Le risque d’inondations dans les zones urbaines a considérablement augmenté au cours des dernières décennies avec la croissance rapide de la population et le processus d’urbanisation à proximité des cours d’eau et des zones inondables. Afin de faire face à ce risque, différents acteurs se réunissent dans le but de proposer une solution d’aménagement du territoire, capable de le maîtriser au mieux. La solution proposée doit répondre à plusieurs objectifs de natures différentes (économiques, sociaux, politiques,…) qui sont le plus souvent contradictoires. Des outils numériques d’aide à la décision sont actuellement disponibles et fréquemment utilisés par les aménageurs pour les aider dans leurs choix d’une solution adéquate. Cependant ces outils se basent généralement sur des approches empiriques et l’efficacité des solutions proposées reste incertaine. Dans ce contexte, l’objectif des travaux réalisés au cours de cette thèse, consiste à développer une approche complémentaire aux outils d’aide à la décision en se basant principalement sur des méthodes numériques directes, telles que la modélisation 3D, la simulation numérique et l’optimisation multicritères. L’approche consiste dans un premier temps à coupler la modélisation géométrique 3D issue de Système d’Information Géographique « SIG » avec la modélisation en mécanique des fluides « CFD », afin de représenter le phénomène d’inondation urbaine avec une précision proche du réel. Cette étape permet de fournir une cartographie tridimensionnelle de différentes caractéristiques de l’inondation (Vitesses, Hauteur d’eau, étendue de l’inondation, …), et par conséquent localiser les différentes parties de la ville à aménager en priorité. Dans un second temps, en se basant sur les résultats obtenus dans la première partie, des stratégies d'optimisation multicritères sont mises en œuvre afin de trouver parmi une multitude de solutions proposées, représentant des projets d’aménagement, celle la plus convenable pour la situation étudiée, et qui satisfasse simultanément les différentes contraintes techniques, économiques et environnementales. Une telle approche permet aux décideurs à la fois d’accélérer leur procédure d’analyse du risque dans la zone urbaine et de les rassurer sur l’efficacité de la solution choisie face à ce risque. / The risk and impact of floods in urban areas has been increased in the last few decades as population and urbanization processes rapidly increase and subsequently more and more people and properties are being concentrated in flood-prone coastal zones and river flood-plains. To cope with this risk, different stakeholders meet in order to provide a land planning solution able of better managing the risk. The proposed solution must meet different kinds of objectives simultaneously (geographical, economic, social, political,...). These ones are often contradictory. Digital tools for decision support are currently available and commonly used by developers to help them in their choice of an appropriate solution. However, these tools are usually based on empirical approaches and the effectiveness of the proposed solutions is uncertain. In this context, the principal objective of this research working is to develop a complementary numerical approach to the tools of decision support based primarily on direct numerical methods, such as 3D modeling, numerical simulation and multi-criteria optimization. As a first step, the proposed approach consists to couple the geometric modeling, based on 3D data of GIS (Geographic Information System) , with the CFD modeling (Computational fluid dynamics) in order to represent the urban flooding scenario with an accuracy close to the actual . This step will provide a three-dimensional mapping of the different characteristics of the flood (velocity and height of water, the flood extent ...). Thus we can easily and quickly locate different parts of the city that will be developed in priority. As a second step, based on the results obtained in the first step, some advanced strategies of the multi-criteria optimization are implemented to find among a multitude of proposed solutions, representing the most suitable development projects for the situation studied, and meets the various technical, economic and environmental constraints. Such approach allows decision makers to both accelerate their process of risk analysis, in the urban area, and reassure the effectiveness of the chosen solution against this risk.

The study analyses various methods to solve multiple criteria optimization problems of different kinds and defines principles of parallel computing. A multiple criteria optimization problem has been solved applying a computer network and a new strategy that analyses and uses intermediate results in the calculation process has been suggested. The optimization problem has been solved applying a computer network and parallel computing software MPI (Message Passage Interface). Numerous experimental trials have been carried out to investigate efficiency of the designed strategy in the solution of multiple criteria optimization problems. A computer network with different number of computers solved a single problem of different duration and final results of various strategies have been compared. The experiments have proved the designed strategy to be more precise in results and more economical in computing time.

No description available.

Data mining techniques, such as clustering, have become a mainstay in many applications such as bioinformatics, geographic information systems, and marketing. Over the last decade, due to new demands posed by these applications, clustering techniques have been significantly adapted and extended. One such extension is the idea of finding clusters in a dataset that preserve information about some auxiliary variable. These approaches tend to guide the clustering algorithms that are traditionally unsupervised learning techniques with the background knowledge of the auxiliary variable. The auxiliary information could be some prior class label attached to the data samples or it could be the relations between data samples across different datasets. In this dissertation, we consider the latter problem of simultaneously clustering several vector valued datasets by taking into account the relationships between the data samples. We formulate objective functions that can be used to find clusters that are local in each individual dataset and at the same time maximally similar or dissimilar with respect to clusters across datasets. We introduce diverse applications of these clustering algorithms: (1) time series segmentation (2) reconstructing temporal models from time series segmentations (3) simultaneously clustering several datasets according to database schemas using a multi-criteria optimization and (4) clustering datasets with many-many relationships between data samples. For each of the above, we demonstrate applications, including modeling the yeast cell cycle and the yeast metabolic cycle, understanding the temporal relationships between yeast biological processes, and cross-genomic studies involving multiple organisms and multiple stresses. The key contribution is to structure the design of complex clustering algorithms over a database schema in terms of clustering algorithms over the underlying entity sets. / Ph. D.

