Bayesian binary regression model: an application to in-hospital death after AMI prediction

Um modelo bayesiano de regressão binária é desenvolvido para predizer óbito hospitalar em pacientes acometidos por infarto agudo do miocárdio. Métodos de Monte Carlo via Cadeias de Markov (MCMC) são usados para fazer inferência e validação. Uma estratégia para construção de modelos, baseada no uso do fator de Bayes, é proposta e aspectos de validação são extensivamente discutidos neste artigo, incluindo a distribuição a posteriori para o índice de concordância e análise de resíduos. A determinação de fatores de risco, baseados em variáveis disponíveis na chegada do paciente ao hospital, é muito importante para a tomada de decisão sobre o curso do tratamento. O modelo identificado se revela fortemente confiável e acurado, com uma taxa de classificação correta de 88% e um índice de concordância de 83%.

Dynamic viscosity of binary and ternary mixtures containing poly(ethylene glycol), potassium phosphate, and water

Dynamic viscosity of binary mixtures of poly(ethylene glycol) molar mass 1500 da + water, potassium phosphate + water, and ternary mixtures of poly(ethylene glycol) molar mass 1500 da + potassium phosphate + water were determined at 303.15 K Binary and ternary mixture viscosities showed a direct logarithm-type relation with the increase of poly(ethylene glycol) and potassium phosphate contents. The models used for viscosity correlation gave a good fit to the experimental data.

Relating propelinear and binary G-linear codes

In this paper we establish the connections between two different extensions of Z(4)-linearity for binary Hamming spaces, We present both notions - propelinearity and G-linearity - in the context of isometries and group actions, taking the viewpoint of geometrically uniform codes extended to discrete spaces. We show a double inclusion relation: binary G-linear codes are propelinear codes, and translation-invariant propelinear codes are G-linear codes. (C) 2002 Elsevier B.V. B.V. All rights reserved.

Molecular model for the binary complex of uropepsin and pepstatin

The three-dimensional structure of human uropepsin complexed with pepstatin has been modelled using human pepsin as a template. Uropepsin is an aspartic proteinase from the urine, produced in the form of pepsinogen A in the gastric mucosa. The structure is bilobal, consisting of two predominantly beta -sheet lobes which, as observed in other aspartic proteinases, are related by a pseudo twofold axis. A structural comparison between binary complexes of pepsin:pepstatin and uropepsin:pepstatin is discussed. (C) 2001 Academic Press.

Environmental coordination chemistry: Binary systems comprising some bivalent cations and monocarboxylates in aqueous solution. Ionic medium effects on equilibrium constants

The molar single activity coefficients associated with propionate ion (Pr) have been determined at 25 degrees C and ionic strengths comprised between 0.300 and 3.00 M, adjusted with NaClO4, as background electrolyte. The investigation was carried out potentiometrically by using a second class Hg/Hg2Pr2 electrode. It was found that the dependence of propionate activity coefficients as a function of ionic strength (I) can be assessed through the following empirical equation: log y(Pr) = -0.185 I-3/2 + 0.104 I-2. Next, simple equations relating stoichiometric protonation constants of several monocarboxylates and formation constants associated with 1:1 complexes involving some bivalent cations and selected monocarboxylates, in aqueous solution, at 25 degrees C, as a function of ionic strength were derived, allowing the interconversion of parameters from one ionic strength to another, up to I = 3.00 M. In addition, thermodynamic formation constants as well as parameters associated with activity coefficients of the complex species in the equilibria are estimated. The body of results shows that the proposed calculation procedure is very consistent with critically selected experimental data.

Ionic medium effects on equilibrium constants .2. Binary systems comprising some bivalent cations and monocarboxylates in aqueous solution

Simple equations were derived relating stoichiometric protonation constants of several monocarboxylates and formation constants associated with 1:1 complexes involving some bivalent cations and selected monocarboxylates, in aqueous sodium perchlorate media, at 25 degrees C, as a function of ionic strength (I), allowing the interconversion of parameters from one ionic strength to another, up to I = 3.00 M. In addition, thermodynamic formation constants as well as activity coefficients of the species involved in the equilibria were estimated. The results show that the proposed calculation procedure is very consistent with critically selected experimental data.

Synthesis and properties of branched polyethylene/high-density polyethylene blends using a homogeneous binary catalyst system composed of early and late transition metal complexes

Branched polyethylene/high-density polyethylene blends (BPE/HDPE) with a wide range of molecular weights, melt flow indexes (MFI), and intrinsic viscosity were prepared using the homogeneous binary catalyst system composed by Ni(alpha-diimine)Cl-2 (1) (alpha-diimine = 1,4-bis(2,6-diisopropylphenyl)-acenaphthenediimine) and {Tp(Ms*)} TiCl3 (2) (Tp(Ms*)=hydridobis(3-mesitylpyrazol-1-yl)(5-mesityl-pyrazol-1-yl)) activated with MAO and/or TIBA in hexane at two different polymerization temperatures (30 and 55 degreesC) and by varying the nickel loading molar fraction (x(Ni)). At all Temperatures, a non-linear correlation between the x(Ni) and the productivity was observed, suggesting the occurrence of a synergistic effect between the nickel and the titanium catalyst precursors, which is more pronounced at 55 degreesC. The molecular weight of the BPE/HDPE blends considerably decreases with increasing Al/M molar ratio. The melt flow indexes (MFI) and intrinsic viscosities (eta) are strongly affected by x(Ni), but the melting temperatures are nearly constant, 132 +/- 3 degreesC. Dynamic mechanical thermal analysis (DMTA) shows the formation of different polymeric materials where the stiffness vanes according, to the x(Ni) and temperature used in the polymerization reaction. The surface morphology of the BPE/HDPE blends studied by scanning electron microscopy (SEM) revealed a low miscibility between the PE phases resulting in the formation of a sandwich structure after etching with o-xylene.

