Дисертації з теми "Analyse exploratoire de données multivariées"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-36 дисертацій для дослідження на тему "Analyse exploratoire de données multivariées".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте дисертації для різних дисциплін та оформлюйте правильно вашу бібліографію.
Verbanck, Marie. "Analyse exploratoire de données transcriptomiques : de leur visualisation à l'intégration d’information extérieure." Rennes, Agrocampus Ouest, 2013. http://www.theses.fr/2013NSARG011.
Повний текст джерелаWe propose new methodologies of exploratory statistics which are dedicated to the analysis of transcriptomic data (DNA microarray data). Transcriptomic data provide an image of the transcriptome which itself is the result of phenomena of activation or inhibition of gene expression. However, the image of the transcriptome is noisy. That is why, firstly we focus on the issue of transcriptomic data denoising, in a visualisation framework. To do so, we propose a regularised version of principal component analysis. This regularised version allows to better estimate and visualise the underlying signal of noisy data. In addition, we can wonder if the knowledge of only the transcriptome is enough to understand the complexity of relationships between genes. That is why we propose to integrate other sources of information about genes, and in an active way, in the analysis of transcriptomic data. Two major mechanisms seem to be involved in the regulation of gene expression, regulatory proteins (for instance transcription factors) and regulatory networks on the one hand, chromosomal localisation and genome architecture on the other hand. Firstly, we focus on the regulation of gene expression by regulatory proteins; we propose a gene clustering algorithm based on the integration of functional knowledge about genes, which is provided by Gene Ontology annotations. This algorithm provides clusters constituted by genes which have both similar expression profiles and similar functional annotations. The clusters thus constituted are then better candidates for interpretation. Secondly, we propose to link the study of transcriptomic data to chromosomal localisation in a methodology developed in collaboration with geneticists
Béranger, Boris. "Modélisation de la structure de dépendance d'extrêmes multivariés et spatiaux." Thesis, Paris 6, 2016. http://www.theses.fr/2016PA066004/document.
Повний текст джерелаProjection of future extreme events is a major issue in a large number of areas including the environment and risk management. Although univariate extreme value theory is well understood, there is an increase in complexity when trying to understand the joint extreme behavior between two or more variables. Particular interest is given to events that are spatial by nature and which define the context of infinite dimensions. Under the assumption that events correspond marginally to univariate extremes, the main focus is then on the dependence structure that links them. First, we provide a review of parametric dependence models in the multivariate framework and illustrate different estimation strategies. The spatial extension of multivariate extremes is introduced through max-stable processes. We derive the finite-dimensional distribution of the widely used Brown-Resnick model which permits inference via full and composite likelihood methods. We then use Skew-symmetric distributions to develop a spectral representation of a wider max-stable model: the extremal Skew-t model from which most models available in the literature can be recovered. This model has the nice advantages of exhibiting skewness and nonstationarity, two properties often held by environmental spatial events. The latter enables a larger spectrum of dependence structures. Indicators of extremal dependence can be calculated using its finite-dimensional distribution. Finally, we introduce a kernel based non-parametric estimation procedure for univariate and multivariate tail density and apply it for model selection. Our method is illustrated by the example of selection of physical climate models
Lazar, Cosmin. "Méthodes non supervisées pour l’analyse des données multivariées." Reims, 2008. http://theses.univ-reims.fr/exl-doc/GED00000846.pdf.
Повний текст джерелаMany scientific disciplines deal with multivariate data. Different recordings of the same phenomenon are usually embedded in a multivariate data set. Multivariate data analysis gathers efficient tools for extracting relevant information in order to comprehend the phenomenon in study. Gathering data into groups or classes according to some similarity criteria is an essential step in the analysis. Intrinsic dimension or dimension reduction of multivariate data, the choice of the similarity criterion, cluster validation are problems which still let open questions. This work tries to make a step further concerning two of the problems mentioned above: the choice of the similarity measure for data clustering and the dimension reduction of multivariate data. The choice of the similarity measure for data clustering is investigated from the concentration phenomenon of metrics point of view. Non Euclidean metrics are tested as alternative to the classical Euclidian distance as similarity measure. We tested if less concentrated metrics are more discriminative for multivariate data clustering. We also proposed indices which take into account the inter-classes distance (e. G. Davies-Bouldin index) in order to find the optimal metric when the classes are supposed to be Gaussian. Blind Source Separation (BSS) methods are also investigated for dimension reduction of multivariate data. A BSS method based on a geometrical interpretation of the linear mixing model is proposed. BSS methods which take into account application constraints are used for dimension reduction in two different applications of multivariate imaging. These methods allow the extraction of meaningful factors from the whole data set; they also allow reducing the complexity and the computing time of the clustering algorithms which are used further in analysis. Applications on multivariate image analysis are also presented
Mnassri, Baligh. "Analyse de données multivariées et surveillance des processus industriels par analyse en composantes principales." Phd thesis, Aix-Marseille Université, 2012. http://tel.archives-ouvertes.fr/tel-00749282.
