Teses / dissertações sobre o tema "Processus heuristiques"
Crie uma referência precisa em APA, MLA, Chicago, Harvard, e outros estilos
Veja os 39 melhores trabalhos (teses / dissertações) para estudos sobre o assunto "Processus heuristiques".
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.
Baczkowski, Mylène. "Amélioration du processus de déploiement d'une solution PLM par l'utilisation de cartes heuristiques et de persona : cas LASCOM". Thesis, Bordeaux 1, 2012. http://www.theses.fr/2012BOR14714/document.
Texto completo da fonteThis thesis concerns research on PLM tools. We especially focus here on improvement of the deployment process of PLM tools in enterprises. We develop a methodology to help PLM software developers to design and deploy a PLM solution among their customers. Our proposition, centered on final users of PLM solution, is build around two unusual tools for enterprise modeling: mind map and persona. Mind map is used as a communication element between developer and customer during the entire project. Mind map is a common support to exchange data and encourage reflection. It offers a new dynamic and a new dimension in the definition of the PLM solution for customer and developer since it makes easier description of customer’s organization and process. We enrich our proposition with persona. Persona completes mind map and permits an easier identification of users’ needs. Such a tool allows us to be more efficient on accompaniment and implication of customer and users. Mind map is a unique support for software developer and customer to follow life cycle of the software. It is based on a top-down approach. Persona is centered on users in the company and on their environment. It is a bottom-up approach. Association of these tools allows us obtaining a double exploration of the system that provides a new dimension in enterprise modeling with a view to software deployment. This proposition increase pertinence and quality of the users’ needs analysis and of customer organization modeling. As a consequence it also improves design and deployment of the PLM solution which is closed to the users’ needs and well adapted to the company’s organization and processes
Champagne, Pierre. "Le processus décisionnel des directeurs de comptes de PME dans le domaine du financement bancaire : analyse des heuristiques et des biais cognitifs". Thèse, Université du Québec à Trois-Rivières, 1996. http://depot-e.uqtr.ca/4985/1/000672170.pdf.
Texto completo da fonteTeichteil, Florent. "Approche symbolique et heuristique de la planification en environnement incertain : optimisation d'une stratégie de déplacement et de prise d'information". Toulouse, ENSAE, 2005. http://www.theses.fr/2005ESAE0028.
Texto completo da fonteCorona, Gabriel. "Utilisation de croyances heuristiques pour la planification multi-agent dans le cadre des Dec-POMDP". Electronic Thesis or Diss., Nancy 1, 2011. http://www.theses.fr/2011NAN10026.
Texto completo da fonteIn this thesis, we focus on planning in decentralised sequentialdecision taking in uncertainty. In the centralised case, the MDP andPOMDP frameworks leads to efficient planning algorithms. The Dec-POMDPframework is used to model decentralised problems. This kind ofproblems is in a higher class of complexity than the centralisedproblem. For this reason, until recently, only very small problem could be solved and only for very small horizons. Recently, some heuristic algorithms have been proposed to handle problem of higher size but there is no theoretic proof of the solution quality. In this thesis, we show how to use a heuristic information in the problem, modelled as a probability distribution on the centralised beliefs, to guide the search for a good approximate policy. Using this heuristic information, we formulate each time step of the planning procedure as a combinatorial optimisation problem. This formulation leads to policies of better quality than previously existing approaches
Corona, Gabriel. "Utilisation de croyances heuristiques pour la planification multi-agent dans le cadre des Dec-POMDP". Phd thesis, Université Henri Poincaré - Nancy I, 2011. http://tel.archives-ouvertes.fr/tel-00598689.
Texto completo da fonteAmmar, Adel Amin. "Adaptation et mise en place d'un processus d'innovation et de conception au sein d'une PME". Phd thesis, Paris, ENSAM, 2010. http://pastel.archives-ouvertes.fr/pastel-00566135.
