ANP / Este trabalho propõe o uso de Mapas Cognitivos Fuzzy Dinâmicos (DFCM, do inglês Dynamic Fuzzy Cognitive Maps), uma evolução dos Mapas Cognitivos Fuzzy (FCM), para o desenvolvimento de sistemas autônomos para tomada de decisões. O FCM representa o conhecimento de forma simbólica, através de conceitos e relações causais dispostas em um grafo. Na sua versão clássica, os FCMs são usados no desenvolvimento de modelos estáticos, sendo inapropriados para o desenvolvimento de modelos temporais ou dinâmicos devido à ocorrência simultânea de todas as causalidades em uma estrutura fixa dos grafos, i.e., os conceitos e suas relações causais são invariantes no tempo. O DFCM utiliza o mesmo formalismo matemático do FCM através de grafos, acrescentando funcionalidades, como por exemplo, a capacidade de auto adaptação através de algoritmos de aprendizagem de máquina e a possibilidade de inclusão de novos tipos de conceitos e relações causais ao modelo FCM clássico. A partir dessas inclusões, é possível construir modelos DFCM para tomada de decisões dinâmicas, as quais são necessárias no desenvolvimento de ferramentas inteligentes em áreas de conhecimento correlatas à engenharia, de modo especifico a construção de modelos aplicados em Robótica Autônoma. Em especial, para as áreas de Robótica de Enxame e Vida artificial, como abordados nesta pesquisa. O sistema autônomo desenvolvido neste trabalho aborda problemas com diferentes objetivos (como desviar de obstáculos, coletar alvos ou alimentos, explorar o ambiente), hierarquizando as ações necessárias para atingi-los, através do uso de uma arquitetura para o planejamento, inspirada no modelo clássico de Subsunção de Brooks, e uma máquina de estados para o gerenciamento das ações. Conceitos de aprendizagem de máquina, em especial Aprendizagem por Reforço, são empregadas no DFCM para a adaptação dinâmica das relações de casualidade, possibilitando o controlador a lidar com eventos não modelados a priori. A validação do controlador DFCM proposto é realizada por meio de experimentos simulados através de aplicações nas áreas supracitadas. / This dissertation proposes the use of Dynamic Fuzzy Cognitive Maps (DFCM), an evolution of Fuzzy Cognitive Maps (FCM), for the development of autonomous system to decision-taking. The FCM represents knowledge in a symbolic way, through concepts and causal relationships disposed in a graph. In its standard form, the FCMs are limited to the development of static models, in other words, classical FCMs are inappropriate for development of temporal or dynamic models due to the simultaneous occurrence of all causalities in a permanent structure, i.e., the concepts and the causal relationships are time-invariant. The DFCM uses the same mathematical formalism of the FCM, adding features to its predecessor, such as self-adaptation by means of machine learning algorithms and the possibility of inclusion of new types of concepts and causal relationships into the classical FCM model. From these inclusions, it is possible to develop DFCM models for dynamic decision-making problems, which are needed to the development of intelligent tools in engineering and other correlated areas, specifically, the construction of autonomous systems applied in Autonomous Robotic. In particular, to the areas of Swarm Robotics and Artificial Life, as approached in this research. The developed autonomous system deals with multi-objective problems (such as deviate from obstacle, collect target or feed, explore the environment), hierarchizing the actions needed to reach them, through the use of an architecture for planning, inspired by the Brook’s classical Subsumption model, and a state machine for the management of the actions. Learning machine algorithms, in particular Reinforcement Learning, are implemented in the DFCM to dynamically tune the causalities, enabling the controller to handle not modelled event a priori. The proposed DFCM model is validated by means of simulated experiments applied in the aforementioned areas.