Повний текст джерелаDans l'objectif d'un choix optimal du modèle ACP, une étude comparative de quelques critères connus dans la littérature nous a permis de conclure que le problème rencontré est souvent lié à une ignorance des variables indépendantes et quasi-indépendantes. Dans ce cadre, nous avons réalisé deux démonstrations mettant en évidence les limitations de deux critères en particulier la variance non reconstruite (VNR). En s'appuyant sur le principe d'une telle variance, nous avons proposé trois nouveaux critères. Parmi eux, deux ont été considérés comme étant empiriques car seule l'expérience permettra de prouver leur efficacité. Le troisième critère noté VNRVI représente un remède à la limitation du critère VNR. Une étude de sa consistance théorique a permis d'établir les conditions garantissant l'optimalité de son choix. Les résultats de simulation ont validé une telle théorie en prouvant ainsi que le critère VNRVI étant plus efficace que ceux étudiés dans cette thèse.
Dans le cadre d'un diagnostic de défauts par ACP, l'approche de reconstruction des indices de détection ainsi que celle des contributions ont été utilisées. A travers une étude de généralisation, nous avons étendu le concept d'isolabilité de défauts par reconstruction à tout indice quadratique. Une telle généralisation nous a permis d'élaborer une analyse théorique d'isolabilité de défauts par reconstruction de la distance combinée versus celles des indices SPE et T2 de Hotelling en mettant en avant l'avantage de l'utilisation d'une telle distance. D'autre part, nous avons proposé une nouvelle méthode de contribution par décomposition partielle de l'indice SPE. Cette approche garantit un diagnostic correct de défauts simples ayant de grandes amplitudes. Nous avons également étendu une méthode de contribution classiquement connue par la RBC au cas multidimensionnel. Ainsi, la nouvelle forme garantit un diagnostic correct de défauts multiples de grandes amplitudes. En considérant la complexité de défauts, nous avons exploité la nouvelle approche de contribution RBC afin de proposer une nouvelle qui s'appelle RBCr. Cette dernière s'appuie sur un seuil de tolérance pour l'isolation de défauts. Une analyse de diagnosticabilité basée sur la RBCr montre que celle-ci garantit l'identification des défauts détectables. Ces derniers sont garantis isolables si leurs amplitudes satisfont les mêmes conditions d'isolabilité établies pour l'approche de reconstruction des indices.
Pialot, Daniel Paul Marc. "Analyse des données de milieu en hydrobiologie : apport des techniques d'analyse multivariées." Lyon 1, 1985. http://www.theses.fr/1985LYO11680.
Повний текст джерелаLe, Floch Edith. "Méthodes multivariées pour l'analyse jointe de données de neuroimagerie et de génétique." Phd thesis, Université Paris Sud - Paris XI, 2012. http://tel.archives-ouvertes.fr/tel-00753829.
Повний текст джерелаLe, floch Edith. "Méthodes multivariées pour l'analyse jointe de données de neuroimagerie et de génétique." Thesis, Paris 11, 2012. http://www.theses.fr/2012PA112214/document.
Повний текст джерелаBrain imaging is increasingly recognised as an interesting intermediate phenotype to understand the complex path between genetics and behavioural or clinical phenotypes. In this context, a first goal is to propose methods to identify the part of genetic variability that explains some neuroimaging variability. Classical univariate approaches often ignore the potential joint effects that may exist between genes or the potential covariations between brain regions. Our first contribution is to improve the sensitivity of the univariate approach by taking advantage of the multivariate nature of the genetic data in a local way. Indeed, we adapt cluster-inference techniques from neuroimaging to Single Nucleotide Polymorphism (SNP) data, by looking for 1D clusters of adjacent SNPs associated with the same imaging phenotype. Then, we push further the concept of clusters and we combined voxel clusters and SNP clusters, by using a simple 4D cluster test that detects conjointly brain and genome regions with high associations. We obtain promising preliminary results on both simulated and real datasets .Our second contribution is to investigate exploratory multivariate methods to increase the detection power of imaging genetics studies, by accounting for the potential multivariate nature of the associations, at a longer range, on both the imaging and the genetics sides. Recently, Partial Least Squares (PLS) regression or Canonical Correlation Analysis (CCA) have been proposed to analyse genetic and transcriptomic data. Here, we propose to transpose this idea to the genetics vs. imaging context. Moreover, we investigate the use of different strategies of regularisation and dimension reduction techniques combined with PLS or CCA, to face the overfitting issues due to the very high dimensionality of the data. We propose a comparison study of the different strategies on both a simulated dataset and a real fMRI and SNP dataset. Univariate selection appears to be necessary to reduce the dimensionality. However, the generalisable and significant association uncovered on the real dataset by the two-step approach combining univariate filtering and L1-regularised PLS suggests that discovering meaningful imaging genetics associations calls for a multivariate approach
Rigouste, Loïs. "Méthodes probabilistes pour l'analyse exploratoire de données textuelles." Phd thesis, Télécom ParisTech, 2006. http://pastel.archives-ouvertes.fr/pastel-00002424.
Повний текст джерелаBry, Xavier. "Une méthodologie exploratoire pour l'analyse et la synthèse d'un modèle explicatif : l'Analyse en Composantes Thématiques." Paris 9, 2004. https://portail.bu.dauphine.fr/fileviewer/index.php?doc=2004PA090055.
