Artificial analysis of molecular marker loci linked to tree resistance response by an artificial neural network

One of the biggest challenges that software developers face is to make an accurate estimate of the project effort. Radial basis function neural networks have been used to software effort estimation in this work using NASA dataset. This paper evaluates and compares radial basis function versus a regression model. The results show that radial basis function neural network have obtained less Mean Square Error than the regression method.

Contributions to Bayesian network learning with applications to neuroscience

Neuronal morphology is a key feature in the study of brain circuits, as it is highly related to information processing and functional identification. Neuronal morphology affects the process of integration of inputs from other neurons and determines the neurons which receive the output of the neurons. Different parts of the neurons can operate semi-independently according to the spatial location of the synaptic connections. As a result, there is considerable interest in the analysis of the microanatomy of nervous cells since it constitutes an excellent tool for better understanding cortical function. However, the morphologies, molecular features and electrophysiological properties of neuronal cells are extremely variable. Except for some special cases, this variability makes it hard to find a set of features that unambiguously define a neuronal type. In addition, there are distinct types of neurons in particular regions of the brain. This morphological variability makes the analysis and modeling of neuronal morphology a challenge. Uncertainty is a key feature in many complex real-world problems. Probability theory provides a framework for modeling and reasoning with uncertainty. Probabilistic graphical models combine statistical theory and graph theory to provide a tool for managing domains with uncertainty. In particular, we focus on Bayesian networks, the most commonly used probabilistic graphical model. In this dissertation, we design new methods for learning Bayesian networks and apply them to the problem of modeling and analyzing morphological data from neurons. The morphology of a neuron can be quantified using a number of measurements, e.g., the length of the dendrites and the axon, the number of bifurcations, the direction of the dendrites and the axon, etc. These measurements can be modeled as discrete or continuous data. The continuous data can be linear (e.g., the length or the width of a dendrite) or directional (e.g., the direction of the axon). These data may follow complex probability distributions and may not fit any known parametric distribution. Modeling this kind of problems using hybrid Bayesian networks with discrete, linear and directional variables poses a number of challenges regarding learning from data, inference, etc. In this dissertation, we propose a method for modeling and simulating basal dendritic trees from pyramidal neurons using Bayesian networks to capture the interactions between the variables in the problem domain. A complete set of variables is measured from the dendrites, and a learning algorithm is applied to find the structure and estimate the parameters of the probability distributions included in the Bayesian networks. Then, a simulation algorithm is used to build the virtual dendrites by sampling values from the Bayesian networks, and a thorough evaluation is performed to show the model’s ability to generate realistic dendrites. In this first approach, the variables are discretized so that discrete Bayesian networks can be learned and simulated. Then, we address the problem of learning hybrid Bayesian networks with different kinds of variables. Mixtures of polynomials have been proposed as a way of representing probability densities in hybrid Bayesian networks. We present a method for learning mixtures of polynomials approximations of one-dimensional, multidimensional and conditional probability densities from data. The method is based on basis spline interpolation, where a density is approximated as a linear combination of basis splines. The proposed algorithms are evaluated using artificial datasets. We also use the proposed methods as a non-parametric density estimation technique in Bayesian network classifiers. Next, we address the problem of including directional data in Bayesian networks. These data have some special properties that rule out the use of classical statistics. Therefore, different distributions and statistics, such as the univariate von Mises and the multivariate von Mises–Fisher distributions, should be used to deal with this kind of information. In particular, we extend the naive Bayes classifier to the case where the conditional probability distributions of the predictive variables given the class follow either of these distributions. We consider the simple scenario, where only directional predictive variables are used, and the hybrid case, where discrete, Gaussian and directional distributions are mixed. The classifier decision functions and their decision surfaces are studied at length. Artificial examples are used to illustrate the behavior of the classifiers. The proposed classifiers are empirically evaluated over real datasets. We also study the problem of interneuron classification. An extensive group of experts is asked to classify a set of neurons according to their most prominent anatomical features. A web application is developed to retrieve the experts’ classifications. We compute agreement measures to analyze the consensus between the experts when classifying the neurons. Using Bayesian networks and clustering algorithms on the resulting data, we investigate the suitability of the anatomical terms and neuron types commonly used in the literature. Additionally, we apply supervised learning approaches to automatically classify interneurons using the values of their morphological measurements. Then, a methodology for building a model which captures the opinions of all the experts is presented. First, one Bayesian network is learned for each expert, and we propose an algorithm for clustering Bayesian networks corresponding to experts with similar behaviors. Then, a Bayesian network which represents the opinions of each group of experts is induced. Finally, a consensus Bayesian multinet which models the opinions of the whole group of experts is built. A thorough analysis of the consensus model identifies different behaviors between the experts when classifying the interneurons in the experiment. A set of characterizing morphological traits for the neuronal types can be defined by performing inference in the Bayesian multinet. These findings are used to validate the model and to gain some insights into neuron morphology. Finally, we study a classification problem where the true class label of the training instances is not known. Instead, a set of class labels is available for each instance. This is inspired by the neuron classification problem, where a group of experts is asked to individually provide a class label for each instance. We propose a novel approach for learning Bayesian networks using count vectors which represent the number of experts who selected each class label for each instance. These Bayesian networks are evaluated using artificial datasets from supervised learning problems. Resumen La morfología neuronal es una característica clave en el estudio de los circuitos cerebrales, ya que está altamente relacionada con