Two-Phase Mapping for Projecting Massive Data Sets

Most multidimensional projection techniques rely on distance (dissimilarity) information between data instances to embed high-dimensional data into a visual space. When data are endowed with Cartesian coordinates, an extra computational effort is necessary to compute the needed distances, making multidimensional projection prohibitive in applications dealing with interactivity and massive data. The novel multidimensional projection technique proposed in this work, called Part-Linear Multidimensional Projection (PLMP), has been tailored to handle multivariate data represented in Cartesian high-dimensional spaces, requiring only distance information between pairs of representative samples. This characteristic renders PLMP faster than previous methods when processing large data sets while still being competitive in terms of precision. Moreover, knowing the range of variation for data instances in the high-dimensional space, we can make PLMP a truly streaming data projection technique, a trait absent in previous methods.

Interactive Vector Field Feature Identification

We introduce a flexible technique for interactive exploration of vector field data through classification derived from user-specified feature templates. Our method is founded on the observation that, while similar features within the vector field may be spatially disparate, they share similar neighborhood characteristics. Users generate feature-based visualizations by interactively highlighting well-accepted and domain specific representative feature points. Feature exploration begins with the computation of attributes that describe the neighborhood of each sample within the input vector field. Compilation of these attributes forms a representation of the vector field samples in the attribute space. We project the attribute points onto the canonical 2D plane to enable interactive exploration of the vector field using a painting interface. The projection encodes the similarities between vector field points within the distances computed between their associated attribute points. The proposed method is performed at interactive rates for enhanced user experience and is completely flexible as showcased by the simultaneous identification of diverse feature types.

Novel Statistical Methods in Quantitative Genetics : Modeling Genetic Variance for Quantitative Trait Loci Mapping and Genomic Evaluation

This thesis develops and evaluates statistical methods for different types of genetic analyses, including quantitative trait loci (QTL) analysis, genome-wide association study (GWAS), and genomic evaluation. The main contribution of the thesis is to provide novel insights in modeling genetic variance, especially via random effects models. In variance component QTL analysis, a full likelihood model accounting for uncertainty in the identity-by-descent (IBD) matrix was developed. It was found to be able to correctly adjust the bias in genetic variance component estimation and gain power in QTL mapping in terms of precision.  Double hierarchical generalized linear models, and a non-iterative simplified version, were implemented and applied to fit data of an entire genome. These whole genome models were shown to have good performance in both QTL mapping and genomic prediction. A re-analysis of a publicly available GWAS data set identified significant loci in Arabidopsis that control phenotypic variance instead of mean, which validated the idea of variance-controlling genes.  The works in the thesis are accompanied by R packages available online, including a general statistical tool for fitting random effects models (hglm), an efficient generalized ridge regression for high-dimensional data (bigRR), a double-layer mixed model for genomic data analysis (iQTL), a stochastic IBD matrix calculator (MCIBD), a computational interface for QTL mapping (qtl.outbred), and a GWAS analysis tool for mapping variance-controlling loci (vGWAS).

Uso da análise discriminante regularizada (RDA) no reconhecimento de padrões em imagens digitais hiperespectral de sensoriamento remoto

