Otimização do processo de aprendizagem da estrutura gráfica de Redes Bayesianas em BigData

A automação na gestão e análise de dados tem sido um fator crucial para as empresas que necessitam de soluções eficientes em um mundo corporativo cada vez mais competitivo. A explosão do volume de informações, que vem se mantendo crescente nos últimos anos, tem exigido cada vez mais empenho em buscar estratégias para gerenciar e, principalmente, extrair informações estratégicas valiosas a partir do uso de algoritmos de Mineração de Dados, que comumente necessitam realizar buscas exaustivas na base de dados a fim de obter estatísticas que solucionem ou otimizem os parâmetros do modelo de extração do conhecimento utilizado; processo que requer computação intensiva para a execução de cálculos e acesso frequente à base de dados. Dada a eficiência no tratamento de incerteza, Redes Bayesianas têm sido amplamente utilizadas neste processo, entretanto, à medida que o volume de dados (registros e/ou atributos) aumenta, torna-se ainda mais custoso e demorado extrair informações relevantes em uma base de conhecimento. O foco deste trabalho é propor uma nova abordagem para otimização do aprendizado da estrutura da Rede Bayesiana no contexto de BigData, por meio do uso do processo de MapReduce, com vista na melhora do tempo de processamento. Para tanto, foi gerada uma nova metodologia que inclui a criação de uma Base de Dados Intermediária contendo todas as probabilidades necessárias para a realização dos cálculos da estrutura da rede. Por meio das análises apresentadas neste estudo, mostra-se que a combinação da metodologia proposta com o processo de MapReduce é uma boa alternativa para resolver o problema de escalabilidade nas etapas de busca em frequência do algoritmo K2 e, consequentemente, reduzir o tempo de resposta na geração da rede.

Structure learning of graphical models for task-oriented robot grasping

In the collective imaginaries a robot is a human like machine as any androids in science fiction. However the type of robots that you will encounter most frequently are machinery that do work that is too dangerous, boring or onerous. Most of the robots in the world are of this type. They can be found in auto, medical, manufacturing and space industries. Therefore a robot is a system that contains sensors, control systems, manipulators, power supplies and software all working together to perform a task. The development and use of such a system is an active area of research and one of the main problems is the development of interaction skills with the surrounding environment, which include the ability to grasp objects. To perform this task the robot needs to sense the environment and acquire the object informations, physical attributes that may influence a grasp. Humans can solve this grasping problem easily due to their past experiences, that is why many researchers are approaching it from a machine learning perspective finding grasp of an object using information of already known objects. But humans can select the best grasp amongst a vast repertoire not only considering the physical attributes of the object to grasp but even to obtain a certain effect. This is why in our case the study in the area of robot manipulation is focused on grasping and integrating symbolic tasks with data gained through sensors. The learning model is based on Bayesian Network to encode the statistical dependencies between the data collected by the sensors and the symbolic task. This data representation has several advantages. It allows to take into account the uncertainty of the real world, allowing to deal with sensor noise, encodes notion of causality and provides an unified network for learning. Since the network is actually implemented and based on the human expert knowledge, it is very interesting to implement an automated method to learn the structure as in the future more tasks and object features can be introduced and a complex network design based only on human expert knowledge can become unreliable. Since structure learning algorithms presents some weaknesses, the goal of this thesis is to analyze real data used in the network modeled by the human expert, implement a feasible structure learning approach and compare the results with the network designed by the expert in order to possibly enhance it.

Automatic extraction of femur contours from calibrated fluoroscopic images

Automatic identification and extraction of bone contours from X-ray images is an essential first step task for further medical image analysis. In this paper we propose a 3D statistical model based framework for the proximal femur contour extraction from calibrated X-ray images. The automatic initialization is solved by an estimation of Bayesian network algorithm to fit a multiple component geometrical model to the X-ray data. The contour extraction is accomplished by a non-rigid 2D/3D registration between a 3D statistical model and the X-ray images, in which bone contours are extracted by a graphical model based Bayesian inference. Preliminary experiments on clinical data sets verified its validity

Ensemble transcript interaction networks: A case study on Alzheimer's disease

Systems biology techniques are a topic of recent interest within the neurological field. Computational intelligence (CI) addresses this holistic perspective by means of consensus or ensemble techniques ultimately capable of uncovering new and relevant findings. In this paper, we propose the application of a CI approach based on ensemble Bayesian network classifiers and multivariate feature subset selection to induce probabilistic dependences that could match or unveil biological relationships. The research focuses on the analysis of high-throughput Alzheimer's disease (AD) transcript profiling. The analysis is conducted from two perspectives. First, we compare the expression profiles of hippocampus subregion entorhinal cortex (EC) samples of AD patients and controls. Second, we use the ensemble approach to study four types of samples: EC and dentate gyrus (DG) samples from both patients and controls. Results disclose transcript interaction networks with remarkable structures and genes not directly related to AD by previous studies. The ensemble is able to identify a variety of transcripts that play key roles in other neurological pathologies. Classical statistical assessment by means of non-parametric tests confirms the relevance of the majority of the transcripts. The ensemble approach pinpoints key metabolic mechanisms that could lead to new findings in the pathogenesis and development of AD

