Fusion of probabilistic knowledge-based classification rules and learning automata for automatic recognition of digital images

In this paper, the fusion of probabilistic knowledge-based classification rules and learning automata theory is proposed and as a result we present a set of probabilistic classification rules with self-learning capability. The probabilities of the classification rules change dynamically guided by a supervised reinforcement process aimed at obtaining an optimum classification accuracy. This novel classifier is applied to the automatic recognition of digital images corresponding to visual landmarks for the autonomous navigation of an unmanned aerial vehicle (UAV) developed by the authors. The classification accuracy of the proposed classifier and its comparison with well-established pattern recognition methods is finally reported.

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 morfolog��a neuronal es una caracter��stica clave en el estudio de los circuitos cerebrales, ya que est�� altamente relacionada con el procesado de informaci��n y con los roles funcionales. La morfolog��a neuronal afecta al proceso de integraci��n de las se��ales 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 localizaci��n espacial de las conexiones sin��pticas. Por tanto, existe un inter��s considerable en el an��lisis de la microanatom��a de las c��lulas nerviosas, ya que constituye una excelente herramienta para comprender mejor el funcionamiento de la corteza cerebral. Sin embargo, las propiedades morfol��gicas, moleculares y electrofisiol��gicas de las c��lulas neuronales son extremadamente variables. Excepto en algunos casos especiales, esta variabilidad morfol��gica dificulta la definici��n de un conjunto de caracter��sticas que distingan claramente un tipo neuronal. Adem��s, existen diferentes tipos de neuronas en regiones particulares del cerebro. La variabilidad neuronal hace que el an��lisis y el modelado de la morfolog��a neuronal sean un importante reto cient��fico. La incertidumbre es una propiedad clave en muchos problemas reales. La teor��a de la probabilidad proporciona un marco para modelar y razonar bajo incertidumbre. Los modelos gr��ficos probabil��sticos combinan la teor��a estad��stica y la teor��a 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 m��s utilizado dentro de los modelos gr��ficos probabil��sticos. En esta tesis hemos dise��ado nuevos m��todos para aprender redes bayesianas, inspirados por y aplicados al problema del modelado y an��lisis de datos morfol��gicos de neuronas. La morfolog��a de una neurona puede ser cuantificada usando una serie de medidas, por ejemplo, la longitud de las dendritas y el ax��n, el n��mero de bifurcaciones, la direcci��n de las dendritas y el ax��n, 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 direcci��n del ax��n). Estos datos pueden llegar a seguir distribuciones de probabilidad muy complejas y pueden no ajustarse a ninguna distribuci��n param��trica conocida. El modelado de este tipo de problemas con redes bayesianas h��bridas incluyendo variables discretas, lineales y direccionales presenta una serie de retos en relaci��n al aprendizaje a partir de datos, la inferencia, etc. En esta tesis se propone un m��todo para modelar y simular ��rboles dendr��ticos 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 par��metros de las distribuciones de probabilidad que constituyen las redes bayesianas. Despu��s, se usa un algoritmo de simulaci��n para construir dendritas virtuales mediante el muestreo de valores de las redes bayesianas. Finalmente, se lleva a cabo una profunda evaluaci ��n para verificar la capacidad del modelo a la hora de generar dendritas realistas. En esta primera