Teses / dissertações sobre o tema "Représentation de données de réseau"
Crie uma referência precisa em APA, MLA, Chicago, Harvard, e outros estilos
Veja os 50 melhores trabalhos (teses / dissertações) para estudos sobre o assunto "Représentation de données de réseau".
Ao lado de cada fonte na lista de referências, há um botão "Adicionar à bibliografia". Clique e geraremos automaticamente a citação bibliográfica do trabalho escolhido no estilo de citação de que você precisa: APA, MLA, Harvard, Chicago, Vancouver, etc.
Você também pode baixar o texto completo da publicação científica em formato .pdf e ler o resumo do trabalho online se estiver presente nos metadados.
Veja as teses / dissertações das mais diversas áreas científicas e compile uma bibliografia correta.
Petit, Laurent. "Etude de la qualité des données pour la représentation des réseaux techniques urbains : applications au réseau d'assainissement". Artois, 1999. http://www.theses.fr/1999ARTO0203.
Texto completo da fontePoussevin, Mickael. "Apprentissage de représentation pour des données générées par des utilisateurs". Electronic Thesis or Diss., Paris 6, 2015. https://accesdistant.sorbonne-universite.fr/login?url=https://theses-intra.sorbonne-universite.fr/2015PA066040.pdf.
Texto completo da fonteIn this thesis, we study how representation learning methods can be applied to user-generated data. Our contributions cover three different applications but share a common denominator: the extraction of relevant user representations. Our first application is the item recommendation task, where recommender systems build user and item profiles out of past ratings reflecting user preferences and item characteristics. Nowadays, textual information is often together with ratings available and we propose to use it to enrich the profiles extracted from the ratings. Our hope is to extract from the textual content shared opinions and preferences. The models we propose provide another opportunity: predicting the text a user would write on an item. Our second application is sentiment analysis and, in particular, polarity classification. Our idea is that recommender systems can be used for such a task. Recommender systems and traditional polarity classifiers operate on different time scales. We propose two hybridizations of these models: the former has better classification performance, the latter highlights a vocabulary of surprise in the texts of the reviews. The third and final application we consider is urban mobility. It takes place beyond the frontiers of the Internet, in the physical world. Using authentication logs of the subway users, logging the time and station at which users take the subway, we show that it is possible to extract robust temporal profiles
Poussevin, Mickael. "Apprentissage de représentation pour des données générées par des utilisateurs". Thesis, Paris 6, 2015. http://www.theses.fr/2015PA066040/document.
Texto completo da fonteIn this thesis, we study how representation learning methods can be applied to user-generated data. Our contributions cover three different applications but share a common denominator: the extraction of relevant user representations. Our first application is the item recommendation task, where recommender systems build user and item profiles out of past ratings reflecting user preferences and item characteristics. Nowadays, textual information is often together with ratings available and we propose to use it to enrich the profiles extracted from the ratings. Our hope is to extract from the textual content shared opinions and preferences. The models we propose provide another opportunity: predicting the text a user would write on an item. Our second application is sentiment analysis and, in particular, polarity classification. Our idea is that recommender systems can be used for such a task. Recommender systems and traditional polarity classifiers operate on different time scales. We propose two hybridizations of these models: the former has better classification performance, the latter highlights a vocabulary of surprise in the texts of the reviews. The third and final application we consider is urban mobility. It takes place beyond the frontiers of the Internet, in the physical world. Using authentication logs of the subway users, logging the time and station at which users take the subway, we show that it is possible to extract robust temporal profiles
Ziat, Ali Yazid. "Apprentissage de représentation pour la prédiction et la classification de séries temporelles". Thesis, Paris 6, 2017. http://www.theses.fr/2017PA066324/document.
Texto completo da fonteThis thesis deals with the development of time series analysis methods. Our contributions focus on two tasks: time series forecasting and classification. Our first contribution presents a method of prediction and completion of multivariate and relational time series. The aim is to be able to simultaneously predict the evolution of a group of time series connected to each other according to a graph, as well as to complete the missing values in these series (which may correspond for example to a failure of a sensor during a given time interval). We propose to use representation learning techniques to forecast the evolution of the series while completing the missing values and taking into account the relationships that may exist between them. Extensions of this model are proposed and described: first in the context of the prediction of heterogeneous time series and then in the case of the prediction of time series with an expressed uncertainty. A prediction model of spatio-temporal series is then proposed, in which the relations between the different series can be expressed more generally, and where these can be learned.Finally, we are interested in the classification of time series. A joint model of metric learning and time-series classification is proposed and an experimental comparison is conducted
Ziat, Ali Yazid. "Apprentissage de représentation pour la prédiction et la classification de séries temporelles". Electronic Thesis or Diss., Paris 6, 2017. http://www.theses.fr/2017PA066324.
Texto completo da fonteThis thesis deals with the development of time series analysis methods. Our contributions focus on two tasks: time series forecasting and classification. Our first contribution presents a method of prediction and completion of multivariate and relational time series. The aim is to be able to simultaneously predict the evolution of a group of time series connected to each other according to a graph, as well as to complete the missing values in these series (which may correspond for example to a failure of a sensor during a given time interval). We propose to use representation learning techniques to forecast the evolution of the series while completing the missing values and taking into account the relationships that may exist between them. Extensions of this model are proposed and described: first in the context of the prediction of heterogeneous time series and then in the case of the prediction of time series with an expressed uncertainty. A prediction model of spatio-temporal series is then proposed, in which the relations between the different series can be expressed more generally, and where these can be learned.Finally, we are interested in the classification of time series. A joint model of metric learning and time-series classification is proposed and an experimental comparison is conducted
Castagliola, Carole. "Héritage et valuation dans les réseaux sémantiques pour les bases de données objets". Compiègne, 1991. http://www.theses.fr/1991COMPD363.