Em cenas naturais, ocorrem com certa freqüência classes espectralmente muito similares, isto é, os vetores média são muito próximos. Em situações como esta, dados de baixa dimensionalidade (LandSat-TM, Spot) não permitem uma classificação acurada da cena. Por outro lado, sabe-se que dados em alta dimensionalidade [FUK 90] tornam possível a separação destas classes, desde que as matrizes covariância sejam suficientemente distintas. Neste caso, o problema de natureza prática que surge é o da estimação dos parâmetros que caracterizam a distribuição de cada classe. Na medida em que a dimensionalidade dos dados cresce, aumenta o número de parâmetros a serem estimados, especialmente na matriz covariância. Contudo, é sabido que, no mundo real, a quantidade de amostras de treinamento disponíveis, é freqüentemente muito limitada, ocasionando problemas na estimação dos parâmetros necessários ao classificador, degradando portanto a acurácia do processo de classificação, na medida em que a dimensionalidade dos dados aumenta. O Efeito de Hughes, como é chamado este fenômeno, já é bem conhecido no meio científico, e estudos vêm sendo realizados com o objetivo de mitigar este efeito. Entre as alternativas propostas com a finalidade de mitigar o Efeito de Hughes, encontram-se as técnicas de regularização da matriz covariância. Deste modo, técnicas de regularização para a estimação da matriz covariância das classes, tornam-se um tópico interessante de estudo, bem como o comportamento destas técnicas em ambientes de dados de imagens digitais de alta dimensionalidade em sensoriamento remoto, como por exemplo, os dados fornecidos pelo sensor AVIRIS. Neste estudo, é feita uma contextualização em sensoriamento remoto, descrito o sistema sensor AVIRIS, os princípios da análise discriminante linear (LDA), quadrática (QDA) e regularizada (RDA) são apresentados, bem como os experimentos práticos dos métodos, usando dados reais do sensor. Os resultados mostram que, com um número limitado de amostras de treinamento, as técnicas de regularização da matriz covariância foram eficientes em reduzir o Efeito de Hughes. Quanto à acurácia, em alguns casos o modelo quadrático continua sendo o melhor, apesar do Efeito de Hughes, e em outros casos o método de regularização é superior, além de suavizar este efeito. Esta dissertação está organizada da seguinte maneira: No primeiro capítulo é feita uma introdução aos temas: sensoriamento remoto (radiação eletromagnética, espectro eletromagnético, bandas espectrais, assinatura espectral), são também descritos os conceitos, funcionamento do sensor hiperespectral AVIRIS, e os conceitos básicos de reconhecimento de padrões e da abordagem estatística. No segundo capítulo, é feita uma revisão bibliográfica sobre os problemas associados à dimensionalidade dos dados, à descrição das técnicas paramétricas citadas anteriormente, aos métodos de QDA, LDA e RDA, e testes realizados com outros tipos de dados e seus resultados.O terceiro capítulo versa sobre a metodologia que será utilizada nos dados hiperespectrais disponíveis. O quarto capítulo apresenta os testes e experimentos da Análise Discriminante Regularizada (RDA) em imagens hiperespectrais obtidos pelo sensor AVIRIS. No quinto capítulo são apresentados as conclusões e análise final. A contribuição científica deste estudo, relaciona-se à utilização de métodos de regularização da matriz covariância, originalmente propostos por Friedman [FRI 89] para classificação de dados em alta dimensionalidade (dados sintéticos, dados de enologia), para o caso especifico de dados de sensoriamento remoto em alta dimensionalidade (imagens hiperespectrais). A conclusão principal desta dissertação é que o método RDA é útil no processo de classificação de imagens com dados em alta dimensionalidade e classes com características espectrais muito próximas.

Detecting cell assemblies in large neuronal populations

Recent progress in the technology for single unit recordings has given the neuroscientific community theopportunity to record the spiking activity of large neuronal populations. At the same pace, statistical andmathematical tools were developed to deal with high-dimensional datasets typical of such recordings.A major line of research investigates the functional role of subsets of neurons with significant co-firingbehavior: the Hebbian cell assemblies. Here we review three linear methods for the detection of cellassemblies in large neuronal populations that rely on principal and independent component analysis.Based on their performance in spike train simulations, we propose a modified framework that incorpo-rates multiple features of these previous methods. We apply the new framework to actual single unitrecordings and show the existence of cell assemblies in the rat hippocampus, which typically oscillate attheta frequencies and couple to different phases of the underlying field rhythm

Information Visualization to Enhance Sensitivity and Selectivity in Biosensing

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

Bright solitons in coupled defocusing NLS equation supported by coupling: Application to Bose-Einstein condensation

We demonstrate the formation of bright solitons in coupled self-defocusing nonlinear Schrodinger (NLS) equation supported by attractive coupling. As an application we use a time-dependent dynamical mean-field model to study the formation of stable bright solitons in two-component repulsive Bose-Einstein condensates (BECs) supported by interspecies attraction in a quasi one-dimensional geometry. When all interactions are repulsive, there cannot be bright solitons. However, bright solitons can be formed in two-component repulsive BECs for a sufficiently attractive interspecies interaction, which induces an attractive effective interaction among bosons of same type. (c) 2005 Elsevier B.V. All rights reserved.

