Particle Competition and Cooperation in Networks for Semi-Supervised Learning with Concept Drift

Concept drift is a problem of increasing importance in machine learning and data mining. Data sets under analysis are no longer only static databases, but also data streams in which concepts and data distributions may not be stable over time. However, most learning algorithms produced so far are based on the assumption that data comes from a fixed distribution, so they are not suitable to handle concept drifts. Moreover, some concept drifts applications requires fast response, which means an algorithm must always be (re) trained with the latest available data. But the process of labeling data is usually expensive and/or time consuming when compared to unlabeled data acquisition, thus only a small fraction of the incoming data may be effectively labeled. Semi-supervised learning methods may help in this scenario, as they use both labeled and unlabeled data in the training process. However, most of them are also based on the assumption that the data is static. Therefore, semi-supervised learning with concept drifts is still an open challenge in machine learning. Recently, a particle competition and cooperation approach was used to realize graph-based semi-supervised learning from static data. In this paper, we extend that approach to handle data streams and concept drift. The result is a passive algorithm using a single classifier, which naturally adapts to concept changes, without any explicit drift detection mechanism. Its built-in mechanisms provide a natural way of learning from new data, gradually forgetting older knowledge as older labeled data items became less influent on the classification of newer data items. Some computer simulation are presented, showing the effectiveness of the proposed method.

Static converter: didactic support software

Teaching a course of special electric loads in a continuing education program to power engineers is a difficult task because they are not familiarized with switching topology circuits. Normally, in a typical program, many hours are dedicated to explain the thyristors switching sequence and to draw the converter currents and terminal voltages waveforms for different operative conditions. This work presents teaching support software in order to optimize the time spent in this task and, mainly to benefit the assimilation of the proposed subjects, studying the static converter under different non-ideal operative conditions.

Neural networks training using the constructivism paradigms

The Backpropagation Algorithm (BA) is the standard method for training multilayer Artificial Neural Networks (ANN), although it converges very slowly and can stop in a local minimum. We present a new method for neural network training using the BA inspired on constructivism, an alphabetization method proposed by Emilia Ferreiro based on Piaget philosophy. Simulation results show that the proposed configuration usually obtains a lower final mean square error, when compared with the standard BA and with the BA with momentum factor.

Another prefiltering algorithm for adaptive IIR filtering

An algorithm for adaptive IIR filtering that uses prefiltering structure in direct form is presented. This structure has an estimation error that is a linear function of the coefficients. This property greatly simplifies the derivation of gradient-based algorithms. Computer simulations show that the proposed structure improves convergence speed.

Asymmetrical magnetization in three-phase core type transformers

The performance of the three-phase core type transformers, under AC/DC double excitation is discussed in this work. It is presented a mathematical model that considers the mutual coupling between phases and the magnetic nonlinearity. The validity of the proposed model is verified by means of the experimental and simulated results.

Electric power systems transient stability analysis by neural networks

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Análise do escoamento de HFC-134a em tubos capilares usando o modelo de dois fluidos

This work presents a numerical model to simulate refrigerant flow through capillary tubes, commonly used as expansion devices in refrigeration systems. The capillary tube is considered straight and horizontal. The flow is taken as one-dimensional and adiabatic. Steady state and thermodynamic equilibrium conditions are assumed. The two-fluid model, involving four conservation equations and considering the hidrodynamic nonequilibrium between the liquid and vapor phases is applied to the flow region. The pressure profiles and the mass flow rates given by the model are compared with experimental data.

Uma aplicacao da celula de comutacao ZVS-PWM-GEPAE ao conversor DC-AC

This work presents the design and procedure of a DC-to-AC converter using a ZVS Commutation Cell developed by Barbi and Martins (1991) and applied to the family of DC-to-DC PWM converters. Firstly, we show the cell applied to buck converter. The stages of operation and the main current and voltage equations of the resonant devices are presented. Next, we adapt the converter to the regenerative operation mode. Hence, the full bridge converter at low frequency operation is conected on the DC-to-DC stage (at high frequency) output ends (Seixas, 1993). Commutation of zero voltage for all switches, PWM at constant frequency and neither overvoltage nor additional current stress are observed by digital simulation. The design example and experimental results obtained by prototype rated at 275 V, 1 kW and 40 kHz are also presented.

SAXS measurements of the porosity in Cu(II)-doped SnO2 xerogels during crystallization

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Solucao de sistemas lineares com matrizes e vetores esparsos em computadores vetoriais

This paper presents a methodology for solving a set of linear sparse equations on vector computers. The new methodology is able to exploit the matrix and vector sparsities. The implementation was made on a CRAY Y-MP 2E/232 computer and the results were taken from electric power systems with 118, 320, 725 and 1729 buses. The proposed methodology was compared with three previous methods and the results show the superior performance of the new one.

β-galactosidase immobilization on controlled pore silica

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

On optimizing micropower MOS regulated cascode circuits on switched current techniques

Trade-off between settling time and micropower consumption in MOS regulated cascode current sources as building parts in high-accuracy, current-switching D/A converters is analyzed. The regulation-loop frequency characteristic is obtained and difficulties to impose a dominant-pole condition to the resulting 2nd-order system are discussed. Raising pole frequencies while meeting consumption requirements is basically limited by parasitic capacitances. An alternative is found by imposing a twin-pole system in which design constraints are somewhat relaxed and settling slightly faster. Relationships between pole frequencies, transistor geometry and bias are established. Simulated waveforms obtained with PSpice of designed circuits following a voltage perturbation suggest a good agreement with theory. The proposed approach applied to the design of a micropower current-mode D/A converter improves its simulated settling performance.

Preparation, characterization and spectroscopy of the europium diphenylphosphinate complex

The purpose of this work is to study the preparation and spectroscopic behavior of the europium diphenylphosphinate complex -Eu(DPP)3. Elemental and thermogravimetric analysis, powder X-ray diffractometry, and infrared spectroscopy were applied to characterize the formula of the final product and the sixfold coordination of the Eu3+ ion. Excitation and emission spectra have been recorded at liquid nitrogen and room temperatures. The 5D0→7F2 transition intensity decreases when T decreases in comparison to the 5D0→7F1 transition intensity. Molecular mechanic calculations were developed in order to obtain the spatial coordinates of the Eu3+ and ligand ions. The simple overlap model was used to calculate the total splitting of the 5D0→7F1 transition, 5D0→7F0/5D 0→7F2 ntensity ratio and the intensity parameters, Ωλ (λ=2 and 4). Good agreements between theoretical predictions and experimental results have been obtained with g=2/3 as the effective charge and α=0.8×10-24 cm3 as the isotropic polarizability of the oxygen. © 1998 Elsevier Science S.A.

Highly excited states for the helium atom in the hyperspherical adiabatic approach

The hyperspherical adiabatic approach is used to obtain the highly excited series 1sns 1S e and 1s(n + 1)p 1P o of the helium atom. The introduction of appropriate asymptotic conditions at large values of the hyperspherical radius results in a stable algorithm that allows the calculation of the full atomic spectrum with precision of a few parts per million. Comparison with the variational calculations available in the literature shows that the accuracy of the results improves with increasing principal quantum number. We present the energies up to n = 31 which is the typical value used in multiphoton excitation experiments.