This study develops a reliable intelligent non-destructive evaluation (NDE) expert system for carbon-carbon (C/C) composites based on thermography, ultrasonic, computed tomography and post processing by means of fuzzy expert system technique. Data features and NDE expert knowledge are seamlessly combined in the intelligent system to provide the best possible diagnosis of the potential defects and problems. As a result, this research help ensure C/C composites' integrity and reliability. Four types of orthotropic aerospace composite material groups, which include 2-D pitched based commercial aircraft disc brakes and asmolds, 3-D PAN based C/C composites, and carbon fiber reinforced plastic (CFRP) panels, were tested. Based on the performance testing results of thermography, air-coupled ultrasonic, and x-ray computed tomography, the testing data pattern corresponding to feature and quantification of defects were found. This NDE knowledge databases were transformed to fuzzy logic expert system models. The models succeefully classified and indicated the defect's size and distribution and the intelligent systems perform NDE better than human operators. These fuzzy expert systems not only eliminate human errors in defect detection but also function as NDE experts. In addition, fuzzy expert systems improve the defect detection by incorporating fuzzy expert rules to remove noises and to measure defect size more accurately. In the future, the expert system model could be continuously updated and modified to quantify the size and distribution of defects. The systems developed here can be adapted and applied to build an intelligent NDE expert system for better quality control as well as automatic defect and porosity detection in C/C composite production process.

Orientador: Prof. Dr. Peter M. E. Claessens / Dissertação (mestrado) - Universidade Federal do ABC, Programa de Pós-Graduação em Neurociência e Cognição, 2014. / Zumbido (tinnitus) é um distúrbio comum de audição, muitas vezes debilitante em graus variados. Dado que zumbido é uma condição multifacetada, com sintomas que frequentemente são psicológicos e subjetivos, e com muitas causas potenciais, a diagnose deste distúrbio não é trivial. Por exemplo, zumbido pode ser objetivo e mensurável ou subjetivo e produzido por fatores neurais que podem ser de localização mais periférica ou central. Este projeto de mestrado propõe o desenvolvimento de um sistema especialista médico para apoiar clínicos na indicação de tratamento para zumbido. Este estudo foca em três tipos de tratamento para zumbido, a saber, dieta, medicação e aparelho auditivo, como também nas combinações, para categorização supervisionada. Redes Bayesianas ingênuas (naive) foram utilizadas para relacionar uma diversidade de resultados de exames e elementos de anamnese a indicações de tratamento por clínicos. Como tratamentos não são mutualmente exclusivos, a categorização deve levar em conta casos multi-label, isto é, a possibilidade de indicações diferentes de tratamento simultâneas. Com o objetivo de mapear as probabilidades a posteriori das indicações diferentes de tratamento para classificação multi-label , a diferença entre as distribuições a posteriori foi usada como critério para resolver o problema multi-label. Esta estratégia foi avaliada e o desempenho comparada a uma estratégia mais simples de mapeamento single-label. Os resultados mostram que a acurácia da abordagem multi-label é melhor que o ajuste single-label. O sistema fornece assim um primeiro passo satisfatório do desenvolvimento de um sistema de apoio médico futuramente mais amplo, integrado e dinâmico. / Tinnitus is a common hearing disorder, often debilitating to varying degrees. Given that tinnitus is a multifaceted condition, with symptoms that are often psychological and subjective, and with many different possible causes, its diagnosis is not trivial. For example, tinnitus can be objective and measureable or subjective and produced by neural factors which can either be more peripheral or more centrally located. This Master¿s project proposes the development of a medical expert system to assist clinicians in the indication of treatment for tinnitus. This study focused on three types of treatment for tinnitus, namely, Diet, Medication and Hearing Aid, as well as on their combinations for supervised categorization. Naïve Bayes networks were used to relate a diversity of test results and elements of the anamnesis to treatment referrals by clinicians. Because treatments are not mutually exclusive, the categorization needs to take into account multi-labeling cases, that is, the possibility of several simultaneous treatment indications. In order to map the posterior probabilities of the different treatment indications to multi-labeling classification, the difference between posterior probabilities was used as a criterion to solve the multi-labeling problem. This strategy was evaluated and its performance compared to a simpler single-labeling mapping strategy. The result shows that the accuracy of the multi-labeling approach is higher than a single-labeling adjustment. The system thus provides a first satisfactory step in the development of a more encompassing, integrated and dynamic medical support system.