Повний текст джерелаGhalamallah, Ilhème. "Proposition d'un modèle d'analyse exploratoire multidimensionnelle dans un contexte d'intelligence économique." Toulouse 3, 2009. http://www.theses.fr/2009TOU30293.
Повний текст джерелаA successful business is often conditioned by its ability to identify, collect, process and disseminate information for strategic purposes. Moreover, information technology and knowledge provide constraints that companies must adapt : a continuous stream, a circulation much faster techniques increasingly complex. The risk of being swamped by this information and no longer able to distinguish the essential from the trivial. Indeed, with the advent of new economy dominated by the market, the problem of industrial and commercial enterprise is become very complex. Now, to be competitive, the company must know how to manage their intangible capital. Competitive Intelligence (CI) is a response to the upheavals of the overall business environment and more broadly to any organization. In an economy where everything moves faster and more complex, management Strategic Information has become a key driver of overall business performance. CI is a process and an organizational process that can be more competitive, by monitoring its environment and its dynamics. In this context, we found that much information has strategic significance to the relationship: links between actors in the field, semantic networks, alliances, mergers, acquisitions, collaborations, co-occurrences of all kinds. Our work consists in proposing a model of multivariate analysis dedicated to the IE. This approach is based on the extraction of knowledge by analyzing the evolution of relational databases. We offer a model for understanding the activity of actors in a given field, but also their interactions their development and strategy, this decision in perspective. This approach is based on the designing a system of generic information online analysis to homogenize and organize text data in relational form, and thence to extract implicit knowledge of the content and formatting are adapted to non-specialist decision makers in the field of knowledge extraction
Perrot-Dockès, Marie. "Méthodes régularisées pour l’analyse de données multivariées en grande dimension : théorie et applications." Thesis, Université Paris-Saclay (ComUE), 2019. http://www.theses.fr/2019SACLS304/document.
Повний текст джерелаIn this PhD thesis we study general linear model (multivariate linearmodel) in high dimensional settings. We propose a novel variable selection approach in the framework of multivariate linear models taking into account the dependence that may exist between the responses. It consists in estimating beforehand the covariance matrix of the responses and to plug this estimator in a Lasso criterion, in order to obtain a sparse estimator of the coefficient matrix. The properties of our approach are investigated both from a theoretical and a numerical point of view. More precisely, we give general conditions that the estimators of the covariance matrix and its inverse have to satisfy in order to recover the positions of the zero and non-zero entries of the coefficient matrix when the number of responses is not fixed and can tend to infinity. We also propose novel, efficient and fully data-driven approaches for estimating Toeplitz and large block structured sparse covariance matrices in the case where the number of variables is much larger than the number of samples without limiting ourselves to block diagonal matrices. These approaches are appliedto different biological issues in metabolomics, in proteomics and in immunology
Guigourès, Romain. "Utilisation des modèles de co-clustering pour l'analyse exploratoire des données." Phd thesis, Université Panthéon-Sorbonne - Paris I, 2013. http://tel.archives-ouvertes.fr/tel-00935278.
Повний текст джерелаPagliarecci, Nico. "On the understanding of the vehicle-driver interaction using the objectification of subjective assessment : application to the tire development process." Thesis, Mulhouse, 2020. http://www.theses.fr/2020MULH4104.
Повний текст джерелаThe tire is heavily involved in the performance of a vehicle. Vehicle's fuel consumption (rolling resistance, aerodynamics), noise, comfort, handling and safety are related to the tire chosen. By using objective measurements, it is possible to predict some of those features but for some others like handling we cannot really predict the subjective evaluation made by experienced test drivers. Trial/error methodology is sometimes applied to identify tire potential and to gauge the tire performance related to specific designs and mechanical characteristics.Today, in the automotive industry, the evaluation of vehicle and tire handling performance is still largely performed on a subjective basis by experienced test drivers. This is justified by the fact that customer perception of vehicle performance is also made subjectively and, no reliable relationship has been found to relate objective performance measures to the human perception of performance.An extensive literature review on the objectification of subjective assessment, the vehicle-driver interaction, the vehicle dynamics simulation and the explorative multivariate data analysis as well as statistical hypothesis testing is the first research step aimed to investigate the methodologies, the data analytics and statistical tools used by other researchers.Based on the literature review, the thesis proposes a methodology that allows to translate subjective evaluations into objective metrics (vehicle environment as well as vehicle-tire environment) enabling the prediction of the outcome of a subjective test by using objective measurements leading to a reduction of the iterations during the tire development process. The choice of the most relevant vehicle dynamics model’s complexity depicts the main tire mechanical features affecting the handling performance and their effect on the objective metrics of interest. Specific experimental vehicle dynamics maneuvers have been selected for this study with the aim of unpacking the complexity of the subjective handling assessment without being simplistic and paying attention to interconnectedness of the different variables and their interplay with contextual factors.In the frame of the above-mentioned correlation study, the role of the driver in the driver-vehicle system is investigated. The results presented show that, with the chosen methodology, it is possible to gain insights on the driver’s testing strategy identifying the main vehicle responses affecting all the stages of the subjective evaluation. To deepen and strengthen the understanding of the driver’s role, two panel studies involving professional and non-professional drivers have been carried out. Those allowed the study and analysis of the vehicle-driver interaction in terms of proprioception and vision, audio-visual influences and aftereffects in motion
Guigourès, Romain. "Utilisation des modèles de co-clustering pour l'analyse exploratoire des données." Thesis, Paris 1, 2013. http://www.theses.fr/2013PA010070.
