A fast identification algorithm for Box-Cox transformation based radial basis function neural network

In this letter, a Box-Cox transformation-based radial basis function (RBF) neural network is introduced using the RBF neural network to represent the transformed system output. Initially a fixed and moderate sized RBF model base is derived based on a rank revealing orthogonal matrix triangularization (QR decomposition). Then a new fast identification algorithm is introduced using Gauss-Newton algorithm to derive the required Box-Cox transformation, based on a maximum likelihood estimator. The main contribution of this letter is to explore the special structure of the proposed RBF neural network for computational efficiency by utilizing the inverse of matrix block decomposition lemma. Finally, the Box-Cox transformation-based RBF neural network, with good generalization and sparsity, is identified based on the derived optimal Box-Cox transformation and a D-optimality-based orthogonal forward regression algorithm. The proposed algorithm and its efficacy are demonstrated with an illustrative example in comparison with support vector machine regression.

An improved reliability Cuk based solar inverter with sliding mode control

Many photovoltaic inverter designs make use of a buck based switched mode power supply (SMPS) to produce a rectified sinusoidal waveform. This waveform is then unfolded by a low frequency switching structure to produce a fully sinusoidal waveform. The Cuk SMPS could offer advantages over the buck in such applications. Unfortunately the Cuk converter is considered to be difficult to control using classical methods. Correct closed loop design is essential for stable operation of Cuk converters. Due to these stability issues, Cuk converter based designs often require stiff low bandwidth control loops. In order to achieve this stable closed loop performance, traditional designs invariably need large, unreliable electrolytic capacitors. In this paper, an inverter with a sliding mode control approach is presented which enables the designer to make use of the Cuk converters advantages, while ameliorating control difficulties. This control method allows the selection of passive components based predominantly on ripple and reliability specifications while requiring only one state reference signal. This allows much smaller, more reliable non-electrolytic capacitors to be used. A prototype inverter has been constructed and results obtained which demonstrate the design flexibility of the Cuk topology when coupled with sliding mode control.

Jpowder: a Java-based program for the display and examination of powder diffraction data

The ability to display and inspect powder diffraction data quickly and efficiently is a central part of the data analysis process. Whilst many computer programs are capable of displaying powder data, their focus is typically on advanced operations such as structure solution or Rietveld refinement. This article describes a lightweight software package, Jpowder, whose focus is fast and convenient visualization and comparison of powder data sets in a variety of formats from computers with network access. Jpowder is written in Java and uses its associated Web Start technology to allow ‘single-click deployment’ from a web page, http://www.jpowder.org. Jpowder is open source, free and available for use by anyone.

The exclusive use of integer-order spots for LEED-IV structure analysis of adsorption systems: p(2×2)-O on Ni{111}

Two different ways of performing low-energy electron diffraction (LEED) structure determinations for the p(2 x 2) structure of oxygen on Ni {111} are compared: a conventional LEED-IV structure analysis using integer and fractional-order IV-curves collected at normal incidence and an analysis using only integer-order IV-curves collected at three different angles of incidence. A clear discrimination between different adsorption sites can be achieved by the latter approach as well as the first and the best fit structures of both analyses are within each other's error bars (all less than 0.1 angstrom). The conventional analysis is more sensitive to the adsorbate coordinates and lateral parameters of the substrate atoms whereas the integer-order-based analysis is more sensitive to the vertical coordinates of substrate atoms. Adsorbate-related contributions to the intensities of integer-order diffraction spots are independent of the state of long-range order in the adsorbate layer. These results show, therefore, that for lattice-gas disordered adsorbate layers, for which only integer-order spots are observed, similar accuracy and reliability can be achieved as for ordered adsorbate layers, provided the data set is large enough.

Electrochemical studies of bi- and polymetallic complexes featuring acetylide based bridging ligands

Acetylide-based bridging ligands have been widely used in the preparation of complexes that display a degree of electronic interaction between metal-based redox groups located at the ligand termini. The electrochemical response of these systems has been selectively reviewed, with a focus on the variation in properties that accompany changes in the structure of the bridging ligand and the nature of the metal groups.

Nonlinear model structure design and construction using orthogonal least squares and D-optimality design

A very efficient learning algorithm for model subset selection is introduced based on a new composite cost function that simultaneously optimizes the model approximation ability and model robustness and adequacy. The derived model parameters are estimated via forward orthogonal least squares, but the model subset selection cost function includes a D-optimality design criterion that maximizes the determinant of the design matrix of the subset to ensure the model robustness, adequacy, and parsimony of the final model. The proposed approach is based on the forward orthogonal least square (OLS) algorithm, such that new D-optimality-based cost function is constructed based on the orthogonalization process to gain computational advantages and hence to maintain the inherent advantage of computational efficiency associated with the conventional forward OLS approach. Illustrative examples are included to demonstrate the effectiveness of the new approach.

A mixture of experts network structure construction algorithm for modelling and control

This paper introduces a new fast, effective and practical model structure construction algorithm for a mixture of experts network system utilising only process data. The algorithm is based on a novel forward constrained regression procedure. Given a full set of the experts as potential model bases, the structure construction algorithm, formed on the forward constrained regression procedure, selects the most significant model base one by one so as to minimise the overall system approximation error at each iteration, while the gate parameters in the mixture of experts network system are accordingly adjusted so as to satisfy the convex constraints required in the derivation of the forward constrained regression procedure. The procedure continues until a proper system model is constructed that utilises some or all of the experts. A pruning algorithm of the consequent mixture of experts network system is also derived to generate an overall parsimonious construction algorithm. Numerical examples are provided to demonstrate the effectiveness of the new algorithms. The mixture of experts network framework can be applied to a wide variety of applications ranging from multiple model controller synthesis to multi-sensor data fusion.