Multi-objective Estimation of Distribution Algorithm Based on Joint Modeling of Objectives and Variables

This paper proposes a new multi-objective estimation of distribution algorithm (EDA) based on joint modeling of objectives and variables. This EDA uses the multi-dimensional Bayesian network as its probabilistic model. In this way it can capture the dependencies between objectives, variables and objectives, as well as the dependencies learnt between variables in other Bayesian network-based EDAs. This model leads to a problem decomposition that helps the proposed algorithm to find better trade-off solutions to the multi-objective problem. In addition to Pareto set approximation, the algorithm is also able to estimate the structure of the multi-objective problem. To apply the algorithm to many-objective problems, the algorithm includes four different ranking methods proposed in the literature for this purpose. The algorithm is applied to the set of walking fish group (WFG) problems, and its optimization performance is compared with an evolutionary algorithm and another multi-objective EDA. The experimental results show that the proposed algorithm performs significantly better on many of the problems and for different objective space dimensions, and achieves comparable results on some compared with the other algorithms.

Regularized model learning in EDAs for continuous and multi-objective optimization

Probabilistic modeling is the de�ning characteristic of estimation of distribution algorithms (EDAs) which determines their behavior and performance in optimization. Regularization is a well-known statistical technique used for obtaining an improved model by reducing the generalization error of estimation, especially in high-dimensional problems. `1-regularization is a type of this technique with the appealing variable selection property which results in sparse model estimations. In this thesis, we study the use of regularization techniques for model learning in EDAs. Several methods for regularized model estimation in continuous domains based on a Gaussian distribution assumption are presented, and analyzed from di�erent aspects when used for optimization in a high-dimensional setting, where the population size of EDA has a logarithmic scale with respect to the number of variables. The optimization results obtained for a number of continuous problems with an increasing number of variables show that the proposed EDA based on regularized model estimation performs a more robust optimization, and is able to achieve signi�cantly better results for larger dimensions than other Gaussian-based EDAs. We also propose a method for learning a marginally factorized Gaussian Markov random �eld model using regularization techniques and a clustering algorithm. The experimental results show notable optimization performance on continuous additively decomposable problems when using this model estimation method. Our study also covers multi-objective optimization and we propose joint probabilistic modeling of variables and objectives in EDAs based on Bayesian networks, speci�cally models inspired from multi-dimensional Bayesian network classi�ers. It is shown that with this approach to modeling, two new types of relationships are encoded in the estimated models in addition to the variable relationships captured in other EDAs: objectivevariable and objective-objective relationships. An extensive experimental study shows the e�ectiveness of this approach for multi- and many-objective optimization. With the proposed joint variable-objective modeling, in addition to the Pareto set approximation, the algorithm is also able to obtain an estimation of the multi-objective problem structure. Finally, the study of multi-objective optimization based on joint probabilistic modeling is extended to noisy domains, where the noise in objective values is represented by intervals. A new version of the Pareto dominance relation for ordering the solutions in these problems, namely �-degree Pareto dominance, is introduced and its properties are analyzed. We show that the ranking methods based on this dominance relation can result in competitive performance of EDAs with respect to the quality of the approximated Pareto sets. This dominance relation is then used together with a method for joint probabilistic modeling based on `1-regularization for multi-objective feature subset selection in classi�cation, where six di�erent measures of accuracy are considered as objectives with interval values. The individual assessment of the proposed joint probabilistic modeling and solution ranking methods on datasets with small-medium dimensionality, when using two di�erent Bayesian classi�ers, shows that comparable or better Pareto sets of feature subsets are approximated in comparison to standard methods.

Supporting decision making under uncertainty: Development of a participatory integrated model for water management in the middle Guadiana river basin.

