Thesis (M.S.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1988. / Includes bibliographical references (p. 56-58). / Supported by the U.S. Army Research Office. DAAL-03-86-K-0171 Supported by the Air Force Office of Scientific Research. AFOSR-85-0227B / by Mohamad A. Akra. / M.S.

The healthcare sector has become a key area for the development and application of new technology and, not least, Artificial Intelligence (AI). New reports are constantly being published about how this algorithm-based technology supports or performs various medical tasks. These illustrates the rapid development of AI that is taking place within healthcare and how algorithms are increasingly involved in systems and medical devices designed to support medical decision-making.  The digital revolution and the advancement of AI technologies represent a step change in the way healthcare may be delivered, medical services coordinated and well-being supported. It could allow for easier and faster communication, earlier and more accurate diagnosing and better healthcare at lower costs. However, systems and devices relying on AI differs significantly from other, traditional, medical devices. AI algorithms are – by nature – complex and partly unpredictable. Additionally, varying levels of opacity has made it hard, sometimes impossible, to interpret and explain recommendations or decisions made by or with support from algorithmic decision systems. These characteristics of AI technology raise important technological, practical, ethical and regulatory issues. The objective of this thesis is to analyse the relationship between the EU regulation on medical devices (MDR) and algorithmic decision systems (ADS) used within the medical domain. The principal question is whether the MDR is enough to guarantee safe and robust ADS within the European healthcare sector or if complementary (or completely different) regulation is necessary. In essence, it will be argued that (i) while ADS are heavily reliant on the quality and representativeness of underlying datasets, there are no requirements with regard to the quality or composition of these datasets in the MDR, (ii) while it is believed that ADS will lead to historically unprecedented changes in healthcare , the regulation lacks guidance on how to manage novel risks and hazards, unique to ADS, and that (iii) as increasingly autonomous systems continue to challenge the existing perceptions of how safety and performance is best maintained, new mechanisms (for transparency, human control and accountability) must be incorporated in the systems. It will also be found that the ability of ADS to change after market certification, will eventually necessitate radical changes in the current regulation and a new regulatory paradigm might be needed.

Deoiling of petroleum wastewater is a major concern in petroleum process engineering. The conventional design procedure for deoiling systems consists of nine consecutive stages involving different people or groups. This thesis considers reengineering the conventional procedure, with the aim of increasing the efficiency of the process and productivity of people involved. The thesis then investigates the development of the appropriate computer support tools for the new procedure. The reengineering of the procedure is based on concepts proposed by Hammer (1990). The resulting procedure consists of four stages, where parallelism of the different tasks in the conventional procedure is explicitly considered. A model of the new procedure is described in UML (Unified Modelling Language). The advantage of using UML instead of using just natural language description is that UML uses graphical representation that is easy to use and less prone to ambiguity. Based on the new procedure, a decision support system called CODES (Conceptual DEsign of deoiling Systems) was designed and implemented. CODES supports the stages of wastewater assessment, equipment options at different locations, treatment disposal options and recommendations for final process configuration. Two Case Studies using operating field data are reported. The Case Studies using CODES proved to be straightforward to use and produced appropriate comments on the performance of the existing designs and proposed alternatives to satisfy the design requirements. CODES results agreed with knowledge from previous plant trials. The contribution of this thesis to the deoiling design process is twofold. Firstly, a critical review of the conventional procedure has resulted in a new one, which has potential benefits of improving a company's efficiency by reducing the number of people and activities involved, and shortening the design time. Secondly, the feasibility of applying the new procedure and CODES is successfully demonstrated through the case studies. Limitations and areas of extensions are also identified.

The development of sustainable business models is a challenging task since various factors might influence the results of an assessment. Given the complexity at the municipal level, system interdependencies between different alternatives need to be considered. One possibility to support decision makers is to apply energy system optimization models. Existing optimization models, however, ignore the roles different actors play and the resulting impact they have. To address this research issue, this thesis presents an integrated techno-economic optimization framework called IRPopt (Integrated Resource Planning and Optimization). A proven graph-based energy system approach allows the accurate modeling of deployment systems by considering different energy carriers and technical processes. In addition, a graph-based commercial association approach enables the integration of actor-oriented coordination. This is achieved by the explicit modeling of market actors on one layer and technology processes on another layer as well as resource flow interrelations and commercial agreements mechanism among and between the different layers. Using the optimization framework, various optimization problems are solvable on the basis of a generic objective function. For demonstration purposes, this thesis assesses the business models demand response and community storage. The applied examples demonstrate the modeling capabilities of the developed optimization framework. Further, the dispatch results show the usefulness of the described optimization approach.