Texto completo da fonteBouzeghoub, Mokrane. "Secsi : un système expert en conception de systèmes d'informations, modélisation conceptuelle de schémas de bases de données". Paris 6, 1986. http://www.theses.fr/1986PA066046.
Texto completo da fonteAzorin, Raphael. "Traffic representations for network measurements". Electronic Thesis or Diss., Sorbonne université, 2024. http://www.theses.fr/2024SORUS141.
Texto completo da fonteMeasurements are essential to operate and manage computer networks, as they are critical to analyze performance and establish diagnosis. In particular, per-flow monitoring consists in computing metrics that characterize the individual data streams traversing the network. To develop relevant traffic representations, operators need to select suitable flow characteristics and carefully relate their cost of extraction with their expressiveness for the downstream tasks considered. In this thesis, we propose novel methodologies to extract appropriate traffic representations. In particular, we posit that Machine Learning can enhance measurement systems, thanks to its ability to learn patterns from data, in order to provide predictions of pertinent traffic characteristics.The first contribution of this thesis is a framework for sketch-based measurements systems to exploit the skewed nature of network traffic. Specifically, we propose a novel data structure representation that leverages sketches' under-utilization, reducing per-flow measurements memory footprint by storing only relevant counters. The second contribution is a Machine Learning-assisted monitoring system that integrates a lightweight traffic classifier. In particular, we segregate large and small flows in the data plane, before processing them separately with dedicated data structures for various use cases. The last contributions address the design of a unified Deep Learning measurement pipeline that extracts rich representations from traffic data for network analysis. We first draw from recent advances in sequence modeling to learn representations from both numerical and categorical traffic data. These representations serve as input to solve complex networking tasks such as clickstream identification and mobile terminal movement prediction in WLAN. Finally, we present an empirical study of task affinity to assess when two tasks would benefit from being learned together
Rabaute, Alain. "Obtenir une représentation en continu de la lithologie et de la minéralogie. Exemples d'application du traitement statistique de données de diagraphie aux structures sédimentaires en régime de convergence de plaques (Leg ODP 134, 156 et 160)". Phd thesis, Université Montpellier II - Sciences et Techniques du Languedoc, 1998. http://tel.archives-ouvertes.fr/tel-00425334.
Texto completo da fonteMachens, Anna. "Processus épidémiques sur réseaux dynamiques". Thesis, Aix-Marseille, 2013. http://www.theses.fr/2013AIXM4066/document.
Texto completo da fonteIn this thesis we contribute to provide insights into questions concerning dynamic epidemic processes on data-driven, temporal networks. In particular, we investigate the influence of data representations on the outcome of epidemic processes, shedding some light on the question how much detail is necessary for the data representation and its dependence on the spreading parameters. By introducing an improvement to the contact matrix representation we provide a data representation that could in the future be integrated into multi-scale epidemic models in order to improve the accuracy of predictions and corresponding immunization strategies. We also point out some of the ways dynamic processes are influenced by temporal properties of the data
Jagtap, Surabhi. "Multilayer Graph Embeddings for Omics Data Integration in Bioinformatics". Electronic Thesis or Diss., université Paris-Saclay, 2023. http://www.theses.fr/2023UPAST014.
Texto completo da fonteBiological systems are composed of interacting bio-molecules at different molecular levels. With the advent of high-throughput technologies, omics data at their respective molecular level can be easily obtained. These huge, complex multi-omics data can be useful to provide insights into the flow of information at multiple levels, unraveling the mechanisms underlying the biological condition of interest. Integration of different omics data types is often expected to elucidate potential causative changes that lead to specific phenotypes, or targeted treatments. With the recent advances in network science, we choose to handle this integration issue by representing omics data through networks. In this thesis, we have developed three models, namely BraneExp, BraneNet, and BraneMF, for learning node embeddings from multilayer biological networks generated with omics data. We aim to tackle various challenging problems arising in multi-omics data integration, developing expressive and scalable methods capable of leveraging rich structural semantics of realworld networks
Mohammadi, Samin. "Analysis of user popularity pattern and engagement prediction in online social networks". Thesis, Evry, Institut national des télécommunications, 2018. http://www.theses.fr/2018TELE0019/document.
Texto completo da fonteNowadays, social media has widely affected every aspect of human life. The most significant change in people's behavior after emerging Online Social Networks (OSNs) is their communication method and its range. Having more connections on OSNs brings more attention and visibility to people, where it is called popularity on social media. Depending on the type of social network, popularity is measured by the number of followers, friends, retweets, likes, and all those other metrics that is used to calculate engagement. Studying the popularity behavior of users and published contents on social media and predicting its future status are the important research directions which benefit different applications such as recommender systems, content delivery networks, advertising campaign, election results prediction and so on. This thesis addresses the analysis of popularity behavior of OSN users and their published posts in order to first, identify the popularity trends of users and posts and second, predict their future popularity and engagement level for published posts by users. To this end, i) the popularity evolution of ONS users is studied using a dataset of 8K Facebook professional users collected by an advanced crawler. The collected dataset includes around 38 million snapshots of users' popularity values and 64 million published posts over a period of 4 years. Clustering temporal sequences of users' popularity values led to identifying different and interesting popularity evolution patterns. The identified clusters are characterized by analyzing the users' business sector, called category, their activity level, and also the effect of external events. Then ii) the thesis focuses on the prediction of user engagement on the posts published by users on OSNs. A novel prediction model is proposed which takes advantage of Point-wise Mutual Information (PMI) and predicts users' future reaction to newly published posts. Finally, iii) the proposed model is extended to get benefits of representation learning and predict users' future engagement on each other's posts. The proposed prediction approach extracts user embedding from their reaction history instead of using conventional feature extraction methods. The performance of the proposed model proves that it outperforms conventional learning methods available in the literature. The models proposed in this thesis, not only improves the reaction prediction models to exploit representation learning features instead of hand-crafted features but also could help news agencies, advertising campaigns, content providers in CDNs, and recommender systems to take advantage of more accurate prediction results in order to improve their user services
Prudhomme, Elie. "Représentation et fouille de données volumineuses". Thesis, Lyon 2, 2009. http://www.theses.fr/2009LYO20048/document.
