Two-stage mixed discrete-continuous identification of radial basis function (RBF) neural models for nonlinear systems

The identification of nonlinear dynamic systems using radial basis function (RBF) neural models is studied in this paper. Given a model selection criterion, the main objective is to effectively and efficiently build a parsimonious compact neural model that generalizes well over unseen data. This is achieved by simultaneous model structure selection and optimization of the parameters over the continuous parameter space. It is a mixed-integer hard problem, and a unified analytic framework is proposed to enable an effective and efficient two-stage mixed discrete-continuous; identification procedure. This novel framework combines the advantages of an iterative discrete two-stage subset selection technique for model structure determination and the calculus-based continuous optimization of the model parameters. Computational complexity analysis and simulation studies confirm the efficacy of the proposed algorithm.

Attentional Selection in Object Recognition

A key problem in object recognition is selection, namely, the problem of identifying regions in an image within which to start the recognition process, ideally by isolating regions that are likely to come from a single object. Such a selection mechanism has been found to be crucial in reducing the combinatorial search involved in the matching stage of object recognition. Even though selection is of help in recognition, it has largely remained unsolved because of the difficulty in isolating regions belonging to objects under complex imaging conditions involving occlusions, changing illumination, and object appearances. This thesis presents a novel approach to the selection problem by proposing a computational model of visual attentional selection as a paradigm for selection in recognition. In particular, it proposes two modes of attentional selection, namely, attracted and pay attention modes as being appropriate for data and model-driven selection in recognition. An implementation of this model has led to new ways of extracting color, texture and line group information in images, and their subsequent use in isolating areas of the scene likely to contain the model object. Among the specific results in this thesis are: a method of specifying color by perceptual color categories for fast color region segmentation and color-based localization of objects, and a result showing that the recognition of texture patterns on model objects is possible under changes in orientation and occlusions without detailed segmentation. The thesis also presents an evaluation of the proposed model by integrating with a 3D from 2D object recognition system and recording the improvement in performance. These results indicate that attentional selection can significantly overcome the computational bottleneck in object recognition, both due to a reduction in the number of features, and due to a reduction in the number of matches during recognition using the information derived during selection. Finally, these studies have revealed a surprising use of selection, namely, in the partial solution of the pose of a 3D object.

Local Influence Under Parameter Constraints

Calculations of local influence curvatures and leverage have been well developed when the parameters are unrestricted. In this article, we discuss the assessment of local influence and leverage under linear equality parameter constraints with extensions to inequality constraints. Using a penalized quadratic function we express the normal curvature of local influence for arbitrary perturbation schemes and the generalized leverage matrix in interpretable forms, which depend on restricted and unrestricted components. The results are quite general and can be applied in various statistical models. In particular, we derive the normal curvature under three useful perturbation schemes for generalized linear models. Four illustrative examples are analyzed by the methodology developed in the article.

Local Influence Analysis for Skew-Normal Linear Mixed Models

In this article, we consider local influence analysis for the skew-normal linear mixed model (SN-LMM). As the observed data log-likelihood associated with the SN-LMM is intractable, Cook`s well-known approach cannot be applied to obtain measures of local influence. Instead, we develop local influence measures following the approach of Zhu and Lee (2001). This approach is based on the use of an EM-type algorithm and is measurement invariant under reparametrizations. Four specific perturbation schemes are discussed. Results obtained for a simulated data set and a real data set are reported, illustrating the usefulness of the proposed methodology.

Genetic heterogeneity of residual variance : estimation of variance components using double hierarchical generalized linear models

Background: The sensitivity to microenvironmental changes varies among animals and may be under genetic control. It is essential to take this element into account when aiming at breeding robust farm animals. Here, linear mixed models with genetic effects in the residual variance part of the model can be used. Such models have previously been fitted using EM and MCMC algorithms. Results: We propose the use of double hierarchical generalized linear models (DHGLM), where the squared residuals are assumed to be gamma distributed and the residual variance is fitted using a generalized linear model. The algorithm iterates between two sets of mixed model equations, one on the level of observations and one on the level of variances. The method was validated using simulations and also by re-analyzing a data set on pig litter size that was previously analyzed using a Bayesian approach. The pig litter size data contained 10,060 records from 4,149 sows. The DHGLM was implemented using the ASReml software and the algorithm converged within three minutes on a Linux server. The estimates were similar to those previously obtained using Bayesian methodology, especially the variance components in the residual variance part of the model. Conclusions: We have shown that variance components in the residual variance part of a linear mixed model can be estimated using a DHGLM approach. The method enables analyses of animal models with large numbers of observations. An important future development of the DHGLM methodology is to include the genetic correlation between the random effects in the mean and residual variance parts of the model as a parameter of the DHGLM.