el procesado de información y con los roles funcionales. La morfología neuronal afecta al proceso de integración de las señales de entrada y determina las neuronas que reciben las salidas de otras neuronas. Las diferentes partes de la neurona pueden operar de forma semi-independiente de acuerdo a la localización espacial de las conexiones sinápticas. Por tanto, existe un interés considerable en el análisis de la microanatomía de las células nerviosas, ya que constituye una excelente herramienta para comprender mejor el funcionamiento de la corteza cerebral. Sin embargo, las propiedades morfológicas, moleculares y electrofisiológicas de las células neuronales son extremadamente variables. Excepto en algunos casos especiales, esta variabilidad morfológica dificulta la definición de un conjunto de características que distingan claramente un tipo neuronal. Además, existen diferentes tipos de neuronas en regiones particulares del cerebro. La variabilidad neuronal hace que el análisis y el modelado de la morfología neuronal sean un importante reto científico. La incertidumbre es una propiedad clave en muchos problemas reales. La teoría de la probabilidad proporciona un marco para modelar y razonar bajo incertidumbre. Los modelos gráficos probabilísticos combinan la teoría estadística y la teoría de grafos con el objetivo de proporcionar una herramienta con la que trabajar bajo incertidumbre. En particular, nos centraremos en las redes bayesianas, el modelo más utilizado dentro de los modelos gráficos probabilísticos. En esta tesis hemos diseñado nuevos métodos para aprender redes bayesianas, inspirados por y aplicados al problema del modelado y análisis de datos morfológicos de neuronas. La morfología de una neurona puede ser cuantificada usando una serie de medidas, por ejemplo, la longitud de las dendritas y el axón, el número de bifurcaciones, la dirección de las dendritas y el axón, etc. Estas medidas pueden ser modeladas como datos continuos o discretos. A su vez, los datos continuos pueden ser lineales (por ejemplo, la longitud o la anchura de una dendrita) o direccionales (por ejemplo, la dirección del axón). Estos datos pueden llegar a seguir distribuciones de probabilidad muy complejas y pueden no ajustarse a ninguna distribución paramétrica conocida. El modelado de este tipo de problemas con redes bayesianas híbridas incluyendo variables discretas, lineales y direccionales presenta una serie de retos en relación al aprendizaje a partir de datos, la inferencia, etc. En esta tesis se propone un método para modelar y simular árboles dendríticos basales de neuronas piramidales usando redes bayesianas para capturar las interacciones entre las variables del problema. Para ello, se mide un amplio conjunto de variables de las dendritas y se aplica un algoritmo de aprendizaje con el que se aprende la estructura y se estiman los parámetros de las distribuciones de probabilidad que constituyen las redes bayesianas. Después, se usa un algoritmo de simulación para construir dendritas virtuales mediante el muestreo de valores de las redes bayesianas. Finalmente, se lleva a cabo una profunda evaluaci ón para verificar la capacidad del modelo a la hora de generar dendritas realistas. En esta primera aproximación, las variables fueron discretizadas para poder aprender y muestrear las redes bayesianas. A continuación, se aborda el problema del aprendizaje de redes bayesianas con diferentes tipos de variables. Las mixturas de polinomios constituyen un método para representar densidades de probabilidad en redes bayesianas híbridas. Presentamos un método para aprender aproximaciones de densidades unidimensionales, multidimensionales y condicionales a partir de datos utilizando mixturas de polinomios. El método se basa en interpolación con splines, que aproxima una densidad como una combinación lineal de splines. Los algoritmos propuestos se evalúan utilizando bases de datos artificiales. Además, las mixturas de polinomios son utilizadas como un método no paramétrico de estimación de densidades para clasificadores basados en redes bayesianas. Después, se estudia el problema de incluir información direccional en redes bayesianas. Este tipo de datos presenta una serie de características especiales que impiden el uso de las técnicas estadísticas clásicas. Por ello, para manejar este tipo de información se deben usar estadísticos y distribuciones de probabilidad específicos, como la distribución univariante von Mises y la distribución multivariante von Mises–Fisher. En concreto, en esta tesis extendemos el clasificador naive Bayes al caso en el que las distribuciones de probabilidad condicionada de las variables predictoras dada la clase siguen alguna de estas distribuciones. Se estudia el caso base, en el que sólo se utilizan variables direccionales, y el caso híbrido, en el que variables discretas, lineales y direccionales aparecen mezcladas. También se estudian los clasificadores desde un punto de vista teórico, derivando sus funciones de decisión y las superficies de decisión asociadas. El comportamiento de los clasificadores se ilustra utilizando bases de datos artificiales. Además, los clasificadores son evaluados empíricamente utilizando bases de datos reales. También se estudia el problema de la clasificación de interneuronas. Desarrollamos una aplicación web que permite a un grupo de expertos clasificar un conjunto de neuronas de acuerdo a sus características morfológicas más destacadas. Se utilizan medidas de concordancia para analizar el consenso entre los expertos a la hora de clasificar las neuronas. Se investiga la idoneidad de los términos anatómicos y de los tipos neuronales utilizados frecuentemente en la literatura a través del análisis de redes bayesianas y la aplicación de algoritmos de clustering. Además, se aplican técnicas de aprendizaje supervisado con el objetivo de clasificar de forma automática las interneuronas a partir de sus valores morfológicos. A continuación, se presenta una metodología para construir un modelo que captura las opiniones de todos los expertos. Primero, se genera una red bayesiana para cada experto y se propone un algoritmo para agrupar las redes bayesianas que se corresponden con expertos con comportamientos similares. Después, se induce una red bayesiana que modela la opinión de cada grupo de expertos. Por último, se construye una multired bayesiana que modela las opiniones del conjunto completo de expertos. El análisis del modelo consensuado permite identificar diferentes comportamientos entre los expertos a la hora de clasificar las neuronas. Además, permite extraer un conjunto de características morfológicas relevantes para cada uno de los tipos neuronales mediante inferencia con la multired bayesiana. Estos descubrimientos se utilizan para validar el modelo y constituyen información relevante acerca de la morfología neuronal. Por último, se estudia un problema de clasificación en el que la etiqueta de clase de los datos de entrenamiento es incierta. En cambio, disponemos de un conjunto de etiquetas para cada instancia. Este problema está inspirado en el problema de la clasificación de neuronas, en el que un grupo de expertos proporciona una etiqueta de clase para cada instancia de manera individual. Se propone un método para aprender redes bayesianas utilizando vectores de cuentas, que representan el número de expertos que seleccionan cada etiqueta de clase para cada instancia. Estas redes bayesianas se evalúan utilizando bases de datos artificiales de problemas de aprendizaje supervisado.