Texto completo da fonteDalmas, Benjamin. "Nouvelles approches pour la détection de relations utiles dans les processus : application aux parcours de santé". Thesis, Université Clermont Auvergne (2017-2020), 2018. http://www.theses.fr/2018CLFAC005/document.
Texto completo da fonteEver since the post-World War II baby-boom, France has had to cope with an aging population and with pathologies that have become chronic. These new health problems imply more reccurent, more complex and multidisciplinary medical care. However, multiple obstacles related to the evolution of the society or to the internal organization of the healthcare system hinder the development of new and more adapted health procedures to meet new medical needs. In a context where health expanses have to be reduced, it is necessary to have a better management of health processes.Our work aims at proposing a set of methods to gain an understanding of the elderly health path in the Auvergne region. To this end, a description of the elderly health path is necessary in order to have this missing overview. Moreover, this will enable the identification of the stakeholders, their interactions and the constraints to which they are submitted in the different health procedures.The work presented in this thesis focuses on two problems. The first one consists in developing techniques to efficiently model health paths. With these models, we will be able to analyze how the different segments of a medical care are ordered. The second problem consists in developing techniques to extract relevant information from the data, according to a predefined business point of view, specific to the user who analyzes the model. This knowledge will enable the detection of frequent or abnormal parts of a health path.To resolve these problems, the methods we propose in this thesis are related to process mining and data mining. These disciplines aim at exploiting data available in today's information systems in order to discover useful knowledge. In a first part, we propose a methodology that relies on the expressive power of process models to extract relevant information. In a second part, we propose techniques to build local process models that represent interesting fragments of behavior.The experiments we performed show the efficiency of the methods we propose. Moreover, we analyze data from different application domains to prove the genericity of the developed techniques
Eastes, Richard-Emmanuel. "Processus d'apprentissage, savoirs complexes et traitement de l'information : un modèle théorique à l'usage des praticiens, entre sciences cognitives, didactique et philosophie des sciences". Thesis, Paris 1, 2013. http://www.theses.fr/2013PA010593/document.
Texto completo da fonteAiming at bridging education sciences, cognitive sciences and philosophy of science both theoretically and practically, this thesis develops a didactical model at the interface between these fields: the allosteric learning model developed by Giordan (1988) et al. (1992), understood in the context conceptual change theories paradigm. Fueled by the recent works of cognitive psychologists on learning processes such as neuronal recycling (Dehaene, 2007) or cerebral inhibition (Houdé & Tzourio-Mazoyer, 2003), as well as on various theories related to the thought processes such as behavioral economies (Tversky & Kahneman, 1982) or the Skills-Rules-Knowledge framework model (Rasmussen, 1990), this model develops and refines the concept of allostery through the description and formalization of specific processes that take place in complex learning situations : the deconstruction-reconstruction of conceptions. Based on the theorization of the model, done through the use chemical reactivity formalisms in line with the initial metaphor of allostery, it is possible to deduce various operational and fruitful didactical environments for teaching practitioners or science communication professionals. These theoretical projections are then put to the test through didactic experimentation taking the shape of field research on the notion of counter-intuitive experiment (Eastes & Pellaud, 2004) conducted with different types of target groups
Gater, Ahmed. "Appariement et découverte de processus". Versailles-St Quentin en Yvelines, 2012. http://www.theses.fr/2012VERS0010.
Texto completo da fonteThe importance gained by business processes in modern information systems and service oriented architectures led to the increasing proliferation of process repositories. Matching and retrieving processes are critical functionalities required for the management of such collections. Some existing approaches reduced the problem of process matching to a graph matching problem and adapted existing matching algorithms to this end. However, the NP-completeness of their underlying graph matching algorithms limits the application of these techniques to small-sized processes. Furthermore, these techniques cannot be used in the context of process retrieval by matching the query against the processes of the repository, and ranking them according to their similarities. Motivated by these problems, we propose in this dissertation: (1) two heuristics that aim to speed up the matching of processes while keeping an acceptable quality level of the found matches, and (2) an index structure as well as a query answering algorithm that allow retrieving the processes the most similar to a given query without browsing the processes of a repository. To show the effectiveness of our techniques, we developed a prototype implementing them, and we built up a test collection upon which we evaluated this prototype
Bailey, Ian. "Planification heuristique avec les processus de décision markovien et création d'un environnement de programmation". Mémoire, Université de Sherbrooke, 2005. http://savoirs.usherbrooke.ca/handle/11143/4630.