Повний текст джерелаCo-clustering is a clustering technique aiming at simultaneously partitioning the rows and the columns of a data matrix. Among the existing approaches, MODL is suitable for processing huge data sets with several continuous or categorical variables. We use it as the baseline approach in this thesis. We discuss the reliability of applying such an approach on data mining problems like graphs partitioning, temporal graphs segmentation or curve clustering.MODL tracks very fine patterns in huge data sets, that makes the results difficult to study. That is why, exploratory analysis tools must be defined in order to explore them. In order to help the user in interpreting the results, we define exploratory analysis tools aiming at simplifying the results in order to make possible an overall interpretation, tracking the most interesting patterns, determining the most representative values of the clusters and visualizing the results. We investigate the asymptotic behavior of these exploratory analysis tools in order to make the connection with the existing approaches.Finally, we highlight the value of MODL and the exploratory analysis tools owing to an application on call detailed records from the telecom operator Orange, collected in Ivory Coast
Truong, Thérèse Quy Thy. "Le vandalisme de l’information géographique volontaire : analyse exploratoire et proposition d’une méthodologie de détection automatique." Thesis, Paris Est, 2020. http://www.theses.fr/2020PESC2009.
Повний текст джерелаThe quality of Volunteered Geographic Information (VGI) is currently a topic that question spatial data users as well as authoritative data producers who are willing to exploit the benefits of crowdsourcing. Contrary to most authoritative databases, the advantage of VGI provides open access to spatial data. However, VGI is prone to errors, even to deliberate defacement perpetrated by ill-intended contributors. In the latter case, we may speak of cartographic vandalism of carto-vandalism. This phenomenon is one the main downsides of crowsdsourcing, and despite the small amount of incidents, it may be a barrier to the use of collaborative spatial data. This thesis follows an approach based on VGI quality -- in particular, the objective of this work is to detect vandalism in spatial collaborative data. First, we formalize a definition of the concept of carto-vandalism. Then, assuming that corrupted spatial data come from malicious contributors, we demonstate that qualifying contributors enables to assess the corresponding contributed data. Finally, the experiments explore the ability of learning methods to detect carto-vandalism
Heymann, Sébastien. "Analyse exploratoire de flots de liens pour la détection d'événements." Phd thesis, Université Pierre et Marie Curie - Paris VI, 2013. http://tel.archives-ouvertes.fr/tel-00994766.
Повний текст джерелаSchmutz, Amandine. "Contributions à l'analyse de données fonctionnelles multivariées, application à l'étude de la locomotion du cheval de sport." Thesis, Lyon, 2019. http://www.theses.fr/2019LYSE1241.
Повний текст джерелаWith the growth of smart devices market to provide athletes and trainers a systematic, objective and reliable follow-up, more and more parameters are monitored for a same individual. An alternative to laboratory evaluation methods is the use of inertial sensors which allow following the performance without hindering it, without space limits and without tedious initialization procedures. Data collected by those sensors can be classified as multivariate functional data: some quantitative entities evolving along time and collected simultaneously for a same individual. The aim of this thesis is to find parameters for analysing the athlete horse locomotion thanks to a sensor put in the saddle. This connected device (inertial sensor, IMU) for equestrian sports allows the collection of acceleration and angular velocity along time in the three space directions and with a sampling frequency of 100 Hz. The database used for model development is made of 3221 canter strides from 58 ridden jumping horses of different age and level of competition. Two different protocols are used to collect data: one for straight path and one for curved path. We restricted our work to the prediction of three parameters: the speed per stride, the stride length and the jump quality. To meet the first to objectives, we developed a multivariate functional clustering method that allow the division of the database into smaller more homogeneous sub-groups from the collected signals point of view. This method allows the characterization of each group by it average profile, which ease the data understanding and interpretation. But surprisingly, this clustering model did not improve the results of speed prediction, Support Vector Machine (SVM) is the model with the lowest percentage of error above 0.6 m/s. The same applied for the stride length where an accuracy of 20 cm is reached thanks to SVM model. Those results can be explained by the fact that our database is build from 58 horses only, which is a quite low number of individuals for a clustering method. Then we extend this method to the co-clustering of multivariate functional data in order to ease the datamining of horses’ follow-up databases. This method might allow the detection and prevention of locomotor disturbances, main source of interruption of jumping horses. Lastly, we looked for correlation between jumping quality and signals collected by the IMU. First results show that signals collected by the saddle alone are not sufficient to differentiate finely the jumping quality. Additional information will be needed, for example using complementary sensors or by expanding the database to have a more diverse range of horses and jump profiles
Vrac, Mathieu. "Analyse et modélisation de données probabilistes par décomposition de mélange de copules et application à une base de données climatologiques." Phd thesis, Université Paris Dauphine - Paris IX, 2002. http://tel.archives-ouvertes.fr/tel-00002386.
