Inference of gene regulatory networks from time series by Tsallis entropy

Background: The inference of gene regulatory networks (GRNs) from large-scale expression profiles is one of the most challenging problems of Systems Biology nowadays. Many techniques and models have been proposed for this task. However, it is not generally possible to recover the original topology with great accuracy, mainly due to the short time series data in face of the high complexity of the networks and the intrinsic noise of the expression measurements. In order to improve the accuracy of GRNs inference methods based on entropy (mutual information), a new criterion function is here proposed. Results: In this paper we introduce the use of generalized entropy proposed by Tsallis, for the inference of GRNs from time series expression profiles. The inference process is based on a feature selection approach and the conditional entropy is applied as criterion function. In order to assess the proposed methodology, the algorithm is applied to recover the network topology from temporal expressions generated by an artificial gene network (AGN) model as well as from the DREAM challenge. The adopted AGN is based on theoretical models of complex networks and its gene transference function is obtained from random drawing on the set of possible Boolean functions, thus creating its dynamics. On the other hand, DREAM time series data presents variation of network size and its topologies are based on real networks. The dynamics are generated by continuous differential equations with noise and perturbation. By adopting both data sources, it is possible to estimate the average quality of the inference with respect to different network topologies, transfer functions and network sizes. Conclusions: A remarkable improvement of accuracy was observed in the experimental results by reducing the number of false connections in the inferred topology by the non-Shannon entropy. The obtained best free parameter of the Tsallis entropy was on average in the range 2.5 <= q <= 3.5 (hence, subextensive entropy), which opens new perspectives for GRNs inference methods based on information theory and for investigation of the nonextensivity of such networks. The inference algorithm and criterion function proposed here were implemented and included in the DimReduction software, which is freely available at http://sourceforge.net/projects/dimreduction and http://code.google.com/p/dimreduction/.

Assessing the gain of biological data integration in gene networks inference

Background: A current challenge in gene annotation is to define the gene function in the context of the network of relationships instead of using single genes. The inference of gene networks (GNs) has emerged as an approach to better understand the biology of the system and to study how several components of this network interact with each other and keep their functions stable. However, in general there is no sufficient data to accurately recover the GNs from their expression levels leading to the curse of dimensionality, in which the number of variables is higher than samples. One way to mitigate this problem is to integrate biological data instead of using only the expression profiles in the inference process. Nowadays, the use of several biological information in inference methods had a significant increase in order to better recover the connections between genes and reduce the false positives. What makes this strategy so interesting is the possibility of confirming the known connections through the included biological data, and the possibility of discovering new relationships between genes when observed the expression data. Although several works in data integration have increased the performance of the network inference methods, the real contribution of adding each type of biological information in the obtained improvement is not clear. Methods: We propose a methodology to include biological information into an inference algorithm in order to assess its prediction gain by using biological information and expression profile together. We also evaluated and compared the gain of adding four types of biological information: (a) protein-protein interaction, (b) Rosetta stone fusion proteins, (c) KEGG and (d) KEGG+GO. Results and conclusions: This work presents a first comparison of the gain in the use of prior biological information in the inference of GNs by considering the eukaryote (P. falciparum) organism. Our results indicates that information based on direct interaction can produce a higher improvement in the gain than data about a less specific relationship as GO or KEGG. Also, as expected, the results show that the use of biological information is a very important approach for the improvement of the inference. We also compared the gain in the inference of the global network and only the hubs. The results indicates that the use of biological information can improve the identification of the most connected proteins.

A phylogenomics approach to resolving fungal evolution, and phylogenetic method development