Texto completo da fonteZEGHIB, YACINE. "Vers une approche hybride heuristique et analytique pour le diagnostic de pannes des processus industriels". Université Louis Pasteur (Strasbourg) (1971-2008), 2001. http://www.theses.fr/2001STR13064.
Texto completo da fonteHamel, Johanne. "Création artistique et identité professionnelle: une étude heuristique". Thèse, Université de Sherbrooke, 2011. http://hdl.handle.net/11143/8290.
Texto completo da fontePreza, Mayo José Victor. "Comparaison d'une démarche heuristique l'algorithme de Nancy et de la méthode des plans d'expériences pour la conduite optimale d'un procédé discontinu d'estérification". Vandoeuvre-les-Nancy, INPL, 1996. http://www.theses.fr/1996INPL046N.
Texto completo da fonteSaumard, Adrien. "Estimation par Minimum de Contraste Régulier et Heuristique de Pente en Sélection de Modèles". Phd thesis, Université Rennes 1, 2010. http://tel.archives-ouvertes.fr/tel-00569372.
Texto completo da fonteManaa, Adel. "Ordonnancement de tâches multiprocesseur sur deux processeurs dédiés". Troyes, 2009. http://www.theses.fr/2009TROY0016.
Texto completo da fonteIn this thesis, we study scheduling problems with multiprocessor tasks where a task may simultaneously require more than one processor for its execution. We are particularly interested in the case of two dedicated processors for which we have considered three objective functions: minimising the makespan, minimizing the total (weighted) flowtime and minimizing the total tardiness. For these criteria, we have developed lower bounds, heuristics and exact methods. We have proposed different lower bounds based on intuitive relaxations or lagrangian and surrogate relaxations. Constructive heuristics have been developed and worst case performance ratios of some of them are proved. We have also proposed mathematical models for minimizing the total tardiness and we developed several heuristics based on these models with experimental study of their performance. We have developed exact branch-and-bound methods for which we have proved several dominance properties. Finally, we proposed a specific scheme to randomly test instances for this type of scheduling problems on dedicated processors taking into account the different types of tasks and processor loads and on which we tested our methods
Philemotte, Christophe. "L'heuristique de la Gestalt: une méta-modélisation dynamique en ligne comme assistance du processus d'une métaheuristique". Doctoral thesis, Universite Libre de Bruxelles, 2009. http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/210311.
Texto completo da fonteDe nos jours, il est peu de processus ou de tâches qui ne requièrent pas l'optimisation d'une quantité :diminuer le temps de livraison, diminuer l'espace utilisé, réduire les efforts de développement, C'est donc sans surprise que la recherche en optimisation soit l'un des domaines les plus actifs des sciences des technologies de l'information. En optimisation combinatoire, les métaheuristiques sont à compter parmi le fleuron des techniques algorithmiques. Mais ce succès est encore au prix d'une quantité significative de temps de conception et développement. Ne serait-il pas possible d'aller encore plus loin ?D'automatiser la préparation des métaheuristiques ?En particulier dans des conditions telles le manque de temps, l'ignorance de techniques spécialisées ou encore la mauvaise compréhension du problème traité ?C'est ce à quoi nous répondons dans la présente thèse au moyen d'une approche de méta-modélisation de la recherche :l'heuristique de la Gestalt.
