Estimating Dependency Structure as a Hidden Variable

This paper introduces a probability model, the mixture of trees that can account for sparse, dynamically changing dependence relationships. We present a family of efficient algorithms that use EM and the Minimum Spanning Tree algorithm to find the ML and MAP mixture of trees for a variety of priors, including the Dirichlet and the MDL priors. We also show that the single tree classifier acts like an implicit feature selector, thus making the classification performance insensitive to irrelevant attributes. Experimental results demonstrate the excellent performance of the new model both in density estimation and in classification.

Information sources selection methodology for recommender systems based on intrinsic characteristics and trust measure

El treball desenvolupat en aquesta tesi presenta un profund estudi i proveïx solucions innovadores en el camp dels sistemes recomanadors. Els mètodes que usen aquests sistemes per a realitzar les recomanacions, mètodes com el Filtrat Basat en Continguts (FBC), el Filtrat Col·laboratiu (FC) i el Filtrat Basat en Coneixement (FBC), requereixen informació dels usuaris per a predir les preferències per certs productes. Aquesta informació pot ser demogràfica (Gènere, edat, adreça, etc), o avaluacions donades sobre algun producte que van comprar en el passat o informació sobre els seus interessos. Existeixen dues formes d'obtenir aquesta informació: els usuaris ofereixen explícitament aquesta informació o el sistema pot adquirir la informació implícita disponible en les transaccions o historial de recerca dels usuaris. Per exemple, el sistema recomanador de pel·lícules MovieLens (http://movielens.umn.edu/login) demana als usuaris que avaluïn almenys 15 pel·lícules dintre d'una escala de * a * * * * * (horrible, ...., ha de ser vista). El sistema genera recomanacions sobre la base d'aquestes avaluacions. Quan els usuaris no estan registrat en el sistema i aquest no té informació d'ells, alguns sistemes realitzen les recomanacions tenint en compte l'historial de navegació. Amazon.com (http://www.amazon.com) realitza les recomanacions tenint en compte les recerques que un usuari a fet o recomana el producte més venut. No obstant això, aquests sistemes pateixen de certa falta d'informació. Aquest problema és generalment resolt amb l'adquisició d'informació addicional, se li pregunta als usuaris sobre els seus interessos o es cerca aquesta informació en fonts addicionals. La solució proposada en aquesta tesi és buscar aquesta informació en diverses fonts, específicament aquelles que contenen informació implícita sobre les preferències dels usuaris. Aquestes fonts poden ser estructurades com les bases de dades amb informació de compres o poden ser no estructurades com les pàgines web on els usuaris deixen la seva opinió sobre algun producte que van comprar o posseïxen. Nosaltres trobem tres problemes fonamentals per a aconseguir aquest objectiu: 1 . La identificació de fonts amb informació idònia per als sistemes recomanadors. 2 . La definició de criteris que permetin la comparança i selecció de les fonts més idònies. 3 . La recuperació d'informació de fonts no estructurades. En aquest sentit, en la tesi proposada s'ha desenvolupat: 1 . Una metodologia que permet la identificació i selecció de les fonts més idònies. Criteris basats en les característiques de les fonts i una mesura de confiança han estat utilitzats per a resoldre el problema de la identificació i selecció de les fonts. 2 . Un mecanisme per a recuperar la informació no estructurada dels usuaris disponible en la web. Tècniques de Text Mining i ontologies s'han utilitzat per a extreure informació i estructurar-la apropiadament perquè la utilitzin els recomanadors. Les contribucions del treball desenvolupat en aquesta tesi doctoral són: 1. Definició d'un conjunt de característiques per a classificar fonts rellevants per als sistemes recomanadors 2. Desenvolupament d'una mesura de rellevància de les fonts calculada sobre la base de les característiques definides 3. Aplicació d'una mesura de confiança per a obtenir les fonts més fiables. La confiança es definida des de la perspectiva de millora de la recomanació, una font fiable és aquella que permet millorar les recomanacions. 4. Desenvolupament d'un algorisme per a seleccionar, des d'un conjunt de fonts possibles, les més rellevants i fiable utilitzant les mitjanes esmentades en els punts previs. 5. Definició d'una ontologia per a estructurar la informació sobre les preferències dels usuaris que estan disponibles en Internet. 6. Creació d'un procés de mapatge que extreu automàticament informació de les preferències dels usuaris disponibles en la web i posa aquesta informació dintre de l'ontologia. Aquestes contribucions permeten aconseguir dos objectius importants: 1 . Millorament de les recomanacions usant fonts d'informació alternatives que sigui rellevants i fiables. 2 . Obtenir informació implícita dels usuaris disponible en Internet.