Texto completo da fonte/
Bougrain, Laurent. "Étude de la construction par réseaux neuromimétiques de représentations interprétables : application à la prédiction dans le domaine des télécommunications". Nancy 1, 2000. http://www.theses.fr/2000NAN10241.
Texto completo da fonteArtificial neural networks constitute good tools for certain types of computational modelling (being potentially efficient, easy to adapt and fast). However, they are often considered difficult to interpret, and are sometimes treated as black boxes. However, whilst this complexity implies that it is difficult to understand the internal organization that develops through learning, it usually encapsulates one of the key factors for obtaining good results. First, to yield a better understanding of how artificial neural networks behave and to validate their use as knowledge discovery tools, we have examined various theoretical works in order to demonstrate the common principles underlying both certain classical artificial neural network, and statistical methods for regression and data analysis. Second, in light of these studies, we have explained the specificities of some more complex artificial neural networks, such as dynamical and modular networks, in order to exploit their respective advantages in constructing a revised model for knowledge extraction, adjusted to the complexity of the phenomena we want to model. The artificial neural networks we have combined (and the subsequent model we developed) can, starting from task data, enhance the understanding of the phenomena modelled through analysing and organising the information for the task. We demonstrate this in a practical prediction task for telecommunication, where the general domain knowledge alone is insufficient to model the phenomena satisfactorily. This leads us to conclude that the possibility for practical application of out work is broad, and that our methods can combine with those already existing in the data mining and the cognitive sciences
Mohammadi, Samin. "Analysis of user popularity pattern and engagement prediction in online social networks". Electronic Thesis or Diss., Evry, Institut national des télécommunications, 2018. http://www.theses.fr/2018TELE0019.
Texto completo da fonteNowadays, social media has widely affected every aspect of human life. The most significant change in people's behavior after emerging Online Social Networks (OSNs) is their communication method and its range. Having more connections on OSNs brings more attention and visibility to people, where it is called popularity on social media. Depending on the type of social network, popularity is measured by the number of followers, friends, retweets, likes, and all those other metrics that is used to calculate engagement. Studying the popularity behavior of users and published contents on social media and predicting its future status are the important research directions which benefit different applications such as recommender systems, content delivery networks, advertising campaign, election results prediction and so on. This thesis addresses the analysis of popularity behavior of OSN users and their published posts in order to first, identify the popularity trends of users and posts and second, predict their future popularity and engagement level for published posts by users. To this end, i) the popularity evolution of ONS users is studied using a dataset of 8K Facebook professional users collected by an advanced crawler. The collected dataset includes around 38 million snapshots of users' popularity values and 64 million published posts over a period of 4 years. Clustering temporal sequences of users' popularity values led to identifying different and interesting popularity evolution patterns. The identified clusters are characterized by analyzing the users' business sector, called category, their activity level, and also the effect of external events. Then ii) the thesis focuses on the prediction of user engagement on the posts published by users on OSNs. A novel prediction model is proposed which takes advantage of Point-wise Mutual Information (PMI) and predicts users' future reaction to newly published posts. Finally, iii) the proposed model is extended to get benefits of representation learning and predict users' future engagement on each other's posts. The proposed prediction approach extracts user embedding from their reaction history instead of using conventional feature extraction methods. The performance of the proposed model proves that it outperforms conventional learning methods available in the literature. The models proposed in this thesis, not only improves the reaction prediction models to exploit representation learning features instead of hand-crafted features but also could help news agencies, advertising campaigns, content providers in CDNs, and recommender systems to take advantage of more accurate prediction results in order to improve their user services
Bounar, Boualem. "Génération automatique de programmes sur une base de données en réseau : couplage PROLOG-Base de données en réseau". Lyon 1, 1986. http://www.theses.fr/1986LYO11703.
Texto completo da fonteBrossier, Gildas. "Problèmes de représentation de données par des arbres". Rennes 2, 1986. http://www.theses.fr/1986REN20014.
Texto completo da fonteFirst, we begin by studying the properties of distance tables associated with tree-representations, and the relation between these distances. Then we define ordered representations, construct a class of ordering algorithms and study their optimal properties under different conditions. The decomposition properties of distance tables allow us to construct fast algorithms for representations with some optimal properties we extend results when data are asymmetry matrices. Last of all we show in the case of rectangular matrices the necessary and sufficient conditions for the simultaneous representations of two sets of data. When conditions are not satisfied we propose some approximation algorithms
Le, Morvan Marine. "Développement de représentations et d'algorithmes efficaces pour l'apprentissage statistique sur des données génomiques". Thesis, Paris Sciences et Lettres (ComUE), 2018. http://www.theses.fr/2018PSLEM041/document.