Bien que les champignons soient régulièrement utilisés comme modèle d'étude des systèmes eucaryotes, leurs relations phylogénétiques soulèvent encore des questions controversées. Parmi celles-ci, la classification des zygomycètes reste inconsistante. Ils sont potentiellement paraphylétiques, i.e. regroupent de lignées fongiques non directement affiliées. La position phylogénétique du genre Schizosaccharomyces est aussi controversée: appartient-il aux Taphrinomycotina (précédemment connus comme archiascomycetes) comme prédit par l'analyse de gènes nucléaires, ou est-il plutôt relié aux Saccharomycotina (levures bourgeonnantes) tel que le suggère la phylogénie mitochondriale? Une autre question concerne la position phylogénétique des nucléariides, un groupe d'eucaryotes amiboïdes que l'on suppose étroitement relié aux champignons. Des analyses multi-gènes réalisées antérieurement n'ont pu conclure, étant donné le choix d'un nombre réduit de taxons et l'utilisation de six gènes nucléaires seulement. Nous avons abordé ces questions par le biais d'inférences phylogénétiques et tests statistiques appliqués à des assemblages de données phylogénomiques nucléaires et mitochondriales. D'après nos résultats, les zygomycètes sont paraphylétiques (Chapitre 2) bien que le signal phylogénétique issu du jeu de données mitochondriales disponibles est insuffisant pour résoudre l'ordre de cet embranchement avec une confiance statistique significative. Dans le Chapitre 3, nous montrons à l'aide d'un jeu de données nucléaires important (plus de cent protéines) et avec supports statistiques concluants, que le genre Schizosaccharomyces appartient aux Taphrinomycotina. De plus, nous démontrons que le regroupement conflictuel des Schizosaccharomyces avec les Saccharomycotina, venant des données mitochondriales, est le résultat d'un type d'erreur phylogénétique connu: l'attraction des longues branches (ALB), un artéfact menant au regroupement d'espèces dont le taux d'évolution rapide n'est pas représentatif de leur véritable position dans l'arbre phylogénétique. Dans le Chapitre 4, en utilisant encore un important jeu de données nucléaires, nous démontrons avec support statistique significatif que les nucleariides constituent le groupe lié de plus près aux champignons. Nous confirmons aussi la paraphylie des zygomycètes traditionnels tel que suggéré précédemment, avec support statistique significatif, bien que ne pouvant placer tous les membres du groupe avec confiance. Nos résultats remettent en cause des aspects d'une récente reclassification taxonomique des zygomycètes et de leurs voisins, les chytridiomycètes. Contrer ou minimiser les artéfacts phylogénétiques telle l'attraction des longues branches (ALB) constitue une question récurrente majeure. Dans ce sens, nous avons développé une nouvelle méthode (Chapitre 5) qui identifie et élimine dans une séquence les sites présentant une grande variation du taux d'évolution (sites fortement hétérotaches - sites HH); ces sites sont connus comme contribuant significativement au phénomène d'ALB. Notre méthode est basée sur un test de rapport de vraisemblance (likelihood ratio test, LRT). Deux jeux de données publiés précédemment sont utilisés pour démontrer que le retrait graduel des sites HH chez les espèces à évolution accélérée (sensibles à l'ALB) augmente significativement le support pour la topologie « vraie » attendue, et ce, de façon plus efficace comparée à d'autres méthodes publiées de retrait de sites de séquences. Néanmoins, et de façon générale, la manipulation de données préalable à l'analyse est loin d’être idéale. Les développements futurs devront viser l'intégration de l'identification et la pondération des sites HH au processus d'inférence phylogénétique lui-même.

Measuring and testing for the systemically important financial institutions

This paper analyzes the measure of systemic importance ∆CoV aR proposed by Adrian and Brunnermeier (2009, 2010) within the context of a similar class of risk measures used in the risk management literature. In addition, we develop a series of testing procedures, based on ∆CoV aR, to identify and rank the systemically important institutions. We stress the importance of statistical testing in interpreting the measure of systemic importance. An empirical application illustrates the testing procedures, using equity data for three European banks.

Acurácia dos indicadores clínicos do diagnóstico de enfermagem volume de líquidos excessivo em pacientes submetidos à hemodiálise

