, presenting bifurcation branches in its zero dynamics-we are able in to identify this type of bifurcation indicating its close relation with the Hartman - Grobman theorem telling about decomposition into stable and the unstable manifolds for hyperbolic points.

Trade liberalization and industrial pollution in Brazil

Includes bibliography

Necessary and sufficient condition for generalized passivity, passification and application to multivariable adaptive systems

Recently, a generalized passivity concept for linear multivariable systems was obtained which allows circumventing the restrictiveness of the usual passivity concept. The latter is associated with the classical SPR (Strictly Positive Real) condition whereas the new concept of passivity is associated with the so called WSPR condition and its advantage in multivariable systems is that it does not require a restrictive symmetry condition of SPR systems. As a result, it allows the design of multivariable adaptive control that, unlike some existing factorization approaches, does not imply in additional overparameterization of the adaptive controller. In this paper, we complete a previously established WSPR sufficient condition and prove that it is also necessary. We also propose some methods of passification by either premultiplying the system output tracking error vector or the system input vector by an adequate passifying matrix multiplier, so that the resulting input/output transfer function becomes WSPR. The efficiency of our proposals are illustrated by simulation utilizing a well known robotics adaptive visual servoing problem. © 2011 IFAC.

Integrated single-stage converters with Tri-state modulation suitable for photovoltaic systems

The aim of this work is to present two topological simplified converters named Tri-state Boost and Tri-state Buck-Boost integrated single-phase inverters. An important operation capability can be achieved for these converters using a Tri-state Modulation control scheme. This is the inductive power decoupling and the independent input output control. These features are directly related with the photovoltaic micro-converter needs, improving efficiency, cost and mainly lifetime. These features for the proposed modulation are confirmed through experimental results. © 2011 IEEE.

Production structure of the services sector in countries at different development levels

Includes bibliography

Desindustrialização na economia brasileira no período 2000-2011: abordagens e indicadores

Pós-graduação em Economia - FCLAR