Submitted by Secretaria Pós de Produção (tpp@vm.uff.br) on 2017-07-27T20:00:22Z No. of bitstreams: 1 D2016 - Ana Paula dos Santos.pdf: 1475202 bytes, checksum: 995f3768e015149be9bbdbae4aff8e20 (MD5) / Made available in DSpace on 2017-07-27T20:00:22Z (GMT). No. of bitstreams: 1 D2016 - Ana Paula dos Santos.pdf: 1475202 bytes, checksum: 995f3768e015149be9bbdbae4aff8e20 (MD5) / A baixa discriminação e o esquema de multiplicadores pouco realistas são frequentemente apontadas como limitações da Análise Envoltória de Dados (DEA, de Data Envelopment Analysis). Com o propósito de amenizá-las, o modelo MCDEA (Multiple Criteria DEA) foi desenvolvido sob uma perspectiva multiobjetivo. Como na maioria dos problemas multiobjetivo, o modelo MCDEA não costuma gerar uma solução ótima única, mas um conjunto de soluções não dominadas. Buscando obter uma solução, que, tanto quanto possível, otimize conjuntamente as funções objetivo do modelo MCDEA, foram propostas abordagens baseadas na metodologia de programação por metas (GP, de Goal Programming). Dentre elas, destacam-se os modelos GPDEA, que usam programação por metas do tipo soma ponderada. Contudo, recentemente, os modelos GPDEA foram considerados inválidos, sem que nenhuma formulação alternativa baseada em programação por metas fosse proposta. Visando preencher tal lacuna, esta tese tem o objetivo de desenvolver formulações que solucionem, apropriadamente, o modelo MCDEA, para o caso de retornos constantes e variáveis de escala, mediante o uso de programação por metas do tipo soma ponderada. Essas formulações foram denominadas modelos WGP-MCDEA (Weighted GP-MCDEA), e englobam tanto a orientação a inputs como a outputs. Os modelos propostos geram as soluções básicas não dominadas dos modelos MCDEA correspondentes, quando os níveis de aspiração para as metas são precisamente definidos com este fim. Quando esses níveis são relaxados, em geral, os modelos WGP-MCDEA geram as soluções não dominadas dos modelos MCDEA correspondentes que cobrem a maior área na região de indiferença dos pesos. / Low discrimination and unrealistic multipliers schemes are often cited as limitations of DEA. To mitigate those limitations, the MCDEA model was developed under a multi-objective perspective. As in most multiple objective problems, MCDEA model does not usually result in a unique optimal solution, but in a set of non-dominated solutions. In an attempt to obtain a satisfactory solution, which, as far as possible, jointly optimizes MCDEA´s objective functions, some goal-programming-based approaches were proposed. Among those proposals, we highlight the GPDEA models, which use weighted goal programming. However, recently, GPDEA models were considered invalid, without any alternative goal-programming-based formulation being proposed. Seeking to fill this gap, the objective of this dissertation is to develop formulations that appropriately solve MCDEA model for the cases of constant and variable returns-to-scale, by means of weighted goal programming. These formulations were called WGP-MCDEA models, and include both input and output orientations. The proposed models generate the basic non-dominated solutions of the corresponding MCDEA models when the goals´ aspiration levels are specifically defined for this purpose. When those aspiration levels are smoothened, the WP-MCDEA models generally produce the non-dominated solution of the corresponding MCDEA models that cover the largest area in the indifference region.

