Orientadores: Gilberto Shigueo Nakamiti, Heloisa Vieira da Rocha / Dissertação (mestrado profissional) - Universidade Estadual de Campinas, Instituto de Computação / Made available in DSpace on 2018-08-04T19:58:40Z (GMT). No. of bitstreams: 1 Julio_MarciaReginaFerroMoss_M.pdf: 5134591 bytes, checksum: 7b347ade85c8652d790d671fd0d3bd1c (MD5) Previous issue date: 2005 / Resumo: No momento da escolha da solução para um problema, muitas vezes o ser humano se vale de experiências passadas, ocorridas com problemas semelhantes e que, portanto, podem prever soluções de sucesso ou não. Sistemas Baseados em Casos (SBC) podem utilizar soluções anteriores para interpretar uma nova situação, ou criar uma solução apropriada para um novo problema. Este trabalho apresenta um estudo de métricas de similaridade em sistemas baseados em casos, aplicados à área da saúde, mais especificamente sobre epicondilite lateral, uma tendinite do cotovelo. O estudo sobre métricas de similaridade em sistemas baseados em casos foi realizado a partir de levantamentos bibliográficos sobre Raciocínio Baseados em Casos e sobretudo com o estudo e aprendizado obtido por meio da aplicação de RBC na área da Saúde. A aplicação foi desenvolvida com a participação de profissionais da área da saúde que muito colaboraram na construção da aplicação, bem como com o fornecimento de casos reais para os cadastros na base de casos e aplicação de testes de validação / Abstract: When solving a problem, humans ofien use past experiences with similar situations, which can help the prediction of failure or success. Case-Based Systems use past experiences to interpret a new situation, or to create an appropiate solution for a new problem. For work presents a study on similarity metrics in case-based systems, and an application concerning the health area, more specifically about Lateral Epiconditis, an elbow tendinitis. The study on similarity metrics in case-based systems was conducted from bibliographic research and more importantly, with the study and learning abtained with the health area application development. Health area professionals took part and helped the application development, as well as provided real cases to configure and validate the system / Mestrado / Engenharia de Software / Mestre Profissional em Computação

Orientador: Mauro Sergio Miskulin, Rosana G. S. Miskulin / Tese (doutorado) - Universidade Estadual de Campinas, Faculdade de Engenharia Eletrica e de Computação / Made available in DSpace on 2018-08-08T03:31:45Z (GMT). No. of bitstreams: 1 PivaJunior_Dilermando_D.pdf: 2474733 bytes, checksum: 6f2118117d2c8fc9a5f56f799d06aafe (MD5) Previous issue date: 2006 / Resumo: Este trabalho apresenta a arquitetura computacional AUXILIAR, que foi especificada com o objetivo de potencializar a ação docente em módulos de Ensino de Engenharia. Para tanto foi implementado um mecanismo que, além de facilitar o processo de avaliação, procura por casos similares ocorridos com outros alunos em situações passadas semelhantes. Esta busca permite que o sistema possa redefinir o conteúdo que o aluno deve ser submetido e eliminar as deficiências detectadas durante a avaliação formativa, sem a necessidade de uma maior intervenção do professor no processo educativo. Para atingir tais objetivos foram utilizados conceitos de Inteligência Artificial, especificamente Raciocínio Baseado em Casos aplicado à Educação, e conceitos de Avaliação Formativa, buscando, com essa abordagem e com a utilização de metodologia específica para construção de cursos Online (AUXILIARCONSTRUTOR), facilitar a organização dos conteúdos pedagógicos a serem disponibilizados em cursos Online. Ao final, são apresentados resultados preliminares da utilização da arquitetura computacional AUXILIAR, em uma primeira implementação, em dois momentos, 1º e 2º semestres de 2005, e envolvendo disciplinas e turmas distintas de cursos específicos de Engenharia da Computação, Ciência da Computação e Tecnologia em Informática. Com essas perspectivas esta pesquisa procura investigar o desenvolvimento de uma ferramenta computacional inteligente utilizando a metodologia de Raciocínio Baseado em Casos (RBC) que potencializará a ação docente no gerenciamento, condução e redirecionamento dos alunos em módulos de ensino em cursos Online na área de Engenharia, proporcionando uma melhoria na aprendizagem / Abstract: This study presents the AUXILIAR computational architecture, which was specified with the objective of enhancing the professor action in the Engineering Teaching modules. To carry this out, it was implemented a mechanism that, besides facilitating the evaluation process, it looks for similar cases occurred with students on past similar situation. This search allows the system to redefine the content¿s student that must be submitted and eliminates the detected deficiencies during the formative evaluation without the professor¿s intervention in the educative process. To reach these proposals, have been used concepts on Artificial Intelligence, specifically Case-Based Reasoning applied to Education, and concepts of Formative Evaluation aiming with this focus and also with the usage of specific methodology applied to online courses assembling (called, AUXILIAR-CONTRUTOR), to facilitate the pedagogical contents organization to be available in online courses. At the end of the study, preliminary results of AUXILIAR computational architecture usage are presented, in a first implementation, in two moments (first and second half of 2005), involving distinct disciplines and classes of the Computing Engineering, Computer Science and Information Technology courses. With these perspectives, this research looks to investigate the development of an intelligent computational tool using the methodology of Case Based Reasoning (CBR) that enhances the teaching action in the management, conduction and redirection of the students in modules of education in online courses of Engineering area, providing an improvement in the learning / Doutorado / Automação / Doutor em Engenharia Elétrica