Function of C1A barley peptidases and their inhibitors (cystatins) in barley seed germination : Funcion de las peptidasas C1A de cebada y sus inhibidores (cistatinas) en la germinacion de la semilla

Plant proteolysis is a metabolic process where specific enzymes called peptidases degrade proteins. In plants, this complex process involves broad metabolic networks and different sub-cellular compartments. Several types of peptidases take part in the proteolytic process, mainly cysteine-, serine-, aspartyl- and metallo- peptidases. Among the cysteine-peptidases, the papain-like or C1A peptidases (family C1, clan CA) are extensively present in land plants and are classified into catepsins L-, B-, H- and Flike. The catalytic mechanism of these C1A peptidases is highly conserved and involves the three amino acids Cys, His and Asn in the catalytic triad, and a Gln residue which seems essential for maintaining an active enzyme conformation. These proteins are synthesized as inactive precursors, which comprise an N-terminal signal peptide, a propeptide, and the mature protein. In barley, we have identified 33 cysteine-peptidases from the papain-like family, classifying them into 8 different groups. Five of them corresponded to cathepsins L-like (5 subgroups), 1 cathepsin B-like group, 1 cathepsin F-like group and 1 cathepsin H-like group. Besides, C1A peptidases are the specific targets of the plant proteinaceous inhibitors known as phytocystatins (PhyCys). The cystatin inhibitory mechanism is produced by a tight and reversible interaction with their target enzymes. In barley, the cystatin gene family is comprised by 13 members. In this work we have tried to elucidate the role of the C1A cysteine-peptidases and their specific inhibitors (cystatins) in the germination process of the barley grain. Therefore, we selected a representative member of each group/subgroup of C1A peptidases (1 cathepsin B-like, 1 cathepsin F-like, 1 cathepsin H-like and 5 cathepsins L-like). The molecular characterization of the cysteine-peptidases was done and the peptidase-inhibitor interaction was analyzed in vitro and in vivo. A study in the structural basis for specificity of pro-peptide/enzyme interaction in barley C1A cysteine-peptidases has been also carried out by inhibitory assays and the modeling of the three-dimensional structures. The barley grain maturation produces the accumulation of storage proteins (prolamins) in the endosperm which are mobilized during germination to supply the required nutrients until the photosynthesis is fully established. In this work, we have demonstrated the participation of the cysteine-peptidases and their inhibitors in the degradation of the different storage protein fractions (hordeins, albumins and globulins) present in the barley grain. Besides, transgenic barley plants overexpressing or silencing cysteine-peptidases or cystatins were obtained by Agrobacterium-mediated transformation of barley immature embryos to analyze their physiological function in vivo. Preliminary assays were carried out with the T1 grains of several transgenic lines. Comparing the knock-out and the overexpressing lines with the WT, alterations in the germination process were detected and were correlated with their grain hordein content. These data will be validated with the homozygous grains that are being produced through the double haploid technique by microspore culture. Resumen La proteólisis es un proceso metabólico por el cual se lleva a cabo la degradación de las proteínas de un organismo a través de enzimas específicas llamadas proteasas. En plantas, este complejo proceso comprende un entramado de rutas metabólicas que implican, además, diferentes compartimentos subcelulares. En la proteólisis participan numerosas proteasas, principalmente cisteín-, serín-, aspartil-, y metalo-proteasas. Dentro de las cisteín-proteasas, las proteasas tipo papaína o C1A (familia C1, clan CA) están extensamente representadas en plantas terrestres, y se clasifican en catepsinas tipo L, B, H y F. El mecanismo catalítico de estas proteasas está altamente conservado y la triada catalítica formada por los aminoácidos Cys, His y Asn, y a un aminoácido Gln, que parece esencial