aproximaci��n, las variables fueron discretizadas para poder aprender y muestrear las redes bayesianas. A continuaci��n, se aborda el problema del aprendizaje de redes bayesianas con diferentes tipos de variables. Las mixturas de polinomios constituyen un m��todo para representar densidades de probabilidad en redes bayesianas h��bridas. Presentamos un m��todo para aprender aproximaciones de densidades unidimensionales, multidimensionales y condicionales a partir de datos utilizando mixturas de polinomios. El m��todo se basa en interpolaci��n con splines, que aproxima una densidad como una combinaci��n lineal de splines. Los algoritmos propuestos se eval��an utilizando bases de datos artificiales. Adem��s, las mixturas de polinomios son utilizadas como un m��todo no param��trico de estimaci��n de densidades para clasificadores basados en redes bayesianas. Despu��s, se estudia el problema de incluir informaci��n direccional en redes bayesianas. Este tipo de datos presenta una serie de caracter��sticas especiales que impiden el uso de las t��cnicas estad��sticas cl��sicas. Por ello, para manejar este tipo de informaci��n se deben usar estad��sticos y distribuciones de probabilidad espec��ficos, como la distribuci��n univariante von Mises y la distribuci��n 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 s��lo se utilizan variables direccionales, y el caso h��brido, en el que variables discretas, lineales y direccionales aparecen mezcladas. Tambi��n se estudian los clasificadores desde un punto de vista te��rico, derivando sus funciones de decisi��n y las superficies de decisi��n asociadas. El comportamiento de los clasificadores se ilustra utilizando bases de datos artificiales. Adem��s, los clasificadores son evaluados emp��ricamente utilizando bases de datos reales. Tambi��n se estudia el problema de la clasificaci��n de interneuronas. Desarrollamos una aplicaci��n web que permite a un grupo de expertos clasificar un conjunto de neuronas de acuerdo a sus caracter��sticas morfol��gicas m��s 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 t��rminos anat��micos y de los tipos neuronales utilizados frecuentemente en la literatura a trav��s del an��lisis de redes bayesianas y la aplicaci��n de algoritmos de clustering. Adem��s, se aplican t��cnicas de aprendizaje supervisado con el objetivo de clasificar de forma autom��tica las interneuronas a partir de sus valores morfol��gicos. A continuaci��n, se presenta una metodolog��a 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. Despu��s, se induce una red bayesiana que modela la opini��n de cada grupo de expertos. Por ��ltimo, se construye una multired bayesiana que modela las opiniones del conjunto completo de expertos. El an��lisis del modelo consensuado permite identificar diferentes comportamientos entre los expertos a la hora de clasificar las neuronas. Adem��s, permite extraer un conjunto de caracter��sticas morfol��gicas relevantes para cada uno de los tipos neuronales mediante inferencia con la multired bayesiana. Estos descubrimientos se utilizan para validar el modelo y constituyen informaci��n relevante acerca de la morfolog��a neuronal. Por ��ltimo, se estudia un problema de clasificaci��n 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 est�� inspirado en el problema de la clasificaci��n de neuronas, en el que un grupo de expertos proporciona una etiqueta de clase para cada instancia de manera individual. Se propone un m��todo para aprender redes bayesianas utilizando vectores de cuentas, que representan el n��mero de expertos que seleccionan cada etiqueta de clase para cada instancia. Estas redes bayesianas se eval��an utilizando bases de datos artificiales de problemas de aprendizaje supervisado.