Innovation is one of the most important sources of competitive advantage. It helps a company to fuel the growth of new products and services, sustain incumbents, create new markets, transform industries, and promote the global competitiveness of nations. Because of its importance, companies need to manage innovation. It is very important for a company to be able to measure its innovativeness because one cannot effectively manage without measurement. A good measurement model will help a company to understand its current capability and identify areas that need improvement. In this research a systematic approach was developed for a company to measure its innovativeness. The measurement of innovativeness is based on output indicators. Output indicators are used because they cannot be manipulated. A hierarchical decision model (HDM) was constructed from output indicators. The hierarchy consisted of three levels: innovativeness index, output indicators and sub-factors. Experts' opinions were collected and quantified. A new concept developed by Dr. Dundar Kocaoglu and referred to as "desirability functions" was implemented in this research. Inconsistency of individual experts, disagreement among experts, intraclass correlation coefficients and statistical F-tests were calculated to test the reliability of the experts' judgments. Sensitivity analysis was used to test the sensitivity of the output indicators, which indicated the allowable range of the changes in the output indicators in order to maintain the priority of the sub-factors. The outcome of this research is a decision model/framework that provides an innovativeness index based on readily measurable company output indicators. The model was applied to product innovation in the technology-driven semiconductor industry. Five hypothetical companies were developed to simulate the application of the model/framework. The profiles of the hypothetical companies were varied considerably to provide a deeper understanding of the model/framework. Actual data from two major corporations in the semiconductor industry were then used to demonstrate the application of the model. According to the experts, the top three sub-factors to measure the innovativeness of a company are revenue from new products (28%), market share of new products (21%), and products that are new to the world (20%).

Many entrepreneurs and companies use loans to cover their business needs. Usually it is difficult to choose the best offer. The possible solution is the utilization of methods of multiple-criteria decision-making, which make the decision process easier. The goal of this thesis is to describe these methods and use them practically to choose the best loan offer. It was found out that most of the companies do not use these methods. The results are usually significantly affected by the criterion which was the most preferred. For the most of the companies the offer made by MONETA Money Bank, a.s. was the most favourable.

Dealing with optimization problems with more than one objective has been an important research area in evolutionary computation. The class of multi-objective problems (MOPs) is an important one because multi-objectivity exists in almost all aspects of human life; whereby there usually exist several compromises in each problem. Multi-objective evolutionary algorithms (MOEAs) have been applied widely in many real-world problems. This is because (1) they work with a population during the course of action, which hence offer more flexible control to find a set of efficient solutions, and (2) real-world problems are usually black-box where an explicit mathematical representation is unknown. However, MOEAs usually require a large amount of computational effort. This is a sub- stantial challenge in bringing MOEAs to practice. This thesis primarily aims to address this challenge through an investigation into issues of scalability and the balance between exploration and exploitation. These have been outstanding research challenges, not only for MOEAs, but also for evolutionary algorithms in general. A distributed framework of local models using explicit niching is introduced as an overarching umbrella to solve multi-objective optimization problems. This framework is used to address the two-part question about first, the role of communication messages and second, the role of explicit niching in distributed evolutionary multi-objective optimization. The concept behind the framework of local models is for the search to be conducted locally in different areas of the decision search space, which allows the local models to be distributed on different processing nodes. During the optimization process, local models interact (exchange messages) with each other using rules inspired from Particle Swarm Optimization (PSO). Hence, the hypothesis of this work is that running simultaneously several search engines in different local areas is better for exploiting local information, while exchanging messages among those diverse engines can provide a better exploration strategy. For this framework, as the models work locally, they gain access to some global knowledge of each other. In order to validate the proposed framework, a series of experiments on a wide range of test problems was conducted. These experiments were motivated by the following studies which in their totality contribute to the verification of our hypothesis: (1) studying the performance of the framework under different aspects such as initialization, convergence, diversity, scalability, and sensitivity to the framework's parameters, (2) investigating interleaving guidance in both the decision and objective spaces, (3) applying local models using estimation of distributions, (4) evaluating local models in noisy environments and (5) the role of communication messages and explicit niching in distributed computing. The experimental results showed that: (1) the use of local models increases the chance of MOEAs to improve their performance in finding the Pareto optimal front, (2) interaction strategies using PSO rules are suitable for controlling local models, and that they also can be coupled with specialization in order to refine the obtained non-dominated set, (3) estimation of distribution improves when coupled with local models, (4) local models work well in noisy environments, and (5) the communication cost in distributed systems with local models can be reduced significantly by using summary information (such as the direction information naturally determined by local models) as the communication messages, in comparison with conventional approaches using descriptive information of individuals. In summary, the proposed framework is a successful step towards efficient distributed MOEAs.