A difficult issue in stress management is to use biomedical sensor signal in the diagnosis and treatment of stress. Clinicians often make their diagnosis and decision based on manual inspection of physiological signals such as, ECG, heart rate, finger temperature etc. However, the complexity associated with manual analysis and interpretation of the signals makes it difficult even for experienced clinicians. Today the diagnosis and decision is largely dependent on how experienced the clinician is interpreting the measurements.  A computer-aided decision support system for diagnosis and treatment of stress would enable a more objective and consistent diagnosis and decisions. A challenge in the field of medicine is the accuracy of the system, it is essential that the clinician is able to judge the accuracy of the suggested solutions. Case-based reasoning systems for medical applications are increasingly multi-purpose and multi-modal, using a variety of different methods and techniques to meet the challenges of the medical domain. This research work covers the development of an intelligent clinical decision support system for diagnosis, classification and treatment in stress management. The system uses a finger temperature sensor and the variation in the finger temperature is one of the key features in the system. Several artificial intelligence techniques have been investigated to enable a more reliable and efficient diagnosis and treatment of stress such as case-based reasoning, textual information retrieval, rule-based reasoning, and fuzzy logic. Functionalities and the performance of the system have been validated by implementing a research prototype based on close collaboration with an expert in stress. The case base of the implemented system has been initiated with 53 reference cases classified by an experienced clinician. A case study also shows that the system provides results close to a human expert. The experimental results suggest that such a system is valuable both for less experienced clinicians and for experts where the system may function as a second option. / IPOS, PROEK