Following the Integrated Water Resources Management approach, the European Water Framework Directive demands Member States to develop water management plans at the catchment level. Those plans have to integrate the different interests and must be developed with stakeholder participation. To face these requirements, managers need tools to assess the impacts of possible management alternatives on natural and socio-economic systems. These tools should ideally be able to address the complexity and uncertainties of the water system, while serving as a platform for stakeholder participation. The objective of our research was to develop a participatory integrated assessment model, based on the combination of a crop model, an economic model and a participatory Bayesian network, with an application in the middle Guadiana sub-basin, in Spain. The methodology is intended to capture the complexity of water management problems, incorporating the relevant sectors, as well as the relevant scales involved in water management decision making. The integrated model has allowed us testing different management, market and climate change scenarios and assessing the impacts of such scenarios on the natural system (crops), on the socio-economic system (farms) and on the environment (water resources). Finally, this integrated assessment modelling process has allowed stakeholder participation, complying with the main requirements of current European water laws.

Participatory modelling to support decision making in water management under uncertainty: Two comparative case studies in the Guadiana river basin, Spain.

A participatory modelling process has been conducted in two areas of the Guadiana river (the upper and the middle sub-basins), in Spain, with the aim of providing support for decision making in the water management field. The area has a semi-arid climate where irrigated agriculture plays a key role in the economic development of the region and accounts for around 90% of water use. Following the guidelines of the European Water Framework Directive, we promote stakeholder involvement in water management with the aim to achieve an improved understanding of the water system and to encourage the exchange of knowledge and views between stakeholders in order to help building a shared vision of the system. At the same time, the resulting models, which integrate the different sectors and views, provide some insight of the impacts that different management options and possible future scenarios could have. The methodology is based on a Bayesian network combined with an economic model and, in the middle Guadiana sub-basin, with a crop model. The resulting integrated modelling framework is used to simulate possible water policy, market and climate scenarios to find out the impacts of those scenarios on farm income and on the environment. At the end of the modelling process, an evaluation questionnaire was filled by participants in both sub-basins. Results show that this type of processes are found very helpful by stakeholders to improve the system understanding, to understand each others views and to reduce conflict when it exists. In addition, they found the model an extremely useful tool to support management. The graphical interface, the quantitative output and the explicit representation of uncertainty helped stakeholders to better understand the implications of the scenario tested. Finally, the combination of different types of models was also found very useful, as it allowed exploring in detail specific aspects of the water management problems.

Clustering basado en redes bayesianas con predictoras continuas: aplicaciones en neurociencia

Desentrañar el funcionamiento del cerebro es uno de los principales desafíos a los que se enfrenta la ciencia actual. Un área de estudio que ha despertado muchas expectativas e interés es el análisis de la estructura cortical desde el punto de vista morfológico, de manera que se cree una simulación del cerebro a nivel molecular. Con ello se espera poder profundizar en el estudio de numerosas enfermedades neurológicas y patológicas. Con el desarrollo de este proyecto se persigue el estudio del soma y de las espinas desde el punto de vista de la neuromorfología teórica. Es común en el estado del arte que en el análisis de las características morfológicas de una neurona en tres dimensiones el soma sea ignorado o, en el mejor de los casos, que sea sustituido por una simple esfera. De hecho, el concepto de soma resulta abstracto porque no se dispone de una dfinición estricta y robusta que especifique exactamente donde finaliza y comienzan las dendritas. En este proyecto se alcanza por primera vez una definición matemática de soma para determinar qué es el soma. Con el fin de simular somas se ahonda en los atributos utilizados en el estado del arte. Estas propiedades, de índole genérica, no especifican una morfología única. Es por ello que se propone un método que agrupe propiedades locales y globales de la morfología. En disposición de las características se procede con la categorización del cuerpo celular en distintas clases a partir de un nuevo subtipo de red bayesiana dinámica adaptada al espacio. Con ello se discute la existencia de distintas clases de somas y se descubren las diferencias entre los somas piramidales de distintas capas del cerebro. A partir del modelo matemático se simulan por primera vez somas virtuales. Algunas morfologías de espinas han sido atribuidas a ciertos comportamientos cognitivos. Por ello resulta de interés dictaminar las clases existentes y relacionarlas con funciones de la actividad cerebral. La clasificación más extendida (Peters y Kaiserman-Abramof, 1970) presenta una definición ambigua y subjetiva dependiente de la interpretación de cada individuo y por tanto discutible. Este estudio se sustenta en un conjunto de descriptores extraídos mediante una técnica de análisis topológico local para representaciones 3D. Sobre estos datos se trata de alcanzar el conjunto de clases más adecuado en el que agrupar las espinas así como de describir cada grupo mediante reglas unívocas. A partir de los resultados, se discute la existencia de un continuo de espinas y las propiedades que caracterizan a cada subtipo de espina. ---ABSTRACT---Unravel how the brain works is one of the main challenges faced by current science. A field of study which has aroused great expectations and interest is the analysis of the cortical structure from a morphological point of view, so that a molecular level simulation of the brain is achieved. This is expected to deepen the study of many neurological and pathological diseases. This project seeks the study of the soma and spines from the theoretical neuromorphology point of view. In the state of the art it is common that when it comes to analyze the morphological characteristics of a three dimension neuron the soma is ignored or, in the best case, it is replaced by a simple sphere. In fact, the concept of soma is abstract because there is not a robust and strict definition on exactly where it ends and dendrites begin. In this project a mathematical definition is reached for the first time to determine what a soma is. With the aim to simulate somas the atributes applied in the state of the art are studied. These properties, generic in nature, do not specify a unique morphology. It is why it was proposed a method to group local and global morphology properties. In arrangement of the characteristics it was proceed with the categorization of the celular body into diferent classes by using a new subtype of dynamic Bayesian network adapted to space. From the result the existance of different classes of somas and diferences among pyramidal somas from distinct brain layers are discovered. From the mathematical model virtual somas were simulated for the first time. Some morphologies of spines have been attributed to certain cognitive behaviours. For this reason it is interesting to rule the existent classes and to relate them with their functions in the brain activity. The most extended classification (Peters y Kaiserman-Abramof, 1970) presents an ambiguous and subjective definition that relies on the interpretation of each individual and consequently it is arguable. This study was based on the set of descriptors extracted from a local topological analysis technique for 3D representations. On these data it was tried to reach the most suitable set of classes to group the spines as well as to describe each cluster by unambiguous rules. From these results, the existance of a continuum of spines and the properties that characterize each spine subtype were discussed .

