Este trabalho apresenta a construção de um sistema especialista aplicado ao diagnóstico de doenças cardíacas, usando como ferramenta computacional redes Bayesianas. O trabalho envolveu a interação entre diferentes áreas do conhecimento, engenharia e medicina, com maior foco na metodologia da construção de sistemas especialistas. São apresentados os processos de definição do problema, modelagem qualitativa e quantitativa, e avaliação. Neste trabalho, os processos de modelagem e avaliação foram realizados com o auxílio de um especialista médico e de dados bibliográficos. São apresentados como resultados a rede Bayesiana construída e um software para manipulação de redes Bayesianas denominado iBNetz. / This work presents the construction of an expert system applied to the diagnosis of heart diseases, using Bayesian networks as a modeling tool. The work involved interactions between two different fields, engineering and medicine, with special emphasis on the methodology of building expert systems. The processes of problem definition, qualitative and quantitative modeling, and evaluation are presented here. In this work, the modeling and evaluation processes have been conducted with the aid of a medical expert and bibliographic sources. The work has produced a Bayesian network for diagnosis and a software, called iBNetz, for creating and manipulating Bayesian networks.

O problema de escassez da água para o abastecimento humano vem se agravando a cada ano que passa. As demandas vem crescendo e precisam ser supridas da melhor maneira possível sob pena de limitar o processo de desenvolvimento regional. Para tanto, deve-se recorrer ao planejamento e gerenciamento dos recursos hídricos como forma de se promover ao seu uso racional. Descreve-se neste trabalho a implantação de um sistema de apoio ao planejamento e gerenciamento de recursos hídricos, dando uma maior ênfase ao modelo hidrológico distribuído utilizado para gerar as vazões na bacia hidrográfica. Avalia-se sua calibração e validação realizada com dados fluviométricos e de níveis de açudes. Apresentam-se os resultados de estudo de potencialidade da bacia hidrográfica, e por último as disponibilidades dos principais açudes. Todas estas etapas formam realizadas tendo sempre a visão especializada e integrada da bacia hidrográfica do rio do Peixe. / The problem of scarcity of water for human supply has increased each year. The needs have increased and must be fullfilled as satisfactory as possible. If not the development process ofthe region could be limited. In this way, we must use the planning and management of water resources to promote a rational use. This dissertation describes the implantation of a support system to the planning and management of water resources, focusing the hydrologic distributed model used to generate the inflows in the basin. The calibration and validation processes with sets of data formed by gauge stream go stations and reservoir levels are analyzed. The results of a study of the potentiality of the basin, and finally the availability of the mains reservoirs are presented. All this steps were made with a specialized and integrated view of the Peixe river basin.

Alguns dos problemas enfrentados pelas cidades que ainda sofrem com um crescimento rápido são, não raro, conseqüência da falta de políticas públicas que possam orientar o crescimento espacial de forma sustentável e com qualidade de vida. Há uma clara necessidade de instrumentos efetivos de controle e monitoramento da mobilidade urbana, bem como de políticas mais sustentáveis destinadas a orientar o crescimento e ordenamento espacial. Neste contexto, a elaboração de um sistema de suporte à decisão através de uma interface on-line pode proporcionar novas perspectivas para um planejamento da mobilidade mais participativo e sustentável. Assim, um dos objetivos desta pesquisa foi desenvolver uma ferramenta computacional destinada a promover um processo integrado e sustentável para elaboração e monitoramento de planos diretores de mobilidade urbana. A proposta focou no processo de tomada de decisão participativo envolvendo