Smooth landscape solvent dynamics in electron transfer reactions

Solvent effects play a major role in controlling electron-transfer reactions. The solvent dynamics happens on a very high-dimensional surface, and this complex landscape is populated by a large number of minima. A critical problem is to understand the conditions under which the solvent dynamics can be represented by a single collective reaction coordinate. When this unidimensional representation is valid, one recovers the successful Marcus theory. In this study the approach used in a previous work [V. B. P. Leite and J. N. Onuchic; J. Phys. Chem. 100, 7680 (1996)] is extended to treat a more realistic solvent model, which includes energy correlation. The dynamics takes place in a smooth and well behaved landscape. The single shell of solvent molecules around a cavity is described by a two-dimensional system with periodic boundary conditions with nearest neighbor interaction. It is shown how the polarization-dependent effects can be inferred. The existence of phase transitions depends on a factor y proportional to the contribution from the two parameters of the model. For the present model, γ suggests the existence of weak kinetic phase transitions, which are used in the analysis of solvent effects in charge-transfer reactions. © 1999 American Institute of Physics.

Mass-imbalanced three-body systems in two dimensions

We consider three-body systems in two dimensions with zero-range interactions for general masses and interaction strengths. The momentum-space Schrödinger equation is solved numerically and in the Born-Oppenheimer (BO) approximation. The BO expression is derived using separable potentials and yields a concise adiabatic potential between the two heavy particles. The BO potential is Coulomb-like and exponentially decreasing at small and large distances, respectively. While we find similar qualitative features to previous studies, we find important quantitative differences. Our results demonstrate that mass-imbalanced systems that are accessible in the field of ultracold atomic gases can have a rich three-body bound state spectrum in two-dimensional geometries. Small light-heavy mass ratios increase the number of bound states. For 87Rb-87Rb-6Li and 133Cs- 133Cs-6Li we find respectively three and four bound states. © 2013 IOP Publishing Ltd.

Representação e armazenamento de dados cadastrais 3D em banco de dados geográficos

Pós-graduação em Ciências Cartográficas - FCT

Visualization of Protein Folding Funnels in Lattice Models

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

Learning kernels for support vector machines with polynomial powers of sigmoid

In the pattern recognition research field, Support Vector Machines (SVM) have been an effectiveness tool for classification purposes, being successively employed in many applications. The SVM input data is transformed into a high dimensional space using some kernel functions where linear separation is more likely. However, there are some computational drawbacks associated to SVM. One of them is the computational burden required to find out the more adequate parameters for the kernel mapping considering each non-linearly separable input data space, which reflects the performance of SVM. This paper introduces the Polynomial Powers of Sigmoid for SVM kernel mapping, and it shows their advantages over well-known kernel functions using real and synthetic datasets.

Aprendizado de máquina baseado em tensores e suas aplicacções para floresta de caminhos ótimos

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Homework: Is There More To It Than Answers?

In this action research study of my two high school geometry classrooms, I investigated the use of homework. By changing the focus on homework away from the answers to the process involved in getting the answers, I found that students felt more confident, utilized their class time better, and placed more effort on complex problems. Their questions also became more specific and more effective for finding gaps in their understanding. As a result of this research, I plan to change my strategy in the practice of homework. I will give students the answers on multi-step problems to allow them the opportunity to utilize problem solving and critical thinking skills to gain practice in autonomous learning.

EFFECT OF THERMAL TREATMENT ON THE CHEMICAL CHARACTERISTICS OF WOOD FROM Eucalyptus grandis W. Hill ex Maiden UNDER DIFFERENT ATMOSPHERIC CONDITIONS

Thermal treatment (thermal rectification) is a process in which technological properties of wood are modified using thermal energy, the result of Which is often value-added wood. Thermally treated wood takes on similar color shades to tropical woods and offers considerable resistance to destructive microorganisms and climate action, in addition to having high dimensional stability and low hygroscopicity. Wood samples of Eucalyptus grandis were subjected to various thermal treatments, as performed in presence (140 degrees C; 160 degrees C; 180 degrees C) or in absence of oxygen (160 degrees C; 180 degrees C; 200 degrees C) inside a thermal treatment chamber, and then studied as to their chemical characteristics. Increasing the maximum treatment temperatures led to a reduction in the holocellulose content of samples as a result of the degradation and volatilization of hemicelluloses, also leading to an increase in the relative lignin content. Except for glucose, all monosaccharide levels were found to decrease in samples after the thermal treatment at a maximum temperature of 200 degrees C. The thermal treatment above 160 degrees C led to increased levels of total extractives in the wood samples, probably ascribed to the emergence of low molecular weight substances as a result of thermal degradation. Overall, it was not possible to clearly determine the effect of presence or absence of oxygen in the air during thermal treatment on the chemical characteristics of the relevant wood samples.