511 |
Méthodes Probabilistes Bayesiennes pour la prise en en compte des incertitudes géométriques : Application à la CAO-RobotiqueMekhnacha, Kamel 16 July 1999 (has links) (PDF)
Cette these porte sur l'utilisation du formalisme bayesien pour la repr´esentation et la manipulation des incertitudes geometriques dans les systemes de Robotique et de CAORobotique. Dans ces systemes, l'utilisation d'un modele geometrique de l'environnement est indispensable. Toutefois, la validite des calculs conduits sur ces mod`eles n´ecessite une repr´esentation des ecarts entre le modele et la realite et une prise en compte de ces ecarts lors de la resolution d'un probleme donne. L'approche proposee repr´esente une extension de la notion de specification par contraintes geometriques dans laquelle la dimension incertaine des modeles est prise en compte. Cette extension consiste a specifier les contraintes sur les positions relatives entre diff´erents corps de l'environnement non pas par de simples equations et inequations, mais par des distributions de probabilite sur les parametres de ces positions. A l'issue de cette specification, une distribution conjointe sur l'ensemble des parametres du modele est construite. Pour un probleme donne, la distribution marginale sur les parametres inconnus de ce dernier est inferee en utilisant les regles des probabilites. La resolution de ce probleme revient a optimiser cette distribution comportant, dans le cas general, une integrale portant sur un espace de grande dimension. La methode de resolution utilisee pour approcher ce double probleme d'integration/optimisation est basee sur un algorithme genetique. Cet algorithme permet en particulier de controler la precision de l'estimation numerique des integrales par une m´ethode stochastique de Monte-Carlo. L'implantation d'un systeme prototype de CAO nous a permis une experimentation assez poussee de l'approche propos´ee. La mise en oeuvre de plusieurs applications robotiques, dont les natures peuvent paraıtre tres differentes, a ete possible grace a la souplesse de la methode de specification utilisee et la robustesse de la methode de resolution implantee.
|
512 |
Détection d'une source faible : modèles et méthodes statistiques. Application à la détection d'exoplanètes par imagerie directe.Smith, Isabelle 26 November 2010 (has links) (PDF)
Cette thèse contribue à la recherche de planètes extra-solaires à partir d'instruments au sol imageant une étoile et son environnement très proche. Le grand contraste lumineux et la proximité entre une potentielle exoplanète et son étoile parente rendent la détection de l'exoplanète extrêmement difficile. Une modélisation qualitative et probabiliste fine des données et l'utilisation de méthodes d'inférence adaptées permettent d'accroître a posteriori les performances des instruments. Cette thèse se focalise ainsi sur l'étape de traitement des données et sur un problème de méthodologie statistique plus général. Chaque étude est abordée sous des angles théoriques et appliqués. La thèse décrit d'abord les données attendues pour le futur instrument SPHERE du Very Large Telescope, simulées à partir d'une modélisation physique détaillée. Un modèle probabiliste simple de ces données permet notamment de construire une procédure d'identification de candidats. Les performances des inférences sont aussi étudiées à partir d'un modèle décrivant de façon plus réaliste les bruits caractérisant les images (bruit de speckle corrélé, bruit de Poisson). On souligne la différence entre les probabilités de fausse alarme calculées à partir du modèle simple et à partir du modèle réaliste. Le problème est ensuite traité dans le cadre bayésien. On introduit et étudie d'abord un outil original de test d'hypothèses : la distribution a posteriori du rapport de vraisemblance, notée PLR. Son étude théorique montre notamment que dans un cadre d'invariance standard le PLR est égal à une p-value fréquentiste. Par ailleurs, un modèle probabiliste des données est développé à partir du modèle initial et un modèle probabiliste de l'intensité de l'exoplanète est proposé. Ils sont finalement utilisés dans le PLR et le facteur de Bayes.
|
513 |
Bayesian Methods in Gaussian Graphical ModelsMitsakakis, Nikolaos 31 August 2010 (has links)
This thesis contributes to the field of Gaussian Graphical Models by exploring either numerically or theoretically various topics of Bayesian Methods in Gaussian Graphical Models and by providing a number of interesting results, the further exploration of which would be promising, pointing to numerous future research directions.