Trasnversal study, with the objective of evaluating the accuracy of clinical indicators of nursing diagnosis excessive fluid volume in patients undergoing hemodialysis. The study occurred in two stages, the first consisted of the evaluation of the diagnostic indicators in study; and the second, the diagnostic inference conducted by nurse diagnosticians. The first stage occurred from december 2012 to april 2013, in a University Hospital and a Hemodialysis Clinic in Northeastern of Brazil, with a sample of 100 chronic renal failure patients on hemodialysis. The data were selected through an interview form and a physical examination, organized into spreadsheets and analyzed as to the presence or absence of the indicators of diagnosis excessive fluid volume. In the second step, the spreadsheets were sent to three nurses diagnosticians, who judged the presence or absence of diagnosis in the clientele searched. This step was conducted from july to september 2013. For analysis of the data, we used descriptive and inferential statistics. In the descriptive analysis, we used measures of central tendency and dispersion. In inferential analysis, we used the tests Chi- square, Fisher and prevalence ratios. The accuracy of the clinical indicators pertaining to the diagnosis were measured as to the specificity, sensitivity, predictive values, likelihood ratios and Diagnostic Odds Ratio. Also developed a logistic regression. The results were organized in tables and discussed with literature. This study was approved by the Ethics Committee in Research of the Federal University of Rio Grande do Norte, with Presentation Certificate for Ethics Appreciation nº 08696212.7.0000.5537. The results revealed that the diagnosis studied was present in 82% of patients. The characteristics with prevalence above 50 % that stood out were: azotemia, decreased hematocrit, electrolyte imbalance, intake exceeds output, anxiety, edema, decreased hemoglobin, oliguria and blood pressure changes. Eight defining characteristics were presented statistically significant association with the nursing diagnosis investigated: pulmonary congestion, intake exceeds output, electrolytes imbalance, jugular vein distension, edema, weight gain over short period of time, agitation and adventitious breath sounds. Among these, the 10 characteristics which showed higher prevalence ratios were: edema and weight gain over short period of time. The features with the highest sensitivity were edema, electrolytes imbalance and intake exceeds output and the standing out with greater specificity were: anasarca, weight gain over short period of time, change in respiratory pattern, adventitious breath sounds, pulmonary congestion, agitation and jugular vein distension. The indicators jugular vein distension, electrolytes imbalance, intake exceeds output, increased central venous pressure and edema, together, were identified in the logistic regression model as the most significant predictors. It is concluded that the identification of accurate clinical indicators allow a good prediction of the nursing diagnosis of excessive fluid volume in patients undergoing hemodialysis in order to assist the nurse in the inference process, which will contribute to the success of patient care. In addition, nurses will consider for diagnostic inference not only his clinical experience, but also scientific evidence of the occurrence of excessive fluid volume, contributing to the control of volemia in these patients

Short-term planning of electric power distribution networks using multiobjective genetic algorithim

The high active and reactive power level demanded by the distribution systems, the growth of consuming centers, and the long lines of the distribution systems result in voltage variations in the busses compromising the quality of energy supplied. To ensure the energy quality supplied in the distribution system short-term planning, some devices and actions are used to implement an effective control of voltage, reactive power, and power factor of the network. Among these devices and actions are the voltage regulators (VRs) and capacitor banks (CBs), as well as exchanging the conductors sizes of distribution lines. This paper presents a methodology based on the Non-Dominated Sorting Genetic Algorithm (NSGA-II) for optimized allocation of VRs, CBs, and exchange of conductors in radial distribution systems. The Multiobjective Genetic Algorithm (MGA) is aided by an inference process developed using fuzzy logic, which applies specialized knowledge to achieve the reduction of the search space for the allocation of CBs and VRs.

Constraint-based analysis of gene interactions using restricted boolean networks and time-series data

Abstract Background A popular model for gene regulatory networks is the Boolean network model. In this paper, we propose an algorithm to perform an analysis of gene regulatory interactions using the Boolean network model and time-series data. Actually, the Boolean network is restricted in the sense that only a subset of all possible Boolean functions are considered. We explore some mathematical properties of the restricted Boolean networks in order to avoid the full search approach. The problem is modeled as a Constraint Satisfaction Problem (CSP) and CSP techniques are used to solve it. Results We applied the proposed algorithm in two data sets. First, we used an artificial dataset obtained from a model for the budding yeast cell cycle. The second data set is derived from experiments performed using HeLa cells. The results show that some interactions can be fully or, at least, partially determined under the Boolean model considered. Conclusions The algorithm proposed can be used as a first step for detection of gene/protein interactions. It is able to infer gene relationships from time-series data of gene expression, and this inference process can be aided by a priori knowledge available.

