Kernel density construction using orthogonal forward regression

An automatic algorithm is derived for constructing kernel density estimates based on a regression approach that directly optimizes generalization capability. Computational efficiency of the density construction is ensured using an orthogonal forward regression, and the algorithm incrementally minimizes the leave-one-out test score. Local regularization is incorporated into the density construction process to further enforce sparsity. Examples are included to demonstrate the ability of the proposed algorithm to effectively construct a very sparse kernel density estimate with comparable accuracy to that of the full sample Parzen window density estimate.

An orthogonal forward regression technique for sparse kernel density estimation

Using the classical Parzen window (PW) estimate as the desired response, the kernel density estimation is formulated as a regression problem and the orthogonal forward regression technique is adopted to construct sparse kernel density (SKD) estimates. The proposed algorithm incrementally minimises a leave-one-out test score to select a sparse kernel model, and a local regularisation method is incorporated into the density construction process to further enforce sparsity. The kernel weights of the selected sparse model are finally updated using the multiplicative nonnegative quadratic programming algorithm, which ensures the nonnegative and unity constraints for the kernel weights and has the desired ability to reduce the model size further. Except for the kernel width, the proposed method has no other parameters that need tuning, and the user is not required to specify any additional criterion to terminate the density construction procedure. Several examples demonstrate the ability of this simple regression-based approach to effectively construct a SKID estimate with comparable accuracy to that of the full-sample optimised PW density estimate. (c) 2007 Elsevier B.V. All rights reserved.

Sparse modeling using orthogonal forward regression with PRESS statistic and regularization

The paper introduces an efficient construction algorithm for obtaining sparse linear-in-the-weights regression models based on an approach of directly optimizing model generalization capability. This is achieved by utilizing the delete-1 cross validation concept and the associated leave-one-out test error also known as the predicted residual sums of squares (PRESS) statistic, without resorting to any other validation data set for model evaluation in the model construction process. Computational efficiency is ensured using an orthogonal forward regression, but the algorithm incrementally minimizes the PRESS statistic instead of the usual sum of the squared training errors. A local regularization method can naturally be incorporated into the model selection procedure to further enforce model sparsity. The proposed algorithm is fully automatic, and the user is not required to specify any criterion to terminate the model construction procedure. Comparisons with some of the existing state-of-art modeling methods are given, and several examples are included to demonstrate the ability of the proposed algorithm to effectively construct sparse models that generalize well.

Orthogonal-least-squares regression: A unified approach for data modelling

A unified approach is proposed for data modelling that includes supervised regression and classification applications as well as unsupervised probability density function estimation. The orthogonal-least-squares regression based on the leave-one-out test criteria is formulated within this unified data-modelling framework to construct sparse kernel models that generalise well. Examples from regression, classification and density estimation applications are used to illustrate the effectiveness of this generic data-modelling approach for constructing parsimonious kernel models with excellent generalisation capability. (C) 2008 Elsevier B.V. All rights reserved.

Probability density estimation with tunable kernels using orthogonal forward regression

A generalized or tunable-kernel model is proposed for probability density function estimation based on an orthogonal forward regression procedure. Each stage of the density estimation process determines a tunable kernel, namely, its center vector and diagonal covariance matrix, by minimizing a leave-one-out test criterion. The kernel mixing weights of the constructed sparse density estimate are finally updated using the multiplicative nonnegative quadratic programming algorithm to ensure the nonnegative and unity constraints, and this weight-updating process additionally has the desired ability to further reduce the model size. The proposed tunable-kernel model has advantages, in terms of model generalization capability and model sparsity, over the standard fixed-kernel model that restricts kernel centers to the training data points and employs a single common kernel variance for every kernel. On the other hand, it does not optimize all the model parameters together and thus avoids the problems of high-dimensional ill-conditioned nonlinear optimization associated with the conventional finite mixture model. Several examples are included to demonstrate the ability of the proposed novel tunable-kernel model to effectively construct a very compact density estimate accurately.

O uso de implantes orbitários de polietileno granulado de ultra-alto peso molecular no reparo de cavidades anoftálmicas

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

Analysis of the effects of irradiation in osseointegrated dental implants

Objective: The purpose of the present study was to evaluate the influence of radiation in osseointegrated dental implants installed in tibiae of rats.Material and methods: Screw-shaped implants (2.5 mm diameter by 3.5 mm length) were custom made from commercially pure titanium bars. Titanium implants were blasted and sterilized before implantation. Animals were divided into two groups of 12 animals each and the rats were not paired after the groups' formation. The experimental group (group 1) received external irradiation 4 weeks after surgery while in the control group (group 2) animals were kept free of radiation. The shear strength required to detach the implant from bone was measured by push-out testing and osseointegration was histologically evaluated.Results: Results showed that the compressive strength of irradiated implants (33.49 MPa) was significantly lower than the compressive strength of non-irradiated implants (48.05 MPa).Conclusions: We concluded that the mechanical strength bonding between implants and host tissues decreased after irradiation.