Considérant la représentation du problème comme un levier que l'on peut activer sous le processus de recherche mené par une métaheuristique, la thèse suggère la construction d'une abstraction de cette représentation capable d'assister la métaheuristique à trouver de bonnes solutions en contraignant sa recherche. Cette approche, inspirée de la psychologie de la Gestalt, nous l'appelons l'heuristique de la Gestalt. Son fonctionnement repose principalement sur l'agrégation des variables de la représentation. Cette agrégation donne lieu à une abstraction structurelle, mais également fonctionnelle en ce sens que les opérateurs de la métaheuristique doivent désormais respecter l'intégrité des agrégats définis.
Après avoir établi le contexte de la dissertation, nous discutons de la transposition de la psychologie de la Gestalt dans le cadre de l'optimisation combinatoire et des métaheuristiques. S'ensuit la formalisation de l'heuristique de la Gestalt et la description de sa réalisation. Finalement, une série d'études expérimentales sont menées pour éprouver le concept avancé et valider l'implémentation basée sur les algorithmes évolutionnistes que nous proposons. En conclusion, nous affirmons que l'implémentation de l'heuristique de la Gestalt basée, entre autres, sur un algorithme génétique de groupement est capable d'assister positivement des algorithmes génétiques lorsque les instances de problèmes traitées possèdent une structure riche et complexe, que leur taille est importante, que l'on est tôt dans le processus d'optimisation et que l'algorithme génétique n'est pas paramétré spécifiquement.
Doctorat en Sciences de l'ingénieur
info:eu-repo/semantics/nonPublished
Plamondon, Pierrick. "Techniques for the allocation of resources under uncertainty". Doctoral thesis, Québec : Université Laval, 2007. http://www.theses.ulaval.ca/2007/24957/24957.pdf.
Texto completo da fonteAbdennadher, Nabil. "Conception de méthodes de placement et d'ordonnancement de programmes parallèles sur un système multi processeur : évaluation sur un réseau de transputers". Valenciennes, 1991. https://ged.uphf.fr/nuxeo/site/esupversions/be35d3cb-258a-4a5f-bc58-c3be2899b347.
Texto completo da fonteDrouillet, Yohann. "Entre richesse heuristique potentielle et actualisation subtile : processus d’appréhension et épistémologie d’une formation : en quoi l’exercice d’une « douance » nécessiterait-il le recours à l’appréhension d’un formalisme". Electronic Thesis or Diss., Paris 8, 2019. http://www.theses.fr/2019PA080089.
Texto completo da fonteThe formalism of the thesis during the construction and the elaboration in act covers two postures antagonist “a-priori” which stay profoundly paradoxical. It is a conditional scientific in construction which appears discursive and the authority of a posture close to a third included in act. The “douance” as an object of research is questioned as from the practice of the diary by its author since 12 years. The author approaches his research subject more and more following a resumption of studiesin the education sciences; his formalization will then require the help of a working philosophy. When an author doesn’t distinguish always the nature of which creates a problem for himself (such as a catastrophy in the sense of René THOM) he commits himself for the needs of the thesis, a protocol investigating the problem where the nature of the problem can unstablize its resolution. The double status of the diary is implicitly subject and put into question. Its exercise warrants a scientific use in contact of the singularity of the situation. The thesis gives to show that the dater exercises needs to be understood, where the action and experience of the person are formalized, authorizing a paradox in act
Meena, Ashish. "Allocation, assignation et ordonnancement pour les systèmes sur puce multi-processeurs". Lille 1, 2006. http://www.theses.fr/2006LIL10165.
Texto completo da fonteBou, Malham Christelle. "Méthodologie d’optimisation hybride (Exergie/Pinch) et application aux procédés industriels". Thesis, Paris Sciences et Lettres (ComUE), 2018. http://www.theses.fr/2018PSLEM082.