Повний текст джерелаMoudden, Yassir. "Estimation de paramètres physiques de combustion par modélisation du signal d'ionisation et inversion paramétrique." Paris 11, 2003. http://www.theses.fr/2003PA112004.
Повний текст джерелаThe work described in this thesis investigates the possibility of constructing an indirect measurement algorithm of relevant combustion parameters based on ionization signal processing. Indeed, automobile manufacturers are in need of low cost combustion diagnoses to enhance engine control. Because of the extreme complexity of the physical phenomena in which the ionization signal originates, the traditional model-based approach appeared unrealistic and did not bring about conclusive results. We hence turned to performing a blind statistical analysis of experimental data acquired on a test engine. The analysis of high dimensional data being notoriously awkward, it is necessary to first reduce the apparent dimension of the signal data, keeping in mind the necessity of preserving the information useful in terms of our estimation problem. The usual techniques such as Principal Component Analysis, Projection Pursuit, etc. Are used to form and detect relevant variables. Further, a procedure for high dimensional data analysis derived as an extension of Exploratory Projection Pursuit, is suggested and shown to be a profitable tool. With this method, we seek interesting projections of high dimensional data by optimizing probabilistic measures of dependence such as Mutual Information, Hellinger divergence, etc. Finally, results are presented that demonstrate the quality and the stability of the low complexity in-cylinder peak pressure position estimators we derived, for a wide range of engine states
Kherif, Ferath. "Applications de modèles statistiques multivariés à la résolution de problèmes posés par les données d' imagerie fonctionnelle cérébrale." Paris 6, 2003. http://www.theses.fr/2003PA066598.
Повний текст джерелаPfaender, Fabien. "Spatialisation de l'information." Compiègne, 2009. http://www.theses.fr/2009COMP1813.
Повний текст джерелаThe goal of this work is to understand how information presentations affect cognition so as to use them efficiently to mine date, synthesize information and explorer large heterogeneous datasets. We chose an enactive approach as a conceptual framework to understand how informations are perceived and how the way they are presented affects and transform us. In enaction, the world as perceived by a subject is the result of a dynamic coupling between the organism and its environment. Perception itself emerges from the coupling between subject’s actions and its sensations. Following these principles, we proposed that lines are a perceptive support for actions of reading that lead to complex perceptive gestures. Those gestures are the basis of what we called primary structures which exist in every presentation of informations. The structures are analyzed in terms of constraints and liberties they offer both for global gesture support and for local gesture variations. The five structures identified are the list, the diagram, the array, the graph of nodes and edges and the map. Primary structures themselves can also be combined into secondary structures. Thus, knowing how primary and secondary structure are perceived, it becomes possible to understand perceptive and cognitive effect of all spatialization of informations. Finally, given the semiological principles we discovered, we were able to come up with a systematic and spatialization-based metho to explore complex systems and reveal their structure. The method and the semiology have been integrated and tested in a web exploration software we developed for the occasion
Komaty, Ali. "Traitement et analyse des processus stochastiques par EMD et ses extensions." Thesis, Brest, 2014. http://www.theses.fr/2014BRES0107.
Повний текст джерелаThe main contribution of this thesis is aimed towards understanding the behaviour of the empirical modes decomposition (EMD) and its extended versions in stochastic situations
Paillé, Pierre. "Les études sur la paix dans les collèges et universités : une analyse des données, des débats et des courants, avec survol exploratoire de la situation au Québec." Mémoire, Université de Sherbrooke, 1988. http://hdl.handle.net/11143/9209.
Повний текст джерелаLoubier, Eloïse. "Analyse et visualisation de données relationnelles par morphing de graphe prenant en compte la dimension temporelle." Phd thesis, Université Paul Sabatier - Toulouse III, 2009. http://tel.archives-ouvertes.fr/tel-00423655.
Повний текст джерелаNos travaux conduisent à l'élaboration des techniques graphiques permettant la compréhension des activités humaines, de leurs interactions mais aussi de leur évolution, dans une perspective décisionnelle. Nous concevons un outil alliant simplicité d'utilisation et précision d'analyse se basant sur deux types de visualisations complémentaires : statique et dynamique.
L'aspect statique de notre modèle de visualisation repose sur un espace de représentation, dans lequel les préceptes de la théorie des graphes sont appliqués. Le recours à des sémiologies spécifiques telles que le choix de formes de représentation, de granularité, de couleurs significatives permet une visualisation plus juste et plus précise de l'ensemble des données. L'utilisateur étant au cœur de nos préoccupations, notre contribution repose sur l'apport de fonctionnalités spécifiques, qui favorisent l'identification et l'analyse détaillée de structures de graphes. Nous proposons des algorithmes qui permettent de cibler le rôle des données au sein de la structure, d'analyser leur voisinage, tels que le filtrage, le k-core, la transitivité, de retourner aux documents sources, de partitionner le graphe ou de se focaliser sur ses spécificités structurelles.