This study is based on interviews with six students from Stockholm that have shared their feelings/opinions about how they experience their identity as a student. The aim of this master’s thesis is to examine how the identity of students is constructed but also how the post modern society affects the life that the students are living. With a higher demand on education and responsibility of making the right decisions, the student’s main concern is not only her studies, but also the goal to succeed in her life. The result points out that the environment which the student lives in has an influence on how the identity develops. The identity has nothing to do with the actually fact that the student studies, but with how the student acts outside the university.

Este trabalho apresenta os princípios básicos utilizados no desenvolvimento de um sistema especialista para síntese de cavernas de embarcações. Uma fatia do navio, contendo o anel transversal a ser analisado, é extraída do restante da estrutura e modelada como bidimensional. A interação da fatia com a estrutura longitudinal é feita considerando os elementos longitudinais pesados como apoios elásticos nos pontos de interseção com a fatia. A interação com o chapeamento é representada por uma distribuição de tensões de cisalhamento ao longo dos elementos no anel. Consegue-se, assim, condições de contorno para o modelo bidimensional muito semelhantes àquelas encontradas em um modelo tridimensional. O sistema desenvolvido, denominado TRANSEC, admite como dados de entrada a linha moldada da seção transversal, discretizada em elementos de viga, os carregamentos devido a pressão lateral ou concentrado, e uma tabela de perfis de onde o sistema buscará o perfil adequado para cada trecho de viga discretizado. O perfil adequado ou ótimo será aquele de menor peso e que resulte em solicitações estruturais enquadradas em uma faixa de tensões admissíveis previamente estabelecida pelo usuário. O sistema é composto por três módulos: um de elementos finitos, responsável pelos cálculos estruturais; um módulo gráfico, encarregado da elaboração de desenhos da estrutura; e um módulo de gerenciamento, com o objetivo de fornecer uma comunicação amigável com o usuário, além de gerenciar os outros dois módulos. O programa foi utilizado para a síntese de duas estruturas anteriormente otimizadas por modelos tridimensionais em elementos finitos. Foram encontrados resultados similares pelas duas metodologias porém com uma diferença significativa: o tempo dispensado utilizando o sistema TRANSEC, poucas horas, contra semanas pelo modelo tridimensional. O sistema TRANSEC se mostrou uma poderosa ferramenta, principalmente nas fases iniciais da espiral de projeto de embarcações. / This work presents the basic principles used in the development of an expert system for ship's transversal frame synthesis. A slice of the ship which contains the transversal frame is taken out from the remaining structure and modelled as a two-dimensional shape. The interaction of the transversal frame with the longitudinal structure is done considering the longitudinal stiffeners as elastic supports for the slice. The interaction with the shell plating is represented by a shear stress distribuition along the transverse frame. Based on this assumption, it is possible to get boundary conditions for the two-dimensional model similar to those associated with a three-dimensional model. The developed system, named TRANSEC, accept as input data the transverse section molded line, discretized by beam elements ; the load due to the lateral pressure and a beam cross section table from where the system chooses which one is suitable for each discrete piece of the beam. The suitable or optimum beam cross section will be the one with less weigh and which results in structural loads according to previouly adopted admissible stress levels. The system contains three units: one of Finite Element, that does structural calculus; one Graphic Module for the model's drawings and one Manager Module, aiming to provide a user friendly communication, besides controling the two other modules. The program was applied on two structures synthesis that were optimized by three-dimesional Finite Element models. The obtained results are similar for both procedures, but with a significant difference: the time spent on using the expert system, few hours, is much less than the days spent on using three-dimensinal models. The TRANSEC system can be considered a powerful tool , mainly in the initial phase of ship transverse structural design.

This thesis in its theoretical part summarizes international knowledge of the problematics of expert systems and their application in automotive diagnostics. In the practical part it solves the methodology and selection of appropriate expert system for the development of diagnostic application. This issue is further elaborated by the methodology of an expert´s knowledge transfer into the knowledge database and creating application for its use within the Windows, Web and Android platforms. Beside the working out the product itself it also provides instructions for others who are interested in preparing similar applications and topic for the future development of the already prepared tool.