Conselho Nacional de Desenvolvimento Científico e Tecnológico / In a collaborative risk management scenario, project stakeholders often need natural forms of recording and reusing past risk management experiences so that they could better assess whether there are threats to the goals of new projects. The contribution of this dissertation is to propose an enhanced case-based reasoning (CBR) approach to support project participants to exploit such experiences, which are here expressed as collaborative risk management discussion cases. In this context, collaborative risk discussion of software project can be carried out by a existing risk discussion system (SEVERO, POZZEBON, et al., 2013), where such dialogues follow a communication protocol (SEVERO, FONTOURA, et al., 2013) e argumentation schemes (REED e WALTON, 2007). This research aims to propose an enhanced case-based reasoning approach, which is structured through traditional factual attributes in combination with argumentation attributes. Furthermore, different forms of CBR queries are exploited, such queries are based on facts and arguments so that past risk discussion cases could be retrieved from a case base. Finally, CBR explanation techniques, in particular case-based explanation templates, are exploited, allowing users from this risk discussion system a better understanding of how and why the most similar cases to a given query may be relevant to the solution of found problems in current risk discussions. To demonstrate the practical utility of this approach, a case study involving the collaborative experience-based risk management of a software project is discussed, as well as the results of an experiment conducted which show positive evidence for the acceptance and applicability of the approach in the solution of current problems of collaborative risk management by using past experiences. / Em um cenário de gerenciamento colaborativo de riscos, as partes interessadas de um projeto precisam muitas vezes gravar e reusar experiências passadas de gerenciamento de riscos de maneiras naturais para que tais interessados possam melhor avaliar se existem ameaças aos objetivos de novos projetos. A contribuição desta pesquisa é propor uma abordagem avançada de Raciocínio Baseado em Casos (Case-Based Reasoning - CBR) para apoiar os participantes de projetos na exploração de tais experiências, que aqui são expressas como casos de discussão de gerenciamento colaborativo de riscos. Neste contexto, discussões colaborativas de riscos de projetos de software podem ser realizadas por meio de um sistema de discussão de riscos já existente (SEVERO, POZZEBON, et al., 2013) tais debates seguem um protocolo de comunicação (SEVERO, FONTOURA, et al., 2013) e esquemas de argumentação (REED e WALTON, 2007). Esta pesquisa apresenta a exploração de casos avançados, que possuem além de características factuais tradicionais em CBR, o uso de características argumentativas. Além disso, diferentes formas de consultas CBR são exploradas para que casos passados de discussão de riscos possam ser recuperados a partir de uma base de casos. Estas consultas são baseadas em ambos os tipos de características presentes em um caso. Para finalizar, técnicas de explicação em CBR, em especial templates de explicação baseado em casos, são exploradas, permitindo aos usuários deste sistema de discussão de riscos um melhor entendimento de como e por que os casos mais similares a uma consulta podem ser relevantes para a solução de problemas encontrados em discussões de riscos atuais. Para demonstrar a utilidade prática desta abordagem, é discutido um estudo de casos envolvendo gerenciamento colaborativo de riscos baseado em experiência, bem como os resultados de um experimento realizado, que apresentam evidências positivas para a aceitação e aplicabilidade da abordagem na solução de problemas atuais de gerenciamento colaborativo de riscos com o uso de soluções de experiências passadas.

Quality of service is commonly used to shape network traffic to meet specified criteria. The various scenarios include limiting and reserving bandwidth for a particular application, host or user, prioritizing latency sensitive traffic or equal distribution of unreserved bandwidth. The DynShaper software distributes and controls a traffic quota by more sophisticated means than fixed per user limits and simple disconnection after the user reaches the limit. It distributes the quota on a daily basis, where each day receives the same share. The users are sorted into predefined groups with different bandwidths depending on their recent consumption. This classification is periodically updated to ensure the sorting order is maintained. The bandwidths of these groups is dynamically adjusted depending on the actual consumption to provide an efficient utilization. This thesis presents another distribution model using a case-based reasoning approach, a method for machine learning which is classified as conventional artificial intelligence. Case-based reasoning tries to solve new problems based on the solutions of similar problems from the past. Controlling the network traffic to remain within a fixed quota can be modeled as such a problem if the traffic patterns are recurring. Possible solutions can be derived from statistical data and altered to suit the new problems. When an untested solution is applied, the software supervises the execution and revises the solution accordingly, if the actual results deviate from the precalculated schedule.