Logical omniscience as infeasibility

Logical theories for representing knowledge are often plagued by the so-called Logical Omniscience Problem. The problem stems from the clash between the desire to model rational agents, which should be capable of simple logical inferences, and the fact that any logical inference, however complex, almost inevitably consists of inference steps that are simple enough. This contradiction points to the fruitlessness of trying to solve the Logical Omniscience Problem qualitatively if the rationality of agents is to be maintained. We provide a quantitative solution to the problem compatible with the two important facets of the reasoning agent: rationality and resource boundedness. More precisely, we provide a test for the logical omniscience problem in a given formal theory of knowledge. The quantitative measures we use are inspired by the complexity theory. We illustrate our framework with a number of examples ranging from the traditional implicit representation of knowledge in modal logic to the language of justification logic, which is capable of spelling out the internal inference process. We use these examples to divide representations of knowledge into logically omniscient and not logically omniscient, thus trying to determine how much information about the reasoning process needs to be present in a theory to avoid logical omniscience.

Modelado de sistemas multimedia para personalización y recomendación híbrida a partir del consumo audiovisual de los usuarios

This doctoral thesis focuses on the modeling of multimedia systems to create personalized recommendation services based on the analysis of users’ audiovisual consumption. Research is focused on the characterization of both users’ audiovisual consumption and content, specifically images and video. This double characterization converges into a hybrid recommendation algorithm, adapted to different application scenarios covering different specificities and constraints. Hybrid recommendation systems use both content and user information as input data, applying the knowledge from the analysis of these data as the initial step to feed the algorithms in order to generate personalized recommendations. Regarding the user information, this doctoral thesis focuses on the analysis of audiovisual consumption to infer implicitly acquired preferences. The inference process is based on a new probabilistic model proposed in the text. This model takes into account qualitative and quantitative consumption factors on the one hand, and external factors such as zapping factor or company factor on the other. As for content information, this research focuses on the modeling of descriptors and aesthetic characteristics, which influence the user and are thus useful for the recommendation system. Similarly, the automatic extraction of these descriptors from the audiovisual piece without excessive computational cost has been considered a priority, in order to ensure applicability to different real scenarios. Finally, a new content-based recommendation algorithm has been created from the previously acquired information, i.e. user preferences and content descriptors. This algorithm has been hybridized with a collaborative filtering algorithm obtained from the current state of the art, so as to compare the efficiency of this hybrid recommender with the individual techniques of recommendation (different hybridization techniques of the state of the art have been studied for suitability). The content-based recommendation focuses on the influence of the aesthetic characteristics on the users. The heterogeneity of the possible users of these kinds of systems calls for the use of different criteria and attributes to create effective recommendations. Therefore, the proposed algorithm is adaptable to different perceptions producing a dynamic representation of preferences to obtain personalized recommendations for each user of the system. The hypotheses of this doctoral thesis have been validated by conducting a set of tests with real users, or by querying a database containing user preferences - available to the scientific community. This thesis is structured based on the different research and validation methodologies of the techniques involved. In the three central chapters the state of the art is studied and the developed algorithms and models are validated via self-designed tests. It should be noted that some of these tests are incremental and confirm the validation of previously discussed techniques. Resumen Esta tesis doctoral se centra en el modelado de sistemas multimedia para la creación de servicios personalizados de recomendación a partir del análisis de la actividad de consumo audiovisual de los usuarios. La investigación se focaliza en la caracterización tanto del consumo audiovisual del usuario como de la naturaleza de los contenidos, concretamente imágenes y vídeos. Esta doble caracterización de usuarios y contenidos confluye en un algoritmo de recomendación híbrido que se adapta a distintos escenarios de aplicación, cada uno de ellos con distintas peculiaridades y restricciones. Todo sistema de recomendación híbrido toma como datos de partida tanto información del usuario como del contenido, y utiliza este conocimiento como entrada para algoritmos que permiten generar recomendaciones personalizadas. Por la parte de la información del usuario, la tesis se centra en el análisis del consumo audiovisual para inferir preferencias que, por lo tanto, se adquieren de manera implícita. Para ello, se ha propuesto un nuevo modelo probabilístico que tiene en cuenta factores de consumo tanto cuantitativos como cualitativos, así como otros factores de contorno, como el factor de zapping o el factor de compañía, que condicionan la incertidumbre de la inferencia. En cuanto a la información del contenido, la investigación se ha centrado en la definición de descriptores de carácter estético y morfológico que resultan influyentes en el usuario y que, por lo tanto, son útiles para la recomendación. Del mismo modo, se ha considerado una prioridad que estos descriptores se puedan extraer automáticamente de un contenido sin exigir grandes requisitos computacionales y, de tal forma que se garantice la posibilidad de aplicación a escenarios reales de diverso tipo. Por último, explotando la información de preferencias del usuario y de descripción de los contenidos ya obtenida, se ha creado un nuevo algoritmo de recomendación basado en contenido. Este algoritmo se cruza con un algoritmo de filtrado colaborativo de referencia en el estado del arte, de tal manera que se compara la eficiencia de este recomendador híbrido (donde se ha investigado la idoneidad de las diferentes técnicas de hibridación del estado del arte) con cada una de las técnicas individuales de recomendación. El algoritmo de recomendación basado en contenido que se ha creado se centra en las posibilidades de la influencia de factores estéticos en los usuarios, teniendo en cuenta que la heterogeneidad del conjunto de usuarios provoca que los criterios y atributos que condicionan las preferencias de cada individuo sean diferentes. Por lo tanto, el algoritmo se adapta a las diferentes percepciones y articula una metodología dinámica de representación de las preferencias que permite obtener recomendaciones personalizadas, únicas para cada usuario del sistema. Todas las hipótesis de la tesis han sido debidamente validadas mediante la realización de pruebas con usuarios reales o con bases de datos de preferencias de usuarios que están a disposición de la comunidad científica. La diferente metodología de investigación y validación de cada una de las técnicas abordadas condiciona la estructura de la tesis, de tal manera que los tres capítulos centrales se estructuran sobre su propio estudio del estado del arte y los algoritmos y modelos desarrollados se validan mediante pruebas autónomas, sin impedir que, en algún caso, las pruebas sean incrementales y ratifiquen la validación de técnicas expuestas anteriormente.