Bond strength of Epiphany (TM) Sealer combined with different adhesive systems photo-activated with LED and QTH

The Epiphany (TM) Sealer is a new dual-curing resin-based sealer and has been introduced as an alternative to gutta-percha and traditional root canal sealers. The canal filling is claimed to create a seal with the dentinal tubules within the root canal system producing a 'monoblock' effect between the sealer and dentinal tubules. Therefore, considering the possibility to incorporate the others adhesive systems, it is important to study the bond strength of the resulting cement. Forty-eight root mandibular canines were sectioned 8-mm below CEJ. The dentine discs were prepared using a tapered diamond bur and irrigated with 1% NaOCl and 17% EDTA. Previous the application Epiphany (TM) Sealer, the Epiphany (TM) Primer, AdheSE, and One Up Bond F were applied to the root canal walls. The LED and QTH (Quartz Tungsten Halogen) were used to photo-activation during 45 s with power density of 400 and 720 mW/cm(2), respectively. The specimens were performed on a universal testing machine at a cross-head speed of 1 mm/min until bond failure occurred. The force was recorded and the debonding values were used to calculate Push-out bond strength. The analysis of variance (ANOVA) and Tukey's post-hoc tests showed significant statistical differences (P < 0.05) to Epiphany (TM) Sealer/Epiphany (TM) Primer/QTH and EpiphanyTM Sealer/AdheSE/QTH, which had the highest mean values of bond strength. The efficiency of resin-based filling materials are dependent the type of light curing unit used including the power density, the polymerization characteristics of these resin-based filling materials, depending on the primer/adhesive used.

Novel production method of porous surface Ti samples for biomedical application

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

Bond strengths, degree of conversion of the cement and molecular structure of the adhesive-dentine joint in fibre post restorations

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Does the thickness of the resin cement affect the bond strength of a fiber post to the root dentin?

This study aimed to evaluate the influence of cement thickness on the bond strength of a fiber-reinforced composite (FRC) post system to the root dentin. Eighteen single-rooted human teeth were decoronated (length: 16 mm), the canals were prepared, and the specimens were randomly allocated to 2 groups (n = 9): group 1 (low cement thickness), in which size 3 FRC posts were cemented using adhesive plus resin cement; and group 2 (high cement thickness), in which size 1 FRC posts were cemented as in group 1. Specimens were sectioned, producing 5 samples (thickness: 1.5 mm). For cement thickness evaluation, photographs of the samples were taken using an optical microscope, and the images were analyzed. Each sample was tested in push-out, and data were statistically analyzed. Bond strengths of groups 1 and 2 did not show significant differences (P = .558), but the cement thicknesses for these groups were significantly different (P < .0001). The increase in cement thickness did not significantly affect the bond strength (r2 = 0.1389, P = .936). Increased cement thickness surrounding the FRC post did not impair the bond strength.

Sustainable bioenergy: a framework for decision makers

Includes bibliography

How narrow is the spectrum of submaximal speeds in swimming?

The purpose of this study was to identify the boundary of submaximal speed zones (i.e., exercise intensity domains) between maximal aerobic speed (S-400) and lactate threshold (LT) in swimming. A 400-m all-out test, a 7 × 200 m incremental step test, and two to four 30-minute submaximal tests were performed by 12 male endurance swimmers (age = 24.5 ± 9.6 years; body mass = 71.3 ± 9.8 kg) to determine S-400, speed corresponding to LT, and maximal lactate steady state (MLSS). S-400 was 1.30 ± 0.09 m·s -1 (400 m-5:08 minutes:seconds). The speed at LT (1.08 ± 0.02 m·s-1; 83.1 ± 2.2 %S-400) was lower than the speed at MLSS (1.14 ± 0.02 m·s-1; 87.5 ± 1.9 %S-400). Maximal lactate steady state occurred at 26 ± 10% of the difference between the speed at LT and S-400. Mean blood lactate values at the speeds corresponding to LT and MLSS were 2.45 ± 1.13 mmol·L-1 and 4.30 ± 1.32 mmol·L-1, respectively. The present findings demonstrate that the range of intensity zones between LT and MLSS (i.e., heavy domain) and between MLSS and S-400 (i.e., severe domain) are very narrow in swimming with LT occurring at 83% S-400 in trained swimmers. Precision and sensitivity of the measurement of aerobic indexes (i.e., LT and MLSS) should be considered when conducting exercise training and testing in swimming. © 2013 National Strength and Conditioning Association.

Efeito do pré-tratamento da dentina radicular com clorexidina e etanol na retenção de pinos de fibra de vidro cimentados com cimento resinoso

Pós-graduação em Ciências Odontológicas - FOAR

Análise teórico-experimental de um tabuleiro misto madeira-concreto composto por vigas circulares

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)