Many concrete problems, ranging from Portfolio selection to Water resource management, may be cast into a multiobjective programming framework. The simplistic way of superseding blindly conflictual goals by one objective function let no chance to the model but to churn out meaningless outcomes. Hence interest of discussing ways for tackling Multiobjective Programming Problems. More than this, in many real-life situations, uncertainty and imprecision are in the state of affairs. In this dissertation we discuss ways for solving Multiobjective Programming Problems with fixed and fuzzy coefficients. No preference, a priori, a posteriori, interactive and metaheuristic methods are discussed for the deterministic case. As far as the fuzzy case is concerned, two approaches based respectively on possibility measures and on Embedding Theorem for fuzzy numbers are described. A case study is also carried out for the sake of illustration. We end up with some concluding remarks along with lines for further development, in this field. / Operations Research / M. Sc. (Operations Research)

A comparison of social elitist concepts in the works of Karl Marx, Vilfredo Pareto, and Karl Mannheim reveals similar patterns in the uses of these concepts. By listing seven criteria that were developed and by the use of a topical analysis method, similarities are presented and explained. Additional comparisons according to schools of thought and specific national setting are also presented. Structural similarities were identified among the theories; however, content patterns are not evident because of the lack of an accepted definition of the elite. The analysis and the comparison of the concepts of the elite in the works of these major thinkers facilitate and deepen the understanding of this concept in sociological work.

Thèse numérisée par la Direction des bibliothèques de l'Université de Montréal.

This thesis is concerned with developing methodologies that enable existing models to be effectively reused. Results of this thesis are presented in the framework of Quantitative Structural-Activity Relationship (QSAR) models, but their application is much more general. QSAR models relate chemical structures with their biological, chemical or environmental activity. There are many applications that offer an environment to build and store predictive models. Unfortunately, they do not provide advanced functionalities that allow for efficient model selection and for interpretation of model predictions for new data. This thesis aims to address these issues and proposes methodologies for dealing with three research problems: model governance (management), model identification (selection), and interpretation of model predictions. The combination of these methodologies can be employed to build more efficient systems for model reuse in QSAR modelling and other areas. The first part of this study investigates toxicity data and model formats and reviews some of the existing toxicity systems in the context of model development and reuse. Based on the findings of this review and the principles of data governance, a novel concept of model governance is defined. Model governance comprises model representation and model governance processes. These processes are designed and presented in the context of model management. As an application, minimum information requirements and an XML representation for QSAR models are proposed. Once a collection of validated, accepted and well annotated models is available within a model governance framework, they can be applied for new data. It may happen that there is more than one model available for the same endpoint. Which one to chose? The second part of this thesis proposes a theoretical framework and algorithms that enable automated identification of the most reliable model for new data from the collection of existing models. The main idea is based on partitioning of the search space into groups and assigning a single model to each group. The construction of this partitioning is difficult because it is a bi-criteria problem. The main contribution in this part is the application of Pareto points for the search space partition. The proposed methodology is applied to three endpoints in chemoinformatics and predictive toxicology. After having identified a model for the new data, we would like to know how the model obtained its prediction and how trustworthy it is. An interpretation of model predictions is straightforward for linear models thanks to the availability of model parameters and their statistical significance. For non linear models this information can be hidden inside the model structure. This thesis proposes an approach for interpretation of a random forest classification model. This approach allows for the determination of the influence (called feature contribution) of each variable on the model prediction for an individual data. In this part, there are three methods proposed that allow analysis of feature contributions. Such analysis might lead to the discovery of new patterns that represent a standard behaviour of the model and allow additional assessment of the model reliability for new data. The application of these methods to two standard benchmark datasets from the UCI machine learning repository shows a great potential of this methodology. The algorithm for calculating feature contributions has been implemented and is available as an R package called rfFC.

The aim of the thesis is to analyse the product range manufactured by the company TON, which is a traditional Czech producer of bent wood furniture and especially chairs. The company TON has managed to maintain its position in the market for long 150 years, mainly thanks to the sensitive perception of changes in customer needs and adapting its product portfolio meeting them. In the theoretical part of the thesis are defined the basic concept of the marketing mix, product mix and described the methods and analysis as SLEPT analysis, Porter analysis, Portfolio analysis and Pareto analysis, which are then used in the practical part of the thesis. Based on the analysis there are formulated the conclusions which give recommendations on optimizing the product range and on effective use of certain elements of marketing mix for placing the product portfolio on target markets.

The Paper is focused on risk analysis of composite bumper Arway S production process. The bumper is produced by Composite Components company for Iveco bus producer. According to discussions of expert team, several types of quality discrepancies were discovered. By using FTA analysis we discovered causes of those discrepancies. FMEA method and Pareto Analysis helped to set most dangerous discrepancies which cumulative seriousness reached 54 %. In discussion, the expert team set corrective action. In parallel with FMEA and Pareto Analysis 8D method was used. It's results were in line with other methods and complete the whole image of the issue. Arway S is a key product and so some of those proposed corrective actions were realized immediately. As a result, the appearance of rejections with specific defect almost vanished.