Une caractéristique majeure des données stratégiques est leur forte évolutivité. Or l'analyse statistique ne permet pas toujours d'étudier cette composante, d'anticiper les risques encourus, d'identifier l'origine d'une tendance, d'observer les acteurs ou termes ayant un rôle décisif au cœur de structures évolutives.
Le point majeur de notre contribution pour les graphes dynamiques représentant des données à la fois relationnelles et temporelles, est le morphing de graphe. L'objectif est de faire ressortir les tendances significatives en se basant sur la représentation, dans un premier temps, d'un graphe global toutes périodes confondues puis en réalisant une animation entre les visualisations successives des graphes attachés à chaque période. Ce procédé permet d'identifier des structures ou des événements, de les situer temporellement et d'en faire une lecture prédictive.
Ainsi notre contribution permet la représentation des informations, et plus particulièrement l'identification, l'analyse et la restitution des structures stratégiques sous jacentes qui relient entre eux et à des moments donnés les acteurs d'un domaine, les mots-clés et concepts qu'ils utilisent.
Combrexelle, Sébastien. "Multifractal analysis for multivariate data with application to remote sensing." Phd thesis, Toulouse, INPT, 2016. http://oatao.univ-toulouse.fr/16477/1/Combrexelle.pdf.
Повний текст джерелаLoubier, Éloïse. "Analyse et visualisation de données relationnelles par morphing de graphe prenant en compte la dimension temporelle." Toulouse 3, 2009. http://thesesups.ups-tlse.fr/2264/.
Повний текст джерелаWith word wide exchanges, companies must face increasingly strong competition and masses of information flows. They have to remain continuously informed about innovations, competition strategies and markets and at the same time they have to keep the control of their environment. The Internet development and globalization reinforced this requirement and on the other hand provided means to collect information. Once summarized and synthesized, information generally is under a relational form. To analyze such a data, graph visualization brings a relevant mean to users to interpret a form of knowledge which would have been difficult to understand otherwise. The research we have carried out results in designing graphical techniques that allow understanding human activities, their interactions but also their evolution, from the decisional point of view. We also designed a tool that combines ease of use and analysis precision. It is based on two types of complementary visualizations: statics and dynamics. The static aspect of our visualization model rests on a representation space in which the precepts of the graph theory are applied. Specific semiologies such as the choice of representation forms, granularity, and significant colors allow better and precise visualizations of the data set. The user being a core component of our model, our work rests on the specification of new types of functionalities, which support the detection and the analysis of graph structures. We propose algorithms which make it possible to target the role of the data within the structure, to analyze their environment, such as the filtering tool, the k-core, and the transitivity, to go back to the documents, and to give focus on the structural specificities. One of the main characteristics of strategic data is their strong evolution. However the statistical analysis does not make it possible to study this component, to anticipate the incurred risks, to identify the origin of a trend, and to observe the actors or terms having a decisive role in the evolution structures. With regard to dynamic graphs, our major contribution is to represent relational and temporal data at the same time; which is called graph morphing. The objective is to emphasize the significant tendencies considering the representation of a graph that includes all the periods and then by carrying out an animation between successive visualizations of the graphs attached to each period. This process makes it possible to identify structures or events, to locate them temporally, and to make a predictive reading of it. Thus our contribution allows the representation of advanced information and more precisely the identification, the analysis, and the restitution of the underlying strategic structures which connect the actors of a domain, the key words, and the concepts they use; this considering the evolution feature
Boiret, Mathieu. "Towards chemometric methodologies on hyperspectral imaging for low dose compound detection : application on Raman microscopy." Thesis, Montpellier, 2015. http://www.theses.fr/2015MONTS291.
Повний текст джерелаHyperspectral imaging is now considered as a powerful analytical tool in the pharmaceutical environment, both during development to ensure the drug product quality and to solve production issues on commercialized products.In this thesis, Raman microscopy is used to study the distribution of actives and excipients in a pharmaceutical drug product, by especially focusing on the identification of a low dose compound. This latter product is defined as a compound which has low spatial and spectra contributions, meaning that it is scattered in a few pixels of the image and that its spectral response is mixed with the other compounds of the formulation. While most chemometric tools are based on the decomposition of statistical moments (requiring sufficient variations between samples or image pixels), some limitations have been rapidly reached. The first part of this thesis highlights the difficulty to detect a low dose compound in a product by using independent component analysis or multivariate curve resolution. Different methodologies are proposed to circumvent these limitations. For both techniques, reduction of dimensions and filtering steps appears as critical parameters of the method. The second part of the thesis focusses on the signal space to determine absence/presence compound maps or to detect the compounds in an unknown formulation. The proposed methods are only based on the spectral space of each formulation compound. There are perfectly suitable to a low dose compound and should be well-adapted to other analytical techniques or to other environments
Traore, Oumar Issiaka. "Méthodologie de traitement et d'analyse de signaux expérimentaux d'émission acoustique : application au comportement d'un élément combustible en situation accidentelle." Thesis, Aix-Marseille, 2018. http://www.theses.fr/2018AIXM0011/document.
