Particle swarm optimization aided orthogonal forward regression for unified data modeling

We propose a unified data modeling approach that is equally applicable to supervised regression and classification applications, as well as to unsupervised probability density function estimation. A particle swarm optimization (PSO) aided orthogonal forward regression (OFR) algorithm based on leave-one-out (LOO) criteria is developed to construct parsimonious radial basis function (RBF) networks with tunable nodes. Each stage of the construction process determines the center vector and diagonal covariance matrix of one RBF node by minimizing the LOO statistics. For regression applications, the LOO criterion is chosen to be the LOO mean square error, while the LOO misclassification rate is adopted in two-class classification applications. By adopting the Parzen window estimate as the desired response, the unsupervised density estimation problem is transformed into a constrained regression problem. This PSO aided OFR algorithm for tunable-node RBF networks is capable of constructing very parsimonious RBF models that generalize well, and our analysis and experimental results demonstrate that the algorithm is computationally even simpler than the efficient regularization assisted orthogonal least square algorithm based on LOO criteria for selecting fixed-node RBF models. Another significant advantage of the proposed learning procedure is that it does not have learning hyperparameters that have to be tuned using costly cross validation. The effectiveness of the proposed PSO aided OFR construction procedure is illustrated using several examples taken from regression and classification, as well as density estimation applications.

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.

Regression based D-optimality experimental design for sparse kernel density estimation

This paper derives an efficient algorithm for constructing sparse kernel density (SKD) estimates. The algorithm first selects a very small subset of significant kernels using an orthogonal forward regression (OFR) procedure based on the D-optimality experimental design criterion. The weights of the resulting sparse kernel model are then calculated using a modified multiplicative nonnegative quadratic programming algorithm. Unlike most of the SKD estimators, the proposed D-optimality regression approach is an unsupervised construction algorithm and it does not require an empirical desired response for the kernel selection task. The strength of the D-optimality OFR is owing to the fact that the algorithm automatically selects a small subset of the most significant kernels related to the largest eigenvalues of the kernel design matrix, which counts for the most energy of the kernel training data, and this also guarantees the most accurate kernel weight estimate. The proposed method is also computationally attractive, in comparison with many existing SKD construction algorithms. Extensive numerical investigation demonstrates the ability of this regression-based approach to efficiently construct a very sparse kernel density estimate with excellent test accuracy, and our results show that the proposed method compares favourably with other existing sparse methods, in terms of test accuracy, model sparsity and complexity, for constructing kernel density estimates.

Radial basis function classifier construction using particle swarm optimisation aided orthogonal forward regression

We develop a particle swarm optimisation (PSO) aided orthogonal forward regression (OFR) approach for constructing radial basis function (RBF) classifiers with tunable nodes. At each stage of the OFR construction process, the centre vector and diagonal covariance matrix of one RBF node is determined efficiently by minimising the leave-one-out (LOO) misclassification rate (MR) using a PSO algorithm. Compared with the state-of-the-art regularisation assisted orthogonal least square algorithm based on the LOO MR for selecting fixednode RBF classifiers, the proposed PSO aided OFR algorithm for constructing tunable-node RBF classifiers offers significant advantages in terms of better generalisation performance and smaller model size as well as imposes lower computational complexity in classifier construction process. Moreover, the proposed algorithm does not have any hyperparameter that requires costly tuning based on cross validation.

Power properties if invariant tests for spatial autocorrelation in linear regression

This paper derives some exact power properties of tests for spatial autocorrelation in the context of a linear regression model. In particular, we characterize the circumstances in which the power vanishes as the autocorrelation increases, thus extending the work of Krämer (2005). More generally, the analysis in the paper sheds new light on how the power of tests for spatial autocorrelation is affected by the matrix of regressors and by the spatial structure. We mainly focus on the problem of residual spatial autocorrelation, in which case it is appropriate to restrict attention to the class of invariant tests, but we also consider the case when the autocorrelation is due to the presence of a spatially lagged dependent variable among the regressors. A numerical study aimed at assessing the practical relevance of the theoretical results is included

Redox-active polymers based on nonbridged metal−metal bonds. Electrochemical formation of [Os(bpy)(CO)(L)]n(bpy = 2,2‘-bipyridine; L = CO, MeCN) and of their reduced forms: a spectroelectrochemical study