Global warming is affecting the Earth climate year by year, the biggest difference being observable in increasing temperatures in the World Ocean. Following the long- term global ocean warming trend, average sea surface temperatures across the global tropics and subtropics have increased by 0.4–1◦C in the last 40 years. These rates become even higher in semi-enclosed southern seas, such as the Red Sea, threaten- ing the survival of thermal-sensitive species. As average sea surface temperatures are projected to continue to rise, careful study of future developments of extreme temper- atures is paramount for the sustainability of marine ecosystem and biodiversity. In this thesis, we use Extreme-Value Theory to study sea surface temperature extremes from a gridded dataset comprising 16703 locations over the Red Sea. The data were provided by Operational SST and Sea Ice Analysis (OSTIA), a satellite-based data system designed for numerical weather prediction. After pre-processing the data to account for seasonality and global trends, we analyze the marginal distribution of ex- tremes, defined as observations exceeding a high spatially varying threshold, using the Generalized Pareto distribution. This model allows us to extrapolate beyond the ob- served data to compute the 100-year return levels over the entire Red Sea, confirming the increasing trend of extreme temperatures. To understand the dynamics govern- ing the dependence of extreme temperatures in the Red Sea, we propose a flexible local approach based on R-Pareto processes, which extend the univariate Generalized Pareto distribution to the spatial setting. Assuming that the sea surface temperature varies smoothly over space, we perform inference based on the gradient score method over small regional neighborhoods, in which the data are assumed to be stationary in space. This approach allows us to capture spatial non-stationarity, and to reduce the overall computational cost by taking advantage of distributed computing resources. Our results reveal an interesting extremal spatial dependence structure: in particular, from our estimated model, we conclude that significant extremal dependence prevails for distances up to about 2500 km, which roughly corresponds to the Red Sea length.

This study is conducted with the aims to develop a new ranking method for multi-criteria decision making problem with conflicting criteria. Such a problem has a set of Pareto solutions, where the act of improving a value of one solution will result in depreciating some of the others. Thus, in this type of problem, there is no unique solution. However, out of many available options, the Decision Maker eventually has to choose only one solution. With this problem as the motivation, the current study develops a compromise ranking algorithm, namely a trade-off ranking method. The trade-off ranking method able to give a trade-off solution with the least compromise compared to other choices as the best solution. The properties of the algorithm are studied in the thesis on several test cases. The proposed method is compared against several multi-criteria decision making methods with ranking based on the distance measure, which are the TOPSIS, relative distance and VIKOR. The sensitivity analysis and uncertainty test are carried out to examine the methods robustness. A critical criteria analysis is also done to test for the most critical criterion in a multi-criteria problem. The decision making method is considered further in a fuzzy environment problem where the fuzzy trade-off ranking is developed and compared against existing fuzzy decision making methods.

The role of feedback in the design of aircraft stability and control is becoming increasingly important. The basic reason driving this trend is the necessity to cope with a growing number of more stringent requirements, which are sometimes conflicting. This work presents a design methodology applicable to flight control laws, which can be either a control and stability augmentation system (CSAS) or an automatic flight control system (AFCS). A key feature of the proposed method is the definition of a simple cost function, which incorporates both performance and robustness requirements. The optimization of this cost function is employed to tune some of the control law parameters. It is also presented how to integrate this optimization procedure with the other important design steps, such as requirements definition, data filtering, control law structure definition, shaping the input-output transmission via pre-filters, etc. It is emphasized, at this point, that the format of this cost function is able to encapsulate, in a straightforward manner, the requirements normally applicable to the feedback portion of flight control laws. It is also flexible enough to accommodate different choices of data preprocessing, as well as different choices of feedback structure. The final design step is the setting of appropriate scheduling function for each of the defined scheduled parameters. For illustration purposes, four design examples are presented, namely a yaw damper, a bank angle rate/side slip angle regulator, a pitch attitude rate regulator and a pressure altitude regulator. The aircraft model under consideration is based on available data from Boeing 747. Sensors and actuators dynamics, as well as transport delays due to digital control implementation, are considered. The results show that the proposed methodology is able to satisfactorily fulfill the design requirements normally applicable to flight control laws.

This work aims to demonstrate an approach to design a fly-by-wire mobile surface control system for a commercial jet employing multiobjective optimization techniques. This approach consists on sizing a set of design parameters of the control system based on model simulation and response analysis coupled with optimization algorithms in a multiobjective design environment. An overview on control surface systems is presented, focusing on fly-by-wire. To provide the theoretical basis, a review on optimization theory and methods is presented, as well it is developed the system mathematical model. The system in focus is of electro-hydraulic actuation, where a controller acts on a servo valve, that commands an actuator for positioning control of an aircraft rudder. The design approach was to optimize a set of system components parameters, such as controller gains, servo valve and hydraulic actuator parameters, that result in adequate workloads and produce a system that meets the design requirements and is cost-effective. The model, to be simulated and analyzed, is implemented in MATLAB/Simulink, from where the system response characteristics are passed to the optimization environment. A multiobjective genetic algorithm is applied, and as a result from the optimization process we obtain a Pareto set, from where an optimal design is chosen for a detailed analysis.