Inteligencia artificial para la predicción y control del acabado superficial en procesos de fresado a alta velocidad

El objetivo principal de esta tesis doctoral es profundizar en el análisis y diseño de un sistema inteligente para la predicción y control del acabado superficial en un proceso de fresado a alta velocidad, basado fundamentalmente en clasificadores Bayesianos, con el prop´osito de desarrollar una metodolog´ıa que facilite el diseño de este tipo de sistemas. El sistema, cuyo propósito es posibilitar la predicción y control de la rugosidad superficial, se compone de un modelo aprendido a partir de datos experimentales con redes Bayesianas, que ayudar´a a comprender los procesos dinámicos involucrados en el mecanizado y las interacciones entre las variables relevantes. Dado que las redes neuronales artificiales son modelos ampliamente utilizados en procesos de corte de materiales, también se incluye un modelo para fresado usándolas, donde se introdujo la geometría y la dureza del material como variables novedosas hasta ahora no estudiadas en este contexto. Por lo tanto, una importante contribución en esta tesis son estos dos modelos para la predicción de la rugosidad superficial, que se comparan con respecto a diferentes aspectos: la influencia de las nuevas variables, los indicadores de evaluación del desempeño, interpretabilidad. Uno de los principales problemas en la modelización con clasificadores Bayesianos es la comprensión de las enormes tablas de probabilidad a posteriori producidas. Introducimos un m´etodo de explicación que genera un conjunto de reglas obtenidas de árboles de decisión. Estos árboles son inducidos a partir de un conjunto de datos simulados generados de las probabilidades a posteriori de la variable clase, calculadas con la red Bayesiana aprendida a partir de un conjunto de datos de entrenamiento. Por último, contribuimos en el campo multiobjetivo en el caso de que algunos de los objetivos no se puedan cuantificar en números reales, sino como funciones en intervalo de valores. Esto ocurre a menudo en aplicaciones de aprendizaje automático, especialmente las basadas en clasificación supervisada. En concreto, se extienden las ideas de dominancia y frontera de Pareto a esta situación. Su aplicación a los estudios de predicción de la rugosidad superficial en el caso de maximizar al mismo tiempo la sensibilidad y la especificidad del clasificador inducido de la red Bayesiana, y no solo maximizar la tasa de clasificación correcta. Los intervalos de estos dos objetivos provienen de un m´etodo de estimación honesta de ambos objetivos, como e.g. validación cruzada en k rodajas o bootstrap.---ABSTRACT---The main objective of this PhD Thesis is to go more deeply into the analysis and design of an intelligent system for surface roughness prediction and control in the end-milling machining process, based fundamentally on Bayesian network classifiers, with the aim of developing a methodology that makes easier the design of this type of systems. The system, whose purpose is to make possible the surface roughness prediction and control, consists of a model learnt from experimental data with the aid of Bayesian networks, that will help to understand the dynamic processes involved in the machining and the interactions among the relevant variables. Since artificial neural networks are models widely used in material cutting proceses, we include also an end-milling model using them, where the geometry and hardness of the piecework are introduced as novel variables not studied so far within this context. Thus, an important contribution in this thesis is these two models for surface roughness prediction, that are then compared with respecto to different aspects: influence of the new variables, performance evaluation metrics, interpretability. One of the main problems with Bayesian classifier-based modelling is the understanding of the enormous posterior probabilitiy tables produced. We introduce an explanation method that generates a set of rules obtained from decision trees. Such trees are induced from a simulated data set generated from the posterior probabilities of the class variable, calculated with the Bayesian network learned from a training data set. Finally, we contribute in the multi-objective field in the case that some of the objectives cannot be quantified as real numbers but as interval-valued functions. This often occurs in machine learning applications, especially those based on supervised classification. Specifically, the dominance and Pareto front ideas are extended to this setting. Its application to the surface roughness prediction studies the case of maximizing simultaneously the sensitivity and specificity of the induced Bayesian network classifier, rather than only maximizing the correct classification rate. Intervals in these two objectives come from a honest estimation method of both objectives, like e.g. k-fold cross-validation or bootstrap.