The surveillance of geographic borders and critical infrastructures using limited sensor capability has always been a challenging task in many homeland security applications. While geographic borders may be very long and may go through isolated areas, critical assets may be large and numerous and may be located in highly populated areas. As a result, it is virtually impossible to secure each and every mile of border around the country, and each and every critical infrastructure inside the country. Most often, a compromise must be made between the percentage of border or critical asset covered by surveillance systems and the induced cost. Although threats to homeland security can be conceived to take place in many forms, those regarding illegal penetration of the air, land, and maritime domains under the cover of day-to-day activities have been identified to be of particular interest. For instance, the proliferation of drug smuggling, illegal immigration, international organized crime, resource exploitation, and more recently, modern piracy, require the strengthening of land border and maritime awareness and increasingly complex and challenging national security environments. The complexity and challenges associated to the above mission and to the protection of the homeland may explain why a methodology enabling the design and optimization of distributed detection systems architectures, able to provide accurate scanning of the air, land, and maritime domains, in a specific geographic and climatic environment, is a capital concern for the defense and protection community. This thesis proposes a methodology aimed at addressing the aforementioned gaps and challenges. The methodology particularly reformulates the problem in clear terms so as to facilitate the subsequent modeling and simulation of potential operational scenarios. The needs and challenges involved in the proposed study are investigated and a detailed description of a multidisciplinary strategy for the design and optimization of detection architectures in terms of detection performance and cost is provided. This implies the creation of a framework for the modeling and simulation of notional scenarios, as well as the development of improved methods for accurate optimization of detection architectures. More precisely, the present thesis describes a new approach to determining detection architectures able to provide effective coverage of a given geographical environment at a minimum cost, by optimizing the appropriate number, types, and locations of surveillance and detection systems. The objective of the optimization is twofold. First, given the topography of the terrain under study, several promising locations are determined for each sensor system based on the percentage of terrain it is covering. Second, architectures of sensor systems able to effectively cover large percentages of the terrain at minimal costs are determined by optimizing the number, types and locations of each detection system in the architecture. To do so, a modified Genetic Algorithm and a modified Particle Swarm Optimization are investigated and their ability to provide consistent results is compared. Ultimately, the modified Particle Swarm Optimization algorithm is used to obtain a Pareto frontier of detection architectures able to satisfy varying customer preferences on coverage performance and related cost.

No description available.

Infrastructure privatization decisions have an enormous financial and social impact on all stakeholders, including the public sector, the private sector, and the general public. Appropriate privatization decisions, however, are difficult to make due to the conflicting nature of the objectives of the various stakeholders. This research introduces a multi-criteria decision-making framework for evaluating and comparing a wide range of privatization schemes for infrastructure facilities. The framework is designed to resolve conflicts that arise because of the varying points of view of the stakeholders, and accordingly, determine the most appropriate decision that satisfies all stakeholders’ preferences. The developed framework is expected to help in re-engineering the traditional conflict resolution process, particularly for construction conflict resolution and infrastructure privatization decisions. The framework provides decision support at the management level through three successive decision support processes related to 1. Screening of feasible solutions using the Elimination Method of multiple criteria decision analysis (MCDA); 2. Analyzing the actions and counteractions of decision makers using conflict resolution and decision stability concepts to determine the most stable resolution; and 3. Considering the uncertainty in decision maker’s preferences using Info-gap Theory to evaluate the robustness of varying uncertainty levels of the decisions. Based on the research, a procedure and a decision support system (DSS) have been developed and tested on real-life case studies of a wastewater treatment plant and a construction conflict. The results of the two case studies show that the proposed DSS can be used to support decisions effectively with respect to both construction conflicts and infrastructure privatization. The developed system is simple to apply and can therefore save time and avoid the costs associated with unsatisfactory decisions. This research is expected to contribute significantly to the understanding and selecting of proper Public-Private-Partnership (PPP) programs for infrastructure assets.