Contribución a la automatización de sistemas de respuesta frente a intrusiones mediante ontologías

La seguridad en redes informáticas es un área que ha sido ampliamente estudiada y objeto de una extensa investigación en los últimos años. Debido al continuo incremento en la complejidad y sofisticación de los ataques informáticos, el aumento de su velocidad de difusión, y la lentitud de reacción frente a las intrusiones existente en la actualidad, se hace patente la necesidad de mecanismos de detección y respuesta a intrusiones, que detecten y además sean capaces de bloquear el ataque, y mitiguen su impacto en la medida de lo posible. Los Sistemas de Detección de Intrusiones o IDSs son tecnologías bastante maduras cuyo objetivo es detectar cualquier comportamiento malicioso que ocurra en las redes. Estos sistemas han evolucionado rápidamente en los últimos años convirtiéndose en herramientas muy maduras basadas en diferentes paradigmas, que mejoran su capacidad de detección y le otorgan un alto nivel de fiabilidad. Por otra parte, un Sistema de Respuesta a Intrusiones (IRS) es un componente de seguridad que puede estar presente en la arquitectura de una red informática, capaz de reaccionar frente a los incidentes detectados por un Sistema de Detección de Intrusiones (IDS). Por desgracia, esta tecnología no ha evolucionado al mismo ritmo que los IDSs, y la reacción contra los ataques detectados es lenta y básica, y los sistemas presentan problemas para ejecutar respuestas de forma automática. Esta tesis doctoral trata de hacer frente al problema existente en la reacción automática frente a intrusiones, mediante el uso de ontologías, lenguajes formales de especificación de comportamiento y razonadores semánticos como base de la arquitectura del sistema de un sistema de respuesta automática frente a intrusiones o AIRS. El objetivo de la aproximación es aprovechar las ventajas de las ontologías en entornos heterogéneos, además de su capacidad para especificar comportamiento sobre los objetos que representan los elementos del dominio modelado. Esta capacidad para especificar comportamiento será de gran utilidad para que el AIRS infiera la respuesta óptima frente a una intrusión en el menor tiempo posible. Abstract Security in networks is an area that has been widely studied and has been the focus of extensive research over the past few years. The number of security events is increasing, and they are each time more sophisticated, and quickly spread, and slow reaction against intrusions, there is a need for intrusion detection and response systems to dynamically adapt so as to better detect and respond to attacks in order to mitigate them or reduce their impact. Intrusion Detection Systems (IDSs) are mature technologies whose aim is detecting malicious behavior in the networks. These systems have quickly evolved and there are now very mature tools based on different paradigms (statistic anomaly-based, signature-based and hybrids) with a high level of reliability. On the other hand, Intrusion Response System (IRS) is a security technology able to react against the intrusions detected by IDS. Unfortunately, the state of the art in IRSs is not as mature as with IDSs. The reaction against intrusions is slow and simple, and these systems have difficulty detecting intrusions in real time and triggering automated responses. This dissertation is to address the existing problem in automated reactions against intrusions using ontologies, formal behaviour languages and semantic reasoners as the basis of the architecture of an automated intrusion response systems or AIRS. The aim is to take advantage of ontologies in heterogeneous environments, in addition to its ability to specify behavior of objects representing the elements of the modeling domain. This ability to specify behavior will be useful for the AIRS in the inference process of the optimum response against an intrusion, as quickly as possible.