Foreground segmentation in depth imagery using depth and spatial dynamic models for video surveillance applications

Low-cost systems that can obtain a high-quality foreground segmentation almostindependently of the existing illumination conditions for indoor environments are verydesirable, especially for security and surveillance applications. In this paper, a novelforeground segmentation algorithm that uses only a Kinect depth sensor is proposedto satisfy the aforementioned system characteristics. This is achieved by combininga mixture of Gaussians-based background subtraction algorithm with a new Bayesiannetwork that robustly predicts the foreground/background regions between consecutivetime steps. The Bayesian network explicitly exploits the intrinsic characteristics ofthe depth data by means of two dynamic models that estimate the spatial and depthevolution of the foreground/background regions. The most remarkable contribution is thedepth-based dynamic model that predicts the changes in the foreground depth distributionbetween consecutive time steps. This is a key difference with regard to visible imagery,where the color/gray distribution of the foreground is typically assumed to be constant.Experiments carried out on two different depth-based databases demonstrate that theproposed combination of algorithms is able to obtain a more accurate segmentation of theforeground/background than other state-of-the art approaches.

Advanced background modeling with RGB-D sensors through classifiers combination and inter-frame foreground prediction

An innovative background modeling technique that is able to accurately segment foreground regions in RGB-D imagery (RGB plus depth) has been presented in this paper. The technique is based on a Bayesian framework that efficiently fuses different sources of information to segment the foreground. In particular, the final segmentation is obtained by considering a prediction of the foreground regions, carried out by a novel Bayesian Network with a depth-based dynamic model, and, by considering two independent depth and color-based mixture of Gaussians background models. The efficient Bayesian combination of all these data reduces the noise and uncertainties introduced by the color and depth features and the corresponding models. As a result, more compact segmentations, and refined foreground object silhouettes are obtained. Experimental results with different databases suggest that the proposed technique outperforms existing state-of-the-art algorithms.

Comportamiento del paciente de la clínica dental. Modelo basado en la percepción de la calidad del servicio y fidelización del paciente