Ce manuscrit de thèse porte sur le problème du test basé modèle de systèmes de production existants, tels ceux de notre partenaire industriel Michelin, l’un des trois plus grands fabricants de pneumatiques au monde. Un système de production est composé d’un ensemble de machines de production contrôlées par un ou plusieurs logiciels au sein d’un atelier dans une usine. Malgré les nombreux travaux dans le domaine du test basé modèle, l’écriture de modèles permettant de décrire un système sous test ou sa spécification reste un problème récurrent, en partie à cause de la complexité d’une telle tâche. De plus, un modèle est utile lorsqu’il est à jour par rapport à ce qu’il décrit, ce qui implique de le maintenir dans le temps. Pour autant, conserver une documentation à jour reste compliqué puisqu’il faut souvent le faire manuellement. Dans notre contexte, il est important de souligner le fait qu’un système de production fonctionne en continu et ne doit être ni arrêté ni perturbé, ce qui limite l’usage des techniques de test classiques. Pour pallier le problème de l’écriture de modèles, nous proposons une approche pour construire automatiquement des modèles depuis des séquences d’événements observés (traces) dans un environnement de production. Pour se faire, nous utilisons les informations fournies par les données échangées entre les éléments qui composent un système de production. Nous adoptons une approche boîte noire et combinons les notions de système expert, inférence de modèles et machine learning, afin de créer des modèles comportementaux. Ces modèles inférés décrivent des comportements complets, enregistrés sur un système analysé. Ces modèles sont partiels, mais également très grands (en terme de taille), ce qui les rend difficilement utilisable par la suite. Nous proposons une technique de réduction spécifique à notre contexte qui conserve l’équivalence de traces entre les modèles de base et les modèles fortement réduits. Grâce à cela, ces modèles inférés deviennent intéressant pour la génération de documentation, la fouille de données, mais également le test. Nous proposons une méthode passive de test basé modèle pour répondre au problème du test de systèmes de production sans interférer sur leur bon fonctionnement. Cette technique permet d’identifier des différences entre deux systèmes de production et réutilise l’inférence de modèles décrite précédemment. Nous introduisons deux relations d’implantation : une relation basée sur l’inclusion de traces, et une seconde relation plus faible proposée, pour remédier au fait que les modèles inférés soient partiels. Enfin, ce manuscrit de thèse présente Autofunk, un framework modulaire pour l’inférence de modèles et le test de systèmes de production qui aggrège les notions mentionnées précédemment. Son implémentation en Java a été appliquée sur différentes applications et systèmes de production chez Michelin dont les résultats sont donnés dans ce manuscrit. Le prototype développé lors de la thèse a pour vocation de devenir un outil standard chez Michelin. / This thesis tackles the problem of testing (legacy) production systems such as those of our industrial partner Michelin, one of the three largest tire manufacturers in the world, by means of Model-based Testing. A production system is defined as a set of production machines controlled by a software, in a factory. Despite the large body of work within the field of Model-based Testing, a common issue remains the writing of models describing either the system under test or its specification. It is a tedious task that should be performed regularly in order to keep the models up to date (which is often also true for any documentation in the Industry). A second point to take into account is that production systems often run continuously and should not be disrupted, which limits the use of most of the existing classical testing techniques. We present an approach to infer exact models from traces, i.e. sequences of events observed in a production environment, to address the first issue. We leverage the data exchanged among the devices and software in a black-box perspective to construct behavioral models using different techniques such as expert systems, model inference, and machine learning. It results in large, yet partial, models gathering the behaviors recorded from a system under analysis. We introduce a context-specific algorithm to reduce such models in order to make them more usable while preserving trace equivalence between the original inferred models and the reduced ones. These models can serve different purposes, e.g., generating documentation, data mining, but also testing. To address the problem of testing production systems without disturbing them, this thesis introduces an offline passive Model-based Testing technique, allowing to detect differences between two production systems. This technique leverages the inferred models, and relies on two implementation relations: a slightly modified version of the existing trace preorder relation, and a weaker implementation proposed to overcome the partialness of the inferred models.Overall, the thesis presents Autofunk, a modular framework for model inference and testing of production systems, gathering the previous notions. Its Java implementation has been applied to different applications and production systems at Michelin, and this thesis gives results from different case studies. The prototype developed during this thesis should become a standard tool at Michelin.

Master ’s thesis deals with evaluation of investment using advanced methods of analysis and modeling with regards to the best offer. The content of the thesis consists of creating two decision making systems based on fuzzy logic. The thesis also contains a theoretical basics which are necessary for the creation of both systems and evaluating the benefits of the solution.

The theoretical part of the thesis contains a brief description of the anatomy and electrophysiology of the heart, as well as both, surface and intracardiac electrocardiograms. The thesis also describes the different types of cardiac tachycardias, their differential diagnosis and what is known as The Expert System. The practical section of the thesis notes and outlines the tree diagrams, and additionally describes various software solutions of The Expert System. Further, the thesis includes the classification of the heart rhythm, using The Expert System method with three typical tachycardia cases, and including a list of questions asked by The Expert System to the user. Answers to all questions asked are being assessed in the text, as well as illustrated in submitted examples of intracardiac ECG recordings. The Expert System has been verified during a series of catheterization procedures on 26 patients (where the evaluated cardiac rhythm was 34). The classication of the type of heart rhythm (per The Expert System) when comparing the results with the doctors coincided in 100 % of tested cases.