Learning Bayesian networks from data by the incremental compilation of new network polynomials

Probabilistic graphical models are a huge research field in artificial intelligence nowadays. The scope of this work is the study of directed graphical models for the representation of discrete distributions. Two of the main research topics related to this area focus on performing inference over graphical models and on learning graphical models from data. Traditionally, the inference process and the learning process have been treated separately, but given that the learned models structure marks the inference complexity, this kind of strategies will sometimes produce very inefficient models. With the purpose of learning thinner models, in this master thesis we propose a new model for the representation of network polynomials, which we call polynomial trees. Polynomial trees are a complementary representation for Bayesian networks that allows an efficient evaluation of the inference complexity and provides a framework for exact inference. We also propose a set of methods for the incremental compilation of polynomial trees and an algorithm for learning polynomial trees from data using a greedy score+search method that includes the inference complexity as a penalization in the scoring function.

Aprendizaje colaborativo en enseñanza a distancia: entorno genérico para configurar, realizar y analizar actividades en grupo

En esta tesis se ha profundizado en el estudio y desarrollo de modelos de soporte para el aprendizaje colaborativo a distancia, que ha permitido proponer una arquitectura fundamentada en los principios del paradigma CSCL (Computer Supported Collaborative Learning). La arquitectura propuesta aborda un tipo de problema concreto que requiere el uso de técnicas derivadas del Trabajo Colaborativo, la Inteligencia Artificial, Interfaces de Usuario así como ideas tomadas de la Pedagogía y la Psicología. Se ha diseñado una solución completa, abierta y genérica. La arquitectura aprovecha las nuevas tecnologías para lograr un sistema efectivo de apoyo a la educación a distancia. Está organizada en cuatro niveles: el de Configuración, el de Experiencia, el de Organización y el de Análisis. A partir de ella se ha implementado un sistema llamado DEGREE. En DEGREE, cada uno de los niveles de la arquitectura da lugar a un subsistema independiente pero relacionado con los otros. La aplicación saca partido del uso de espacios de trabajo estructurados. El subsistema Configurador de Experiencias permite definir los elementos de un espacio de trabajo y una experiencia y adaptarlos a cada tipo de usuario. El subsistema Manejador de Experiencias recoge las contribuciones de los usuarios para construir una solución conjunta de un problema. Las intervenciones de los alumnos se estructuran basándose en un grafo conversacional genérico. Además, se registran todas las acciones de los usuarios para representar explícitamente el proceso completo que lleva a la solución. Estos datos también se almacenan en una memoria común que constituye el subsistema llamado Memoria Organizativa de Experiencias. El subsistema Analizador estudia las intervenciones de los usuarios. Este análisis permite inferir conclusiones sobre la forma en que trabajan los grupos y sus actitudes frente a la colaboración, teniendo en cuenta además el conocimiento subjetivo del observador. El proceso de desarrollo en paralelo de la arquitectura y el sistema ha seguido un ciclo de refinamiento en cinco fases con sucesivas etapas de prototipado y evaluación formativa. Cada fase de este proceso se ha realizado con usuarios reales y se han considerado las opiniones de los usuarios para mejorar las funcionalidades de la arquitectura así como la interfaz del sistema. Esta aproximación ha permitido, además, comprobar la utilidad práctica y la validez de las propuestas que sustentan este trabajo.---ABSTRACT---In this thesis, we have studied in depth the development of support models for distance collaborative learning and subsequently devised an architecture based on the Computer Supported Collaborative Learning paradigm principles. The proposed architecture addresses a specific problem: coordinating groups of students to perform collaborative distance learning activities. Our approach uses Cooperative Work, Artificial Intelligence and Human-Computer Interaction techniques as well as some ideas from the fields of Pedagogy and Psychology. We have designed a complete, open and generic solution. Our architecture exploits the new information technologies to achieve an effective system for education purposes. It is organised into four levels: Configuration, Experience, Organisation and Reflection. This model has been implemented into a system called DEGREE. In DEGREE, each level of the architecture gives rise to an independent subsystem related to the other ones. The application benefits from the use of shared structured workspaces. The configuration subsystem allows customising the elements that define an experience and a workspace. The experience subsystem gathers the users' contributions to build joint solutions to a given problem. The students' interventions build up a structure based on a generic conversation graph. Moreover, all user actions are registered in order to represent explicitly the complete process for reaching the group solution. Those data are also stored into a common memory, which constitutes the organisation subsystem. The user interventions are studied by the reflection subsystem. This analysis allows us inferring conclusions about the way in which the group works and its attitudes towards collaboration. The inference process takes into account the observer's subjective knowledge. The process of developing both the architecture and the system in parallel has run through a five-pass cycle involving successive stages of prototyping and formative evaluation. At each stage of that process, we have considered the users' feedback for improving the architecture's functionalities as well as the system interface. This approach has allowed us to prove the usability and validity of our proposal.