Structure of turbulent flow over arrays of cubical roughness

The structure of turbulent flow over large roughness consisting of regular arrays of cubical obstacles is investigated numerically under constant pressure gradient conditions. Results are analysed in terms of first- and second-order statistics, by visualization of instantaneous flow fields and by conditional averaging. The accuracy of the simulations is established by detailed comparisons of first- and second-order statistics with wind-tunnel measurements. Coherent structures in the log region are investigated. Structure angles are computed from two-point correlations, and quadrant analysis is performed to determine the relative importance of Q2 and Q4 events (ejections and sweeps) as a function of height above the roughness. Flow visualization shows the existence of low-momentum regions (LMRs) as well as vortical structures throughout the log layer. Filtering techniques are used to reveal instantaneous examples of the association of the vortices with the LMRs, and linear stochastic estimation and conditional averaging are employed to deduce their statistical properties. The conditional averaging results reveal the presence of LMRs and regions of Q2 and Q4 events that appear to be associated with hairpin-like vortices, but a quantitative correspondence between the sizes of the vortices and those of the LMRs is difficult to establish; a simple estimate of the ratio of the vortex width to the LMR width gives a value that is several times larger than the corresponding ratio over smooth walls. The shape and inclination of the vortices and their spatial organization are compared to recent findings over smooth walls. Characteristic length scales are shown to scale linearly with height in the log region. Whilst there are striking qualitative similarities with smooth walls, there are also important differences in detail regarding: (i) structure angles and sizes and their dependence on distance from the rough surface; (ii) the flow structure close to the roughness; (iii) the roles of inflows into and outflows from cavities within the roughness; (iv) larger vortices on the rough wall compared to the smooth wall; (v) the effect of the different generation mechanism at the wall in setting the scales of structures.

Algorithm for generating defective graphene sheets

An algorithm is presented for the generation of molecular models of defective graphene fragments, containing a majority of 6-membered rings with a small number of 5- and 7-membered rings as defects. The structures are generated from an initial random array of points in 2D space, which are then subject to Delaunay triangulation. The dual of the triangulation forms a Voronoi tessellation of polygons with a range of ring sizes. An iterative cycle of refinement, involving deletion and addition of points followed by further triangulation, is performed until the user-defined criteria for the number of defects are met. The array of points and connectivities are then converted to a molecular structure and subject to geometry optimization using a standard molecular modeling package to generate final atomic coordinates. On the basis of molecular mechanics with minimization, this automated method can generate structures, which conform to user-supplied criteria and avoid the potential bias associated with the manual building of structures. One application of the algorithm is the generation of structures for the evaluation of the reactivity of different defect sites. Ab initio electronic structure calculations on a representative structure indicate preferential fluorination close to 5-ring defects.

A singular vector perspective of 4D-Var: Filtering and interpolation

Four-dimensional variational data assimilation (4D-Var) combines the information from a time sequence of observations with the model dynamics and a background state to produce an analysis. In this paper, a new mathematical insight into the behaviour of 4D-Var is gained from an extension of concepts that are used to assess the qualitative information content of observations in satellite retrievals. It is shown that the 4D-Var analysis increments can be written as a linear combination of the singular vectors of a matrix which is a function of both the observational and the forecast model systems. This formulation is used to consider the filtering and interpolating aspects of 4D-Var using idealized case-studies based on a simple model of baroclinic instability. The results of the 4D-Var case-studies exhibit the reconstruction of the state in unobserved regions as a consequence of the interpolation of observations through time. The results also exhibit the filtering of components with small spatial scales that correspond to noise, and the filtering of structures in unobserved regions. The singular vector perspective gives a very clear view of this filtering and interpolating by the 4D-Var algorithm and shows that the appropriate specification of the a priori statistics is vital to extract the largest possible amount of useful information from the observations. Copyright © 2005 Royal Meteorological Society

Time patterns in UK demand for alcohol and tobacco: an application of the EM algorithm

Capturing the pattern of structural change is a relevant task in applied demand analysis, as consumer preferences may vary significantly over time. Filtering and smoothing techniques have recently played an increasingly relevant role. A dynamic Almost Ideal Demand System with random walk parameters is estimated in order to detect modifications in consumer habits and preferences, as well as changes in the behavioural response to prices and income. Systemwise estimation, consistent with the underlying constraints from economic theory, is achieved through the EM algorithm. The proposed model is applied to UK aggregate consumption of alcohol and tobacco, using quarterly data from 1963 to 2003. Increased alcohol consumption is explained by a preference shift, addictive behaviour and a lower price elasticity. The dynamic and time-varying specification is consistent with the theoretical requirements imposed at each sample point. (c) 2005 Elsevier B.V. All rights reserved.