High voltage transmission lines are used for distributing electricity and have to work reliably as it directly affects their performance. Therefore, inspections and maintenances are required in order to keep them working and to find damages as soon as possible. These inspections are still done by humans, which costs a lot of resources, as it is not only dangerous but also cost- and time consuming. This Bachelor's thesis proposes an alternative way of inspection that can be done by presenting an expert system that is able to help the flight controller of an unmanned aerial vehicle. The implementation is done by splitting the main objective into smaller scenarios, each building the fundamentals for developing further flight missions. CLIPS is the expert system programming language used in order to write scripts for each scenario. Tests to verify the functionality and executability of the implemented concept were done using three dfferent methods. The first test was made using a simulation, the next step was to use the hardware that is used in the field and the last test was to execute the implementation on a real copter. / Hochspannungsleitungen werden zur Verteilung von Strom verwendet und müssen zuverlässig funktionieren, da sich ihre Zuverlässigkeit direkt auf die Leistung auswirkt. Deshalb sind Inspektionen und Wartungen erforderlich, um die Funktionsfähigkeit aufrechtzuerhalten und Schäden so schnell wie möglich zu erkennen. Diese Inspektionen werden noch immer vom Menschen durchgeführt, was viele Ressourcen kostet, da es nicht nur gefährlich, sondern auch kosten- und zeitaufwendig ist. Diese Bachelorarbeit schlägt eine alternative Art und Weise Inspektionen durchzuführen vor, indem sie ein Expertensystem verwendet, das in der Lage ist bei der Führung des Flug-Controllers eines unbemannten Luftfahrzeugs zu helfen. Die Umsetzung erfolgt durch die Aufteilung des Hauptziels in kleinere Szenarien, die jeweils die Grundlagen für die Entwicklung weiterer Flugmissionen bilden. CLIPS ist die verwendete Expertensystem-Programmiersprache, um Skripte für jedes Szenario zu schreiben. Tests zur Uberprüfung der Funktionalität und Ausführbarkeit des implementierten Konzepts wurden mit Hilfe von drei verschiedenen Methoden durchgeführt. Der erste Test wurde mit einer Simulation erhoben. Der nächste Schritt war die Verwendung von Hardware, die in echten Einsätzen benutzt wird und der letzte Test war die Ausführung der Implementierung auf einem echten Quadrocopter.

Treatment decision-making in head and neck oncology is gaining complexity by the increasing evidence pointing towards more individualized and selective treatment options. Therefore, decision making in multidisciplinary teams is becoming the key point in the clinical pathways. Clinical decision-support systems based on Bayesian networks can support complex decision-making processes by providing mathematically correct and transparent advises. In the last three decades, different clinical applications of Bayesian networks have been proposed. Because appropriate data for model learning and testing is often unobtainable, expert modeling is required. To decrease the modeling and validation effort, networks usually represent small or highly simplified decision structures. However, especially systems for supporting multidisciplinary treatment decisions may only gain a user’s confidence if the systems’ results are comprehensive and comprehensible. Challenges in developing such systems relate to knowledge engineering, model validation, system interaction, clinical implementation and standardization. These challenges are well-known, however, they are not or only partially addressed by the developers. The thesis presented a methodology for the development of Bayesian network-based clinical treatment decision support systems. For this purpose, a concept introduced interactions between actors and systems. The proposed concept emphasizes model development with an exemplary use case of model interaction. A graph model design was presented that allows integrating all relevant variables of multidisciplinary treatment decisions. At the current stage, we developed TreLynCa: A graph model representing the treatment decisions of laryngeal cancer. From TreLynCa, a subnetwork that represents the TNM staging is completed by the required probabilistic parameters, and finally validated. The model validation required the development of a validation cycle in combination with existing data- and expert-based validation methods. Furthermore, modeling methods were developed that enable domain experts to model autonomously without Bayesian network expertise. Specifically, a novel graph modeling method was developed, and an existing method for modeling probabilistic parameters was extended. Both methods transform Bayesian network modeling tasks into a natural language form and provide a regulated modeling environment. A method for graph modeling is based on the presented graph model design with a regulated and restricted modeling procedure. This modeling procedure is supposed to enable collaborative modeling of compatible models. The method is currently under development. A method for probabilistic modeling is extended to reduce the modeling effort to a linear time. The method has been implemented as a web tool and was tested and evaluated in two studies. Finally, for clinical application of the TNM model, requirements were collected and constructed in a visual framework. In collaboration with visual scientists, the framework has been implemented and evaluated.