Texto completo da fonteSince the first sequencing of the human genome in the early 2000s, large endeavours have set out to map the genetic variability among individuals, or DNA alterations in cancer cells. They have laid foundations for the emergence of precision medicine, which aims at integrating the genetic specificities of an individual with its conventional medical record to adapt treatment, or prevention strategies.Translating DNA variations and alterations into phenotypic predictions is however a difficult problem. DNA sequencers and microarrays measure more variables than there are samples, which poses statistical issues. The data is also subject to technical biases and noise inherent in these technologies. Finally, the vast and intricate networks of interactions among proteins obscure the impact of DNA variations on the cell behaviour, prompting the need for predictive models that are able to capture a certain degree of complexity. This thesis presents novel methodological contributions to address these challenges. First, we define a novel representation for tumour mutation profiles that exploits prior knowledge on protein-protein interaction networks. For certain cancers, this representation allows improving survival predictions from mutation data as well as stratifying patients into meaningful subgroups. Second, we present a new learning framework to jointly handle data normalisation with the estimation of a linear model. Our experiments show that it improves prediction performances compared to handling these tasks sequentially. Finally, we propose a new algorithm to scale up sparse linear models estimation with two-way interactions. The obtained speed-up makes this estimation possible and efficient for datasets with hundreds of thousands of main effects, thereby extending the scope of such models to the data from genome-wide association studies
Ali, Soulafa. "Agrégation des données spatiales sur un réseau régulier". Université Joseph Fourier (Grenoble), 2004. http://www.theses.fr/2004GRE10093.
Texto completo da fonteThis thesis considers the problem of aggregation of spatial data resulting from a unilateral spatial ARM A model on a regular grid in Z2. We extend the definition of random aggregation to spatial cas then we limit ourselves to the particular case of deterministic aggregation without overlapping. We show that this type of aggregation preserves the ARM A structure in the case of unilateral spatial processes when Z2 is provided with the quarter-plan order. If the initial process X, is an ARM A (p,q) where p= (p1,p2), q= (q1,q2) and pi, qi≥1 pour i=1. 2,then the aggregated process Y is also an ARM A (p*, q*). We also give the expression of the orders p* and q*. We show that spatial aggregation preserves also the structure of the unilateral spatial M A process. We prove that the aggregation processus of an AR is an ARM A one. In particular we treat the simple case of aggregation of an 1-ordre AR model. We derive the expression of the estimates of the initial process parameters in terms of aggregated process ones. These latter ones are obtained from an extension of the innovation algorithm to the spatial framework which can be applied to square-integrable, and not necessarily stationary processes
Boullé, Marc. "Recherche d'une représentation des données efficace pour la fouille des grandes bases de données". Phd thesis, Télécom ParisTech, 2007. http://pastel.archives-ouvertes.fr/pastel-00003023.
Texto completo da fonteKhalife, Sammy. "Graphes, géométrie et représentations pour le langage et les réseaux d'entités". Thesis, Institut polytechnique de Paris, 2020. http://www.theses.fr/2020IPPAX055.
Texto completo da fonteThe automated treatment of familiar objects, either natural or artifacts, always relies on a translation into entities manageable by computer programs. The choice of these abstract representations is always crucial for the efficiency of the treatments and receives the utmost attention from computer scientists and developers. However, another problem rises: the correspondence between the object to be treated and "its" representation is not necessarily one-to-one! Therefore, the ambiguous nature of certain discrete structures is problematic for their modeling as well as their processing and analysis with a program. Natural language, and in particular its textual representation, is an example. The subject of this thesis is to explore this question, which we approach using combinatorial and geometric methods. These methods allow us to address the problem of extracting information from large networks of entities and to construct representations useful for natural language processing.Firstly, we start by showing combinatorial properties of a family of graphs implicitly involved in sequential models. These properties essentially concern the inverse problem of finding a sequence representing a given graph. The resulting algorithms allow us to carry out an experimental comparison of different sequential models used in language modeling.Secondly, we consider an application for the problem of identifying named entities. Following a review of recent solutions, we propose a competitive method based on the comparison of knowledge graph structures which is less costly in annotating examples dedicated to the problem. We also establish an experimental analysis of the influence of entities from capital relations. This analysis suggests to broaden the framework for applying the identification of entities to knowledge bases of different natures. These solutions are used today in a software library in the banking sector.Then, we perform a geometric study of recently proposed representations of words, during which we discuss a geometric conjecture theoretically and experimentally. This study suggests that language analogies are difficult to transpose into geometric properties, and leads us to consider the paradigm of distance geometry in order to construct new representations.Finally, we propose a methodology based on the paradigm of distance geometry in order to build new representations of words or entities. We propose algorithms for solving this problem on some large scale instances, which allow us to build interpretable and competitive representations in performance for extrinsic tasks. More generally, we propose through this paradigm a new framework and research leadsfor the construction of representations in machine learning
Sassi, Salma. "Le système ICOP : représentation, visualisation et communication de l'information à partir d'une représentation iconique des données". Lyon, INSA, 2009. http://theses.insa-lyon.fr/publication/2009ISAL0064/these.pdf.
Texto completo da fonteInformation systems are in continuous development since their creation. Using these systems offers the possibility to information access and treatment. Although, the general operation is always the same: gathering non-described, unreferenced, and unoriginal data, as well as the difficulty in accessing updated data. . . We do not know where the searched information is, or who created it. The time and the number of intermediate persons that are necessary for data search, reduce the circulation of information. This is true in all domains including the medical domain. The communication of shared and temporal information remains an important problem. Our study on current systems showed three main limitations that increase the information dispersal on the same domain. The first problem is that the current interfaces do not correspond to user needs and work. The second problem is that some of information systems do not communicate. This makes impossible to generate an overall view of the information which are connected to the same project. Finally the third problem concerns the information access that requires the access to diverse resources. These last ones are generally heterogeneous within the syntax or semantic level. Complex ontologies containing thousands of terms are created to resolve the semantic conflicts. Nevertheless, the syntax and the unique data structure remain a difficult problem to be resolved. Essentially, our contribution consists in cooperating heterogeneous information systems. For this reason, we propose semantic mediation architecture. Domain meta-ontology and task meta-ontology are associated to assure the information sources convergence. We also use annotations and metadata that facilitate the information resources description in order to make correspondences between them, to resolve conflicts and finally to exploit the data themselves. The second part of our contribution concerns a new tool of graphic and chronological visualization. This system allows to represent on a temporal component the information related to a given domain, and also to show the needed and the authorized information to the user. We develop these proposals by illustrating them in an application domain that presents many complexity factors: medical information systems. Our proposals were validated throughout two prototypes development: the OR (Object Reconstruction) prototype and the Travel’In prototype
Muhlenbach, Fabrice. "Evaluation de la qualité de la représentation en fouille de données". Lyon 2, 2002. http://demeter.univ-lyon2.fr:8080/sdx/theses/lyon2/2002/muhlenbach_f.