Texto completo da fonteIn the perspective of the prevailing and alarming energy scene, this doctoral work puts forward a methodology that couples pinch and exergy analysis in a way to surpass their individual limitations in the aim of generating optimal operating conditions and topology for industrial processes. A global methodology, a hybrid of the two thermodynamic methods in an intertwined approach with heuristic rules and numerical optimization, is therefore evoked. Using new optimizing exergy-based criteria, exergy analysis is used not only to assess the exergy losses but also to guide the potential improvements in industrial processes structure and operating conditions. And while pinch analysis considers only heat integration to satisfy existent needs, the proposed methodology allows including other forms of recoverable exergy and explores new synergy pathways through conversion systems. After exhibiting the guidelines of the proposed methodology, the entire approach is demonstrated on two industrial systems, a vacuum gasoil hydrotreating process and a natural gas liquefaction process. The application of the methodological framework on realistic processes demonstrated how to adjust each process operating conditions and how to implement conversion systems ensuing substantial energy savings
Tobon, valencia Estefania. "Contribution à la formalisation d’un processus PDP agile dans le cadre de l’industrie 4.0". Thesis, Paris, HESAM, 2020. http://www.theses.fr/2020HESAE030.
Texto completo da fonteManufacturing SMEs (Small and Medium-sized Enterprises), major actors of the global industry, are subjected to strong pressure from the market to respond in shorter delays to customized needs with competitive prices. The evolution of production planning activities through the 4.0 technologies can provide answers for facing these challenges. However, considering the large number of industry 4.0 technologies, it is not easy for SMEs to select the most adequate technologies for their industrial and organizational context and the most adequate activities that could enhance a digital improvement. Planning a digital transformation project requires the definition of the 4.0 scope as well as a clear vision of the performance objectives to be achieved. Nevertheless, our review of the scientific literature shows that SMEs lack models for carrying digital transformation in planning activities.This thesis proposes a 4.0 production planning approach, focused on the Master Production Schedule (MPS), for manufacturing SMEs. In order to reach our research goal, we conducted a prospective study to specify the industrial need of the MPS process within a group of manufacturing SMEs. This study revealed that the main levers of the transformation concerned the process and the tools for supporting decision-making. Regarding the process, we present a methodology for selecting the activities to be done in a new way based on two improvement levers, monitoring and optimization. On this basis, we propose the integration of the 4.0 technologies in the MPS. As for decision support tools, we propose two optimization approaches for the MPS in the context of SME with an assemble-to-order (ATO) strategy, multiple assembly lines, several bottlenecks, diverse master items and a mainly artisanal production process. We also present the integration of these optimization approaches in the MPS activities
Ballout, Ali. "Apprentissage actif pour la découverte d'axiomes". Electronic Thesis or Diss., Université Côte d'Azur, 2024. http://www.theses.fr/2024COAZ4026.
Texto completo da fonteThis thesis addresses the challenge of evaluating candidate logical formulas, with a specific focus on axioms, by synergistically combining machine learning with symbolic reasoning. This innovative approach facilitates the automatic discovery of axioms, primarily in the evaluation phase of generated candidate axioms. The research aims to solve the issue of efficiently and accurately validating these candidates in the broader context of knowledge acquisition on the semantic Web.Recognizing the importance of existing generation heuristics for candidate axioms, this research focuses on advancing the evaluation phase of these candidates. Our approach involves utilizing these heuristic-based candidates and then evaluating their compatibility and consistency with existing knowledge bases. The evaluation process, which is typically computationally intensive, is revolutionized by developing a predictive model that effectively assesses the suitability of these axioms as a surrogate for traditional reasoning. This innovative model significantly reduces computational demands, employing reasoning as an occasional "oracle" to classify complex axioms where necessary.Active learning plays a pivotal role in this framework. It allows the machine learning algorithm to select specific data for learning, thereby improving its efficiency and accuracy with minimal labeled data. The thesis demonstrates this approach in the context of the semantic Web, where the reasoner acts as the "oracle," and the potential new axioms represent unlabeled data.This research contributes significantly to the fields of automated reasoning, natural language processing, and beyond, opening up new possibilities in areas like bioinformatics and automated theorem proving. By effectively marrying machine learning with symbolic reasoning, this work paves the way for more sophisticated and autonomous knowledge discovery processes, heralding a paradigm shift in how we approach and leverage the vast expanse of data on the semantic Web
Bardin, Sébastien. "Vers un Model Checking avec accélération plate des systèmes hétérogènes". Phd thesis, École normale supérieure de Cachan - ENS Cachan, 2005. http://tel.archives-ouvertes.fr/tel-00131834.
