Modified radial basis function neural network using output transformation

A modified radial basis function (RBF) neural network and its identification algorithm based on observational data with heterogeneous noise are introduced. The transformed system output of Box-Cox is represented by the RBF neural network. To identify the model from observational data, the singular value decomposition of the full regression matrix consisting of basis functions formed by system input data is initially carried out and a new fast identification method is then developed using Gauss-Newton algorithm to derive the required Box-Cox transformation, based on a maximum likelihood estimator (MLE) for a model base spanned by the largest eigenvectors. Finally, the Box-Cox transformation-based RBF neural network, with good generalisation and sparsity, is identified based on the derived optimal Box-Cox transformation and an orthogonal forward regression algorithm using a pseudo-PRESS statistic to select a sparse RBF model with good generalisation. The proposed algorithm and its efficacy are demonstrated with numerical examples.

Elastic-net prefiltering for two-class classification

A two-stage linear-in-the-parameter model construction algorithm is proposed aimed at noisy two-class classification problems. The purpose of the first stage is to produce a prefiltered signal that is used as the desired output for the second stage which constructs a sparse linear-in-the-parameter classifier. The prefiltering stage is a two-level process aimed at maximizing a model's generalization capability, in which a new elastic-net model identification algorithm using singular value decomposition is employed at the lower level, and then, two regularization parameters are optimized using a particle-swarm-optimization algorithm at the upper level by minimizing the leave-one-out (LOO) misclassification rate. It is shown that the LOO misclassification rate based on the resultant prefiltered signal can be analytically computed without splitting the data set, and the associated computational cost is minimal due to orthogonality. The second stage of sparse classifier construction is based on orthogonal forward regression with the D-optimality algorithm. Extensive simulations of this approach for noisy data sets illustrate the competitiveness of this approach to classification of noisy data problems.

Particle swarm optimisation assisted classification using elastic net prefiltering

A novel two-stage construction algorithm for linear-in-the-parameters classifier is proposed, aiming at noisy two-class classification problems. The purpose of the first stage is to produce a prefiltered signal that is used as the desired output for the second stage to construct a sparse linear-in-the-parameters classifier. For the first stage learning of generating the prefiltered signal, a two-level algorithm is introduced to maximise the model's generalisation capability, in which an elastic net model identification algorithm using singular value decomposition is employed at the lower level while the two regularisation parameters are selected by maximising the Bayesian evidence using a particle swarm optimization algorithm. Analysis is provided to demonstrate how “Occam's razor” is embodied in this approach. The second stage of sparse classifier construction is based on an orthogonal forward regression with the D-optimality algorithm. Extensive experimental results demonstrate that the proposed approach is effective and yields competitive results for noisy data sets.

Filtro kl/dvs para atenuação do ruído "ground roll"

In geophysics there are several steps in the study of the Earth, one of them is the processing of seismic records. These records are obtained through observations made on the earth surface and are useful for information about the structure and composition of the inaccessible parts in great depths. Most of the tools and techniques developed for such studies has been applied in academic projects. The big problem is that the seismic processing power unwanted, recorded by receivers that do not bring any kind of information related to the reflectors can mask the information and/or generate erroneous information from the subsurface. This energy is known as unwanted seismic noise. To reduce the noise and improve a signal indicating a reflection, without losing desirable signals is sometimes a problem of difficult solution. The project aims to get rid of the ground roll noise, which shows a pattern characterized by low frequency, low rate of decay, low velocity and high amplituds. The Karhunen-Loève Transform is a great tool for identification of patterns based on the eigenvalues and eigenvectors. Together with the Karhunen-Loève Transform we will be using the Singular Value Decomposition, since it is a great mathematical technique for manipulating data

Parâmetro de regularização em problemas inversos: estudo numérico com a transformada de Radon