Texto completo da fonteKnowledge discovery tries to produce novel and usable knowledge from the databases. In this whole process, data mining is the crucial machine learning step but we must asked some questions first: how can we have an a priori idea of the way of the labels of the class attribute are separable or not? How can we deal with databases where some examples are mislabeled? How can we transform continuous predictive attributes in discrete ones in a supervised way by taking into account the global information of the data ? We propose some responses to these problems. Our solutions take advantage of the properties of geometrical tools: the neighbourhood graphs. The neighbourhood between examples projected in a multidimensional space gives us a way of characterising the likeness between the examples to learn. We develop a statistical test based on the weight of edges that we must suppress from a neighbourhood graph for having only subgraphs of a unique class. This gives information about the a priori class separability. This work is carried on in the context of the detection of examples from a database that have doubtful labels: we propose a strategy for removing and relabeling these doubtful examples from the learning set to improve the quality of the resulting predictive model. These researches are extended in the special case of a continuous class to learn: we present a structure test to predict this kind of variable. Finally, we present a supervised polythetic discretization method based on the neighbourhood graphs and we show its performances by using it with a new supervised machine learning algorithm
Magaud, Nicolas. "Changements de Représentation des Données dans le Calcul des Constructions". Phd thesis, Université de Nice Sophia-Antipolis, 2003. http://tel.archives-ouvertes.fr/tel-00005903.
Texto completo da fontepreuves formelles en théorie des types. Nous traitons cette question
lors de l'étude
de la correction du programme de calcul de la racine carrée de GMP.
A partir d'une description formelle, nous construisons
un programme impératif avec l'outil Correctness. Cette description
prend en compte tous les détails de l'implantation, y compris
l'arithmétique de pointeurs utilisée et la gestion de la mémoire.
Nous étudions aussi comment réutiliser des preuves formelles lorsque
l'on change la représentation concrète des données.
Nous proposons un outil qui permet d'abstraire
les propriétés calculatoires associées à un type inductif dans
les termes de preuve.
Nous proposons également des outils pour simuler ces propriétés
dans un type isomorphe. Nous pouvons ainsi passer, systématiquement,
d'une représentation des données à une autre dans un développement
formel.
Thomopoulos, Rallou. "Représentation et interrogation élargie de données imprécises et faiblement structurées". Paris, Institut national d'agronomie de Paris Grignon, 2003. http://www.theses.fr/2003INAP0018.
Texto completo da fonteThis work is part of a project applied to predictive microbiology, which is built on a database and on its querying system. The data used in the project are weakly structured, they may be imprecise, and cannot provide exact answers to every query, so that a flexible querying system is necessary for the querying of the database. We use the conceptual graph model in order to take into account weakly structured data, and fuzzy set theory, in order to represent imprecise data and fuzzy queries. The purpose of this work is to provide a combination of these two formalisms
Gaillard, Jeremy. "Représentation et échange de données tridimensionnelles géolocalisées de la ville". Thesis, Lyon, 2018. http://www.theses.fr/2018LYSE2023/document.
Texto completo da fonteAdvances in 3D data acquisition techniques (laser scanning, photography, etc.) has led to a sharp increase in the quantity of available 3D geolocated data. More and more cities provide the scanned data on open access platforms. To ensure the intercompatibility of different data sources, standards have been developed for exchange protocols and file formats. Moreover, thanks to new web standards and the increase in processing power of personal devices, it is now possible to integrate rich content, such as 3D applications, directly in a web page. These two elements make it possible to share and exploit 3D city data into a web browser.The subject of my thesis, co-financed by the Oslandia company, is the 3D representation of city data on the Web. More precisely, the goal is to retrieve and visualize a great quantity of city data from one or several distant servers in a thin client. This data is heterogenous: it can be 3D representations of buildings (meshes) or terrain (height maps), but also semantic information such as pollution levels (volume data), the position of bike stations (points) and their availability, etc. During my thesis, I explored various ways of organising this data in generic structures in order to allow the progressive transmission of high volumes of 3D data. Taking into account the multiscale nature of the city is a key element in the design of these structures. Adapting the visualisation of the data to the user is another important objective of my thesis. Because of the high number of uses of 3D city models, the user’s needs vary greatly: some specific areas are of higher interest, data has to be represented in a certain way... I explore different methods to satisfy these needs, either by priroritising some data over others during the loading stage, or by generating personalised scenesbased on a set of preferences defined by the user
Duroselle, Raphaël. "Robustesse au canal des systèmes de reconnaissance de la langue". Electronic Thesis or Diss., Université de Lorraine, 2021. http://www.theses.fr/2021LORR0250.