Contribution to proactivity in mobile context-aware recommender systems

Los sistemas de recomendaci��n son potentes herramientas de filtrado de informaci��n que permiten a usuarios solicitar sugerencias sobre ��tems que cubran sus necesidades. Tradicionalmente estas recomendaciones han estado basadas en opiniones de los mismos, as�� como en datos obtenidos de su consumo hist��rico o comportamiento en el propio sistema. Sin embargo, debido a la gran penetraci��n y uso de los dispositivos m��viles en nuestra sociedad, han surgido nuevas oportunidades en el campo de los sistemas de recomendaci��n m��viles gracias a la informaci��n contextual que se puede obtener sobre la localizaci��n o actividad de los usuarios. Debido a este estilo de vida en el que todo tiende a la movilidad y donde los usuarios est��n plenamente interconectados, la informaci��n contextual no s��lo es f��sica, sino que tambi��n adquiere una dimensi��n social. Todo esto ha dado lugar a una nueva ��rea de investigaci��n relacionada con los Sistemas de Recomendaci��n Basados en Contexto (CARS) m��viles donde se busca incrementar el nivel de personalizaci��n de las recomendaciones al usar dicha informaci��n. Por otro lado, este nuevo escenario en el que los usuarios llevan en todo momento un terminal m��vil consigo abre la puerta a nuevas formas de recomendar. Sustituir el tradicional patr��n de uso basado en petici��n-respuesta para evolucionar hacia un sistema proactivo es ahora posible. Estos sistemas deben identificar el momento m��s adecuado para generar una recomendaci��n sin una petici��n expl��cita del usuario, siendo para ello necesario analizar su contexto. Esta tesis doctoral propone un conjunto de modelos, algoritmos y m��todos orientados a incorporar proactividad en CARS m��viles, a la vez que se estudia el impacto que este tipo de recomendaciones tienen en la experiencia de usuario con el fin de extraer importantes conclusiones sobre "qu��", "cu��ndo" y "c��mo" se debe notificar proactivamente. Con este prop��sito, se comienza planteando una arquitectura general para construir CARS m��viles en escenarios sociales. Adicionalmente, se propone una nueva forma de representar el proceso de recomendaci��n a trav��s de una interfaz REST, lo que permite crear una arquitectura independiente de dispositivo y plataforma. Los detalles de su implementaci��n tras su puesta en marcha en el entorno bancario espa��ol permiten asimismo validar el sistema construido. Tras esto se presenta un novedoso modelo para incorporar proactividad en CARS m��viles. ��ste muestra las ideas principales que permiten analizar una situaci��n para decidir cu��ndo es apropiada una recomendaci��n proactiva. Para ello se presentan algoritmos que establecen relaciones entre lo propicia que es una situaci��n y c��mo esto influye en los elementos a recomendar. Asimismo, para demostrar la viabilidad de este modelo se describe su aplicaci��n a un escenario de recomendaci��n para herramientas de creaci��n de contenidos educativos. Siguiendo el modelo anterior, se presenta el dise��o e implementaci��n de nuevos interfaces m��viles de usuario para recomendaciones proactivas, as�� como los resultados de su evaluaci��n entre usuarios, lo que aport�� importantes conclusiones para identificar cu��les son los factores m��s relevantes a considerar en el dise��o de sistemas proactivos. A ra��z de los resultados anteriores, el ��ltimo punto de esta tesis presenta una metodolog��a para calcular cu��n apropiada es una situaci��n de cara a recomendar de manera proactiva siguiendo el modelo propuesto. Como conclusi��n, se describe la validaci��n llevada a cabo tras la aplicaci��n de la arquitectura, modelo de recomendaci��n y m��todos descritos en este trabajo en una red social de aprendizaje europea. Finalmente, esta tesis discute las conclusiones obtenidas a lo largo de la extensa investigaci��n llevada a cabo, y que ha propiciado la consecuci��n de una buena base te��rica y pr��ctica para la creaci��n de sistemas de recomendaci��n m��viles proactivos basados en informaci��n contextual. ABSTRACT Recommender systems are powerful information filtering tools which offer users personalized suggestions about items whose aim is to satisfy their needs. Traditionally the information used to make recommendations has been based on users��� ratings or data on the item���s consumption history and transactions carried out in the system. However, due to the remarkable growth in mobile devices in our society, new opportunities have arisen to improve these systems by implementing them in ubiquitous environments which provide rich context-awareness information on their location or current activity. Because of this current all-mobile lifestyle, users are socially connected permanently, which allows their context to be enhanced not only with physical information, but also with a social dimension. As a result of these novel contextual data sources, the advent of mobile Context-Aware Recommender Systems (CARS) as a research area has appeared to improve the level of personalization in recommendation. On the other hand, this new scenario in which users have their mobile devices with them all the time offers the possibility of looking into new ways of making recommendations. Evolving the traditional user request-response pattern to a proactive approach is now possible as a result of this rich contextual scenario. Thus, the key idea is that recommendations are made to the user when the current situation is appropriate, attending to the available contextual information without an explicit user request being necessary. This dissertation proposes a set of models, algorithms and methods to incorporate proactivity into mobile CARS, while the impact of proactivity is studied in terms of user experience to extract significant outcomes as to "what", "when" and "how" proactive recommendations have to be notified to users. To this end, the development of this dissertation starts from the proposal of a general architecture for building mobile CARS in scenarios with rich social data along with a new way of managing a recommendation process through a REST interface to make this architecture multi-device and cross-platform compatible. Details as regards its implementation and evaluation in a Spanish banking scenario are provided to validate its usefulness and user acceptance. After that, a novel model is presented for proactivity in mobile CARS which shows the key ideas related to decide when a situation warrants a proactive recommendation by establishing algorithms that represent the relationship between the appropriateness of a situation and the suitability of the candidate items to be recommended. A validation of these ideas in the area of e-learning authoring tools is also presented. Following the previous model, this dissertation presents the design and implementation of new mobile user interfaces for proactive notifications. The results of an evaluation among users testing these novel interfaces is also shown to study the impact of proactivity in the user experience of mobile CARS, while significant factors associated to proactivity are also identified. The last stage of this dissertation merges the previous outcomes to design a new methodology to calculate the appropriateness of a situation so as to incorporate proactivity into mobile CARS. Additionally, this work provides details about its validation in a European e-learning social network in which the whole architecture and proactive recommendation model together with its methods have been implemented. Finally, this dissertation opens up a discussion about the conclusions obtained throughout this research, resulting in useful information from the different design and implementation stages of proactive mobile CARS.