para el mantenimiento de la conformación activa de la proteína. Las proteasas C1A se sintetizan como precursores inactivos y comprenden un péptido señal en el extremo N-terminal, un pro-péptido y la proteína madura. En cebada hemos identificado 33 cisteín-proteasas de tipo papaína y las hemos clasificado filogenéticamente en 8 grupos diferentes. Cinco de ellos pertenecen a las catepsinas tipo L (5 subgrupos), un grupo a las catepsinas tipo-B, otro a las catepsinas tipo-F y un último a las catepsinas tipo-H. Las proteasas C1A son además las dianas específicas de los inhibidores protéicos de plantas denominados fitocistatinas. El mecanismo de inhibición de las cistatinas está basado en una fuerte interacción reversible. En cebada, se conoce la familia génica completa de las cistatinas, que está formada por 13 miembros. En el presente trabajo se ha investigado el papel de las cisteín-proteasas de cebada y sus inhibidores específicos en el proceso de la germinación de la semilla. Para ello, se seleccionó una proteasa representante de cada grupo/subgrupo (1 catepsina tipo- B, 1 tipo-F, 1 tipo-H, y 5 tipo-L, una por cada subgrupo). Se ha llevado a cabo su caracterización molecular y se ha analizado la interacción enzima-inhibidor tanto in vivo como in vitro. También se han realizado estudios sobre las bases estructurales que demuestran la especificidad en la interacción enzima/propéptido en las proteasas C1A de cebada, mediante ensayos de inhibición y la predicción de modelos estructurales de la interacción. Finalmente, y dado que durante la maduración de la semilla se almacenan proteínas de reserva (prolaminas) en el endospermo que son movilizadas durante la germinación para suministrar los nutrientes necesarios hasta que la nueva planta pueda realizar la fotosíntesis, en este trabajo se ha demostrado la participación de las cisteínproteasas y sus inhibidores en la degradación de las diferentes tipos de proteínas de reserva (hordeinas, albúmins y globulinas) presentes en el grano de cebada. Además, se han obtenido plantas transgénicas de cebada que sobre-expresan o silencian cistatinas y cisteín-proteasas con el fin de analizar la función fisiológica in vivo. Se han realizado análisis preliminares en las semillas T1 de varias líneas tránsgenicas de cebada y al comparar las líneas knock-out y las líneas de sobre-expresión con las silvestres, se han detectado alteraciones en la germinación que están además correlacionadas con el contenido de hordeinas de las semillas. Estos datos serán validados en las semillas homocigotas que se están generando mediante la técnica de dobles haploides a partir del cultivo de microesporas.

Structure function and Multifractal spectrum applied to Digital Elevation Model

A Digital Elevation Model (DEM) provides the information basis used for many geographic applications such as topographic and geomorphologic studies, landscape through GIS (Geographic Information Systems) among others. The DEM capacity to represent Earth?s surface depends on the surface roughness and the resolution used. Each DEM pixel depends on the scale used characterized by two variables: resolution and extension of the area studied. DEMs can vary in resolution and accuracy by the production method, although there are statistical characteristics that keep constant or very similar in a wide range of scales. Based on this property, several techniques have been applied to characterize DEM through multiscale analysis directly related to fractal geometry: multifractal spectrum and the structure function. The comparison of the results by both methods is discussed. The study area is represented by a 1024 x 1024 data matrix obtained from a DEM with a resolution of 10 x 10 m each point, which correspond with a region known as ?Monte de El Pardo? a property of Spanish National Heritage (Patrimonio Nacional Español) of 15820 Ha located to a short distance from the center of Madrid. Manzanares River goes through this area from North to South. In the southern area a reservoir is found with a capacity of 43 hm3, with an altitude of 603.3 m till 632 m when it is at the highest capacity. In the middle of the reservoir the minimum altitude of this area is achieved.