múltiplos segmentos da sociedade, sobretudo em cidades pequenas e médias. Outro objetivo foi verificar se, através da utilização do sistema proposto, os avaliadores (especialistas ou não-especialistas), modificariam significativamente seu nível de percepção com relação à mobilidade urbana. Para atingir a estes objetivos, a pesquisa foi dividida em duas fases. Inicialmente foi desenvolvido o sistema de suporte à decisão para internet, denominado PLANUTS - PLANejamento Urbano e de Transportes integrado e Sustentável. Este sistema é composto por quatro módulos de avaliação da mobilidade urbana e um módulo administrativo. O funcionamento da ferramenta proposta foi demonstrado, na prática, através de sua aplicação junto a um grupo de especialistas e não-especialistas em Bauru, cidade média localizada no estado de São Paulo, Brasil. Com a aplicação foi possível simular etapas do desenvolvimento de um plano diretor de transporte e mobilidade participativo, com a definição de indicadores de mobilidade. A aplicação também foi útil para demonstrar a contribuição do sistema na mudança de percepção dos usuários com relação a questões que envolvem aspectos da mobilidade. Os resultados obtidos conduziram às seguintes conclusões: i) o sistema PLANUTS pode contribuir para a participação de diferentes segmentos da sociedade no processo de avaliação da mobilidade urbana; ii) a utilização do sistema possibilita uma ampliação no conhecimento e definição dos temas que envolvem a mobilidade urbana; e iii) é possível definir um conjunto de indicadores representativos dos problemas mais importantes de mobilidade com vistas a um sistema de indicadores de mobilidade no município. / Some of the problems faced by fast growing cities are often a consequence of the lack of public policies able to drive the spatial growth towards sustainable development and a better quality of life. There is a clear need of more effective tools for urban mobility monitoring and control, as well as sustainable policies for guiding urban growth and spatial distribution. In such a context, the construction of a web-based decision support system can produce new perspectives for mobility planning in a more participative and sustainable way. Therefore, one of the objectives of this research was to develop a computational tool for promoting an integrated and sustainable process of construction and management of mobility master plans. The focus of the proposal was on a participative decision-making process involving multiple segments of the society, mainly of small and medium-sized cities. Another objective of the research was to test if the use of the proposed system could significantly change the perception level of the participants (experts or non-experts) regarding urban mobility. In order to reach the stated objectives, the research was conducted in two phases. The first step was the development of the internet-based decision support system named PLANUTS (which stands for PLANnig Urban and Transportation integrated and Sustainable systems). It comprises four modules for the evaluation of urban mobility and one administrative module. The use of the proposed tool was shown, in practice, through an application with a group of experts and another one of non-experts in Bauru, which is a medium-sized city located in the state of São Paulo, Brazil. The application made possible to simulate some steps of the development of a participative mobility master plan, with the definition of mobility indicators. It was also useful for showing the contribution of the system in changing the users\' perception regarding mobility issues. The results obtained led to the following conclusions: i) PLANUTS can be used to allow the participation of distinct segments of the society in the evaluation of urban mobility; ii) the use of the system brings an improvement in the definition of the Themes and to the overall knowledge of urban mobility; and iii) it is possible to define a set of indicators associated to the most important mobility problems in order to build a system of urban mobility indicators to the municipality.