Esta tesis doctoral propone un modelo de comportamiento del paciente de la clínica dental, basado en la percepción de la calidad del servicio (SERVQUAL), la fidelización del paciente, acciones de Marketing Relacional y aspectos socioeconómicos relevantes, de los pacientes de clínicas dentales. En particular, el estudio de campo se lleva a cabo en el ámbito geográfico de la Comunidad de Madrid, España, durante los años 2012 y 2013. La primera parte del proceso de elaboración del modelo está basada en la recolección de datos. Para ello, se realizaron cinco entrevistas a expertos dentistas y se aplicaron dos tipos encuestas diferentes: una para el universo formado por el conjunto de los pacientes de las clínicas dentales y la otra para el universo formado el conjunto de los dentistas de las clínicas dentales de la Comunidad de Madrid. Se obtuvo muestras de: 200 encuestas de pacientes y 220 encuestas de dentistas activos colegiados en el Ilustre Colegio Oficial de Odontólogos y Estomatólogos de la I Región Madrid. En la segunda parte de la elaboración del modelo, se realizó el análisis de los datos, la inducción y síntesis del modelo propuesto. Se utilizó la metodología de modelos gráficos probabilísticos, específicamente, una Red Bayesiana, donde se integraron variables (nodos) y sus dependencias estadísticas causales (arcos dirigidos), que representan el conocimiento obtenido de los datos recopilados en las encuestas y el conocimiento derivado de investigaciones precedentes en el área. Se obtuvo una Red Bayesiana compuesta por 6 nodos principales, de los cuales dos de ellos son nodos de observación directa: “Revisit Intention” y “SERVQUAL”, y los otros cuatro nodos restantes son submodelos (agrupaciones de variables), estos son respectivamente: “Attitudinal”, “Disease Information”, “Socioeconomical” y “Services”. Entre las conclusiones principales derivadas del uso del modelo, como herramientas de inferencia y los análisis de las entrevistas realizadas se obtiene que: (i) las variables del nodo “Attitudinal” (submodelo), son las más sensibles y significativas. Al realizarse imputaciones particulares en las variables que conforman el nodo “Attitudinal” (“RelationalMk”, “Satisfaction”, “Recommendation” y “Friendship”) se obtienen altas probabilidades a posteriori en la fidelidad del paciente de la clínica dental, medida por su intención de revisita. (ii) En el nodo “Disease Information” (submodelo) se destaca la relación de dependencia causal cuando se imputa la variable “Perception of disease” en “SERVQUAL”, demostrando que la percepción de la gravedad del paciente condiciona significativamente la percepción de la calidad del servicio del paciente. Como ejemplo destacado, si se realiza una imputación en la variable “Clinic_Type” se obtienen altas probabilidades a posteriori de las variables “SERVQUAL” y “Revisit Intention”, lo que evidencia, que el tipo de clínica dental influye significativamente en la percepción de la calidad del servicio y en la fidelidad del paciente (intención de revisita). (iii) En el nodo “Socioeconomical” (submodelo) la variable “Sex” resultó no ser significativa cuando se le imputaban diferentes valores, por el contrario, la variable “Age” e “Income” mostraban altas variabilidades en las probabilidades a posteriori cuando se imputaba alguna variable del submodelo “Services”, lo que evidencia, que estas variables condicionan la intención de contratar servicios (“Services”), sobretodo en las franjas de edad de 30 a 51 años en pacientes con ingresos entre 3000€ y 4000€. (iv) En el nodo “Services” (submodelo) los pacientes de las clínicas dentales mostraron altas probabilidades a priori para contratar servicios de fisiotrapia oral y gingival: “Dental Health Education” y “Parking”. (v) Las variables de fidelidad del paciente medidas desde su perspectiva comportamental que fueron utilizadas en el modelo: “Visit/year” “Time_clinic”, no aportaron información significativa. Tampoco, la variable de fidelidad del cliente (actitudinal): “Churn Efford”. (vi) De las entrevistas realizadas a expertos dentistas se obtiene que, los propietarios de la clínica tradicional tienen poca disposición a implementar nuevas estrategias comerciales, debido a la falta de formación en la gestión comercial y por falta de recursos y herramientas. Existe un rechazo generalizado hacia los nuevos modelos de negocios de clínicas dentales, especialmente en las franquicias y en lo que a políticas comerciales se refiere. Esto evidencia una carencia de gerencia empresarial en el sector. Como líneas futuras de investigación, se propone profundizar en algunas relaciones de dependencia (causales) como