Texto completo da fonteFrey, Darren. "The identification of individual-specific conflict detection sensitivities". Thesis, Sorbonne Paris Cité, 2017. http://www.theses.fr/2017USPCB238.
Texto completo da fonteRecent state of the art research into cognitive biases has revealed that individuals often detect that they are making certain reasoning errors even when they themselves do not, perhaps cannot, articulate the source of the error. Until now, this research has focused primarily on demonstrating the existence of conflict detection tendencies among even the most biased reasoners. This thesis builds on this research by analyzing three related and unexplored areas of inquiry: (1) subtypes of conflict detection; (2) individual-specific differences among detectors; and (3) the domain generality or specificity of conflict detection sensitivities. By identifying increasingly fine-tuned detection subtypes, the project aims to explore correlations between particular conflict detection sensitivities and other cognitive predictors. It is, essentially, preparatory work for a complete differential analysis of conflict detection sensitivities among reasoners
Zhang, Jian. "Advance Surgery Scheduling with Consideration of Downstream Capacity Constraints and Multiple Sources of Uncertainty". Thesis, Bourgogne Franche-Comté, 2019. http://www.theses.fr/2019UBFCA023.
Texto completo da fonteThis thesis deals with the advance scheduling of elective surgeries in an operating theatre that is composed of operating rooms and downstream recovery units. The arrivals of new patients in each week, the duration of each surgery, and the length-of-stay of each patient in the downstream recovery unit are subject to uncertainty. In each week, the surgery planner should determine the surgical blocks to open and assign some of the surgeries in the waiting list to the open surgical blocks. The objective is to minimize the patient-related costs incurred by performing and postponing surgeries as well as the hospital-related costs caused by the utilization of surgical resources. Considering that the pure mathematical programming models commonly used in literature do not optimize the long-term performance of the surgery schedules, we propose a novel two-phase optimization model that combines Markov decision process (MDP) and stochastic programming to overcome this drawback. The MDP model in the first phase determines the surgeries to be performed in each week and minimizes the expected total costs over an infinite horizon, then the stochastic programming model in the second phase optimizes the assignments of the selected surgeries to surgical blocks. In order to cope with the huge complexity of realistically sized problems, we develop a reinforcement-learning-based approximate dynamic programming algorithm and several column-generation-based heuristic algorithms as the solution approaches. We conduct numerical experiments to evaluate the model and algorithms proposed in this thesis. The experimental results indicate that the proposed algorithms are considerably more efficient than the traditional ones, and that the resulting schedules of the two-phase optimization model significantly outperform those of a conventional stochastic programming model in terms of the patients' waiting times and the total costs on the long run
Obeid, Ali. "Scheduling and Advanced Process Control in semiconductor Manufacturing". Phd thesis, Ecole Nationale Supérieure des Mines de Saint-Etienne, 2012. http://tel.archives-ouvertes.fr/tel-00847032.
Texto completo da fonteGardes, Marie-Line. "Étude de processus de recherche de chercheurs, élèves et étudiants, engagés dans la recherche d’un problème non résolu en théorie des nombres". Thesis, Lyon 1, 2013. http://www.theses.fr/2013LYO10231/document.