Texto completo da fonteLanguage recognition is the task of predicting the language used in a test speech utterance. Since 2017, the best performing systems have been based on a deep neural network which is trained to predict language labels for the whole utterance. These systems suffer from a drop in performance when they are exposed to a change of the transmission channel between train and test data. The goal of this thesis is to investigate approaches to limit this performance drop, for these new systems.An increase in the invariance, with respect to the transmission channel, of the representations used by the neural network can increase the robustness of the system. We show that the regularization of the loss function used to train the neural network is an efficient approach to increase invariance. Two kinds of regularization functions are analysed. Divergence measures between domains reduce effectively the variability between known domains, they can also be used to incorporate unlabeled data into the training set in a semi-supervised learning framework. Metric learning cost functions are able to reduce unknown variabilities within the training set. We show how this regularization method can be enforced for three practical learning settings: unsupervised domain adaptation, multi-domain learning and domain generalization.During this work, we have designed methods for analyzing the quality of the representations. They aim at evaluating the variability of the representations induced by the transmission channel and to compare it to the variability that caused the language. Two tools are proposed: ratio between inter class and intra class covariance matrices and divergence measures between groups of representations. With these tools, we quantitatively evaluate the robustness to a change of transmission channel of the representations and analyse the effect of the regularization functions over the space of representations. We understand that an increase in invariance between channels can lead to more discriminative representations between languages and consequently to an increase in performance over each transmission channel.Finally, we contribute to the improvement of the training recipe of another module of the system, the bottleneck feature extractor. We replace it with a multilingual end-to-end automatic speech recognition neural network. It achieves a simiar performance as a traditional bottleneck feature extractor with a simplified training recipe. The use of data augmentation and regularization methods improves further this module. Moreover we show that a performance gain can be achieved with a joint training of the bottleneck feature extractor along with the language identification neural network. This paves the way to the application of the proposed regularization loss functions to the two modules jointly
Mokrane, Abdenour. "Représentation de collections de documents textuels : application à la caractérisation thématique". Montpellier 2, 2006. http://www.theses.fr/2006MON20162.
Texto completo da fonteWagner, Frédéric. "Redistribution de données à travers un réseau à haut débit". Phd thesis, Université Henri Poincaré - Nancy I, 2005. http://tel.archives-ouvertes.fr/tel-00011705.
Texto completo da fonterégulièrement des données. Un tel échange s'effectue par une redistribution de données. Nous étudions comment effectuer une telle redistribution le plus efficacement possible en minimisant temps de communication et congestion du réseau.
Nous utilisons pour ce faire, une modélisation du problème à l'aide de graphes bipartis. Le modèle choisi permet une prise en compte du délai d'initialisation des communications, des différentes bandes passantes et impose une limite d'une communication simultanée par interface réseau (modèle 1-port) et de k communications simultanées sur la dorsale.
Nous effectuons une validation expérimentale du modèle puis l'utilisons pour développer deux algorithmes d'ordonnancement
des communications. Nous montrons que chacun d'entre eux
est un algorithme d'approximation garantissant un temps d'exécution dans le pire des cas 8/3 fois plus élevé que le temps optimal.
Nous concluons l'étude de ces algorithmes par une série d'expériences démontrant de bonnes performances en pratique.
Enfin, nous étendons le problème initial au cas de grappes hétérogènes :
ce cas imposant de sortir du modèle 1-port, nous montrons comment modifier nos algorithmes pour en tirer parti.
Nous étudions également le cas de redistributions exécutées en régime permanent sur un réseau d'une topologie plus complexe autorisant les communications locales.
El, Zoghby Nicole. "Fusion distribuée de données échangées dans un réseau de véhicules". Phd thesis, Université de Technologie de Compiègne, 2014. http://tel.archives-ouvertes.fr/tel-01070896.
Texto completo da fonteKhraibani, Hussein. "Modélisation statistique de données longitudinales sur un réseau routier entretenu". Ecole centrale de Nantes, 2010. http://www.theses.fr/2010ECDN0040.
Texto completo da fonteRoad transportation has a direct impact on a country's economy. Infrastructures, particularly pavements, deteriorate under the effect of traffic and climate. As a result, they most constantly undergo maintenance which often requires expensive works. The optimization of maintenance strategies and the scheduling of works necessarily pass by a study that makes use of deterioration evolution laws and accounts for the effect of maintenance on these laws. In this respect, numerous theoretical and experimental works ranging linear and nonlinear regressions to more sophisticated methods such as Markov chain have been conducted. The thesis presents a survey of models and methods and focuses on the analysis of survival data (MADS), an analysis which constituted the objective of important works at LCPC. In order to acount for the fact that current databases contain repeated measurements of each pavement section, the thesis proposes a different approach based on the use of nonlinear mixed-effects models (NLME). First, it carries out a comparison between the NLME and MADS models on different databases in terms of the goodness of fit and prediction capability. The comparison then allows to draw conclusions about the applicability of the two models
Allani, Sabri. "Agrégation et dissémination de données dans un réseau véhiculaire VANET". Thesis, Pau, 2018. http://www.theses.fr/2018PAUU3013/document.
Texto completo da fonteSince the last decade, the emergence of affordable wireless devices in vehicle ad-hoc networks has been a key step towards improving road safety as well as transport efficiency. Informing vehicles about interesting safety and non-safety events is of key interest. Thus, the design of an efficient data dissemination protocol has been of paramount importance. A careful scrutiny of the pioneering vehicle-to-vehicle data dissemination approaches highlights that geocasting is the most feasible approach for VANET applications, more especially in safety applications, since safety events are of interest mainly to vehicles located within a specific area, commonly called ZOR or Zone Of Relevance, close to the event. Indeed, the most challenging issue in geocast protocols is the definition of the ZOR for a given event dissemination. In this thesis, our first contribution introduces a new geocast approach, called Data Dissemination Protocol based on Map Splitting(DPMS). The main thrust of DPMS consists of building the zones of relevance through the mining of correlations between vehicles’ trajectories and crossed regions. To do so, we rely on the Formal Concept Analysis (FCA), which is a method of extracting interesting clusters from relational data. The performed experiments show that DPMS outperforms its competitors in terms of effectiveness and efficiency. In another hand, some VANET applications, e.g., Traffic Information System (TIS), require data aggregation in order to inform vehicles about road traffic conditions, which leads to reduce traffic jams and consequently CO2 emission while increasing the user comfort. Therefore, the design of an efficient aggregation protocol that combines correlated traffic information like location, speed and direction known as Floating Car Data (FCD) is a challenging issue. In this thesis, we introduce a new TIS data aggregation protocol called Smart Directional Data Aggregation (SDDA) able to decrease the network overload while obtaining high accurate information on traffic conditions for large road sections. To this end, we introduce three levels of messages filtering: (i) filtering all FCD messages before the aggregation process based on vehicle directions and road speed limitations, (ii) integrating a suppression technique in the phase of information gathering in order to eliminate the duplicate data, and (iii) aggregating the filtered FCD data and then disseminating it to other vehicles. The performed experiments show that the SDDA outperforms existing approaches in terms of effectiveness and efficiency
Khoumeri, El-Hadi. "Représentation des données spatiales à différents niveaux d'abstraction : application à l'archéoastronomie". Phd thesis, Université Pascal Paoli, 2007. http://tel.archives-ouvertes.fr/tel-00188500.