Incorporating proactivity to context-aware recommender systems for e-learning

Recommender systems in e-learning have proved to be powerful tools to find suitable educational material during the learning experience. But traditional user request-response patterns are still being used to generate these recommendations. By including contextual information derived from the use of ubiquitous learning environments, the possibility of incorporating proactivity to the recommendation process has arisen. In this paper we describe methods to push proactive recommendations to e-learning systems users when the situation is appropriate without being needed their explicit request. As a result, interesting learning objects can be recommended attending to the user?s needs in every situation. The impact of this proactive recommendations generated have been evaluated among teachers and scientists in a real e-learning social network called Virtual Science Hub related to the GLOBAL excursion European project. Outcomes indicate that the methods proposed are valid to generate such kind of recommendations in e-learning scenarios. The results also show that the users' perceived appropriateness of having proactive recommendations is high.

An ICT based Project Management Learning Framework

The objective of this paper is to present a framework that can facilitate the university level learning process in the Project Management of different students who are enrolled in different universities in different locations and attending their own Project Management courses, but running a virtual experience in executing and managing projects. The framework includes both information systems and methodological procedures that are integrated in the information system, making it possible to assess learning performance.

Linear Bayes policy for learning in contextual-bandits

Machine and Statistical Learning techniques are used in almost all online advertisement systems. The problem of discovering which content is more demanded (e.g. receive more clicks) can be modeled as a multi-armed bandit problem. Contextual bandits (i.e., bandits with covariates, side information or associative reinforcement learning) associate, to each specific content, several features that define the ���context��� in which it appears (e.g. user, web page, time, region). This problem can be studied in the stochastic/statistical setting by means of the conditional probability paradigm using the Bayes��� theorem. However, for very large contextual information and/or real-time constraints, the exact calculation of the Bayes��� rule is computationally infeasible. In this article, we present a method that is able to handle large contextual information for learning in contextual-bandits problems. This method was tested in the Challenge on Yahoo! dataset at ICML2012���s Workshop ���new Challenges for Exploration & Exploitation 3���, obtaining the second place. Its basic exploration policy is deterministic in the sense that for the same input data (as a time-series) the same results are obtained. We address the deterministic exploration vs. exploitation issue, explaining the way in which the proposed method deterministically finds an effective dynamic trade-off based solely in the input-data, in contrast to other methods that use a random number generator.

University Networking in Developing Countries based on C4D-Learning

In recent years, the establishment of cooperation networks between universities is one of the most important trends in higher education all over the world. Well recognized local and international university networks have been implemented in most educational institutions. It is common to find associations of various prestigious universities collaborating in a high-�����technology research project including a very specialized teaching as well. This is the most common cooperation networks among higher education institutions in developed countries. An increasingly common type of networking between developed and developing universities is related to cooperation for development. This is the case of many universities in Africa that are needed for external help in order to improve its capabilities. Numerous memorandums of understanding regarding first world institutions that collaborate with universities in developing countries describe contributions of eventual visiting professors, teaching material and courses. But probably there exist another type of more important, but less explored association, such as networking among developing universities. The new goal, in this case, is not only the excellence but also the mutual development.

Supporting the design and development of Project Based Learning courses.

The use of Project Based Learning has spread widely over the last decades, not only throughout countries but also among disciplines. One of the most significant characteristics of this methodology is the use of ill-structured problems as central activity during the course, which represents an important difficulty for both teachers and students. This work presents a model, supported by a tool, focused on helping teachers and students in Project Based Learning, overcoming these difficulties. Firstly, teachers are guided in designing the project following the main principles of this methodology. Once the project has been specified at the desired level of depth, the same tool helps students to finish the project specification and organize the implementation. Collaborative work among different users is allowed in both phases. This tool has been satisfactorily tested designing two real projects used in Computer Engineering and Software Engineering degrees.

Fast 2D to 3D conversion using a clustering-based hierarchical search in a machine learning framework

Automatic 2D-to-3D conversion is an important application for filling the gap between the increasing number of 3D displays and the still scant 3D content. However, existing approaches have an excessive computational cost that complicates its practical application. In this paper, a fast automatic 2D-to-3D conversion technique is proposed, which uses a machine learning framework to infer the 3D structure of a query color image from a training database with color and depth images. Assuming that photometrically similar images have analogous 3D structures, a depth map is estimated by searching the most similar color images in the database, and fusing the corresponding depth maps. Large databases are desirable to achieve better results, but the computational cost also increases. A clustering-based hierarchical search using compact SURF descriptors to characterize images is proposed to drastically reduce search times. A significant computational time improvement has been obtained regarding other state-of-the-art approaches, maintaining the quality results.