An approximate Bayesian computation approach to overcome biases that arise when using amplified fragment length polymorphism markers to study population structure

There is great interest in using amplified fragment length polymorphism (AFLP) markers because they are inexpensive and easy to produce. It is, therefore, possible to generate a large number of markers that have a wide coverage of species genotnes. Several statistical methods have been proposed to study the genetic structure using AFLP's but they assume Hardy-Weinberg equilibrium and do not estimate the inbreeding coefficient, F-IS. A Bayesian method has been proposed by Holsinger and colleagues that relaxes these simplifying assumptions but we have identified two sources of bias that can influence estimates based on these markers: (i) the use of a uniform prior on ancestral allele frequencies and (ii) the ascertainment bias of AFLP markers. We present a new Bayesian method that avoids these biases by using an implementation based on the approximate Bayesian computation (ABC) algorithm. This new method estimates population-specific F-IS and F-ST values and offers users the possibility of taking into account the criteria for selecting the markers that are used in the analyses. The software is available at our web site (http://www-leca.uif-grenoble.fi-/logiciels.htm). Finally, we provide advice on how to avoid the effects of ascertainment bias.

Use of a novel Hill-climbing genetic algorithm in protein folding simulations

We have developed a novel Hill-climbing genetic algorithm (GA) for simulation of protein folding. The program (written in C) builds a set of Cartesian points to represent an unfolded polypeptide's backbone. The dihedral angles determining the chain's configuration are stored in an array of chromosome structures that is copied and then mutated. The fitness of the mutated chain's configuration is determined by its radius of gyration. A four-helix bundle was used to optimise simulation conditions, and the program was compared with other, larger, genetic algorithms on a variety of structures. The program ran 50% faster than other GA programs. Overall, tests on 100 non-redundant structures gave comparable results to other genetic algorithms, with the Hill-climbing program running from between 20 and 50% faster. Examples including crambin, cytochrome c, cytochrome B and hemerythrin gave good secondary structure fits with overall alpha carbon atom rms deviations of between 5 and 5.6 Angstrom with an optimised hydrophobic term in the fitness function. (C) 2003 Elsevier Ltd. All rights reserved.

Equilibrium studies on mixed ligand complex formation of Co(II), Ni(II), Cu(II) and Zn(II) with N-(2-hydroxybenzyl)-L-histidine (H(2)hb-L-his) and typical N,N donor ligands: Crystal structure of [Ni(hb-L-his)(bipyridine)]center dot H2O complex

Equilibrium study on complex formation of Co(II), Ni(II), Cu(II) and Zn(II), hereafter M(II), with the quadridentate (O-, N, O-, N) donor ligand, N-(2-hydroxybenzyl)-L-histidine (H(2)hb-L-his, hereafter H2L), in the absence and in the presence of typical (N, N) donor bidentate ligands, 1,10 phenanthroline(phen), 2, 2'-bipyridine(bipy), ethylenediamine(en), hereafter B, in aqueous solution at 25 +/- 1 degrees C was done at a fixed ionic strength, I = 0.1 mol dm(-3) (NaNO3) by combined pH-metric, UV-Vis and EPR measurements provide evidence for the formation of mononuclear and dinuclear binary and mixed ligand complexes of the types: M(L), M(L)(2)(2-), M-2(L)(2+), M-2(H-1L)(+), M(L)(B), (B)M(H-1L)M(B)(+). The imidazole moiety of the ligand is found to act as a bridging bidentate ligand in the dinuclear M-2(L)(2+), M-2(H-1L)(+) and (B)M(H-1L)M(B)(+) complexes, using its N-3 atom and N1-H deprotonated moiety. Stability constants of the complexes provide evidence of discrimination of Cu(II) from the other M(II) ions by this ligand. Solid complexes: [Ni(L)(H2O)(2)] (1), [Cu(L)(H2O)] (2), and [Ni(L)(bipy)] (.) H2O (3) have been isolated and characterized by various physicochemical studies. Single crystal X-ray diffraction of the ternary complex, 3, shows an octahedral [(O-,N,N,O-)(N,N)] geometry with extensive pi-pi stacking of the aromatic rings and H-bonding with imidazole (N1-H), secondary amino N-atom, the lattice H2O molecule, and the carboxylate and phenolate O-atoms. (c) 2006 Elsevier B.V. All rights reserved.