SERVQUALServices; SatisfactionServices; RelationalMKServices, Perception of diseaseSatisfaction, entre otras. Así como, otras variables de medición de la fidelidad comportamental que contribuyan a la mejora del modelo, como por ej. Gasto del paciente y rentabilidad de la visita. ABSTRACT This doctoral dissertation proposes a model of the behavior of the dental-clinic customer, based on the service-quality perception (SERVQUAL), loyalty, Relational Marketing and some relevant socio-economical characteristics, of the dental-clinic customers. In particular, the field study has been developed in the geographical region of Madrid, Spain during the years 2012 and 2013. The first stage of the preparation of the model consist in the data gathering process. For this purpose, five interviews where realized to expert dentists and also two different types of surveys: one for the universe defined by the set of dental-clinic patients and the second for the universe defined by the set of the dentists of the dental clinics of the Madrid Community. A sample of 200 surveys where collected for patients and a sample of 220 surveys where collected from active dentists belonging to the Ilustre Colegio Oficial de Odontólogos y Estomatólogos de la I Región Madrid. In the second stage of the model preparation, the processes of data-analysis, induction and synthesis of the final model where performed. The Graphic Probabilistic Models methodology was used to elaborate the final model, specifically, a Bayesian Network, where the variables (nodes) and their statistical and causal dependencies where integrated and modeled, representing thus, the obtained knowledge from the data obtained by the surveys and the scientific knowledge derived from previous research in the field. A Bayesian Net consisting on six principal nodes was obtained, of which two of them are directly observable: “Revisit Intention” y “SERVQUAL”, and the remaining four are submodels (a grouping of variables). These are: “Attitudinal”, “Disease Information”, “Socioeconomical” and “Services”. The main conclusions derived from the model, as an inference tool, and the analysis of the interviews are: (i) the variables inside the “Attitudinal” node are the most sensitive and significant. By making some particular imputations on the variables that conform the “Attitudinal” node (“RelationalMk”, “Satisfaction”, “Recommendation” y “Friendship”), high posterior probabilities (measured in revisit intention) are obtained for the loyalty of the dental-clinic patient. (ii) In the “Disease Information” node, the causal relation between the “Perception of disease” and “SERVQUAL” when “Perception of disease” is imputed is highlighted, showing that the perception of the severity of the patient’s disease conditions significantly the perception of service quality. As an example, by imputing some particular values to the “Clinic_Type” node high posterior probabilities are obtained for the “SERVQUAL” variables and for “Revisit Intention” showing that the clinic type influences significantly in the service quality perception and loyalty (revisit intention). (iii) In the “Socioeconomical” variable, the variable “Sex” showed to be non-significant, however, the “Age” variable and “Income” show high variability in its posterior probabilities when some variable from the “Services” node where imputed, showing thus, that these variables condition the intention to buy new services (“Services”), especially in the age range from 30 to 50 years in patients with incomes between 3000€ and 4000€. (iv) In the “Services” submodel the dental-clinic patients show high priors to buy services such as oral and gingival therapy, Dental Health Education and “Parking” service. (v) The obtained loyalty measures, from the behavioral perspective, “Visit/year” and “Time_clinic”, do not add significant information to the model. Neither the attitudinal loyalty component “Churn Efford”. (vi) From the interviews realized to the expert dentists it is observed that the owners of the traditional clinics have a low propensity to apply new commercial strategies due to a lack of resources and tools. In general, there exists an opposition to new business models in the sector, especially to the franchise dental model. All of this evidences a lack in business management in the sector. As future lines of research, a deep look into some statistical and causal relations is proposed, such as: SERVQUALServices; SatisfactionServices; RelationalMKServices, Perception of diseaseSatisfaction, as well as new measurement variables related to attitudinal loyalty that contribute to improve the model, for example, profit per patient and per visit.