Gaussian Graphical Models are statistical methods for the investigation and representation of interdependencies between components of continuous random vectors. This thesis aims to investigate some issues related to the application of Bayesian methods for Gaussian Graphical Models. We adopt the popular $G$-Wishart conjugate prior $W_G(\delta,D)$ for the precision matrix. We propose an efficient sampling method for the $G$-Wishart distribution based on the Metropolis Hastings algorithm and show its validity through a number of numerical experiments. We show that this method can be easily used to estimate the Deviance Information Criterion, providing a computationally inexpensive approach for model selection.
In addition, we look at the marginal likelihood of a graphical model given a set of data. This is proportional to the ratio of the posterior over the prior normalizing constant. We explore methods for the estimation of this ratio, focusing primarily on applying the Monte Carlo simulation method of path sampling. We also explore numerically the effect of the completion of the incomplete matrix $D^{\mathcal{V}}$, hyperparameter of the $G$-Wishart distribution, for the estimation of the normalizing constant.
We also derive a series of exact and approximate expressions for the Bayes Factor between two graphs that differ by one edge. A new theoretical result regarding the limit of the normalizing constant multiplied by the hyperparameter $\delta$ is given and its implications to the validity of an improper prior and of the subsequent Bayes Factor are discussed.
|
514 |
Bayesian Methods in Gaussian Graphical ModelsMitsakakis, Nikolaos 31 August 2010 (has links)
This thesis contributes to the field of Gaussian Graphical Models by exploring either numerically or theoretically various topics of Bayesian Methods in Gaussian Graphical Models and by providing a number of interesting results, the further exploration of which would be promising, pointing to numerous future research directions.
Gaussian Graphical Models are statistical methods for the investigation and representation of interdependencies between components of continuous random vectors. This thesis aims to investigate some issues related to the application of Bayesian methods for Gaussian Graphical Models. We adopt the popular $G$-Wishart conjugate prior $W_G(\delta,D)$ for the precision matrix. We propose an efficient sampling method for the $G$-Wishart distribution based on the Metropolis Hastings algorithm and show its validity through a number of numerical experiments. We show that this method can be easily used to estimate the Deviance Information Criterion, providing a computationally inexpensive approach for model selection.
In addition, we look at the marginal likelihood of a graphical model given a set of data. This is proportional to the ratio of the posterior over the prior normalizing constant. We explore methods for the estimation of this ratio, focusing primarily on applying the Monte Carlo simulation method of path sampling. We also explore numerically the effect of the completion of the incomplete matrix $D^{\mathcal{V}}$, hyperparameter of the $G$-Wishart distribution, for the estimation of the normalizing constant.
We also derive a series of exact and approximate expressions for the Bayes Factor between two graphs that differ by one edge. A new theoretical result regarding the limit of the normalizing constant multiplied by the hyperparameter $\delta$ is given and its implications to the validity of an improper prior and of the subsequent Bayes Factor are discussed.
|
515 |
應用全波形空載雷射掃描資料於山區地物分類 / Land cover Classification in Mountain Area Using Full-waveform Airborne Laser Scanned Data湯舜閔, Tang, Shun Min Unknown Date (has links)
空載雷射掃描為一可快速獲取地面物體三維空間資訊之技術,而新型發展之全波形(Full-Waveform)系統可完整記錄雷射回波訊號之波形,透過波形偵測與波形擬合等資料前處理,可得到代表地物獨特反射特性的波形參數資料,包括振幅值(Amplitude)、波形寬(Pulse-width)與後續計算之散射截面積係數(Backscatter cross-section coefficient)。
得到各點位之波形資料後,將以波形資料為主進行位於山區之實驗區地物分類,並將使用由實驗區航照影像提供之RGB波段光譜資料計算之綠度指數(Greenness)與計算影像灰階統計值之紋理參數如均質度(Homogeneity)、熵值(Entropy)與R波段平均值(Mean)等參數輔助分類。分類進行之前,透過抽樣實驗區候選地類包括樹林、草地、道路與樹種建物,並以貝氏定理(Bayes Theorem)分析計算不同地物類別在各分類參數區間內的貝氏機率,接著以多項式函數擬合各地類在不同參數之貝氏機率曲線,並以計算反曲點之方式自動化決定該分類參數之門檻值區間。
分類成果顯示,全波形系統提供之波形資料對於受上層植物遮蔽與陰影區之植物點與道路點之分類有顯著之成果,且透過物體對於波形資料之反射特性不同,具備應用於區別不同建築材質類別之潛力。 / Airborne Laser Scanning is a technique capable of acquiring 3D information of land objects. The latest full-waveform system is further improved with the ability of recording complete waveform of reflected laser signal. After the preprocessing procedures such as pulse detection and pulse fitting, the waveform information including amplitude, pulse width and backscatter cross-section were derived. Such information was valuable as they represented unique properties of land objects.