Synthesis, structure and solution chemistry of quaternary oxovanadium(V) complexes incorporating hydrazone ligands

[VIVO(acac)(2)] reacts with an equimolar amount of benzoyl hydrazone of 2-hydroxyacetophenone (H2L1) or 5-chloro-2-hydroxyacetophenone (H2L2) in the presence of excess pyridine (py) in methanol to produce the quaternary [(VO)-O-V(L-1)(OCH3)(py)] (1) and [(VO)-O-V(L-2)(OCH3)(py)] (2) complexes, respectively, while under similar condition, the benzoyl hydrazones of 2-hydroxy-5-methylacetophenone (H2L3) and 2-hydroxy-5-methoxyacetophenone (H2L4) afforded only the methoxy bridged dimeric [(VO)-O-V(L-3/L-4)(OCH3)](2) complexes. The X-ray structural analysis of 1 and 2 indicates that the geometry around the metal is distorted octahedral where the three equatorial positions are occupied by the phenolate-O, enolate-O and the imine-N of the fully deprotonated hydrazone ligand in its enolic form and the fourth one by a methoxide-O atom. An oxo-O and a pyridine-N atom occupy two axial positions. Quaternary complexes exhibit one quasi-reversible one-electron reduction peak near 0.25 V versus SCE in CH2Cl2 and they decompose appreciably to the corresponding methoxy bridged dimeric complex in CDCl3 solution as indicated by their H-1 NMR spectra. These quaternary VO3+ complexes are converted to the corresponding V2O34+-complexes simply on refluxing them in acetone and to the VO2+-complexes on reaction with KOH in methanol. An equimolar amount of 8-hydroxyquinoline (Hhq) converts these quaternary complexes to the ternary [(VO)-O-V(L)(hq)] complexes in CHCl3. (C) 2009 Elsevier B. V. All rights reserved.

Improved two-pass hexagonal algorithm with parallel implementation for video coding - art. no. 60630J

This paper presents an improved parallel Two-Pass Hexagonal (TPA) algorithm constituted by Linear Hashtable Motion Estimation Algorithm (LHMEA) and Hexagonal Search (HEXBS) for motion estimation. Motion Vectors (MV) are generated from the first-pass LHMEA and used as predictors for second-pass HEXBS motion estimation, which only searches a small number of Macroblocks (MBs). We used bashtable into video processing and completed parallel implementation. The hashtable structure of LHMEA is improved compared to the original TPA and LHMEA. We propose and evaluate parallel implementations of the LHMEA of TPA on clusters of workstations for real time video compression. The implementation contains spatial and temporal approaches. The performance of the algorithm is evaluated by using standard video sequences and the results are compared to current algorithms.

Error analysis of a Monte Carlo algorithm for computing bilinear forms of matrix powers

In this paper we present error analysis for a Monte Carlo algorithm for evaluating bilinear forms of matrix powers. An almost Optimal Monte Carlo (MAO) algorithm for solving this problem is formulated. Results for the structure of the probability error are presented and the construction of robust and interpolation Monte Carlo algorithms are discussed. Results are presented comparing the performance of the Monte Carlo algorithm with that of a corresponding deterministic algorithm. The two algorithms are tested on a well balanced matrix and then the effects of perturbing this matrix, by small and large amounts, is studied.

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.

A-optimality orthogonal forward regression algorithm using branch and bound

In this brief, we propose an orthogonal forward regression (OFR) algorithm based on the principles of the branch and bound (BB) and A-optimality experimental design. At each forward regression step, each candidate from a pool of candidate regressors, referred to as S, is evaluated in turn with three possible decisions: 1) one of these is selected and included into the model; 2) some of these remain in S for evaluation in the next forward regression step; and 3) the rest are permanently eliminated from S. Based on the BB principle in combination with an A-optimality composite cost function for model structure determination, a simple adaptive diagnostics test is proposed to determine the decision boundary between 2) and 3). As such the proposed algorithm can significantly reduce the computational cost in the A-optimality OFR algorithm. Numerical examples are used to demonstrate the effectiveness of the proposed algorithm.

Automatic nonlinear predictive model-construction algorithm using forward regression and the PRESS statistic

An automatic nonlinear predictive model-construction algorithm is introduced based on forward regression and the predicted-residual-sums-of-squares (PRESS) statistic. The proposed algorithm is based on the fundamental concept of evaluating a model's generalisation capability through crossvalidation. This is achieved by using the PRESS statistic as a cost function to optimise model structure. In particular, the proposed algorithm is developed with the aim of achieving computational efficiency, such that the computational effort, which would usually be extensive in the computation of the PRESS statistic, is reduced or minimised. The computation of PRESS is simplified by avoiding a matrix inversion through the use of the orthogonalisation procedure inherent in forward regression, and is further reduced significantly by the introduction of a forward-recursive formula. Based on the properties of the PRESS statistic, the proposed algorithm can achieve a fully automated procedure without resort to any other validation data set for iterative model evaluation. Numerical examples are used to demonstrate the efficacy of the algorithm.