Texto completo da fonteOur thesis deals with the transposition of mathematician’s reserach activity in mathematical classroom, in the domain of number theory. Our research focuses on the study of a research process for researchers, pupils and students involved in the research of an unsolved problem: the Erdös-Straus conjecture. Our mathematical and epistemological analyses allow us to identify different aspects of the mathematician’s work and the elements for progress in his research. The notion of “gesture” is developed to describe, analyze and contextualize different research processes. This analysis reveals the potentiality of this problem to create a research situation in classroom, where pupils are in a position similar to the mathematician’s one. Didactical analyses are based on the construction of such a situation and its experimentation in laboratory. We study the research process of the students with the methodological tools developed in mathematical and epistemological analyses. This analysis shows several potentiality of this situation: a wealth of procedures implemented, effective work on the dialectical aspects of the mathematical research activity and implementation of experimental approach. The notion of “gesture” is relevant to consider the question of the transposition of mathematician’s work
Connault, Pierre. "Calibration d'algorithmes de type Lasso et analyse statistique de données métallurgiques en aéronautique". Thesis, Paris 11, 2011. http://www.theses.fr/2011PA112041.
Texto completo da fonteOur work contains a methodological and an applied part.In the methodological part we study Lasso and a variant of this algorithm : the projectedLasso. We develop slope heuristics to calibrate them.Our approach uses sparsity properties of the Lasso, showing how to remain to a modelselection framework. This both involves a penalized criterion and the tuning of a constant.To this aim, we adopt the classical approaches of Birgé and Massart about slope heuristics.This leads to the notion of canonical penalty.Slope and (tenfold) crossvalidation are then compared through simulations studies.Results suggest the user to consider both of them. In order to increase calculation speed,simplified penalties are (unsuccessfully) tried.The applied part is about aeronautics. The results of the methodological part doapply in reliability : in classical approaches (without Lasso) the large number of variables/number of data ratio leads to an instability of linear models, and to huge calculustimes. Lasso provides a helpful solution.In aeronautics, dealing with reliability questions first needs to study quality of theelaboration and forging processes. Four major axis have to be considered : analysing thefactor of the process, discrimining recipes, studying the impact of time on quality anddetecting outliers. This provides a global statistical strategy of impowerment for processes
Guschinskaya, Olga. "Outils d'aide à la décision pour la conception en avant-projet des systèmes d'usinage à boîtiers multibroches". Phd thesis, Ecole Nationale Supérieure des Mines de Saint-Etienne, 2007. http://tel.archives-ouvertes.fr/tel-00783240.
Texto completo da fonteLi, Zhi. "Commande optimale (en Production et Stock) de Systèmes Assemble-To-Order (ATO) avec prise en compte de demandes en composants individuels". Phd thesis, Ecole Centrale de Lille, 2013. http://tel.archives-ouvertes.fr/tel-00866378.
Texto completo da fonteFang, Jianxin. "Analyse et algorithmes de résolution de systèmes ATO (Assemble-To-Order) : Applications aux systèmes du type W". Thesis, Ecole centrale de Lille, 2017. http://www.theses.fr/2017ECLI0012/document.
Texto completo da fonteWe analyze a W-configuration assemble-to-order system with random lead times, random arrival of demand, and lost sales, in continuous time. We formulate the problem as an infinite-horizon Markov decision process. We deviate from the standard approach by first characterizing a region (the recurrent region) of the state space where all properties of the cost function hold. We then characterize the optimal policy within this region. In particular, we show that within the interior of the recurrent region components are always produced. We also characterize the optimal component allocation policy which specifies whether an arriving product demand should be fulfilled. Our analysis reveals that the optimal allocation policy is counter-intuitive. For instance, even when one product dominates the other, in terms of lost sale cost and lost sale cost rate (i.e., demand rate times the lost sale cost), its demand may not have absolute priority over the other product’s demand. Such a feature has not been observed in many integrated production/inventory settings where inventory allocation follows a fixed priority in satisfying demands. We also show that the structure of the optimal policy remains the same for systems with batch production, Erlang distributed production times, and non-unitary product demand. Finally, we propose efficient heuristics that can be either used as a substitute for the optimal policy or can be used as a starting policy for the common algorithms that are used to obtain the optimal policy in an effort to reduce their computational time
Aupetit, Sébastien. "Contributions aux Modèles de Markov Cachés : métaheuristiques d'apprentissage, nouveaux modèles et visualisation de dissimilarité". Phd thesis, Université François Rabelais - Tours, 2005. http://tel.archives-ouvertes.fr/tel-00168392.