Modified Mohr-Coulomb fracture model for anisotropic sheet materials under limited triaxial stress conditions

 This paper reviews recent work of the authors to model necking and fracture for anisotropic materials, which requires consideration of the stress conditions that vary through the thickness of the sheet, and in particular, taking into consideration the conditions at individual integration points. Although the prior work adequately addresses the roll of triaxial stress conditions on necking, the fracture model developed in the prior work was limited in its application to analysis of plane-stress conditions. In this work, a fracture model is developed for application to a limited range of triaxial stress conditions, in which the through-thickness shear stresses are assumed to be negligible, but the normal stress is allowed to be non-zero. The model is extended in a way that reduces to the prior anisotropic fracture model under plane stress conditions, but includes the contribution of a triaxial stress condition in a way that retains the desired features
of the Mohr-Coulomb Model.

Seleção para peso pós-desmama em um rebanho Gir. 1. Resposta direta e correlacionada em 21 anos de seleção

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Use of direct and iterative solvers for estimation of SNP effects in genome-wide selection

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Parameter space for a dissipative Fermi-Ulam model

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

Detecting Loci under Recent Positive Selection in Dairy and Beef Cattle by Combining Different Genome-Wide Scan Methods

As the methodologies available for the detection of positive selection from genomic data vary in terms of assumptions and execution, weak correlations are expected among them. However, if there is any given signal that is consistently supported across different methodologies, it is strong evidence that the locus has been under past selection. In this paper, a straightforward frequentist approach based on the Stouffer Method to combine P-values across different tests for evidence of recent positive selection in common variations, as well as strategies for extracting biological information from the detected signals, were described and applied to high density single nucleotide polymorphism (SNP) data generated from dairy and beef cattle (taurine and indicine). The ancestral Bovinae allele state of over 440,000 SNP is also reported. Using this combination of methods, highly significant (P<3.17×10-7) population-specific sweeps pointing out to candidate genes and pathways that may be involved in beef and dairy production were identified. The most significant signal was found in the Cornichon homolog 3 gene (CNIH3) in Brown Swiss (P = 3.82×10-12), and may be involved in the regulation of pre-ovulatory luteinizing hormone surge. Other putative pathways under selection are the glucolysis/gluconeogenesis, transcription machinery and chemokine/cytokine activity in Angus; calpain-calpastatin system and ribosome biogenesis in Brown Swiss; and gangliosides deposition in milk fat globules in Gyr. The composite method, combined with the strategies applied to retrieve functional information, may be a useful tool for surveying genome-wide selective sweeps and providing insights in to the source of selection.

Avaliação agronômica e modo de reprodução de híbridos intraespecíficos de Brachiaria decumbens

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Análise de polimorfismos em genes do eixo somatotrópico em bovinos Nelore selecionados para crescimento

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Associações genéticas com o marcador alfa actina 1, e variabilidade genética de características de importância econômica de frangos de corte

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Genetic parameters and simultaneous selection for root yield, adaptability and stability of cassava genotypes

O objetivo deste trabalho foi estimar parâmetros genéticos e avaliar a seleção simultânea quanto à produtividade de raízes e à adaptabilidade e estabilidade de genótipos de mandioca. Os efeitos dos genótipos foram considerados como fixos e aleatórios, e a metodologia de modelos mistos (REML/Blup) foi utilizada para estimar os parâmetros genéticos e a média harmônica do desempenho relativo dos valores genotípicos (MHPRVG), para seleção simultânea. Dez genótipos foram avaliados em delineamento de blocos ao acaso, com quatro repetições. O experimento foi realizado nos municípios de Altamira, Santarém e Santa Luzia do Pará, PA, nos anos agrícolas de 2009/2010, 2010/2011 e 2011/2012. As raízes foram colhidas 12 meses após o plantio, em todos os locais testados. A produtividade de raízes apresentou baixo coeficiente de variação genotípica (4,25%) e herdabilidade de parcelas individuais no sentido amplo (0,0424), o que resultou em baixo ganho genético. Em razão da baixa correlação genotípica (0,15), a classificação dos genótipos quanto à produtividade de raízes variou de acordo com o ambiente. Os genótipos CPATU 060, CPATU 229 e CPATU 404 destacaram-se quanto à produtividade, adaptabilidade e estabilidade.

Polymorphism analysis in genes of the somatotropic axis in Nellore cattle selected for growth

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