Texto completo da fonteLes producteurs de cartes maintiennent de façon identique une base de donnée par gamme d'échelle sans aucune inter-relation. De ce fait, outre les problèmes classiques de la redondance des données, et l'impossibilité de la propagation des mises à jour, le contrôle des cohérences est rendu très difficile. Pour maintenir la cohérence et éviter les redondances, la solution idéale serait une base de donnée où l'information géométrique est saisie à l'échelle la plus précise, et toutes les visualisations à des échelles moins précises seraient dérivées automatiquement à travers des processus de généralisation cartographique. Malheureusement cette dérivation ne peut être complètement automatisée. Par conséquent, le stockage explicite de plusieurs représentations de la géométrie des objets (une par échelle) s'impose. Néanmoins plusieurs solutions ont été mises en oeuvre pour parer aux inconvénients induits, dont la mise en oeuvre d'une base de donnée multi-échelle : une base de données où toutes les représentations requises coexistent et sont inter-reliées.
Nous présentons les besoins et les problèmes rencontrés par les spécialistes en SHS, en particulier nous mettons en évidence les problèmes soulevés dans le cadre d'une utilisation des SIG pour l'archéoastronomie, puis nous présentons les approches de résolution des problèmes ainsi que la présentation des concepts de base utilisés pour résoudre les problèmes mis en évidence. Les concepts précédents sont traités dans le cadre d'une conception orientée objets (COO). L'approche COO de la multi-représentation est basé sur une modélisation objet en UML. La validation des concepts précédents, est présenté à travers un exemple concret.
L'approche est illustrée par la réalisation du prototype logiciel GIS-3A sous Visual Basic ce qui permet d'une part d'implémenter les différentes notions en utilisant une conception orientée objets et d'autre part de faciliter l'intégration des ces notions dans un SIG (Arcview).
Khoumeri, El-Hadi. "Représentation de données spatiales à différents niveaux d'abstraction : application à l'archéoastronomie". Corte, 2006. http://www.theses.fr/2006CORT3095.
Texto completo da fonteThe producers of maps maintain in an identical way a base of data by range of scale without any interrelationship. To maintain coherence and to avoid the redundancies, the ideal solution would be a base of data where geometrical information is seized on the most precise scale, and all visualizations on less precise scales would be derived automatically through processes of cartographic generalization. Unfortunately this derivation cannot be completely automated. Nevertheless several solutions were implemented to avoid the induced disadvantages, of which the implementation of a base of data multi-scale: a data base where all the necessary representations coexist and are interrelated. We present the needs and the problems encountered by the specialists in social sciences, in particular we highlight the problems raised within the framework of a use of the GIS for the archeaostronomy, and then we present the approaches of resolution of the problems as well as the presentation of the basic concepts used to solve the problems highlighted. The preceding concepts are treated in the framework of a object oriented design (OOD). Approach OOD of the multi-representation is based on a modelling object in UML. The validation of the preceding concepts is presented through a concrete example. The approach is illustrated by the realization of software prototype GIS-3A under Visual BASIC what makes it possible on the one hand to implement the various concepts by using a directed design objects and on the other hand to facilitate the integration of these concepts in a GIS
Daniel-Vatonne, Marie-Christine. "Les termes : un modèle de représentation et structuration de données symboliques". Montpellier 2, 1993. http://www.theses.fr/1993MON20031.
Texto completo da fonteRigaux, Philippe. "Interfaces visuelles et multi-représentation dans les bases de données spatiales". Paris, CNAM, 1995. http://www.theses.fr/1995CNAM0207.
Texto completo da fonteLerat, Nadine. "Représentation et traitement des valeurs nulles dans les bases de données". Paris 11, 1986. http://www.theses.fr/1986PA112383.
Texto completo da fonteThis thesis deals with the representation and treatment of two cases of information incompleteness in the field of databases: non applicable null values and null values representing unknown objects. In the first part, queries on a unique table containing non applicable nulls are translated into a set of queries on conventional multitables. In the second part, unknown null values are represented by Skolem constants and a method adapting to this context a "chase" algorithm allows evaluating queries when functional or inclusion dependencies are satisfied. Eventually, it is shown that these two types of null values can be taken into account simultaneously
Madani, Nacéra. "Etude de l'héritage des propriétés dans les réseaux sémantiques : Notion de réseau d'héritage légal". Paris 13, 1994. http://www.theses.fr/1994PA132016.
Texto completo da fonteEl, Zant Manal. "Contribution à une représentation spatio-temporelle des dépêches épidémiologiques". Aix-Marseille 2, 2008. http://www.theses.fr/2008AIX20666.