Ocasionalmente, decisores se deparam com situações que demandarão a tomada de decisões estratégicas. Trata-se, com freqüência, de decisões que não foram vivenciadas anteriormente - seja no âmbito do organizacional, seja no âmbito pessoal dos decisores envolvidos - e, por isso, essas experiências anteriores podem ser de pouco valor ou podem ser transpostas apenas parcialmente ao novo contexto decisório. Nessas situações, surge um problema real a ser enfrentado pelos decisores e pouco explorado empiricamente pelos estudiosos dos processos decisórios: o problema de decidir como tomar uma decisão estratégica ou, como também conhecido no meio acadêmico, como tomar as metadecisões de um processo decisório. Para tratar desse problema, pesquisou-se a escassa literatura existente e, considerando estudos selecionados sobre processos decisórios, desenvolveu-se um modelo teórico representando os fatores que podem afetar dois tipos de metadecisões: a de processo e a de conteúdo. Em seguida, no contexto de uma organização pública e, no âmbito do desenvolvimento e produção de dois produtos para fins de diagnóstico e terapia, uma investigação foi conduzida envolvendo, no total, sete processos decisórios. Essa investigação objetivou testar o modelo teórico desenvolvido, verificar a existência de alguma associação lógica entre as diferentes metadecisões tomadas ao longo de um processo decisório e, a partir de análises dos resultados, identificar contribuições acadêmicas e práticas ao estado da arte sobre o tema. Como resultado desse esforço, o modelo do processo metadecisório foi revisado com a inclusão de novos fatores que podem influenciar as metadecisões e constatou-se que, ao longo de um processo decisório, parte das metadecisões tomadas podem apresentar uma associação lógica entre si. No conjunto, esses resultados permitiram a conclusão quanto à existência de uma estrutura lógica subjacente ao processo decisório maior do que a identificada por outros autores em estudos anteriores. Dezenove proposições relacionadas a metadecisões e uma metodologia para decidir como decidir integram as contribuições do estudo e abrem a perspectiva para outros estudos investigarem a aplicabilidade e generalidade do modelo desenvolvido e das proposições efetuadas para outros contextos organizacionais. / Occasionally, decision makers face situations where they need to make strategic decisions. Frequently, these decisions are new, and thus, previous experience is only partially helpful, if it is at all. In these situations, there is a real problem that needs to be addressed by the decision maker, which is the problem of deciding how to decide strategic decisions, or, in other words, how to make the metadecisions of a strategic decision. In order to deal with this theme, the scarce literature was reviewed and, along with selected topics about the decision making process, a theoretical model was developed to represent two types of metadecisions: process and content. The next step was the development of an empirical research in a public organization, involving the development and production of two products for diagnosis and therapy purposes. Seven decision processes were studied. The investigation was carried out in order to test the theoretical model, to verify the existence of any logical association among the different metadecisions taken within the decision process and, after the analysis of the results, to generate new contributions to the state of the art of this theme. The main results of this research are the revision and inclusion of new factors in the metadecision model and the identification that some of the metadecisions taken within a strategic decision process may present a logical association with one another. These findings indicated that the subjacent logical structure pointed out by other authors in previous studies can be extended. Nineteen propositions concerning metadecisions and a methodology to decide how to decide are additional contributions of this study. Taken altogether, this investigation opened the perspective of future studies to investigate the problem of deciding how to decide and extend the findings of the present study to other organizational environments.

Les travaux présentés dans ce mémoire s’inscrivent dans le cadre duprojet PANsafer (Vers un Passage A Niveau plus sûr), lauréat de l’appel ANR-VTT2008. Ce projet est labellisé par les deux pôles de compétitivité i-Trans et Véhiculedu Futur. Le travail de la thèse est mené conjointement par le laboratoire IRTESSETde l’UTBM et le laboratoire LEOST de l’IFSTTAR.L’objectif de cette thèse est de développer un système de perception permettantl’interprétation de scénarios dans l’environnement d’un passage à niveau. Il s’agitd’évaluer des situations potentiellement dangereuses par l’analyse spatio-temporelledes objets présents autour du passage à niveau.Pour atteindre cet objectif, le travail est décomposé en trois étapes principales. Lapremière étape est consacrée à la mise en place d’une architecture spatiale des capteursvidéo permettant de couvrir de manière optimale l’environnement du passageà niveau. Cette étape est mise en oeuvre dans le cadre du développement d’unsimulateur d’aide à la sécurité aux passages à niveau en utilisant un système deperception multi-vues. Dans ce cadre, nous avons proposé une méthode d’optimisationpermettant de déterminer automatiquement la position et l’orientation descaméras par rapport à l’environnement à percevoir.La deuxième étape consisteà développer une méthode robuste de suivi d’objets enmouvement à partir d’une séquence d’images. Dans un premier temps, nous avonsproposé une technique permettant la détection et la séparation des objets. Le processusde suivi est ensuite mis en oeuvre par le calcul et la rectification du flotoptique grâce respectivement à un modèle gaussien et un modèle de filtre de Kalman.La dernière étape est destinée à l’analyse des trajectoires 2D reconstruites parl’étape précédente pour l’interprétation de scénarios. Cette analyse commence parune modélisation markovienne des trajectoires 2D. Un système de décision à basede théorie de l’évidence est ensuite proposé pour l’évaluation de scénarios, aprèsavoir modélisé les sources de danger.L’approche proposée a été testée et évaluée avec des données issues de campagnesexpérimentales effectuées sur site réel d’un passage à niveau mis à disposition parRFF. / The main objective of this thesis is to develop a system for monitoringthe close environment of a level crossing. It aims to develop a perception systemallowing the detection and the evaluation of dangerous situations around a levelcrossing.To achieve this goal, the overall problem of this work has been broken down intothree main stages. In the first stage, we propose a method for optimizing automaticallythe location of video sensors in order to cover optimally a level crossingenvironment. This stage addresses the problem of cameras positioning and orientationin order to view optimally monitored scenes.The second stage aims to implement a method for objects tracking within a surveillancezone. It consists first on developing robust algorithms for detecting and separatingmoving objects around level crossing. The second part of this stage consistsin performing object tracking using a Gaussian propagation optical flow based modeland Kalman filtering.On the basis of the previous steps, the last stage is concerned to present a newmodel to evaluate and recognize potential dangerous situations in a level crossingenvironment. This danger evaluation method is built using Hidden Markov Modeland credibility model.Finally, synthetics and real data are used to test the effectiveness and the robustnessof the proposed algorithms and the whole approach by considering various scenarioswithin several situations.This work is developed within the framework of PANsafer project (Towards a saferlevel crossing), supported by the ANR-VTT program (2008) of the French NationalAgency of Research. This project is also labelled by Pôles de compétitivité "i-Trans"and "Véhicule du Futur". All the work, presented in this thesis, has been conductedjointly within IRTES-SET laboratory from UTBM and LEOST laboratory fromIFSTTAR.