Texto completo da fontede métaheuristiques biomimétiques classiques (les algorithmes génétiques, l'algorithme de fourmis artificielles API et l'optimisation par essaim particulaire) au problème de l'apprentissage de MMC. Dans la
deuxième partie, nous proposons un nouveau type de modèle de Markov caché, appelé modèle Markov caché à substitutions de symboles (MMCSS). Un MMCSS permet d'incorporer des connaissances a priori dans le processus d'apprentissage et de reconnaissance. Les premières expérimentations de ces modèles sur des images démontrent leur intérêt. Dans la troisième partie, nous proposons une nouvelle méthode de représentation de dissimilarité appelée matrice de scatterplots pseudo-euclidienne (MSPE), permettant de mieux comprendre les interactions entre des MMC. Cette MSPE est construite à partir
d'une technique que nous nommons analyse en composantes principales à noyau indéfini (ACPNI). Nous terminons par la présentation de la bibliothèque HMMTK, développée au cours de ce travail. Cette dernière intègre des mécanismes de parallélisation et les algorithmes développés au cours de la thèse.
Stan, Oana. "Placement of tasks under uncertainty on massively multicore architectures". Thesis, Compiègne, 2013. http://www.theses.fr/2013COMP2116/document.
Texto completo da fonteThis PhD thesis is devoted to the study of combinatorial optimization problems related to massively parallel embedded architectures when taking into account uncertain data (e.g. execution time). Our focus is on chance constrained programs with the objective of finding the best solution which is feasible with a preset probability guarantee. A qualitative analysis of the uncertain data we have to treat (dependent random variables, multimodal, multidimensional, difficult to characterize through classical distributions) has lead us to design a non parametric method, the so-called "robust binomial approach", valid whatever the joint distribution and which is based on robust optimization and statistical hypothesis testing. We also propose a methodology for adapting approximate algorithms for solving stochastic problems by integrating the robust binomial approach when verifying for solution feasibility. The paractical relevance of our approach is validated through two problems arising in the compilation of dataflow application for manycore platforms. The first problem treats the stochastic partitioning of networks of processes on a fixed set of nodes, by taking into account the load of each node and the uncertainty affecting the weight of the processes. For finding stochastic solutions, a semi-greedy iterative algorithm has been proposed which allowed measuring the robustness and cost of the solutions with regard to those for the deterministic version of the problem. The second problem consists in studying the global placement and routing of dataflow applications on a clusterized architecture. The purpose being to place the processes on clusters such that it exists a feasible routing, a GRASP heuristic has been conceived first for the deterministic case and afterwards extended for the chance constrained variant of the problem
Tran, Tuan Tu. "Comparaisons de séquences biologiques sur architecture massivement multi-cœurs". Phd thesis, Université des Sciences et Technologie de Lille - Lille I, 2012. http://tel.archives-ouvertes.fr/tel-00832663.
Texto completo da fonteRenaud-Goud, Paul. "Energy-aware scheduling : complexity and algorithms". Phd thesis, Ecole normale supérieure de lyon - ENS LYON, 2012. http://tel.archives-ouvertes.fr/tel-00744247.
Texto completo da fonteFaucher, Félix. "Le récit comme outil heuristique". Mémoire, 2013. http://www.archipel.uqam.ca/5426/1/M12914.pdf.
Texto completo da fontePiédalue, Carole. "Transformer l'image en art-thérapie : exploration heuristique du processus de transformation de l'image comme outil thérapeutique dans le développement de la résilience". Thesis, 2005. http://spectrum.library.concordia.ca/8677/1/MR52322.pdf.
Texto completo da fonteBeaulac, Guillaume. "A two speed mind? : for a heuristic interpretation of dual-process theories = L'esprit à deux vitesses? : pour une interprétation heuristique des théories à processus duaux". Mémoire, 2010. http://www.archipel.uqam.ca/3774/1/M11846.pdf.
Texto completo da fonte