Making complex medical decisions is becoming an increasingly challenging task due to the growing amount of available evidence to consider and the higher demand for personalized treatment and patient care. IT systems for the provision of clinical decision support (CDS) can provide sustainable relief if decisions are automatically evaluated and processed. In this paper, we propose an approach for quantifying similarity between new and previously recorded medical cases to enable significant knowledge transfer for reasoning tasks on a patient-level. Methodologically, 102 medical cases with oropharyngeal carcinoma were analyzed retrospectively. Based on independent disease characteristics, patient-specific data vectors including relevant information entities for primary and adjuvant treatment decisions were created. Utilizing the ϕK correlation coefficient as the methodological foundation of our approach, we were able to determine the predictive impact of each characteristic, thus enabling significant reduction of the feature space to allow for further analysis of the intra-variable distances between the respective feature states. The results revealed a significant feature-space reduction from initially 19 down to only 6 diagnostic variables (ϕK correlation coefficient ≥ 0.3, ϕK significance test ≥ 2.5) for the primary and 7 variables (from initially 14) for the adjuvant treatment setting. Further investigation on the resulting characteristics showed a non-linear behavior in relation to the corresponding distances on intra-variable level. Through the implementation of a 10-fold cross-validation procedure, we were further able to identify 8 (primary treatment) matching cases with an evaluation score of 1.0 and 9 (adjuvant treatment) matching cases with an evaluation score of 0.957 based on their shared treatment procedure as the endpoint for similarity definition. Based on those promising results, we conclude that our proposed method for using data-driven similarity measures for application in medical decision-making is able to offer valuable assistance for physicians. Furthermore, we consider our approach as universal in regard to other clinical use-cases, which would allow for an easy-to-implement adaptation for a range of further medical decision-making scenarios.

Erfahrungsmanagement (EM) ist eine Spezialform des Wissensmanagements, die sich mit aufgabenbezogenem Wissen beschäftigt. Diese Arbeit entwickelt ein Rahmenwerk für Assistenzsysteme, die Menschen bei EM-Aufgaben unterstützen. Es untersucht nicht nur technische Fragen (Erfahrungswissen sammeln, strukturieren, speichern und wiederverwenden) sondern auch organisatorische (Erfahrungswissen evaluieren und pflegen) und psychosoziale Aspekte (ein EM-System integrieren, Barrieren vermeiden, den Systemeinsatz bewerten). Fallbasierte Anwendungsbeispiele für industrielle und experimentelle Szenarien zeigen, welche Prozesse wo unterstützt oder gar teilautomatisiert werden können. Sie dienen der experimentellen Evaluierug der Fragen, die ich zu Beginn jedes Anwendungskapitels formuliert habe. / Experience Management (EM) is a special form of Knowledge Management that deals with task-based knowledge. This thesis provides a framework for assistant systems that support human beings in EM tasks. It deals not only with technical issues (how to collect, structure, store, retrieve, and reuse experiential knowledge), but als with organizational issues (how to evaluate and maintain it) and psychosocial questions (how to integrate an EM system, how to avoid barriers, how to evaluate the success of the whole system). Case-based sample applications from both, industrial and experimental scenarios, show to what extend the particular EM processes can be supported or which sub-processes can even be automated. By means of experiments with these implemented samples, we evaluate the topics that are discussed at the beginning of each application chapter.