In general, an inverse problem corresponds to find a value of an element x in a suitable vector space, given a vector y measuring it, in some sense. When we discretize the problem, it usually boils down to solve an equation system f(x) = y, where f : U Rm ! Rn represents the step function in any domain U of the appropriate Rm. As a general rule, we arrive to an ill-posed problem. The resolution of inverse problems has been widely researched along the last decades, because many problems in science and industry consist in determining unknowns that we try to know, by observing its effects under certain indirect measures. Our general subject of this dissertation is the choice of Tykhonov´s regulaziration parameter of a poorly conditioned linear problem, as we are going to discuss on chapter 1 of this dissertation, focusing on the three most popular methods in nowadays literature of the area. Our more specific focus in this dissertation consists in the simulations reported on chapter 2, aiming to compare the performance of the three methods in the recuperation of images measured with the Radon transform, perturbed by the addition of gaussian i.i.d. noise. We choosed a difference operator as regularizer of the problem. The contribution we try to make, in this dissertation, mainly consists on the discussion of numerical simulations we execute, as is exposed in Chapter 2. We understand that the meaning of this dissertation lays much more on the questions which it raises than on saying something definitive about the subject. Partly, for beeing based on numerical experiments with no new mathematical results associated to it, partly for being about numerical experiments made with a single operator. On the other hand, we got some observations which seemed to us interesting on the simulations performed, considered the literature of the area. In special, we highlight observations we resume, at the conclusion of this work, about the different vocations of methods like GCV and L-curve and, also, about the optimal parameters tendency observed in the L-curve method of grouping themselves in a small gap, strongly correlated with the behavior of the generalized singular value decomposition curve of the involved operators, under reasonably broad regularity conditions in the images to be recovered

Identificação dos parâmetros modais utilizando apenas as respostas da estrutura: identificação no domínio do tempo

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Análise de resolução em tomografia interpoços em 3-D

A aplicação de métodos de inversão aos dados de múltiplos levantamentos sísmicos interpoços permite a reconstrução de modelos de vagarosidade em 3-D de alta resolução adequados para monitoramento de processos de recuperação avançada de petróleo e caracterização de reservatórios. Entretanto, a falta de cobertura volumétrica uniforme de raios de levantamentos interpoços exige informação adicional ao sistema tomográfico para obtenção de soluções estáveis. A discretização do modelo em uma malha 3-D com células prismáticas triangulares e a decomposição em valores singulares são utilizadas para avaliar a reconstrução tomográfica em 3-D. O ângulo da projeção de modelos-alvo no subespaço ortogonal ao espaço nulo efetivo da matriz tomográfica é um critério adequado para se otimizar a malha de discretização do modelo interpretativo e a geometria de aquisição dos dados de modo a melhorar o condicionamento da reconstrução tomográfica. Esta abordagem pode ser utilizada durante as iterações lineares para redefinir a malha ou avaliar a necessidade de informação a priori adicional ao sistema tomográfico.

Inversão em geofísica de poço: um estudo sobre ambiguidade

A ambiguidade na inversão de dados de geofísica de poço é estudada através da análise fatorial Q-modal. Este método é baseado na análise de um número finito de soluções aceitáveis, que são ordenadas, no espaço de soluções, segundo a direção de maior ambiguidade. A análise da variação dos parâmetros ao longo dessas soluções ordenadas permite caracterizar aqueles que são mais influentes na ambiguidade. Como a análise Q-modal é baseada na determinação de uma região de ambiguidade, obtida de modo empírico a partir de um número finito de soluções aceitáveis, é possível analisar a ambiguidade devida não só a erros nas observações, como também a pequenos erros no modelo interpretativo. Além disso, a análise pode ser aplicada mesmo quando os modelos interpretativos ou a relação entre os parâmetros não são lineares. A análise fatorial é feita utilizando-se dados sintéticos, e então comparada com a análise por decomposição em valores singulares, mostrando-se mais eficaz, uma vez que requer premissas menos restritivas, permitindo, desse modo, caracterizar a ambiguidade de modo mais realístico. A partir da determinação dos parâmetros com maior influência na ambiguidade do modelo é possível reparametrizá-lo, agrupando-os em um único parâmetro, redefinindo assim o modelo interpretativo. Apesar desta reparametrização incorrer na perda de resolução dos parâmetros agrupados, o novo modelo tem sua ambiguidade bastante reduzida.

Deteccão de complexos QRS em eletrocardiogramas baseada na decomposição em valores singulares em multirresolução

Pós-graduação em Engenharia Elétrica - FEIS

A generalization of the Moore-Penrose inverse related to matrix subspaces of C(nxm)

[EN]A natural generalization of the classical Moore-Penrose inverse is presented. The so-called S-Moore-Penrose inverse of a m x n complex matrix A, denoted by As, is defined for any linear subspace S of the matrix vector space Cnxm. The S-Moore-Penrose inverse As is characterized using either the singular value decomposition or (for the nonsingular square case) the orthogonal complements with respect to the Frobenius inner product. These results are applied to the preconditioning of linear systems based on Frobenius norm minimization and to the linearly constrained linear least squares problem.