In this study, waveform information of all scanned points were utilized to classify land cover in the test area located in mountain area. Additionally, the Greenness value as well as the texture parameters such as Homogeneity, Entropy and Mean of R band calculated from the ortho-image were used for classification. We aimed to classify the point cloud into vegetation, road and building categories. The Bayes Theorem was used to determine the threshold range of each parameters for classification. As a result, the waveform information were useful for classifying road points covered by upper vegetation points and also vegetation and road points located in shadow area. Moreover, through the analysis of reflective properties of different object using waveform parameters, it was of potential to be applied to distinguish material of buildings.
|
516 |
Adaptation of dosing regimen of chemotherapies based on pharmacodynamic modelsPaule, Inès 29 September 2011 (has links) (PDF)
There is high variability in response to cancer chemotherapies among patients. Its sources are diverse: genetic, physiologic, comorbidities, concomitant medications, environment, compliance, etc. As the therapeutic window of anticancer drugs is usually narrow, such variability may have serious consequences: severe (even life-threatening) toxicities or lack of therapeutic effect. Therefore, various approaches to individually tailor treatments and dosing regimens have been developed: a priori (based on genetic information, body size, drug elimination functions, etc.) and a posteriori (that is using information of measurements of drug exposure and/or effects). Mixed-effects modelling of pharmacokinetics and pharmacodynamics (PK-PD), combined with Bayesian maximum a posteriori probability estimation of individual effects, is the method of choice for a posteriori adjustments of dosing regimens. In this thesis, a novel approach to adjust the doses on the basis of predictions, given by a model for ordered categorical observations of toxicity, was developed and investigated by computer simulations. More technical aspects concerning the estimation of individual parameters were analysed to determine the factors of good performance of the method. These works were based on the example of capecitabine-induced hand-and-foot syndrome in the treatment of colorectal cancer. Moreover, a review of pharmacodynamic models for discrete data (categorical, count, time-to-event) was performed. Finally, PK-PD analyses of hydroxyurea in the treatment of sickle cell anemia were performed and used to compare different dosing regimens and determine the optimal measures for monitoring the treatment
|
517 |
Symbolische Interpretation Technischer ZeichnungenBringmann, Oliver 19 January 2003 (has links) (PDF)
Gescannte und vektorisierte technische Zeichnungen werden automatisch unter Nutzung eines Netzes von Modellen in eine hochwertige Datenstruktur migriert. Die Modelle beschreiben die Inhalte der Zeichnungen hierarchisch und deklarativ. Modelle für einzelne Bestandteile der Zeichnungen können paarweise unabhängig entwickelt werden. Dadurch werden auch sehr komplexe Zeichnungsklassen wie Elektroleitungsnetze oder Gebäudepläne zugänglich. Die Modelle verwendet der neue, sogenannte Y-Algorithmus: Hypothesen über die Deutung lokaler Zeichnungsinhalte werden hierarchisch generiert. Treten bei der Nutzung konkurrierender Modelle Konflikte auf, werden diese protokolliert. Mittels des Konfliktbegriffes können konsistente Interpretationen einer kompletten Zeichnung abstrakt definiert und während der Analyse einer konkreten Zeichnung bestimmt werden. Ein wahrscheinlichkeitsbasiertes Gütemaß bewertet jede dieser alternativen, globalen Interpretationen. Das Suchen einer bzgl. dieses Maßes optimalen Interpretation ist ein NP-hartes Problem. Ein Branch and Bound-Algorithmus stellt die adäquate Lösung dar.