Ocasionalmente, decisores se deparam com situações que demandarão a tomada de decisões estratégicas. Trata-se, com freqüência, de decisões que não foram vivenciadas anteriormente - seja no âmbito do organizacional, seja no âmbito pessoal dos decisores envolvidos - e, por isso, essas experiências anteriores podem ser de pouco valor ou podem ser transpostas apenas parcialmente ao novo contexto decisório. Nessas situações, surge um problema real a ser enfrentado pelos decisores e pouco explorado empiricamente pelos estudiosos dos processos decisórios: o problema de decidir como tomar uma decisão estratégica ou, como também conhecido no meio acadêmico, como tomar as metadecisões de um processo decisório. Para tratar desse problema, pesquisou-se a escassa literatura existente e, considerando estudos selecionados sobre processos decisórios, desenvolveu-se um modelo teórico representando os fatores que podem afetar dois tipos de metadecisões: a de processo e a de conteúdo. Em seguida, no contexto de uma organização pública e, no âmbito do desenvolvimento e produção de dois produtos para fins de diagnóstico e terapia, uma investigação foi conduzida envolvendo, no total, sete processos decisórios. Essa investigação objetivou testar o modelo teórico desenvolvido, verificar a existência de alguma associação lógica entre as diferentes metadecisões tomadas ao longo de um processo decisório e, a partir de análises dos resultados, identificar contribuições acadêmicas e práticas ao estado da arte sobre o tema. Como resultado desse esforço, o modelo do processo metadecisório foi revisado com a inclusão de novos fatores que podem influenciar as metadecisões e constatou-se que, ao longo de um processo decisório, parte das metadecisões tomadas podem apresentar uma associação lógica entre si. No conjunto, esses resultados permitiram a conclusão quanto à existência de uma estrutura lógica subjacente ao processo decisório maior do que a identificada por outros autores em estudos anteriores. Dezenove proposições relacionadas a metadecisões e uma metodologia para decidir como decidir integram as contribuições do estudo e abrem a perspectiva para outros estudos investigarem a aplicabilidade e generalidade do modelo desenvolvido e das proposições efetuadas para outros contextos organizacionais. / Occasionally, decision makers face situations where they need to make strategic decisions. Frequently, these decisions are new, and thus, previous experience is only partially helpful, if it is at all. In these situations, there is a real problem that needs to be addressed by the decision maker, which is the problem of deciding how to decide strategic decisions, or, in other words, how to make the metadecisions of a strategic decision. In order to deal with this theme, the scarce literature was reviewed and, along with selected topics about the decision making process, a theoretical model was developed to represent two types of metadecisions: process and content. The next step was the development of an empirical research in a public organization, involving the development and production of two products for diagnosis and therapy purposes. Seven decision processes were studied. The investigation was carried out in order to test the theoretical model, to verify the existence of any logical association among the different metadecisions taken within the decision process and, after the analysis of the results, to generate new contributions to the state of the art of this theme. The main results of this research are the revision and inclusion of new factors in the metadecision model and the identification that some of the metadecisions taken within a strategic decision process may present a logical association with one another. These findings indicated that the subjacent logical structure pointed out by other authors in previous studies can be extended. Nineteen propositions concerning metadecisions and a methodology to decide how to decide are additional contributions of this study. Taken altogether, this investigation opened the perspective of future studies to investigate the problem of deciding how to decide and extend the findings of the present study to other organizational environments.