An interactive web-based learning assistant for structural analysis of continuous beams

There are significant levels of concern about the relevance and the difficulty of learning some issues on Strength of Materials and Structural Analysis. Most students of Continuum Mechanics and Structural Analysis in Civil Engineering usually point out some key learning aspects as especially difficult for acquiring specific skills. These key concepts entail comprehension difficulties but ease access and applicability to structural analysis in more advanced subjects. Likewise, some elusive but basic structural concepts, such as flexibility, stiffness or influence lines, are paramount for developing further skills required for advanced structural design: tall buildings, arch-type structures as well as bridges. As new curricular itineraries are currently being implemented, it appears appropriate to devise a repository of interactive web-based applications for training in those basic concepts. That will hopefully train the student to understand the complexity of such concepts, to develop intuitive knowledge on actual structural response and to improve their preparation for exams. In this work, a web-based learning assistant system for influence lines on continuous beams is presented. It consists of a collection of interactive user-friendly applications accessible via Web. It is performed in both Spanish and English languages. Rather than a ���black box��� system, the procedure involves open interaction with the student, who can simulate and virtually envisage the structural response. Thus, the student is enabled to set the geometric, topologic and mechanic layout of a continuous beam and to change or shift the loading and the support conditions. Simultaneously, the changes in the beam response prompt on the screen, so that the effects of the several issues involved in structural analysis become apparent. The system is performed through a set of web pages which encompasses interactive exercises and problems, written in JavaScript under JQuery and DyGraphs frameworks, given that their efficiency and graphic capabilities are renowned. Students can freely boost their self-study on this subject in order to face their exams more confidently. Besides, this collection is expected to be added to the "Virtual Lab of Continuum Mechanics" of the UPM, launched in 2013 (http://serviciosgate.upm.es/laboratoriosvirtuales/laboratorios/medios-continuos-en-construcci%C3%B3n)

Enhancing web-based learning resources with quizzes through an Authoring Tool and an Audience Response System

Quizzes are among the most widely used resources in web-based education due to their many benefits. However, educators need suitable authoring tools that can be used to create reusable quizzes and to enhance existing materials with them. On the other hand, if teachers use Audience Response Systems (ARSs) they can get instant feedback from their students and thereby enhance their instruction. This paper presents an online authoring tool for creating reusable quizzes and enhancing existing learning resources with them, and a web-based ARS that enables teachers to launch the created quizzes and get instant feedback from the class. Both the authoring tool and the ARS were evaluated. The evaluation of the authoring tool showed that educators can effectively enhance existing learning resources in an easy way by creating and adding quizzes using that tool. Besides, the different factors that assure the reusability of the created quizzes are also exposed. Finally, the evaluation of the developed ARS showed an excellent acceptance of the system by teachers and students, and also it indicated that teachers found the system easy to set up and use in their classrooms.

Towards a Learning Object pedagogical quality metric based on the LORI evaluation model

Evaluating and measuring the pedagogical quality of Learning Objects is essential for achieving a successful web-based education. On one hand, teachers need some assurance of quality of the teaching resources before making them part of the curriculum. On the other hand, Learning Object Repositories need to include quality information into the ranking metrics used by the search engines in order to save users time when searching. For these reasons, several models such as LORI (Learning Object Review Instrument) have been proposed to evaluate Learning Object quality from a pedagogical perspective. However, no much effort has been put in defining and evaluating quality metrics based on those models. This paper proposes and evaluates a set of pedagogical quality metrics based on LORI. The work exposed in this paper shows that these metrics can be effectively and reliably used to provide quality-based sorting of search results. Besides, it strongly evidences that the evaluation of Learning Objects from a pedagogical perspective can notably enhance Learning Object search if suitable evaluations models and quality metrics are used. An evaluation of the LORI model is also described. Finally, all the presented metrics are compared and a discussion on their weaknesses and strengths is provided.

Cooperative Learning Model based on Multi-Agent Architecture for Embedded Intelligent Systems

Cooperative systems are suitable for many types of applications and nowadays these system are vastly used to improve a previously defined system or to coordinate multiple devices working together. This paper provides an alternative to improve the reliability of a previous intelligent identification system. The proposed approach implements a cooperative model based on multi-agent architecture. This new system is composed of several radar-based systems which identify a detected object and transmit its own partial result by implementing several agents and by using a wireless network to transfer data. The proposed topology is a centralized architecture where the coordinator device is in charge of providing the final identification result depending on the group behavior. In order to find the final outcome, three different mechanisms are introduced. The simplest one is based on majority voting whereas the others use two different weighting voting procedures, both providing the system with learning capabilities. Using an appropriate network configuration, the success rate can be improved from the initial 80% up to more than 90%.