Genetic Algorithms (Binary and Real Codes) for the Optimisation of a Fermentation Process for Butanol Production

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

Bayesian outlier analysis in binary regression

We propose alternative approaches to analyze residuals in binary regression models based on random effect components. Our preferred model does not depend upon any tuning parameter, being completely automatic. Although the focus is mainly on accommodation of outliers, the proposed methodology is also able to detect them. Our approach consists of evaluating the posterior distribution of random effects included in the linear predictor. The evaluation of the posterior distributions of interest involves cumbersome integration, which is easily dealt with through stochastic simulation methods. We also discuss different specifications of prior distributions for the random effects. The potential of these strategies is compared in a real data set. The main finding is that the inclusion of extra variability accommodates the outliers, improving the adjustment of the model substantially, besides correctly indicating the possible outliers.

Spectrophotometric study of binary and ternary systems involving metal ions and benzylidenepyruvates: Equilibria in aqueous solutions

The protonation of 4-dimethylaminobenzylidenepyruvate (DMBP) and 2-chloro-4-dimethylaminobenzylidenepyruvate (2-CI-DMBP) and their complex formation with Mn(II), Co(II), Ni(II), Cu(II), Zn(II), Pb(II), Cd(II) and Al(III) have been studied by potentiometric and spectrophotometric methods at 25 °C and ionic strength 0.500 M, held with sodium perchlorate. The stability order found for 1 :1 complexes of both ligands is Al(III) > Cu(II) > Pb(II) > Ni(II) > Zn(II) > Co(II) > Cd(II) > Mn(II). The stability changes move in the same direction as the pKa of the ligands. The results are compared with literature values reported for metal ion pyruvate systems. Thermodynamic stabilities of ternary complexes formed in Cu(II)-B-L- systems, where B = 2,2′-bipyridyl (bipy), ethylenediamine or glycinate and L = DMBP or 2-CI-DMBP, were also determined. The Cu(bipy)L+ species are more stable than would be expected on purely statistical grounds. The importance of the :t system associated with bipy on the enhanced stability of its mixed ligand complexes is stressed. Analytical applications of the investigated ligands are outlined.

Phonons in binary BCC lithium-sodium alloys

The dispersion relations along the principal symmetry directions in BCC lithium-sodium alloys are calculated using second-order perturbation theory. The local modified Hoshino-Youngmodel potential was used for the lithium and the local Harrison model potential for sodium. The phonon density of states, the root mean square displacements and (Θ-T) curves are also calculated. In the absence of experimental data, just the theoretical predictions are presented here.

EXAFS and Raman spectroscopy study of binary indium fluoride glasses

Extended X-ray absorption fine spectroscopy (EXAFS) and Raman scattering studies of InF3-BaF2 and InF3-SrF2 binary glasses are reported. For all compositions, the local structure of the glasses is built with InF6 units. For all glasses studied, the indium neighbour's number and the In-F mean bond length are equal to the values of the InF3 crystalline phase (6 and 0.205 nm, respectively). © 1996 Chapman & Hall.

Variational studies and replica symmetry breaking in the generalization problem of the binary perceptron

We analyze the average performance of a general class of learning algorithms for the nondeterministic polynomial time complete problem of rule extraction by a binary perceptron. The examples are generated by a rule implemented by a teacher network of similar architecture. A variational approach is used in trying to identify the potential energy that leads to the largest generalization in the thermodynamic limit. We restrict our search to algorithms that always satisfy the binary constraints. A replica symmetric ansatz leads to a learning algorithm which presents a phase transition in violation of an information theoretical bound. Stability analysis shows that this is due to a failure of the replica symmetric ansatz and the first step of replica symmetry breaking (RSB) is studied. The variational method does not determine a unique potential but it allows construction of a class with a unique minimum within each first order valley. Members of this class improve on the performance of Gibbs algorithm but fail to reach the Bayesian limit in the low generalization phase. They even fail to reach the performance of the best binary, an optimal clipping of the barycenter of version space. We find a trade-off between a good low performance and early onset of perfect generalization. Although the RSB may be locally stable we discuss the possibility that it fails to be the correct saddle point globally. ©2000 The American Physical Society.

BBA: A binary bat algorithm for feature selection

Feature selection aims to find the most important information from a given set of features. As this task can be seen as an optimization problem, the combinatorial growth of the possible solutions may be in-viable for a exhaustive search. In this paper we propose a new nature-inspired feature selection technique based on the bats behaviour, which has never been applied to this context so far. The wrapper approach combines the power of exploration of the bats together with the speed of the Optimum-Path Forest classifier to find the set of features that maximizes the accuracy in a validating set. Experiments conducted in five public datasets have demonstrated that the proposed approach can outperform some well-known swarm-based techniques. © 2012 IEEE.