Texto completo da fonteA spatio-temporal representation of event structures is important for an automatic comprehension of disease outbreak reports. The dispersion of components in this type of reports makes it difficult to have such a representation. This work describes an automatic extraction of event structures representation of these texts. We built an information extraction system by using cascaded finite state transducers which allowed the realization of three tasks : the named entity recognition, the arguments annotation and representation and the event structure representation. We obtained with this method a recall between 74. 24% and 100% for the named entity recognition task and a recall between 97. 18% and 99. 54% for argument representation task. Thereafter, we contributed to a normalization task in anaphoric pronouns resolution and in some inferences resolution concerning disease causation, concerned person, spatial and temporal location. We obtained a precision between 70. 83% and 100% for anaphoric pronouns resolution. The evaluation of inferences rules resolutions consisted in finding some counterexamples in the corpora for evaluation
Kharrat, Ahmed. "Fouille de données spatio-temporelles appliquée aux trajectoires dans un réseau". Versailles-St Quentin en Yvelines, 2013. http://www.theses.fr/2013VERS0042.
Texto completo da fonteRecent years have seen the development of data mining techniques for many application areas in order to analyze large and complex data. At the same time, the increasing deployment of location-acquisition technologies such as GPS, leads to produce a large datasets of geolocation traces. In this thesis, we are interested in mining trajectories of moving objects, such as vehicles in the road network. We propose a method for discovering dense routes by clustering similar road sections according to both traffic and location in each time period. The traffic estimation is based on the collected spatio-temporal trajectories. We also propose a characterization approach of the temporal evolution of dense routes by a graph connecting dense routes over consecutive time periods. This graph is labelled by a degree of evolution. Our last proposal concerns the discovery of mobility patterns and using these patterns to define a new representation of generalised trajectories
Souty, Cécile. "Méthodes d'analyse de données de surveillance épidémiologique : application au réseau Sentinelles". Thesis, Paris 6, 2016. http://www.theses.fr/2016PA066183.
Texto completo da fonteDisease surveillance networks are usually based on a group of health professionals or institutions which monitor one or more diseases. These data providers report cases seen among their patients. The characteristics of these providers, their spatial distribution and their participation to the network cannot be controlled: they are not a random sample of health professionals. Representativeness must be considered in networks where collected information are not exhaustive. It ensures that the network could provide an accurate representation of the population affected by the disease. In this thesis, we are interested in estimation methods for data produced by a surveillance network based on voluntary participation. The different works are based on the experience of the French practice-based Sentinelles network.The Horvitz-Thompson estimator was used to reduce the bias of incidence estimates. Inclusion probabilities were based on the difference in activity of participating and non-participating general practitioners in surveillance. We also study the impact of the spatial sampling of professionals participating to a surveillance network. By a simulation study, we show that sample weights based on local medical density eliminates the temporal and spatial variations of the providers. We ultimately applied these adjustments to estimate influenza vaccine effectiveness using data provided by GPs participating to the French Sentinelles network.These works show the contribution of appropriate statistical methods for epidemiological data collected in primary care to accurately inform public health authorities
Royan, Jérôme. "Visualisation interactive de scènes urbaines vastes et complexes à travers un réseau". Rennes 1, 2005. http://www.theses.fr/2005REN1S013.
Texto completo da fonteOuellet, Etienne. "Représentation et manipulation de données de simulation dans un environnement virtuel immersif". Thesis, Université Laval, 2012. http://www.theses.ulaval.ca/2012/28502/28502.pdf.
Texto completo da fonteAbdessalem, Talel. "Approche des versions de base de données : représentation et interrogation des versions". Paris 9, 1997. https://portail.bu.dauphine.fr/fileviewer/index.php?doc=1997PA090024.
Texto completo da fonteCori, Marcel. "Modèles pour la représentation et l'interrogation de données textuelles et de connaissances". Paris 7, 1987. http://www.theses.fr/1987PA077047.
Texto completo da fonteChihab, Najat. "Représentation des données irrégulièrement espacées par des fonctions B-splines non-uniformes". Paris 13, 2005. http://www.theses.fr/2005PA132043.
Texto completo da fonteClaramunt, Christophe. "Un modèle de vue spatiale pour une représentation flexible de données géographiques". Dijon, 1998. https://hal.archives-ouvertes.fr/tel-01275819.
Texto completo da fonteCourtine, Mélanie. "Changements de représentation pour la classification conceptuelle non supervisée de données complexes". Paris 6, 2002. http://www.theses.fr/2002PA066404.
Texto completo da fonteAldea, Emanuel. "Apprentissage de données structurées pour l'interprétation d'images". Paris, Télécom ParisTech, 2009. http://www.theses.fr/2009ENST0053.
Texto completo da fonteImage interpretation methods use primarily the visual features of low-level or high-level interest elements. However, spatial information concerning the relative positioning of these elements is equally beneficial, as it has been shown previously in segmentation and structure recognition. Fuzzy representations permit to assess at the same time the imprecision degree of a relation and the gradual transition between the satisfiability and the non-satisfiability of a relation. The objective of this work is to explore techniques of spatial information representation and their integration in the learning process, within the context of image classifiers that make use of graph kernels. We motivate our choice of labeled graphs for representing images, in the context of learning with SVM classifiers. Graph kernels have been studied intensively in computational chemistry and biology, but an adaptation for image related graphs is necessary, since image structures and properties of the information encoded in the labeling are fundamentally different. We illustrate the integration of spatial information within the graphical model by considering fuzzy adjacency measures between interest elements, and we define a family of graph representations determined by different thresholds applied to these spatial measures. Finally, we employ multiple kernel learning in order to build up classifiers that can take into account different graphical representations of the same image at once. Results show that spatial information complements the visual features of distinctive elements in images and that adapting the discriminative kernel functions for the fuzzy spatial representations is beneficial in terms of performance
Meddeb, Hamrouni Boubaker. "Méthodes et algorithmes de représentation et de compression de grands dictionnaires de formes". Université Joseph Fourier (Grenoble), 1996. http://www.theses.fr/1996GRE10278.
Texto completo da fonte