Unveiling Protein Functions through the Dynamics of the Interaction Network

Protein interaction networks have become a tool to study biological processes, either for predicting molecular functions or for designing proper new drugs to regulate the main biological interactions. Furthermore, such networks are known to be organized in sub-networks of proteins contributing to the same cellular function. However, the protein function prediction is not accurate and each protein has traditionally been assigned to only one function by the network formalism. By considering the network of the physical interactions between proteins of the yeast together with a manual and single functional classification scheme, we introduce a method able to reveal important information on protein function, at both micro- and macro-scale. In particular, the inspection of the properties of oscillatory dynamics on top of the protein interaction network leads to the identification of misclassification problems in protein function assignments, as well as to unveil correct identification of protein functions. We also demonstrate that our approach can give a network representation of the meta-organization of biological processes by unraveling the interactions between different functional classes

Topology of a percolating soil pore network.

A connectivity function defined by the 3D-Euler number, is a topological indicator and can be related to hydraulic properties (Vogel and Roth, 2001). This study aims to develop connectivity Euler indexes as indicators of the ability of soils for fluid percolation. The starting point was a 3D grey image acquired by X-ray computed tomography of a soil at bulk density of 1.2 mg cm-3. This image was used in the simulation of 40000 particles following a directed random walk algorithms with 7 binarization thresholds. These data consisted of 7 files containing the simulated end points of the 40000 random walks, obtained in Ruiz-Ramos et al. (2010). MATLAB software was used for computing the frequency matrix of the number of particles arriving at every end point of the random walks and their 3D representation.

The Phase Space as a New Representation of the Dynamical Behaviour of Temperature and Enthalpy in a Reefer monitored with a Multidistributed Sensors Network

The study of temperature gradients in cold stores and containers is a critical issue in the food industry for the quality assurance of products during transport, as well as forminimizing losses. The objective of this work is to develop a new methodology of data analysis based on phase space graphs of temperature and enthalpy, collected by means of multidistributed, low cost and autonomous wireless sensors and loggers. A transoceanic refrigerated transport of lemons in a reefer container ship from Montevideo (Uruguay) to Cartagena (Spain) was monitored with a network of 39 semi-passive TurboTag RFID loggers and 13 i-button loggers. Transport included intermodal transit from transoceanic to short shipping vessels and a truck trip. Data analysis is carried out using qualitative phase diagrams computed on the basis of Takens?Ruelle reconstruction of attractors. Fruit stress is quantified in terms of the phase diagram area which characterizes the cyclic behaviour of temperature. Areas within the enthalpy phase diagram computed for the short sea shipping transport were 5 times higher than those computed for the long sea shipping, with coefficients of variation above 100% for both periods. This new methodology for data analysis highlights the significant heterogeneity of thermohygrometric conditions at different locations in the container.

Protein isolate and inulin: chemical, rheological and structural basis

Soy protein isolate is typical vegetable protein with health-enhancing activities. Inulin, a prebiotic no digestible carbohydrate, has functional properties. A mashed potato serving of 200 g with added soy protein isolate and inulin concentrations of 15?60 g kg provides from 3 to 12 g of soy protein isolate and/or inulin, respectively. Currently, no information is available about the possible texture-modifying effect of this non-ionizable polar carbohydrate in different soy-based food systems. In this study, the effect of the addition of soy protein isolate and inulin blends at different soy protein isolate: inulin ratios on the degree of inulin polymerization and the rheological and structural properties of fresh mashed and frozen/thawed mashed potatoes were evaluated. The inulin chemical structure remained intact throughout the various treatments, and soy protein isolate did not affect inulin composition being a protein compatible with this fructan. Small-strain rheology showed that both ingredients behaved like soft fillers. In the frozen/thawed mashed potatoes samples,0 addition of 30 : 30 and 15 : 60 blend ratios significantly increased elasticity (G value) compared with 0 : 0 control, consequently reducing the freeze/thaw stability conferred by the cryoprotectants. Inulin crystallites caused a significant strengthening effect on soy protein isolate gel. Micrographs revealed that soy protein isolate supports the inulin structure by building up a second fine-stranded network. Thereby, possibility of using soy protein isolate and inulin in combination with mashed potatoes to provide a highly nutritious and healthy product is promising.