IR, UV-vis, and EPR spectroelectrochemistry at variable temperatures and in different solvents were applied to investigate in situ the formation of electroactive molecular chains with a nonbridged Os-Os backbone, in particular, the polymer [Os-0(bpy)(CO)(2)](n), (bpy = 2,2'-bipyridine), from a mononuclear Os(II) carbonyl precursor, [Os-II(bpy)(CO)(2)Cl-2]. The one-electron-reduced form, [Os-II(bpy(.-))(CO)(2)Cl-2](-), has been characterized spectroscopically at low temperatures. This radical anion is the key intermediate in the electrochemical propagation process responsible for the metal-metal bond formation. Unambiguous spectroscopic evidence has been gained also for the formation of [{Os-0(bpy(.-))(CO)(2)}(-)](n), the electron-rich electrocatalyst of CO2 reduction. The polymer species are fairly well soluble in butyronitrile, which is important for their potential utilization in nanoscience, for example, as conducting molecular wires. We have also shown that complete solubility is accomplished for the monocarbonyl-acetonitrile derivative of the polymer, [Os-0(bpy)(CO)(MeCN)(2)Cl](n).

Reduced-order modelling of a high-voltage oscillatory impulse generator

The design of high-voltage equipment encompasses the study of oscillatory surges caused by transients such as those produced by switching. By obtaining a model, the response of which reconstructs that observed in the actual system, simulation studies and critical tests can be carried out on the model rather than on the equipment itself. In this paper, methods for the construction of simplified models are described and it is shown how the use of a complex model does not necessarily result in superior response pattern reconstruction.

A hypoplastic model of skeletal muscle development displaying reduced foetal myoblast cell numbers, increased oxidative myofibres and improved specific tension capacity

The major component of skeletal muscle is the myofibre. Genetic intervention inducing over-enlargement of myofibres beyond a certain threshold through acellular growth causes a reduction in the specific tension generating capacity of the muscle. However the physiological parameters of a genetic model that harbours reduced skeletal muscle mass have yet to be analysed. Genetic deletion of Meox2 in mice leads to reduced limb muscle size and causes some patterning defects. The loss of Meox2 is not embryonically lethal and a small percentage of animals survive to adulthood making it an excellent model with which to investigate how skeletal muscle responds to reductions in mass. In this study we have performed a detailed analysis of both late foetal and adult muscle development in the absence of Meox2. In the adult, we show that the loss of Meox2 results in smaller limb muscles that harbour reduced numbers of myofibres. However, these fibres are enlarged. These myofibres display a molecular and metabolic fibre type switch towards a more oxidative phenotype that is induced through abnormalities in foetal fibre formation. In spite of these changes, the muscle from Meox2 mutant mice is able to generate increased levels of specific tension compared to that of the wild type.

Parameter estimation based on stacked regression and evolutionary algorithms

A new parameter-estimation algorithm, which minimises the cross-validated prediction error for linear-in-the-parameter models, is proposed, based on stacked regression and an evolutionary algorithm. It is initially shown that cross-validation is very important for prediction in linear-in-the-parameter models using a criterion called the mean dispersion error (MDE). Stacked regression, which can be regarded as a sophisticated type of cross-validation, is then introduced based on an evolutionary algorithm, to produce a new parameter-estimation algorithm, which preserves the parsimony of a concise model structure that is determined using the forward orthogonal least-squares (OLS) algorithm. The PRESS prediction errors are used for cross-validation, and the sunspot and Canadian lynx time series are used to demonstrate the new algorithms.

Proceedings of the Rank Forum on Vitamin D

The Rank Forum on Vitamin D was held on 2nd and 3rd July 2009 at the University of Surrey, Guildford, UK. The workshop consisted of a series of scene-setting presentations to address the current issues and challenges concerning vitamin D and health, and included an open discussion focusing on the identification of the concentrations of serum 25-hydroxyvitamin D (25(OH)D) (a marker of vitamin D status) that may be regarded as optimal, and the implications this process may have in the setting of future dietary reference values for vitamin D in the UK. The Forum was in agreement with the fact that it is desirable for all of the population to have a serum 25(OH)D concentration above 25 nmol/l, but it discussed some uncertainty about the strength of evidence for the need to aim for substantially higher concentrations (25(OH)D concentrations . 75 nmol/l). Any discussion of ‘optimal’ concentration of serum 25(OH)D needs to define ‘optimal’ with care since it is important to consider the normal distribution of requirements and the vitamin D needs for a wide range of outcomes. Current UK reference values concentrate on the requirements of particular subgroups of the population; this differs from the approaches used in other European countries where a wider range of age groups tend to be covered. With the re-emergence of rickets and the public health burden of low vitamin D status being already apparent, there is a need for urgent action from policy makers and risk managers. The Forum highlighted concerns regarding the failure of implementation of existing strategies in the UK for achieving current vitamin D recommendations.