|
518 |
Bayes strategies and human information seekingLarsson, Bernt, January 1968 (has links)
Akademisk avhandling--Lund. / Extra t.p., with thesis statement, inserted. Bibliography: p. 115-119.
|
519 |
Bayesian learning in financial markets: price adjustments, fundamentals, and risk /Müller, Christoph. January 2009 (has links)
Zugl.: Köln, University, Diss., 2009.
|
520 |
Ευφυείς πράκτορες σε εικονικά περιβάλλοντα μάθησης / Intelligent agents in virtual learning systemsΓιωτόπουλος, Κωνσταντίνος 26 February 2009 (has links)
Σκοπός της διατριβής είναι η ανάλυση, η μελέτη και η μοντελοποίηση της συμπεριφοράς τόσο των ευφυών πρακτόρων όσο και των χρηστών σε εικονικά περιβάλλοντα μάθησης, με τη χρήση τεχνικών υπολογιστικής νοημοσύνης. Το θεματικό αντικείμενο της διδακτορικής διατριβής αποτελεί ένα σύγχρονο αντικείμενο βασικής έρευνας με μεγάλο εύρος πρακτικών εφαρμογών. Η βάση της ερευνητικής δραστηριότητας εστιάζεται σε δύο βασικούς τομείς:
1. Προσαρμόσιμη μοντελοποίηση συμπεριφορών ευφυών πρακτόρων σε εικονικά περιβάλλοντα μάθησης, σύμφωνα με κανόνες βελτιστοποίησης της μαθησιακής επίδρασης στο χρήστη μέσα στο εικονικό περιβάλλον μάθησης.
2. Μοντελοποίηση χρηστών εικονικών περιβαλλόντων μάθησης, με στόχο τη βελτιστοποίηση της μαθησιακής επίδρασης στο χρήστη.
Για τη μοντελοποίηση, τόσο της συμπεριφοράς των ευφυών πρακτόρων, όσο και των χρηστών, χρησιμοποιήθηκαν προηγμένες τεχνικές υπολογιστικής νοημοσύνης (Bayesian Δίκτυα, Γενετικοί και Εξελικτικοί Αλγόριθμοι). Αυτές οι τεχνικές, εκτός από την ευφυΐα, ενσωματώνουν και το επιθυμητό χαρακτηριστικό της προσαρμοσιμότητας, με την έννοια ότι μπορούν να προσαρμόζονται στις αλλαγές του περιβάλλοντος.
Τα παραπάνω αποτελέσματα αξιολογήθηκαν στη χρήση τους σε Ευφυή Εικονικά Συστήματα Μάθησης βασισμένα στο Web (Intelligent Virtual Learning Systems – IVLS), τα οποία αποτελούν ουσιαστικά το μέσον εξαγωγής συμπερασμάτων και υποστηρικτικού υλικού για τη μετρήσιμη συμπεριφορά τόσο των ευφυών πρακτόρων όσο και των χρηστών, μέσα σε τέτοια περιβάλλοντα. / The main objectives of the thesis are the analysis, study and the provision of a behavior modeling procedure of the intelligent agents and the students in virtual e-learning systems using computational intelligence techniques. The domain of the thesis is a topic of basic research with a large scale of applied results. The basis of the research is focused in two main sectors:
1. Adaptive behavior modeling of intelligent agents in virtual learning systems, according to specific optimization rules of the learning process during the interaction of the user/student with the e-learning environment.
2. User modeling of the users of virtual learning environments towards the optimization of the learning process.
For the modeling procedure of the behavior of intelligent agents and of the users specific computational intelligence techniques have been applied (Bayesian Networks, Genetic και Evolutionary Algorithms). The specific techniques provide intelligence to the system and the most important the feature of adaptability.
The aforementioned results have been evaluated on Intelligent Virtual Learning Systems, which constitute the medium for the inference of the results and the mean for supportive material for the measurable behavior of the intelligent agents and of the users in Intelligent Virtual Learning Systems.
|
Page generated in 0.0432 seconds