Type inference for conversation types

Trabalho apresentado no âmbito do Mestrado em Engenharia Informática, como requisito parcial para obtenção do grau de Mestre em Engenharia Informática

Multimodel inference and multimodel averaging in empirical modeling of occupational exposure levels.

Empirical modeling of exposure levels has been popular for identifying exposure determinants in occupational hygiene. Traditional data-driven methods used to choose a model on which to base inferences have typically not accounted for the uncertainty linked to the process of selecting the final model. Several new approaches propose making statistical inferences from a set of plausible models rather than from a single model regarded as 'best'. This paper introduces the multimodel averaging approach described in the monograph by Burnham and Anderson. In their approach, a set of plausible models are defined a priori by taking into account the sample size and previous knowledge of variables influent on exposure levels. The Akaike information criterion is then calculated to evaluate the relative support of the data for each model, expressed as Akaike weight, to be interpreted as the probability of the model being the best approximating model given the model set. The model weights can then be used to rank models, quantify the evidence favoring one over another, perform multimodel prediction, estimate the relative influence of the potential predictors and estimate multimodel-averaged effects of determinants. The whole approach is illustrated with the analysis of a data set of 1500 volatile organic compound exposure levels collected by the Institute for work and health (Lausanne, Switzerland) over 20 years, each concentration having been divided by the relevant Swiss occupational exposure limit and log-transformed before analysis. Multimodel inference represents a promising procedure for modeling exposure levels that incorporates the notion that several models can be supported by the data and permits to evaluate to a certain extent model selection uncertainty, which is seldom mentioned in current practice.

Quantitative genetic modeling and inference in the presence of nonignorable missing data.

Natural selection is typically exerted at some specific life stages. If natural selection takes place before a trait can be measured, using conventional models can cause wrong inference about population parameters. When the missing data process relates to the trait of interest, a valid inference requires explicit modeling of the missing process. We propose a joint modeling approach, a shared parameter model, to account for nonrandom missing data. It consists of an animal model for the phenotypic data and a logistic model for the missing process, linked by the additive genetic effects. A Bayesian approach is taken and inference is made using integrated nested Laplace approximations. From a simulation study we find that wrongly assuming that missing data are missing at random can result in severely biased estimates of additive genetic variance. Using real data from a wild population of Swiss barn owls Tyto alba, our model indicates that the missing individuals would display large black spots; and we conclude that genes affecting this trait are already under selection before it is expressed. Our model is a tool to correctly estimate the magnitude of both natural selection and additive genetic variance.