A Semantic Approach to Problem-Based Learning with Conceptual Models

El aprendizaje basado en problemas se lleva aplicando con ��xito durante las ��ltimas tres d��cadas en un amplio rango de entornos de aprendizaje. Este enfoque educacional consiste en proponer problemas a los estudiantes de forma que puedan aprender sobre un dominio particular mediante el desarrollo de soluciones a dichos problemas. Si esto se aplica al modelado de conocimiento, y en particular al basado en Razonamiento Cualitativo, las soluciones a los problemas pasan a ser modelos que representan el compotamiento del sistema din��mico propuesto. Por lo tanto, la tarea del estudiante en este caso es acercar su modelo inicial (su primer intento de representar el sistema) a los modelos objetivo que proporcionan soluciones al problema, a la vez que adquieren conocimiento sobre el dominio durante el proceso. En esta tesis proponemos KaiSem, un m��todo que usa tecnolog��as y recursos sem��nticos para guiar a los estudiantes durante el proceso de modelado, ayud��ndoles a adquirir tanto conocimiento como sea posible sin la directa supervisi��n de un profesor. Dado que tanto estudiantes como profesores crean sus modelos de forma independiente, estos tendr��n diferentes terminolog��as y estructuras, dando lugar a un conjunto de modelos altamente heterog��neo. Para lidiar con tal heterogeneidad, proporcionamos una t��cnica de anclaje sem��ntico para determinar, de forma autom��tica, enlaces entre la terminolog��a libre usada por los estudiantes y algunos vocabularios disponibles en la Web de Datos, facilitando con ello la interoperabilidad y posterior alineaci��n de modelos. Por ��ltimo, proporcionamos una t��cnica de feedback sem��ntico para comparar los modelos ya alineados y generar feedback basado en las posibles discrepancias entre ellos. Este feedback es comunicado en forma de sugerencias individualizadas que el estudiante puede utilizar para acercar su modelo a los modelos objetivos en cuanto a su terminolog��a y estructura se refiere. ABSTRACT Problem-based learning has been successfully applied over the last three decades to a diverse range of learning environments. This educational approach consists of posing problems to learners, so they can learn about a particular domain by developing solutions to them. When applied to conceptual modeling, and particularly to Qualitative Reasoning, the solutions to problems are models that represent the behavior of a dynamic system. Therefore, the learner's task is to move from their initial model, as their first attempt to represent the system, to the target models that provide solutions to that problem while acquiring domain knowledge in the process. In this thesis we propose KaiSem, a method for using semantic technologies and resources to scaffold the modeling process, helping the learners to acquire as much domain knowledge as possible without direct supervision from the teacher. Since learners and experts create their models independently, these will have different terminologies and structure, giving rise to a pool of models highly heterogeneous. To deal with such heterogeneity, we provide a semantic grounding technique to automatically determine links between the unrestricted terminology used by learners and some online vocabularies of the Web of Data, thus facilitating the interoperability and later alignment of the models. Lastly, we provide a semantic-based feedback technique to compare the aligned models and generate feedback based on the possible discrepancies. This feedback is communicated in the form of individualized suggestions, which can be used by the learner to bring their model closer in terminology and structure to the target models.

Online Learning-based Robust Visual Tracking for Autonomous Landing of Unmanned Aerial Vehicles

Autonomous landing is a challenging and important technology for both military and civilian applications of Unmanned Aerial Vehicles (UAVs). In this paper, we present a novel online adaptive visual tracking algorithm for UAVs to land on an arbitrary field (that can be used as the helipad) autonomously at real-time frame rates of more than twenty frames per second. The integration of low-dimensional subspace representation method, online incremental learning approach and hierarchical tracking strategy allows the autolanding task to overcome the problems generated by the challenging situations such as significant appearance change, variant surrounding illumination, partial helipad occlusion, rapid pose variation, onboard mechanical vibration (no video stabilization), low computational capacity and delayed information communication between UAV and Ground Control Station (GCS). The tracking performance of this presented algorithm is evaluated with aerial images from real autolanding flights using manually- labelled ground truth database. The evaluation results show that this new algorithm is highly robust to track the helipad and accurate enough for closing the vision-based control loop.