It is no secret that 'managerial' solutions are not, on average, nearly as reliable as 'technical' solutions. The focus of this work is to clarify the reasons why this is so, and to seek ways to increase the reliability of managerial solutions. The causes of this situation are both subjective (human factor failure), which can be influenced, and objective (complexity of the problem, the specifics of human behaviour, etc.) that can be only minimally influenced. Significant subjective causes at work were identified as: a. cognitive distortions at the mental level of thinking of the problem solvers; b. deficiencies in making inference and drawing conclusions; c. incorrect argumentation. There are two ways to reduce these causes: 1. cultivation of managerial thinking of the problem solvers; 2. the use of reserves in the implementation of approaches and tools of theoretical disciplines that already operate successfully elsewhere and are beneficial for managerial solutions. The first way deals with procedures for managerial solutions formulated in the language of the relevant discipline (the language of management), expressed by natural language and the chain of formulas (calculations) and visual (graphic) tools in the form of managerial decision trees, diagrams and charts with the rules of 'managerial logic'. This is generally defined as a set of approaches, tools, methods and skills needed for credible justification when solving managerial problems. Specifically it deals with: - the 'case-based reasoning' approach, which aims at finding the best point of view on a given problem and analysing all considered aspects within its context step-by-step in detail; - translating the tools and methods of modern logic (especially its intuitionistic version) from the language of logic into the language of management taking into account the factual content of expressive means of the language of management including the ability of their effective application; - respecting the principles of rational and ethical argumentation within managerial solutions. The second way circumvents managerial solution procedures by recasting the managerial task to the task of a scientific discipline (logic, game theory, etc.) and derives the correct result therein. In this context we talk about the use of knowledge of theoretical disciplines in management. Both of these ways are demonstrated in the work in a number of illustrative examples and the annexed case studies addressing the specific tasks of managerial practice.

Mémoire numérisé par la Division de la gestion de documents et des archives de l'Université de Montréal.

Les travaux présentés dans cette thèse s'inscrivent dans une problématique d'aide à la conception de systèmes, à la planification de leur projet de développement et à leur couplage. L'aide à la conception et à la planification repose sur la formalisation de deux grands types de connaissances : les connaissances méthodologiques utilisables quel que soit le projet de conception et, les connaissances métier spécifiques à un type de conception et/ou de planification donné. Le premier chapitre de la thèse propose un état de l'art concernant les travaux sur le couplage des processus de conception de systèmes et de planification des projets associés et expose la problématique de nos travaux. Deux partie traitent ensuite, d'une part, des connaissances méthodologiques et, d'autre part, des connaissances métier. La première partie expose trois types de couplages méthodologiques. Le couplage structurel propose de formaliser les entités de conception et de planification puis permet leur création et leur association. Le couplage informationnel définit les attributs de faisabilité et de vérification pour ces entités et synchronise les états de ces dernières vis-à-vis de ces attributs. Enfin, le couplage décisionnel consiste à proposer, dans un même espace et sous forme de tableau de bord, les informations nécessaires et suffisantes à la prise de décision par les acteurs du projet de conception. La seconde partie propose de formaliser, d'exploiter et de capitaliser la connaissance métier. Après avoir formalisé ces connaissances sous forme d'une ontologie de concepts, deux mécanismes sont exploités : un mécanisme de réutilisation de cas permettant de réutiliser, en les adaptant, les projets de conception passés et un mécanisme de propagation de contraintes permettant de propager des décisions de la conception vers la planification et réciproquement. / The work presented in this thesis deals with aiding system design, development project planning and its coupling. Aiding design and planning is based on the formalization of two kind of knowledge: methodological knowledge that can be used in all kind of design projects and business knowledge that are dedicated to a particular kind of design and/or planning. The first chapter presents a state of the art about coupling system design process and project planning process and gives the problem of our work. Then, two parts deal with design and planning coupling thanks to, on one hand, methodological knowledge, and on the other hand, business knowledge. The first part presents three types of methodological coupling. The structural coupling defines design and planning entities and permits its simultaneous creation of and its association. The informational coupling defines feasibility and verification attributes for these entities and synchronizes its attribute states. Finally, the decisional coupling consists in proposing, in a single dashboard, the necessary and sufficient information to make a decision by the design project actors. The second part proposes to formalize, to exploit and to capitalize business knowledge. This knowledge is formalized with ontology of concepts. Then, two mechanisms are exploited: a case reuse mechanism that permits to reuse and adapt former design projects and a constraint propagation mechanism that allows propagating decisions from design to planning and reciprocally.