Повний текст джерелаThe objective of the thesis is to contribute to the improvement of the monitoring process of nuclear safety experiments dedicated to study the behavior of the nuclear fuel in a reactivity initiated accident (RIA) context, by using the acoustic emission technique. In particular, we want to identify the physical mechanisms occurring during the experiments through their acoustic signatures. Firstly, analytical derivations and numerical simulations using the spectral finite element method have been performed in order to evaluate the impact of the wave travelpath in the test device on the recorded signals. A resonant frequency has been identified and it has been shown that the geometry and the configuration of the test device may not influence the wave propagation in the low frequency range. Secondly, signal processing methods (spectral subtraction, singular spectrum analysis, wavelets,…) have been explored in order to propose different denoising strategies according to the type of noise observed during the experiments. If we consider only the global SNR improvement ratio, the spectral subtraction method is the most robust to changes in the stochastic behavior of noise. Finally, classical multivariate and functional data analysis tools are used in order to create a machine learning algorithm dedicated to contribute to a better understanding of the phenomenology of RIA accidents. According to the method (multivariate or functional), the obtained algorithms allow to identify the mechanisms in more than 80 % of cases
Boulfani, Fériel. "Caractérisation du comportement de systèmes électriques aéronautiques à partir d'analyses statistiques." Thesis, Toulouse 1, 2021. http://publications.ut-capitole.fr/43780/.
Повний текст джерелаThe characterization of electrical systems is an essential task in aeronautic conception. It consists in particular of sizing the electrical components, defining maintenance frequency and finding the root cause of aircraft failures. Nowadays, the computations are made using electrical engineering theory and simulated physical models. The aim of this thesis is to use statistical approaches based on flight data and machine learning models to characterize the behavior of aeronautic electrical systems. In the first part, we estimate the maximal electrical consumption that the generator should deliver to optimize the generator size and to better understand its real margin. Using the extreme value theory we estimate quantiles that we compare to the theoretical values computed by the electrical engineers. In the second part, we compare different regularized procedures to predict the oil temperature of a generator in a functional data framework. In particular, this study makes it possible to understand the generator behavior under extreme conditions that could not be reproduced physically. Finally, in the last part, we develop a predictive maintenance model that detects the abnormal behavior of a generator to anticipate failures. This model is based on variants of "Invariant Coordinate Selection" adapted to functional data
Mahmoudysepehr, Mehdi. "Modélisation du comportement du tunnelier et impact sur son environnement." Thesis, Centrale Lille Institut, 2020. http://www.theses.fr/2020CLIL0028.
Повний текст джерелаThis PhD thesis research work consists in understanding the behavior of the TBM according to the environment encountered in order to propose safe, durable and quality solutions for the digging of the tunnel.The main objective of this doctoral thesis work is to better understand the behavior of the TBM according to its environment. Thus, we will explore how the TBM reacts according to the different types of terrain and how it acts on the various elements of tunnel structure (voussoirs). This will make it possible to propose an intelligent and optimal dimensioning of the voussoirs and instructions of adapted piloting
Irichabeau, Gabrielle. "Évaluation économique de la dépendance d'une activité au milieu naturel. L'exemple de l'ostréiculture arcachonnaise." Phd thesis, Université Montesquieu - Bordeaux IV, 2011. http://tel.archives-ouvertes.fr/tel-00662006.
Повний текст джерелаBorderon, Marion. "Entre distance géographique et distance sociale : le risque de paludisme-infection en milieu urbain africain : l'exemple de l'agglomération de Dakar, Sénégal." Thesis, Aix-Marseille, 2016. http://www.theses.fr/2016AIXM3004/document.
Повний текст джерелаThis thesis applies an Exploratory Spatial Data Analysis (ESDA) approach to study a complex phenomenon in a data scarce environment: malaria infection in Dakar. Each component of the malaria pathogenic system is necessary but not sufficient to result in an infection when acting in isolation. For malaria infection to occur, three components need to interact: the parasite, the vector, and the human host. The identification of areas where these three components can easily interact is therefore essential in the fight against malaria and the improvement of programs for the prevention and control or elimination of the disease. ESDA, still rarely applied in developing countries, is thus defined as a research approach but also as a way to provide answers to global health challenges. It leads to observation, from different angles, on the social and spatial determinants of malaria infection, as well as the examination of existing interactions between its three components. Several streams of quantitative information were collected, both directly and indirectly related to the study of malaria. More specifically, multi-temporal satellite imagery, census data, and results from social and health surveys have been integrated into a Geographic Information System (GIS) to describe the city and its inhabitants. Combining these datasets has enabled to study the spatial variability of the risk of malaria infection
Phan, Thi-Thu-Hong. "Elastic matching for classification and modelisation of incomplete time series." Thesis, Littoral, 2018. http://www.theses.fr/2018DUNK0483/document.