Factors that determine penumbral tissue loss in acute ischaemic stroke

The goal of acute stroke treatment with intravenous thrombolysis or endovascular recanalization techniques is to rescue the penumbral tissue. Therefore, knowing the factors that influence the loss of penumbral tissue is of major interest. In this study we aimed to identify factors that determine the evolution of the penumbra in patients with proximal (M1 or M2) middle cerebral artery occlusion. Among these factors collaterals as seen on angiography were of special interest. Forty-four patients were included in this analysis. They had all received endovascular therapy and at least minimal reperfusion was achieved. Their penumbra was assessed with perfusion- and diffusion-weighted imaging. Perfusion-weighted imaging volumes were defined by circular singular value decomposition deconvolution maps (Tmax > 6 s) and results were compared with volumes obtained with non-deconvolved maps (time to peak > 4 s). Loss of penumbral volume was defined as difference of post- minus pretreatment diffusion-weighted imaging volumes and calculated in per cent of pretreatment penumbral volume. Correlations between baseline characteristics, reperfusion, collaterals, time to reperfusion and penumbral volume loss were assessed using analysis of covariance. Collaterals (P = 0.021), reperfusion (P = 0.003) and their interaction (P = 0.031) independently influenced penumbral tissue loss, but not time from magnetic resonance (P = 0.254) or from symptom onset (P = 0.360) to reperfusion. Good collaterals markedly slowed down and reduced the penumbra loss: in patients with thrombolysis in cerebral infarction 2 b-3 reperfusion and without any haemorrhage, 27% of the penumbra was lost with 8.9 ml/h with grade 0 collaterals, whereas 11% with 3.4 ml/h were lost with grade 1 collaterals. With grade 2 collaterals the penumbral volume change was -2% with -1.5 ml/h, indicating an overall diffusion-weighted imaging lesion reversal. We conclude that collaterals and reperfusion are the main factors determining loss of penumbral tissue in patients with middle cerebral artery occlusions. Collaterals markedly reduce and slow down penumbra loss. In patients with good collaterals, time to successful reperfusion accounts only for a minor fraction of penumbra loss. These results support the hypothesis that good collaterals extend the time window for acute stroke treatment.

Mineral composition and experimental results from XRD analyses of sediments from ODP Leg 190 sites

X-ray diffraction analyses of the clay-sized fraction of sediments from the Nankai Trough and Shikoku Basin (Sites 1173, 1174, and 1177 of the Ocean Drilling Program) reveal spatial and temporal trends in clay minerals and diagenesis. More detrital smectite was transported into the Shikoku Basin during the early-middle Miocene than what we observe today, and smectite input decreased progressively through the late Miocene and Pliocene. Volcanic ash has been altered to dioctahedral smectite in the upper Shikoku Basin facies at Site 1173; the ash alteration front shifts upsection to the outer trench-wedge facies at Site 1174. At greater depths (lower Shikoku Basin facies), smectite alters to illite/smectite mixed-layer clay, but reaction progress is incomplete. Using ambient geothermal conditions, a kinetic model overpredicts the amount of illite in illite/smectite clays by 15%-20% at Site 1174. Numerical simulations come closer to observations if the concentration of potassium in pore water is reduced or the time of burial is shortened. Model results match X-ray diffraction results fairly well at Site 1173. The geothermal gradient at Site 1177 is substantially lower than at Sites 1173 and 1174; consequently, volcanic ash alters to smectite in lower Shikoku Basin deposits but smectite-illite diagenesis has not started. The absolute abundance of smectite in mudstones from Site 1177 is sufficient (30-60 wt%) to influence the strata's shear strength and hydrogeology as they subduct along the Ashizuri Transect.

Mineral composition of sediments from ODP Leg 190 sites and DSDP Hole 31-297

This data report documents the acquisition of two new sets of normalization factors for semiquantitative X-ray diffraction analyses. One set of factors is for bulk sediment powders, and the other applies to oriented aggregates of clay-sized fractions (<2 µm). We analyzed mixtures of standard minerals with known weight percentages of each component and solved for the normalization factors using matrix singular value decomposition. The components in bulk powders include total clay minerals (a mixture of smectite, illite, and chlorite), quartz, plagioclase, and calcite. For clay-sized fractions, the minerals are smectite, illite, chlorite, and quartz. We tested the utility of the method by analyzing natural mudstone specimens from Site 297 of the Deep Sea Drilling Project, which is located in the Shikoku Basin south of Site 1177 of the Ocean Drilling Program (Ashizuri transect).