Algoritmos para mineria de datos con redes de neuronas

Este trabajo propone una serie de algoritmos con el objetivo de extraer información de conjuntos de datos con redes de neuronas. Se estudian dichos algoritmos con redes de neuronas Enhenced Neural Networks (ENN), debido a que esta arquitectura tiene algunas ventajas cuando se aproximan funciones mediante redes neuronales. En la red ENN los pesos de la matriz principal varián con cada patrón, por lo que se comete un error menor en la aproximación. Las redes de neuronas ENN reúnen la información en los pesos de su red auxiliar, se propone un método para obtener información de la red a través de dichos pesos en formas de reglas y asignando un factor de certeza de dichas reglas. La red ENN obtiene un error cuadrático medio menor que el error teórico de una aproximación matemática por ejemplo mediante polinomios de Taylor. Se muestra como una red ENN, entrenada a partir un conjunto de patrones obtenido de una función de variables reales, sus pesos asociados tienen unas relaciones similares a las que se veri_can con las variables independientes con dicha función de variables reales. Las redes de neuronas ENN aproximan polinomios, se extrae conocimiento de un conjunto de datos de forma similar a la regresión estadística, resolviendo de forma más adecuada el problema de multicolionalidad en caso de existir. Las relaciones a partir de los pesos asociados de la matriz de la red auxiliar se obtienen similares a los coeficientes de una regresión para el mismo conjunto numérico. Una red ENN entrenada a partir de un conjunto de datos de una función boolena extrae el conocimiento a partir de los pesos asociados, y la influencia de las variables de la regla lógica de la función booleana, queda reejada en esos pesos asociados a la red auxiliar de la red ENN. Se plantea una red de base radial (RBF) para la clasificación y predicción en problemas forestales y agrícolas, obteniendo mejores resultados que con el modelo de regresión y otros métodos. Los resultados con una red RBF mejoran al método de regresión si existe colinealidad entre los datos que se dispone y no son muy numerosos. También se detecta que variables tienen más importancia en virtud de la variable pronóstico. Obteniendo el error cuadrático medio con redes RBF menor que con otros métodos, en particular que con el modelo de regresión. Abstract A series of algorithms is proposed in this study aiming at the goal of producing information about data groups with a neural network. These algorithms are studied with Enheced Neural Networks (ENN), owing to the fact that this structure shows sever advantages when the functions are approximated by neural networks. Main matrix weights in th ENN vary on each pattern; so, a smaller error is produced when approximating. The neural network ENN joins the weight information contained in their auxiliary network. Thus, a method to obtain information on the network through those weights is proposed by means of rules adding a certainty factor. The net ENN obtains a mean squared error smaller than the theorical one emerging from a mathematical aproximation such as, for example, by means of Taylor's polynomials. This study also shows how in a neural network ENN trained from a set of patterns obtained through a function of real variables, its associated weights have relationships similar to those ones tested by means of the independent variables connected with such functions of real variables. The neural network ENN approximates polynomials through it information about a set of data may be obtained in a similar way than through statistical regression, solving in this way possible problems of multicollinearity in a more suitable way. Relationships emerging from the associated weights in the auxiliary network matrix obtained are similar to the coeficients corresponding to a regression for the same numerical set. A net ENN trained from a boolean function data set obtains its information from its associated weights. The inuence of the variables of the boolean function logical rule are reected on those weights associated to the net auxiliar of the ENN. A radial basis neural networks (RBF) for the classification and prediction of forest and agricultural problems is proposed. This scheme obtains better results than the ones obtained by means of regression and other methods. The outputs with a net RBF better the regression method if the collineality with the available data and their amount is not very large. Detection of which variables are more important basing on the forecast variable can also be achieved, obtaining a mean squared error smaller that the ones obtained through other methods, in special the one produced by the regression pattern.