Dans le contexte Méditerranéen pluri-complexe aux niveaux écologique que sociopolitique, la mise en place de zones protégées mobilise une grande diversité d’outils basés sur des réalités règlementaires, foncières, financières, scientifiques et techniques. Cette thèse est fondée sur le principe de priorisation des enjeux socio-écologiques de conservation pour une orientation pertinente des options de protection dans les régions du pourtour méditerranéen. Elle s’appuie sur l’exemple précis du Liban, où les initiatives de protection semblent toujours guidées par une réponse à des enjeux socio-politique locaux qui priment sur les enjeux écologiques. Le but est de proposer une démarche objective, basée sur une combinaison de descripteurs écologiques et socio-économiques, qui permettrait une orientation réfléchie et adaptée pour la future désignation des aires protégées. Ainsi, sur base d’une revue bibliographique, des descripteurs adaptés au contexte méditerranéen, ont été identifiés. A partir de ceux-ci nous avons élaboré un outil de support à la décision qui permet de structurer les priorités de conservation de la biodiversité en utilisant les meilleures connaissances disponibles. Cet outil, testé sur plusieurs sites au Liban, propose différentes alternatives de protection priorisées, parmi lesquelles l’utilisateur (ministère, municipalité, région…) serait en mesure de choisir la plus appropriée en fonction du contexte sociopolitique prévalent. Ceci met l’accent sur la forte dimension politique dans la conservation. Si l’objectif est de fournir un outil pour la désignation des aires protégées, les véritables défis se situeront ensuite au niveau des choix d’ordre politique. / In the multi-complex ecological and socio-political Mediterranean context, protected areas establishment is strongly conditioned by a wide range of regulatory, land estate, financial, scientific and technical realities. The support of decision makers in the design and implementation of protected areas networks is thus needed. This thesis is founded the concept of prioritization, where socio-ecological conservation issues are prioritized for an appropriate orientation of protection options in Mediterranean countries. It is based on the specific example of Lebanon, where protection initiatives remain so far poorly adapted to ecological conservation needs. The goal is to provide an objective approach, based on a combination of ecological and socio-economic descriptors that would allow a pertinent and adapted guidance of future protected areas designation. Thus, based on a peer and grey literature review, a set of adapted-to-the-Mediterranean-context descriptors, were identified. Arising from these descriptors, we developed a decision support tool (MedConserve) which structures biodiversity conservation priorities based on the best available knowledge. Tested on different sites in Lebanon, this tool suggests several prioritized protection alternatives, from which the user (ministry, municipality, region, etc.) would be able to select the most appropriate option according to the prevailing socio-political context. This study emphasizes the strong political dimension of conservation. Even if the objective is to provide a tool for protected areas designation, the real challenges will always be related to political choices and decisions.

O trabalho apresenta o sistema de apoio à decisão - SAD, projetado especificamente para pequenas indústrias. A pesquisa concentrou-se em parte no estudo das disciplinas envolvidas no tema análise econômico-financeira de empresas, de forma a recuperar as teorias e conceitos mais pertinentes, para, numa segunda etapa, aplicá-las ao projeto e implementação de um sistema de apoio às decisões de pequenas indústrias. O sistema de apoio à decisão - SAD foi concebido em parceria com 107 empresas de São Paulo, com o objetivo de realizar, de forma acurada e rápida, várias análises de apoio à tomada de decisões, entre as quais destacam-se as seguintes: análise das relações custo - volume - lucro (CVL); análise por taxa-alvo de retorno; cálculo de preços (orçamentos); análise econômica de seleção de produtos e de terceirizações de produtos, subconjuntos e operações. Além de específicas análises de administração financeira, outras relativas ao planejamento da produção são também colocadas à disposição pelo SAD, como é o caso do planejamento de materiais e de subconjuntos - MRP-I, do planejamento de capacidade para operações e máquinas - CRP, e do diagrama De-Para para apoiar arranjo físico, entre outras. O sistema tem oferecido apoio a uma série de tomadas de decisões em pequenas indústrias do Estado de São Paulo, com efetiva melhoria dos seus resultados econômico-financeiros. / This study presents a decision support system - simplified in portuguese as SAD, specifically designed to small manufacturing companies. The research concentrated partly on the study of the disciplines involved in economic-financial analysis of companies, in way to recover the theories and more pertinent concepts, for, in a second stage, to apply them to the project of a decision support system of industries of small load. The SAD was conceived and validated in partnership with 107 small manufacturing companies of São Paulo. It uses Managerial Accounting and Microeconomic models as long as Industrial Engineering methods. The research priorizes practical relevant managerial issues. The SAD was designed to realize accurately and rapidly several analysis to support decision making. The following analysis were highlighted: profit-cost-volume, target rate of return, pricing, products\' selection mix and make-or-buy decisions. Besides specifically financial management analysis, others relative to production planning were made available by the SAD, as materials requirements planning (MRP), capacity requirements planning (CRP), and the \"Chart of weighted values\" that supports lay out. The decision support system - SAD offered decision support to several small manufacturing companies, with effective improvement in their economical, financial and operational results.