Infrastructure privatization decisions have an enormous financial and social impact on all stakeholders, including the public sector, the private sector, and the general public. Appropriate privatization decisions, however, are difficult to make due to the conflicting nature of the objectives of the various stakeholders. This research introduces a multi-criteria decision-making framework for evaluating and comparing a wide range of privatization schemes for infrastructure facilities. The framework is designed to resolve conflicts that arise because of the varying points of view of the stakeholders, and accordingly, determine the most appropriate decision that satisfies all stakeholders’ preferences. The developed framework is expected to help in re-engineering the traditional conflict resolution process, particularly for construction conflict resolution and infrastructure privatization decisions. The framework provides decision support at the management level through three successive decision support processes related to 1. Screening of feasible solutions using the Elimination Method of multiple criteria decision analysis (MCDA); 2. Analyzing the actions and counteractions of decision makers using conflict resolution and decision stability concepts to determine the most stable resolution; and 3. Considering the uncertainty in decision maker’s preferences using Info-gap Theory to evaluate the robustness of varying uncertainty levels of the decisions. Based on the research, a procedure and a decision support system (DSS) have been developed and tested on real-life case studies of a wastewater treatment plant and a construction conflict. The results of the two case studies show that the proposed DSS can be used to support decisions effectively with respect to both construction conflicts and infrastructure privatization. The developed system is simple to apply and can therefore save time and avoid the costs associated with unsatisfactory decisions. This research is expected to contribute significantly to the understanding and selecting of proper Public-Private-Partnership (PPP) programs for infrastructure assets.

The purpose of this thesis is to develop a model for assessing cost effectiveness of applying lean tools. The model consists of eight phases: it starts by understanding customers' requirements using Voice of Customer (VOC) and Quality Function Deployment (QFD) tools. In phase 2, the current state of plant is assessed using lean profile charts based on Balanced Scorecard (BSC) measures. In phase 3 and phase 4, identification of critical problem(s) and generating of improvement suggestion(s) are performed. Phase 5 provide evaluation of the cost effectiveness of implementing the suggested lean methods based on life cycle cost analysis (LCCA) and phase 6 prefers the right alternative based on multiple criteria decision making (MCDM). In phase 7 the selected alternative is supposed to be implemented and finally the user should monitor and control the process to make sure that the improvement is going as planned. The model was verified successfully using a case study methodology at one Swedish sawmill called Södra Timber in Ramkvilla, one part of Södra group. Results obtained from the study showed that the production and human resources perspectives are the most critical problem areas that need to be improved. They got the lowest scores in the lean profile, 63% and 68%, respectively. Using value stream mapping (VSM) it was found that the non value added (NVA) ratios for the core and side products are 87.4% and 90.4%, respectively. Using the model, three improvement alternatives were suggested and evaluated using LCCA and MCDM. Consequently, implementing 5S got the highest score, second came redesigning the facility layout. However, it was estimated that 4.7 % of NVA for the side product would be reduced by redesigning the facility layout. The recommendations were suggested for the company to improve their performance. The novelty of the thesis is based on the fact that it addresses two main issues related to lean manufacturing: firstly, suggesting lean techniques based on assessment of lean profile that is based on BSC and QFD, and secondly assessing the cost effectiveness of the suggested lean methods based on LCCA and MCDM. This thesis provides a generalized model that enables the decision-maker to know and measure, holistically, the company performance with respect to customer requirements. This will enable the company to analyze the critical problems, suggest solutions, evaluate them and make a cost effective decision. Thus, the company can improve its competitiveness.

This research augments current Multiple Objective Evolutionary Algorithms with methods that dramatically reduce the time required to evolve toward a region of interest in objective space. Multiple Objective Evolutionary Algorithms (MOEAs) are superior to other optimization techniques when the search space is of high dimension and contains many local minima and maxima. Likewise, MOEAs are most interesting when applied to non-intuitive complex systems. But, these systems are often computationally expensive to calculate. When these systems require independent computations to evaluate each objective, the computational expense grows with each additional objective. This method has developed methods that reduces the time required for evolution by reducing the number of objective evaluations, while still evolving solutions that are Pareto optimal. To date, all other Multiple Objective Evolutionary Algorithms (MOEAs) require the evaluation of all objectives before a fitness value can be assigned to an individual. The original contributions of this thesis are: 1. Development of a hierarchical search space description that allows association of crossover and mutation settings with elements of the genotypic description. 2. Development of a method for parallel evaluation of individuals that removes the need for delays for synchronization. 3. Dynamical evolution of thresholds for objectives to allow partial evaluation of objectives for individuals. 4. Dynamic objective orderings to minimize the time required for unnecessary objective evaluations. 5. Application of MOEAs to the computationally expensive flare pattern design domain. 6. Application of MOEAs to the optimization of fielded missile warning receiver algorithms. 7. Development of a new method of using MOEAs for automatic design of pattern recognition systems.