Optimisation of algorithms to compute information theoretic indexes

Analysis of big amount of data is a field with many years of research. It is centred in getting significant values, to make it easier to understand and interpret data. Being the analysis of interdependence between time series an important field of research, mainly as a result of advances in the characterization of dynamical systems from the signals they produce. In the medicine sphere, it is easy to find many researches that try to understand the brain behaviour, its operation mode and its internal connections. The human brain comprises approximately 1011 neurons, each of which makes about 103 synaptic connections. This huge number of connections between individual processing elements provides the fundamental substrate for neuronal ensembles to become transiently synchronized or functionally connected. A similar complex network configuration and dynamics can also be found at the macroscopic scales of systems neuroscience and brain imaging. The emergence of dynamically coupled cell assemblies represents the neurophysiological substrate for cognitive function such as perception, learning, thinking. Understanding the complex network organization of the brain on the basis of neuroimaging data represents one of the most impervious challenges for systems neuroscience. Brain connectivity is an elusive concept that refers to diferent interrelated aspects of brain organization: structural, functional connectivity (FC) and efective connectivity (EC). Structural connectivity refers to a network of physical connections linking sets of neurons, it is the anatomical structur of brain networks. However, FC refers to the statistical dependence between the signals stemming from two distinct units within a nervous system, while EC refers to the causal interactions between them. This research opens the door to try to resolve diseases related with the brain, like Parkinson’s disease, senile dementia, mild cognitive impairment, etc. One of the most important project associated with Alzheimer’s research and other diseases are enclosed in the European project called Blue Brain. The center for Biomedical Technology (CTB) of Universidad Politecnica de Madrid (UPM) forms part of the project. The CTB researches have developed a magnetoencephalography (MEG) data processing tool that allow to visualise and analyse data in an intuitive way. This tool receives the name of HERMES, and it is presented in this document. Analysis of big amount of data is a field with many years of research. It is centred in getting significant values, to make it easier to understand and interpret data. Being the analysis of interdependence between time series an important field of research, mainly as a result of advances in the characterization of dynamical systems from the signals they produce. In the medicine sphere, it is easy to find many researches that try to understand the brain behaviour, its operation mode and its internal connections. The human brain comprises approximately 1011 neurons, each of which makes about 103 synaptic connections. This huge number of connections between individual processing elements provides the fundamental substrate for neuronal ensembles to become transiently synchronized or functionally connected. A similar complex network configuration and dynamics can also be found at the macroscopic scales of systems neuroscience and brain imaging. The emergence of dynamically coupled cell assemblies represents the neurophysiological substrate for cognitive function such as perception, learning, thinking. Understanding the complex network organization of the brain on the basis of neuroimaging data represents one of the most impervious challenges for systems neuroscience. Brain connectivity is an elusive concept that refers to diferent interrelated aspects of brain organization: structural, functional connectivity (FC) and efective connectivity (EC). Structural connectivity refers to a network of physical connections linking sets of neurons, it is the anatomical structur of brain networks. However, FC refers to the statistical dependence between the signals stemming from two distinct units within a nervous system, while EC refers to the causal interactions between them. This research opens the door to try to resolve diseases related with the brain, like Parkinson’s disease, senile dementia, mild cognitive impairment, etc. One of the most important project associated with Alzheimer’s research and other diseases are enclosed in the European project called Blue Brain. The center for Biomedical Technology (CTB) of Universidad Politecnica de Madrid (UPM) forms part of the project. The CTB researches have developed a magnetoencephalography (MEG) data processing tool that allow to visualise and analyse data in an intuitive way. This tool receives the name of HERMES, and it is presented in this document.

Electronic structure of copper nitrides as a function of nitrogen content

he nitrogen content dependence of the electronic properties for copper nitride thin films with an atomic percentage of nitrogen ranging from 26 ± 2 to 33 ± 2 have been studied by means of optical (spectroscopic ellipsometry), thermoelectric (Seebeck), and electrical resistivity measurements. The optical spectra are consistent with direct optical transitions corresponding to the stoichiometric semiconductor Cu3N plus a free-carrier contribution, essentially independent of temperature, which can be tuned in accordance with the N-excess. Deviation of the N content from stoichiometry drives to significant decreases from − 5 to − 50 μV/K in the Seebeck coefficient and to large enhancements, from 10− 3 up to 10 Ω cm, in the electrical resistivity. Band structure and density of states calculations have been carried out on the basis of the density functional theory to account for the experimental results.

Decision boundary for discrete Bayesian network classifiers

Bayesian network classifiers are a powerful machine learning tool. In order to evaluate the expressive power of these models, we compute families of polynomials that sign-represent decision functions induced by Bayesian network classifiers. We prove that those families are linear combinations of products of Lagrange basis polynomials. In absence of V-structures in the predictor sub-graph, we are also able to prove that this family of polynomials does in- deed characterize the specific classifier considered. We then use this representation to bound the number of decision functions representable by Bayesian network classifiers with a given structure and we compare these bounds to the ones obtained using Vapnik-Chervonenkis dimension.

Integration of congestion pricing and intertemporal preferences rate integration in social welfare function

Many researchers have used theoretical or empirical measures to assess social benefits in transport policy implementation. However, few have measured social benefits by using discount rates, including the intertemporal preference rate of users, the private investment discount rate, and the intertemporal preference rate of the government. In general, the social discount rate used is the same for all social actors. This paper aims to assess a new method by integrating different types of discount rates belonging to different social actors to measure the real benefits of each actor in the short term, medium term, and long term. A dynamic simulation is provided by a strategic land use and transport interaction model. The method was tested by optimizing a cordon toll scheme in Madrid, Spain. Socioeconomic efficiency and environmental criteria were considered. On the basis of the modified social welfare function, the effects on the measure of social benefits were estimated and compared with the classical welfare function measures. The results show that the use of more suitable discount rates for each social actor had an effect on the selection and definition of optimal strategy of congestion pricing. The usefulness of the measure of congestion toll declines more quickly over time. This result could be the key to understanding the relationship between transport system policies and the distribution of social actors? benefits in a metropolitan context.