Esta tese desenvolveu um Sistema de Suporte a Decisão para auxiliar na concessão de outorga de lançamento de efluentes, através do qual é possível avaliar estratégias de outorga visando facilitar o processo de análise e a efetivação do instrumento. O SSD utiliza em seu processo de análise algoritmos evolucionários para a otimização do processo de alocação de demanda e de carga efluente, visando a maximização dos usos e a minimização dos custos das medidas de tratamento de efluentes, respeitando os limites estabelecidos pela classe de enquadramento dos corpos dágua. Os algoritmos evolutivos analisados foram os Algoritmos Genéticos, Particle Swarm Optimization e o Differential Evolution. Entre as estratégias de outorga consideradas estão o atendimento da legislação ambiental para o lançamento de efluentes, a isonomia entre os usuários, o atendimento aos padrões de qualidade estabelecidos pelo enquadramento dos corpos hídricos e as restrições impostas pelo órgão gestor aos usuários ou as finalidades de uso. Para avaliar o desempenho do SSD foi realizado um estudo de caso na Bacia Hidrográfica do Rio Atibaia, no Estado de São Paulo. O Rio Atibaia foi escolhido por apresentar problemas de disponibilidade hídrica e conflitos pelo uso da água, o que permite avaliar os resultados do SSD para as diferentes estratégias em um caso real. Os resultados obtidos pelos três algoritmos para as estratégias analisadas foram satisfatórios atendendo as restrições e penalidades impostas à função objetivo. Observou-se que a estratégia de outorga que não considerou a Legislação Ambiental para lançamento de efluentes e a questão da isonomia entre os usuários apresentou o menor custo global das medidas de tratamento de efluentes. Este resultado se deve ao fato desta estratégia ser menos restritiva que as demais analisadas, e pelo melhor aproveitamento da vazão disponível no trecho para diluir os efluentes. As estratégias propostas neste estudo tiveram como principal objetivo avaliar o comportamento do SSD na obtenção das análises, assim como analisar a flexibilidade dos algoritmos na introdução de restrições e penalidades. Para a escolha das estratégias de outorga, destaca-se o importante papel do Comitê de Bacia e do órgão gestor para definir as prioridades, tendo em vista que os critérios de outorga, a legislação ambiental e a isonomia, podem acarretar em investimentos mais elevados para a implementação das medidas de tratamento. O Sistema de Suporte a Decisão proposto nesta tese representa um avanço no processo de gestão de recursos hídricos, uma vez que envolve importantes critérios e estratégias na análise da outorga de direito de uso da água, sem dissociar os aspectos de quantidade e qualidade da água e aspectos econômicos para sua efetivação. / This study presents a Decision Support System (DSS) to assist in the issuing of wastewater discharge and water abstraction rights, including the evaluation of alternative pollution control strategies used to facilitate the analysis and implementation of the instrument. The DSS substantiates its analysis with the use of evolutionary algorithms for the optimization of water demand and wastewater discharge allocation. It intends to maximize the uses and minimize the costs of wastewater treatment measures, according to the limits imposed by the water quality standards. The evolutionary algorithms investigated in this study include Genetic Algorithms, Particle Swarm Optimization and Differential Evolution. Among the strategies considered for the issuing of water rights were the compliance with environmental legislation for wastewater discharge, the equality between water users, the water quality standards et by the water bodies classification, and the restrictions imposed by the responsible controlling agency. The SSD was evaluated on a case study area, at Atibaia River, located in the State of Sao Paulo. The Atibaia River was chosen because of the existence of innumerous conflicts of over water use and availability. It allows the assessment of the SSD performance, to different strategies, in a real case scenario. The SSDs results, using all three introduced algorithms, were satisfactory to the strategies analyzed, as they complied with the restrictions and penalties imposed to the objective function. Strategy one, with no restrictions or penalties, had the lowest overall cost of wastewater treatment measures, in comparison to strategy two, equity between water users, and three, compliance with Environmental Laws. This result is due to the fact that strategy one is less restrictive than the two others, and because of the best use of the available flow, in each respective reach, to dilute the wastewater discharge. The main objective of the proposed strategies is to evaluate the performance of the SSD in getting the results, as well as to analyze the flexibility of the algorithms when new restrictions and penalties are introduced in the decision making process. Water users, other stakeholders and the responsible controlling agency have an important role in the selection of suitable strategies and priorities of uses. Higher investments to implement water treatment measures may become necessary according to the strategy chosen. In addition, when a strategy is not well defined, it may cause unnecessary investments. The DSS proposed in this study represents an advance in water resources management. It involves important criteria and strategies used in the analysis of wastewater discharge and water abstraction rights, without disassociating water quality and quantity aspects as well as economic factors for its implementation.