Повний текст джерелаMissing data are a prevalent problem in many domains of pattern recognition and signal processing. Most of the existing techniques in the literature suffer from one major drawback, which is their inability to process incomplete datasets. Missing data produce a loss of information and thus yield inaccurate data interpretation, biased results or unreliable analysis, especially for large missing sub-sequence(s). So, this thesis focuses on dealing with large consecutive missing values in univariate and low/un-correlated multivariate time series. We begin by investigating an imputation method to overcome these issues in univariate time series. This approach is based on the combination of shape-feature extraction algorithm and Dynamic Time Warping method. A new R-package, namely DTWBI, is then developed. In the following work, the DTWBI approach is extended to complete large successive missing data in low/un-correlated multivariate time series (called DTWUMI) and a DTWUMI R-package is also established. The key of these two proposed methods is that using the elastic matching to retrieving similar values in the series before and/or after the missing values. This optimizes as much as possible the dynamics and shape of knowledge data, and while applying the shape-feature extraction algorithm allows to reduce the computing time. Successively, we introduce a new method for filling large successive missing values in low/un-correlated multivariate time series, namely FSMUMI, which enables to manage a high level of uncertainty. In this way, we propose to use a novel fuzzy grades of basic similarity measures and fuzzy logic rules. Finally, we employ the DTWBI to (i) complete the MAREL Carnot dataset and then we perform a detection of rare/extreme events in this database (ii) forecast various meteorological univariate time series collected in Vietnam
Irichabeau, Gabrielle. "Evaluation économique de la dépendance d’une activité au milieu naturel : l'exemple de l'ostréiculrure arcachonnaise." Thesis, Bordeaux 4, 2011. http://www.theses.fr/2011BOR40035/document.
Повний текст джерелаEconomic activities have forms and degrees of dependency variables to the environment. The environment can act as a factor of production as a constraint to the use of certain inputs, such as a constraint for some inputs. Dependence may be related to the availability or quality of certain environmental resources. It will explore the implications of different forms of dependencies bio-physico-chemical as well as legal. In the case of the Arcachon Bay oyster-farming will examine the forms of dependence and economic measure, through the economic impacts associated with the variable availability of living marine resources but also to the natural productivity of the environment. The analysis of socio-economic characteristics of Arcachon Bay oyster-farms will develop a typology of the latter and thus characterize the activity. A production function approach will be used to highlight the varying degrees of sensitivity to changes in environmental conditions of production while the evaluation by the hedonic price method will determine the implicit price of environmental components of the oyster leases value taking into account also the geographical location of oyster leases
Beaufils, Bertrand. "Topological Data Analysis and Statistical Learning for measuring pedestrian activities from inertial sensors." Thesis, université Paris-Saclay, 2020. http://www.theses.fr/2020UPASS107.
Повний текст джерелаThis thesis focuses on the detection of specific movements using ActiMyo, a device developed by the company Sysnav. This system is composed by low-cost miniature inertial sensors that can be worn on the ankle and wrist. In particular, a supervised statistical learning approach aims to detect strides in ankle recordings. This first work, combined with an algorithm patented by Sysnav, allows to compute the trajectory of the pedestrian. This trajectory is then used in a new supervised learning method for the activity recognition, which is valuable information, especially in a medical context. These two algorithms offer an innovative approach based on the alignment of inertial signals and the extraction of candidate intervals which are then classified by the Gradient Boosting Trees algorithm. This thesis also presents a neural network architecture combining convolutional channels and topological data analysis for the detection of movements representative of Parkinson’s disease such as tremors and dyskinesia crises
Bacelar-Nicolau, Leonor. "Health Impact Assessment : Quantifying and Modeling to Better Decide." Thesis, Paris, CNAM, 2017. http://www.theses.fr/2017CNAM1151/document.
Повний текст джерелаHealth Impact Assessment (HIA) is a decision-making support tool to judge a policy as to its potential effects and its distribution on a population’s health (equity). It’s still very often a qualitative approach.The main aim here is to show the usefulness of applying quantified multivariate statistical methodologies to enrich HIA practice, while making the decision-making process easier, by issuing understandable outputs even for non-statisticians.The future of healthcare reforms shifts the center of evaluation of health systems from providers to people’s individual needs and preferences, reducing health inequities in access and health outcomes, using big data linking information from providers to social and economic health determinants. Innovative statistical and assessment methodologies are needed to make this transformation.Data mining and data science methods, however complex, may lead to graphical outputs simple to understand by decision makers. HIA is thus a valuable tool to assure public policies are indeed evaluated while considering health determinants and equity and bringing citizens to the center of the decision-making process
A Avaliação de Impacte na Saúde (AIS) é um instrumento de suporte à decisão para julgar política quanto aos seus efeitos potenciais e à sua distribuição na saúde de uma população (equidade). É geralmente ainda uma abordagem qualitativa.O principal objetivo é mostrar a utilidade das metodologias estatísticas quantitativas e multivariadas para enriquecer a prática de AIS, melhorando a compreensão dos resultados por profissionais não-estatísticos.As futuras reformas dos sistemas de saúde deslocam o centro da avaliação dos serviços de saúde dos prestadores para as necessidades e preferências dos cidadãos, reduzindo iniquidades no acesso à saúde e ganhos em saúde, usando big data que associam informação de prestadores a dados sociais e económicos de determinantes de saúde. São necessárias metodologias estatísticas e de avaliação inovadoras para esta transformação.Métodos de data mining e data science, mesmo complexos, podem gerar resultados gráficos compreensíveis para os decisores. A AIS é assim uma ferramenta valiosa para avaliar políticas públicas considerando determinantes de saúde, equidade e trazendo os cidadãos para o centro da tomada de decisão