Decision boundary for discrete Bayesian network classifiers

Bayesian network classifiers are a powerful machine learning tool. In order to evaluate the expressive power of these models, we compute families of polynomials that sign-represent decision functions induced by Bayesian network classifiers. We prove that those families are linear combinations of products of Lagrange basis polynomials. In absence of V-structures in the predictor sub-graph, we are also able to prove that this family of polynomials does in- deed characterize the specific classifier considered. We then use this representation to bound the number of decision functions representable by Bayesian network classifiers with a given structure and we compare these bounds to the ones obtained using Vapnik-Chervonenkis dimension.

Metodología para la asignación de vehículos de una flota a rutas preestablecidas

En general, la distribución de una flota de vehículos que recorre rutas fijas no se realiza completamente en base a criterios objetivos, primando otros aspectos más difícilmente cuantificables. El análisis apropiado debería tener en consideración la variabilidad existente entre las diferentes rutas dentro de una misma ciudad para así determinar qué tecnología es la que mejor se adapta a las características de cada itinerario. Este trabajo presenta una metodología para optimizar la asignación de una flota de vehículos a sus rutas, consiguiendo reducir el consumo y las emisiones contaminantes. El método propuesto está organizado según el siguiente procedimiento: - Registro de las características cinemáticas de los vehículos que recorren un conjunto representativo de rutas. - Agrupamiento de las líneas en conglomerados de líneas similares empleando un algoritmo jerárquico que optimice el índice de semejanza entre rutas obtenido mediante contraste de hipótesis de las variables representativas. - Generación de un ciclo cinemático específico para cada conglomerado. - Tipificación de variables macroscópicas que faciliten la clasificación de las restantes líneas utilizando una red neuronal entrenada con la información recopilada en las rutas medidas. - Conocimiento de las características de la flota disponible. - Disponibilidad de un modelo que estime, según la tecnología del vehículo, el consumo y las emisiones asociados a las variables cinemáticas de los ciclos. - Desarrollo de un algoritmo de reasignación de vehículos que optimice una función objetivo dependiente de las emisiones. En el proceso de optimización de la flota se plantean dos escenarios de gran trascendencia en la evaluación ambiental, consistentes en minimizar la emisión de dióxido de carbono y su impacto como gas de efecto invernadero (GEI), y alternativamente, la producción de nitróxidos, por su influencia en la lluvia ácida y en la formación de ozono troposférico en núcleos urbanos. Además, en ambos supuestos se introducen en el problema restricciones adicionales para evitar que las emisiones de las restantes sustancias superen los valores estipulados según la organización de la flota actualmente realizada por el operador. La metodología ha sido aplicada en 160 líneas de autobús de la EMT de Madrid, conociéndose los datos cinemáticos de 25 rutas. Los resultados indican que, en ambos supuestos, es factible obtener una redistribución de la flota que consiga reducir significativamente la mayoría de las sustancias contaminantes, evitando que, en contraprestación, aumente la emisión de cualquier otro contaminante. ABSTRACT In general, the distribution of a fleet of vehicles that travel fixed routes is not usually implemented on the basis of objective criteria, thus prioritizing on other features that are more difficult to quantify. The appropriate analysis should consider the existing variability amongst the different routes within the city in order to determine which technology adapts better to the peculiarities of each itinerary. This study proposes a methodology to optimize the allocation of a fleet of vehicles to the routes in order to reduce fuel consumption and pollutant emissions. The suggested method is structured in accordance with the following procedure: - Recording of the kinematic characteristics of the vehicles that travel a representative set of routes. - Grouping of the lines in clusters of similar routes by utilizing a hierarchical algorithm that optimizes the similarity index between routes, which has been previously obtained by means of hypothesis contrast based on a set of representative variables. - Construction of a specific kinematic cycle to represent each cluster of routes. - Designation of macroscopic variables that allow the classification of the remaining lines using a neural network trained with the information gathered from a sample of routes. - Identification and comprehension of the operational characteristics of the existing fleet. - Availability of a model that evaluates, in accordance with the technology of the vehicle, the fuel consumption and the emissions related with the kinematic variables of the cycles. - Development of an algorithm for the relocation of the vehicle fleet by optimizing an objective function which relies on the values of the pollutant emissions. Two scenarios having great relevance in environmental evaluation are assessed during the optimization process of the fleet, these consisting in minimizing carbon dioxide emissions due to its impact as greenhouse gas (GHG), and alternatively, the production of nitroxides for their influence on acid rain and in the formation of tropospheric ozone in urban areas. Furthermore, additional restrictions are introduced in both assumptions in order to prevent that emission levels for the remaining substances exceed the stipulated values for the actual fleet organization implemented by the system operator. The methodology has been applied in 160 bus lines of the EMT of Madrid, for which kinematic information is known for a sample consisting of 25 routes. The results show that, in both circumstances, it is feasible to obtain a redistribution of the fleet that significantly reduces the emissions for the majority of the pollutant substances, while preventing an alternative increase in the emission level of any other contaminant.