abstract: Allocating tasks for a day's or week's schedule is known to be a challenging and difficult problem. The problem intensifies by many folds in multi-agent settings. A planner or group of planners who decide such kind of task association schedule must have a comprehensive perspective on (1) the entire array of tasks to be scheduled (2) idea on constraints like importance cum order of tasks and (3) the individual abilities of the operators. One example of such kind of scheduling is the crew scheduling done for astronauts who will spend time at International Space Station (ISS). The schedule for the crew of ISS is decided before the mission starts. Human planners take part in the decision-making process to determine the timing of activities for multiple days for multiple crew members at ISS. Given the unpredictability of individual assignments and limitations identified with the various operators, deciding upon a satisfactory timetable is a challenging task. The objective of the current work is to develop an automated decision assistant that would assist human planners in coming up with an acceptable task schedule for the crew. At the same time, the decision assistant will also ensure that human planners are always in the driver's seat throughout this process of decision-making. The decision assistant will make use of automated planning technology to assist human planners. The guidelines of Naturalistic Decision Making (NDM) and the Human-In-The -Loop decision making were followed to make sure that the human is always in the driver's seat. The use cases considered are standard situations which come up during decision-making in crew-scheduling. The effectiveness of automated decision assistance was evaluated by setting it up for domain experts on a comparable domain of scheduling courses for master students. The results of the user study evaluating the effectiveness of automated decision support were subsequently published. / Dissertation/Thesis / Masters Thesis Computer Science 2019

abstract: Public institution facility operations and maintenance is a significant factor enabling an institution to achieve its stated objectives in the delivery of public service. To meet the societal need, Facility Directors must make increasingly complex decisions managing the demands of building infrastructure performance expectations with limited resources. The ability to effectively measure a return-on-investment, specific to facility maintenance indirect expenditures, has, therefore, become progressively more critical given the scale of public institutions, the collective age of existing facilities, and the role these institutions play in society. This research centers on understanding the method of prioritizing routine work in support of indirect institutional facility maintenance expense through the lens of K-12 public education in the state of Arizona. The methodology documented herein utilizes a mixed method approach to understand current facility maintenance practices and assess the influence of human behavior when prioritizing routine work. An evidence-based decision support tool, leveraging prior academic research, was developed to coalesce previously disparate academic studies. The resulting process provides a decision framework for prioritizing decision factors most frequently correlated with academic outcomes. A purposeful sample of K-12 unified districts, representing approximately one-third of the state’s student population and spend, resulted in a moderate to a strong negative correlation between facility operations and student outcomes. Correlation results highlight an opportunity to improve decision making, specific to the academic needs of the student. This research documents a methodology for constructing, validation, and testing of a decision support tool for prioritizing routine work orders. Findings from a repeated measures crossover study suggest the decision support tool significantly influenced decision making specific to certain work orders as well as the Plumbing and Mechanical functional areas. However, the decision support tool was less effective when prioritizing Electrical and General Maintenance work orders. Moreover, as decision making transitioned away from subjective experience-based judgment, the prioritization of work orders became increasingly more consistent. The resulting prioritization, therefore, effectively leveraged prior empirical, evidence-based decision factors when utilizing the tool. The results provide a system for balancing the practical experience of the Facility Director with the objective guidance of the decision support tool. / Dissertation/Thesis / Doctoral Dissertation Construction Management 2019