Use of a reduced Schiff-Base ligand to prepare novel chloro-bridged chains of rare Cu(II) trinuclear complexes with mixed azido/oxo and chloro/oxo bridges

Two mixed bridged one-dimensional (1D) polynuclear complexes, [Cu3L2(mu(1,1)-N-3)(2)(mu-Cl)Cl](n) (1) and {[Cu3L2(mu-Cl)(3)Cl]center dot 0.46CH(3)OH}(n), (2), have been synthesized using the tridentate reduced Schiff-base ligand HL (2-[(2-dimethylamino-ethylamino)-methyl]-phenol). The complexes have been characterized by X-ray structural analyses and variable-temperature magnetic susceptibility measurements. In both complexes the basic trinuclear angular units are joined together by weak chloro bridges to form a 1D chain. The trinuclear structure of 1 is composed of two terminal square planar [Cu(L)(mu(1,1)-N-3)] units connected by a central Cu(II) atom through bridging nitrogen atoms of end-on azido ligands and the phenoxo oxygen atom of the tridentate ligand. These four coordinating atoms along with a chloride ion form a distorted trigonal bipyramidal geometry around the central Cu(II). The structure of 2 is similar; the only difference being a Cl bridge replacing the mu(1,1)-N-3 bridge in the trinuclear unit. The magnetic properties of both trinuclear complexes can be very well reproduced with a simple linear symmetrical trimer model (H = JS(i)S(i+1)) with only one intracluster exchange coupling (J) including a weak intertrimer interaction (.j) reproduced with the molecular field approximation. This model provides very satisfactory fits for both complexes in the whole temperature range with the following parameters: g = 2.136(3), J = 93.9(3) cm(-1) and zj= -0.90(3) cm(-1) (z = 2) for 1 and g = 2.073(7), J = -44.9(4) cm(-1) and zJ = -1.26(6) cm(-1) (z = 2) for 2.

The effect of test meal monounsaturated fatty acid: saturated fatty acid ratio on postprandial lipid metabolism

Epidemiological evidence shows that a diet high in monounsaturated fatty acids (MUFA) but low in saturated fatty acids (SFA) is associated with reduced risk of CHD. The hypocholesterolaemic effect of MUFA is known but there has been little research on the effect of test meal MUFA and SFA composition on postprandial lipid metabolism. The present study investigated the effect of meals containing different proportions of MUFA and SFA on postprandial triacylglycerol and non-esterified fatty acid (NEFA) metabolism. Thirty healthy male volunteers consumed three meals containing equal amounts of fat (40 g), but different proportions of MUFA (12, 17 and 24% energy) in random order. Postprandial plasma triacylglycerol, apolipoprotein B-48, cholesterol, HDL-cholesterol, glucose and insulin concentrations and lipoprotein lipase (EC 3.1.1.34) activity were not significantly different following the three meals which varied in their levels of SFA and MUFA. There was a significant difference in the postprandial NEFA response between meals. The incremental area under the curve of postprandial plasma NEFA concentrations was significantly (P = 0.03) lower following the high-MUFA meal. Regression analysis showed that the non-significant difference in fasting NEFA concentrations was the most important factor determining difference between meals, and that the test meal MUFA content had only a minor effect. In conclusion, varying the levels of MUFA and SFA in test meals has little or no effect on postprandial lipid metabolism.

Nickel(II) and copper(II) complexes of unsymmetrical tetradentate reduced Schiff base ligands

Two new reduced Schiff base ligands, [HL1 = 4-(2-[(pyridin-2-ylmethyl)-amino]-ethylimino)-pentan-2-one and HL2 =4-[2-(1-pyridin-2-yl-ethylamino)-ethylimino]-pentan-2-one] have been prepared by reduction of the corresponding tetradentate unsymmetrical schiff bases derived from 1.1: 1 condensation of 1,2-ethanediamine, acetylacetone and pyridine-2-carboxaldehyde/2-acetyl pyridine. Four complexes, [Ni(L-1)]ClO4 (1), [Cu(L-1)]ClO4 (2). [Ni(L-2)]ClO4 (3). and [Cu(L-2)]ClO4 (4) with these two reduced Schiff base ligands have been synthesized and structurally characterized by X-ray crystallography. The mono-negative ligands L-1 and L-2 are chelated in all four complexes through the four donor atoms to form square planar nickel(II) and copper(II) complexes Structures of 3 and 4 reveal that enantiomeric pairs are crystallized together with opposite chirality in the nitrogen and carbon atoms. The two Cu-II complexes (2 and 4) exhibit both irreversible reductive (Cu-II/Cu-II, E-pc. -1.00 and -1.04 V) and oxidative (Cu-II/CUII, E-pa, + 1.22 and + 1.17 V, respectively) responses in cyclic voltammetry. The electrochemically generated Cu-1 species for both the complexes are unstable and undergo disproportionation.