Abstract : The objective is to provide methods to improve the performance, or prediction accuracy of standard stacking approach, which is an ensemble method composed of simple, heterogeneous base models, through the integration of the diversity generation, combination and/or selection stages for regression problems. In Chapter 1, we propose to combine a set of level-1 learners into a level-2 learner, or ensemble. We also propose to inject a diversity generation mechanism into the initial cross-validation partition, from which new cross-validation partitions are generated, and sub-sequent ensembles are trained. Then, we propose an algorithm to select best partition, or corresponding ensemble. In Chapter 2, we formulate the partition selection as a Pareto-based multi-criteria optimization problem, as well as an algorithm to make the partition selection iterative with the aim to improve more the ensemble prediction accuracy. In Chapter 3, we propose to generate multiple populations or partitions by injecting a diversity mechanism to the original dataset. Then, an algorithm is proposed to select the best partition among all partitions generated by the multiple populations. All methods designed and implemented in this thesis get encouraging, and favorably results across different dataset against both state-of-the-art models, and ensembles for regression. / Résumé : L’objectif est de fournir des techniques permettant d’améliorer la performance de l’algorithme de stacking, une méthode ensembliste composée de modèles de base simples et hétérogènes, à travers l’intégration de la génération de la diversité, la sélection et combinaison des modèles. Dans le chapitre 1, nous proposons de combiner différents sous-ensembles de modèles de base obtenus au primer niveau. Nous proposons un mécanisme pour injecter de la diversité dans la partition croisée initiale, à partir de laquelle de nouvelles partitions de validation croisée sont générées, et les ensembles correspondant sont formés. Ensuite, nous proposons un algorithme pour sélectionner la meilleure partition. Dans le chapitre 2, nous formulons la sélection de la partition comme un problème d’optimisation multi-objectif fondé sur un principe de Pareto, ainsi que d’un algorithme pour faire une application itérative de la sélection avec l’objectif d’améliorer d’avantage la précision d’ensemble. Dans le chapitre 3, nous proposons de générer plusieurs populations en injectant un mécanisme de diversité à l’ensemble de données original. Ensuite, un algorithme est proposé pour sélectionner la meilleur partition entre toutes les partitions produite par les multiples populations. Nous avons obtenu des résultats encourageants avec ces algorithmes lors de comparaisons avec des modèles reconnus sur plusieurs bases de données.

Decision trees are one of the most commonly used tools in decision analysis, knowledge representation, machine learning, etc., for its simplicity and interpretability. We consider an extension of dynamic programming approach to process the whole set of decision trees for the given decision table which was previously only attainable by brute-force algorithms. We study decision tables with many-valued decisions (each row may contain multiple decisions) because they are more reasonable models of data in many cases. To address this problem in a broad sense, we consider not only decision trees but also inhibitory trees where terminal nodes are labeled with “̸= decision”. Inhibitory trees can sometimes describe more knowledge from datasets than decision trees. As for cost functions, we consider depth or average depth to minimize time complexity of trees, and the number of nodes or the number of the terminal, or nonterminal nodes to minimize the space complexity of trees. We investigate the multi-stage optimization of trees relative to some cost functions, and also the possibility to describe the whole set of strictly optimal trees. Furthermore, we study the bi-criteria optimization cost vs. cost and cost vs. uncertainty for decision trees, and cost vs. cost and cost vs. completeness for inhibitory trees. The most interesting application of the developed technique is the creation of multi-pruning and restricted multi-pruning approaches which are useful for knowledge representation and prediction. The experimental results show that decision trees constructed by these approaches can often outperform the decision trees constructed by the CART algorithm. Another application includes the comparison of 12 greedy heuristics for single- and bi-criteria optimization (cost vs. cost) of trees. We also study the three approaches (decision tables with many-valued decisions, decision tables with most common decisions, and decision tables with generalized decisions) to handle inconsistency of decision tables. We also analyze the time complexity of decision and inhibitory trees over arbitrary sets of attributes represented by information systems in the frameworks of local (when we can use in trees only attributes from problem description) and global (when we can use in trees arbitrary attributes from the information system) approaches.

In a peer-to-peer shared ride system, transportation clients with traffic demand negotiate with transportation hosts offering shared ride services for ad-hoc ridesharing in a continuously changing environment, using wireless geosensor networks. Due to the distinctive characteristic of this system—a complex and non-deterministic transportation network, and a local peer-to-peer communication strategy—clients will always have limited transportation knowledge, both from a spatial and a temporal perspective. Clients hear only from nearby hosts, and they do not know the future availability of current or new hosts. Clients can plan optimal trips prior to departure according to their current knowledge, but it is unlikely that these trips will be final optimal trip due to continuously changing traffic conditions. Therefore, it is necessary to evaluate the trip quality in this dynamic environment in order to assess different communication and wayfinding strategies. (For complete abstract open document)

This thesis is devoted to the development of extensions of dynamic programming to the study of decision trees. The considered extensions allow us to make multi-stage optimization of decision trees relative to a sequence of cost functions, to count the number of optimal trees, and to study relationships: cost vs cost and cost vs uncertainty for decision trees by construction of the set of Pareto-optimal points for the corresponding bi-criteria optimization problem. The applications include study of totally optimal (simultaneously optimal relative to a number of cost functions) decision trees for Boolean functions, improvement of bounds on complexity of decision trees for diagnosis of circuits, study of time and memory trade-off for corner point detection, study of decision rules derived from decision trees, creation of new procedure (multi-pruning) for construction of classifiers, and comparison of heuristics for decision tree construction. Part of these extensions (multi-stage optimization) was generalized to well-known combinatorial optimization problems: matrix chain multiplication, binary search trees, global sequence alignment, and optimal paths in directed graphs.

No description available.

No description available.