Nonlinear model structure detection using optimum experimental design and orthogonal least squares

A very efficient learning algorithm for model subset selection is introduced based on a new composite cost function that simultaneously optimizes the model approximation ability and model adequacy. The derived model parameters are estimated via forward orthogonal least squares, but the subset selection cost function includes an A-optimality design criterion to minimize the variance of the parameter estimates that ensures the adequacy and parsimony of the final model. An illustrative example is included to demonstrate the effectiveness of the new approach.

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.

Givens rotation based fast backward elimination algorithm for RBF neural network pruning

A fast backward elimination algorithm is introduced based on a QR decomposition and Givens transformations to prune radial-basis-function networks. Nodes are sequentially removed using an increment of error variance criterion. The procedure is terminated by using a prediction risk criterion so as to obtain a model structure with good generalisation properties. The algorithm can be used to postprocess radial basis centres selected using a k-means routine and, in this mode, it provides a hybrid supervised centre selection approach.

Image fusion based on median filters and SOFM neural networks: a three-step scheme

This paper presents a new image data fusion scheme by combining median filtering with self-organizing feature map (SOFM) neural networks. The scheme consists of three steps: (1) pre-processing of the images, where weighted median filtering removes part of the noise components corrupting the image, (2) pixel clustering for each image using self-organizing feature map neural networks, and (3) fusion of the images obtained in Step (2), which suppresses the residual noise components and thus further improves the image quality. It proves that such a three-step combination offers an impressive effectiveness and performance improvement, which is confirmed by simulations involving three image sensors (each of which has a different noise structure).

Supramolecular assemblies of metal ions in complex bimetallic and trimetallic salts based on hexacyanoferrate(III) ion

Two complex heterometallic salts with formulae Tl-6[Fe(CN)(6)](1) (33)(NO3)(OH) (1) and [Co(bpy)(2)(CN)(2)](2){[Ag(CN)(2)](0) (5)[Fe(CN)(6)](0) (5)} 8H(2)O (2) have been synthesized and fully characterized Single crystal X-ray analyses reveal that compound 1 is comprised of discrete Tl+ cations and [Fe(CN)(6)](3-) anions together with OH- and NO3- anions Compound 2 contains [Co(bpy)(2)(CN)(2)](+) cations and {[Ag(CN)(2)][Fe(CN)(6)]}(-) anions together with eight molecules of water of crystallization Both structures form unprecedented three-dimensional supramolecular networks via non covalent interactions Another important observation is that the stereochemically active inert (lone) pair present on Tl+ plays little role in controlling the structure of 1 The water molecules in 2 play important roles in providing stability organizing a supramolecular network through hydrogen bonding In the syntheses of 1 and 2 Fe(II) is oxidized to Fe(III) and Co(II) to Co(III) respectively facilitating the formation of the salts that are obtained Both compounds exhibit photoluminescence emission in solution near the visible region.

Structure adaptation of linear MMSE adaptive filters

The tap-length, or the number of the taps, is an important structural parameter of the linear MMSE adaptive filter. Although the optimum tap-length that balances performance and complexity varies with scenarios, most current adaptive filters fix the tap-length at some compromise value, making them inefficient to implement especially in time-varying scenarios. A novel gradient search based variable tap-length algorithm is proposed, using the concept of the pseudo-fractional tap-length, and it is shown that the new algorithm can converge to the optimum tap-length in the mean. Results of computer simulations are also provided to verify the analysis.

Moisture vertical structure, column water vapor, and tropical deep convection

The vertical structure of the relationship between water vapor and precipitation is analyzed in 5 yr of radiosonde and precipitation gauge data from the Nauru Atmospheric Radiation Measurement (ARM) site. The first vertical principal component of specific humidity is very highly correlated with column water vapor (CWV) and has a maximum of both total and fractional variance captured in the lower free troposphere (around 800 hPa). Moisture profiles conditionally averaged on precipitation show a strong association between rainfall and moisture variability in the free troposphere and little boundary layer variability. A sharp pickup in precipitation occurs near a critical value of CWV, confirming satellite-based studies. A lag–lead analysis suggests it is unlikely that the increase in water vapor is just a result of the falling precipitation. To investigate mechanisms for the CWV–precipitation relationship, entraining plume buoyancy is examined in sonde data and simplified cases. For several different mixing schemes, higher CWV results in progressively greater plume buoyancies, particularly in the upper troposphere, indicating conditions favorable for deep convection. All other things being equal, higher values of lower-tropospheric humidity, via entrainment, play a major role in this buoyancy increase. A small but significant increase in subcloud layer moisture with increasing CWV also contributes to buoyancy. Entrainment coefficients inversely proportional to distance from the surface, associated with mass flux increase through a deep lower-tropospheric layer, appear promising. These yield a relatively even weighting through the lower troposphere for the contribution of environmental water vapor to midtropospheric buoyancy, explaining the association of CWV and buoyancy available for deep convection.

On combination of SMOTE and particle swarm optimization based radial basis function classifier for imbalanced problems

The combination of the synthetic minority oversampling technique (SMOTE) and the radial basis function (RBF) classifier is proposed to deal with classification for imbalanced two-class data. In order to enhance the significance of the small and specific region belonging to the positive class in the decision region, the SMOTE is applied to generate synthetic instances for the positive class to balance the training data set. Based on the over-sampled training data, the RBF classifier is constructed by applying the orthogonal forward selection procedure, in which the classifier structure and the parameters of RBF kernels are determined using a particle swarm optimization algorithm based on the criterion of minimizing the leave-one-out misclassification rate. The experimental results on both simulated and real imbalanced data sets are presented to demonstrate the effectiveness of our proposed algorithm.