Decisions Support Systems (DSSs) are used to enhance decision maker speed and effectiveness. However, without a view of an entire system, any decision may have unanticipated effects such as sub-optimal outcomes. The purpose of this research is to show that with a system-level analysis, more informed decisions can be made that take into account a larger system or greater number of dimensions or objectives. This research also explores the benefits of using a DSS over analysis of unprocessed data and the effectiveness of integrating a product design generator (PDG) with a business DSS, creating a system DSS, where system-level effects can be analyzed. These are connected using software which allows them to be interactive, and dynamically updating. After this DSS was developed a variation was also made and decision makers evaluated these tools to identify how they performed in comparison to each other. In one variation, aspects of the tool were split up, guiding the decision maker through the analysis while the other did not. Using survey questions and recording decision makers' actions, it was found that decision makers are significantly faster and came to better conclusions when using the DSS over unprocessed data. However, it was also seen that the difference between the two variants of the System DSS tests was insignificant. This suggests that the limits in potential interactions in the one variant of a system DSS did not substantially reduce the ability of a decision maker to explore and make good design decisions. Overall this research showed that having a system-level tool is better than the unprocessed data, and that more extreme differences in a DSS are required for improved comparisons to establish which visualizations and elements are most effective in a System DSS. Future effort should be made to completely isolate different portions of the System DSS and see how well users are able to make decisions with it compared to the full system analysis.

L'objectif de cette thèse est de fournir des outils d'aide à la décision pour piloter les plateformes logistiques à court de moyen terme. La première partie décrit la problématique concernée et les notions essentielles dans le cadre des chaînes logistiques. Dans la deuxième partie, le problème de la planification est étudié, nous proposons des modèles linéaires pour minimiser les coûts de personnel, qui prennent en compte les flux : leurs variations saisonnières, la possibilité de les négocier localement en amont et en aval, ainsi que leur organisation et celle du travail. Ainsi, l'outil peut être utilisé dans la coordination des flux entres les partenaires de la chaîne livrées en amont et en aval de la plateforme et la négociation des dates de livraison. Ces modèles sont testés et validés sur des instances générées aléatoirement, sur des configurations inspirées de problèmes réels. Dans la troisième partie, nous travaillons sur l'ordonnancement des activités de préparation de commandes. Ici, nous combinons deux familles de contraintes difficiles : l'arrivée de composants (ressources consommables) à des dates et en quantités connues à l'amont de la plateforme, et des tournées de livraison à dates fixées à l'aval. Trois cas particuliers sont étudiés, selon la façon dont les tournées sont organisées. Nous proposons des procédures par séparation et évaluation pour ces problèmes, et un modèle linéaire en nombres entiers pour le cas le plus simple. Des expériences sont faites sur des familles d'instances générées aléatoirement et de manière partiellement hétérogène. Plusieurs perspectives de généralisation sont proposées / The aim of this thesis is to provide decision support systems to control logistic platforms at the mid-term and short-term levels. Several problems and main notions concerning logistic platform context are described in the first part. In the second part, planning problems are studied. Two linear programming models are proposed to minimize the workforce costs. These models take into account several characteristics : seasonal flow variations, work and flow organization in the platform, and local negotiations of the upstream and downstream flows. In consequence, our decision support system can be used in the flow coordination between supply chain partners. Two types of negotiations are considered : negotiations of upstream and downstream delivered quantities and negotiation of delivery dates. These models have been tested on pertinent randomly generated instances inspired from concerete problems. In the third part of the thesis, the external flows of the platforme are assumed to be fixed. Orders preparation scheduling problem inside the platform is considered. Two families of strong contraints are combined : staircase availability of components (consumable resources) and dixed delivery dates. According to the way the downstream deliveries are organized and penalised, three different cases (based on industrial applications) have been studied. We proposed three branch and bound procedures for these problems, and an integer linear program for the easiest problem. Experimental analysis has been done over heterogeneous randomly generated instance families. In the last part, a series of perspectives for this work are proposed