Modelo de gestión de un embalse en tiempo real durante avenidas basado en redes bayesianas entrenadas con el método de optimización PLEM

En la actualidad, la gestión de embalses para el control de avenidas se realiza, comúnmente, utilizando modelos de simulación. Esto se debe, principalmente, a su facilidad de uso en tiempo real por parte del operador de la presa. Se han desarrollado modelos de optimización de la gestión del embalse que, aunque mejoran los resultados de los modelos de simulación, su aplicación en tiempo real se hace muy difícil o simplemente inviable, pues está limitada al conocimiento de la avenida futura que entra al embalse antes de tomar la decisión de vertido. Por esta razón, se ha planteado el objetivo de desarrollar un modelo de gestión de embalses en avenidas que incorpore las ventajas de un modelo de optimización y que sea de fácil uso en tiempo real por parte del gestor de la presa. Para ello, se construyó un modelo de red Bayesiana que representa los procesos de la cuenca vertiente y del embalse y, que aprende de casos generados sintéticamente mediante un modelo hidrológico agregado y un modelo de optimización de la gestión del embalse. En una primera etapa, se generó un gran número de episodios sintéticos de avenida utilizando el método de Monte Carlo, para obtener las lluvias, y un modelo agregado compuesto de transformación lluvia- escorrentía, para obtener los hidrogramas de avenida. Posteriormente, se utilizaron las series obtenidas como señales de entrada al modelo de gestión de embalses PLEM, que optimiza una función objetivo de costes mediante programación lineal entera mixta, generando igual número de eventos óptimos de caudal vertido y de evolución de niveles en el embalse. Los episodios simulados fueron usados para entrenar y evaluar dos modelos de red Bayesiana, uno que pronostica el caudal de entrada al embalse, y otro que predice el caudal vertido, ambos en un horizonte de tiempo que va desde una a cinco horas, en intervalos de una hora. En el caso de la red Bayesiana hidrológica, el caudal de entrada que se elige es el promedio de la distribución de probabilidad de pronóstico. En el caso de la red Bayesiana hidráulica, debido al comportamiento marcadamente no lineal de este proceso y a que la red Bayesiana devuelve un rango de posibles valores de caudal vertido, se ha desarrollado una metodología para seleccionar un único valor, que facilite el trabajo del operador de la presa. Esta metodología consiste en probar diversas estrategias propuestas, que incluyen zonificaciones y alternativas de selección de un único valor de caudal vertido en cada zonificación, a un conjunto suficiente de episodios sintéticos. Los resultados de cada estrategia se compararon con el método MEV, seleccionándose las estrategias que mejoran los resultados del MEV, en cuanto al caudal máximo vertido y el nivel máximo alcanzado por el embalse, cualquiera de las cuales puede usarse por el operador de la presa en tiempo real para el embalse de estudio (Talave). La metodología propuesta podría aplicarse a cualquier embalse aislado y, de esta manera, obtener, para ese embalse particular, diversas estrategias que mejoran los resultados del MEV. Finalmente, a modo de ejemplo, se ha aplicado la metodología a una avenida sintética, obteniendo el caudal vertido y el nivel del embalse en cada intervalo de tiempo, y se ha aplicado el modelo MIGEL para obtener en cada instante la configuración de apertura de los órganos de desagüe que evacuarán el caudal. Currently, the dam operator for the management of dams uses simulation models during flood events, mainly due to its ease of use in real time. Some models have been developed to optimize the management of the reservoir to improve the results of simulation models. However, real-time application becomes very difficult or simply unworkable, because the decision to discharge depends on the unknown future avenue entering the reservoir. For this reason, the main goal is to develop a model of reservoir management at avenues that incorporates the advantages of an optimization model. At the same time, it should be easy to use in real-time by the dam manager. For this purpose, a Bayesian network model has been developed to represent the processes of the watershed and reservoir. This model learns from cases generated synthetically by a hydrological model and an optimization model for managing the reservoir. In a first stage, a large number of synthetic flood events was generated using the Monte Carlo method, for rain, and rain-added processing model composed of runoff for the flood hydrographs. Subsequently, the series obtained were used as input signals to the reservoir management model PLEM that optimizes a target cost function using mixed integer linear programming. As a result, many optimal discharge rate events and water levels in the reservoir levels were generated. The simulated events were used to train and test two models of Bayesian network. The first one predicts the flow into the reservoir, and the second predicts the discharge flow. They work in a time horizon ranging from one to five hours, in intervals of an hour. In the case of hydrological Bayesian network, the chosen inflow is the average of the probability distribution forecast. In the case of hydraulic Bayesian network the highly non-linear behavior of this process results on a range of possible values of discharge flow. A methodology to select a single value has been developed to facilitate the dam operator work. This methodology tests various strategies proposed. They include zoning and alternative selection of a single value in each discharge rate zoning from a sufficient set of synthetic episodes. The results of each strategy are compared with the MEV method. The strategies that improve the outcomes of MEV are selected and can be used by the dam operator in real time applied to the reservoir study case (Talave). The methodology could be applied to any single reservoir and, thus, obtain, for the particular reservoir, various strategies that improve results from MEV. Finally, the methodology has been applied to a synthetic flood, obtaining the discharge flow and the reservoir level in each time interval. The open configuration floodgates to evacuate the flow at each interval have been obtained applying the MIGEL model.

Fusión de redes Bayesianas Gaussianas

Las redes Bayesianas constituyen un modelo ampliamente utilizado para la representación de relaciones de dependencia condicional en datos multivariantes. Su aprendizaje a partir de un conjunto de datos o expertos ha sido estudiado profundamente desde su concepción. Sin embargo, en determinados escenarios se demanda la obtención de un modelo común asociado a particiones de datos o conjuntos de expertos. En este caso, se trata el problema de fusión o agregación de modelos. Los trabajos y resultados en agregación de redes Bayesianas son de naturaleza variada, aunque escasos en comparación con aquellos de aprendizaje. En este documento, se proponen dos métodos para la agregación de redes Gaussianas, definidas como aquellas redes Bayesianas que modelan una distribución Gaussiana multivariante. Los métodos presentados son efectivos, precisos y producen redes con menor cantidad de parámetros en comparación con los modelos obtenidos individualmente. Además, constituyen un enfoque novedoso al incorporar nociones exploradas tradicionalmente por separado en el estado del arte. Futuras aplicaciones en entornos escalables hacen dichos métodos especialmente atractivos, dada su simplicidad y la ganancia en compacidad de la representación obtenida.---ABSTRACT---Bayesian networks are a widely used model for the representation of conditional dependence relationships among variables in multivariate data. The task of learning them from a data set or experts has been deeply studied since their conception. However, situations emerge where there is a need of obtaining a consensuated model from several data partitions or a set of experts. This situation is referred to as model fusion or aggregation. Results about Bayesian network aggregation, although rich in variety, have been scarce when compared to the learning task. In this context, two methods are proposed for the aggregation of Gaussian Bayesian networks, that is, Bayesian networks whose underlying modelled distribution is a multivariate Gaussian. Both methods are effective, precise and produce networks with fewer parameters in comparison with the models obtained by individual learning. They constitute a novel approach given that they incorporate notions traditionally explored separately in the state of the art. Future applications in scalable computer environments make such models specially attractive, given their simplicity and the gaining in sparsity of the produced model.