Desenvolveu-se uma metodologia para integração de dois modelos matemáticos, um de quantidade de água, em rede de fluxo, denominado ACQUANET com outro de qualidade de água, de uma dimensão, aplicado a represas, denominado CE-QUAL-R1. Para tanto, foi elaborada uma INTERFACE em linguagem de programação possibilitando que as vazões resultantes, simuladas pelo ACQUANET, servissem como dados de entrada ao CE-QUAL-R1 para simular a distribuição vertical das variáveis de qualidade de água em uma represa. Essa metodologia foi aplicada à Represa Jaguari-Jacareí no Sistema Cantareira em São Paulo, Brasil, como alternativa de gerenciamento quali-quantitativo, além de possibilitar o uso de retirada de água em diferentes profundidades, através da operação de tomadas d’água seletivas existentes. / A methodology was developed for the integration of two mathematical models, one of water quantity in network named ACQUANET with other of water quality, in one dimension, applied in revervoirs, named CE-QUAL-R1. In order to achieve this goal, an INTERFACE was developed to link the CE-QUAL-R1 with ACQUANET outflow results. It should be highlighted that ACQUANET has been used for beginning values of CE-QUAL-R1 and to simulate the vertical distribution of water quality variables in a reservoir. This methodology was applied to Jaguari-Jacarei Reservoir, of Cantareira System in Sao Paulo, Brazil, as a management quality and quantity tool of the system and it showed the use possibility of withdrawal of outflowing waters from different depths, through existing selective withdrawals ports operation.

Für viele Krankheitsbilder und Indikationen ist ein breites Spektrum an Arzneimitteln und Arzneimittelkombinationen verfügbar. Darüber hinaus stellen Therapieziele oft Kompromisse zwischen medizinischen Zielstellungen und Präferenzen und Erwartungen von Patienten dar, um Zufriedenheit und Adhärenz zu gewährleisten. Die Auswahl der optimalen Therapieoption kann daher eine große Herausforderung für den behandelnden Arzt darstellen. Klinische Entscheidungsunterstützungssysteme, die Wirksamkeit oder Risiken unerwünschter Arzneimittelwirkung für Behandlungsoptionen vorhersagen, können diesen Entscheidungsprozess unterstützen und \linebreak Leitlinien-basierte Empfehlungen ergänzen, wenn Leitlinien oder wissenschaftliche Literatur fehlen oder ungeeignet sind. Bis heute sind keine derartigen Systeme verfügbar. Im Rahmen dieser Arbeit wird die Anwendung von Methoden aus der Domäne der Recommender Systems (RS) und des Maschinellen Lernens (ML) in solchen Unterstützungssystemen untersucht. Aufgrund ihres erfolgreichen Einsatzes in anderen Empfehlungssystemen und der einfachen Interpretierbarkeit werden zum einen Nachbarschafts-basierte Collaborative Filter (CF) an die besonderen Anforderungen und Herausforderungen der Therapieempfehlung angepasst. Zum anderen werden ein Modell-basierter CF-Ansatz (SLIM) und ein ML Algorithmus (GBM) erprobt. Alle genannten Ansätze werden anhand eines exemplarischen Therapieempfehlungssystems evaluiert, das auf die Behandlung der Autoimmunkrankheit Psoriasis abzielt. Um das Risiko der Empfehlung kontraindizierter oder gar gesundheitsgefährdender Medikamente zu reduzieren, werden Regeln aus evidenzbasierten Leitlinien und Expertenempfehlungen implementiert, um solche Therapieoptionen aus den Empfehlungslisten herauszufiltern. Insbesondere die Nachbarschafts-basierten CF-Algorithmen zeigen insgesamt kleine durchschnittliche Abweichungen zwischen geschätztem und tatsächlichem Therapie-Outcome. Auch die aus den Outcome-Schätzungen abgeleiteten Empfehlungen zeigen eine hohe Übereinstimmung mit der tatsächlich angewandten Behandlung. Die Modell-basierten Ansätze sind den Nachbarschafts-basierten Ansätzen insgesamt unterlegen, was auf den begrenzten Umfang der verfügbaren Trainingsdaten zurückzuführen ist und die Generalisierungsfähigkeit der Modelle erschwert. Im Vergleich mit menschlichen Experten sind alle untersuchten Algorithmen jedoch hinsichtlich Übereinstimmung mit der tatsächlich angewandten Therapie unterlegen. Eine objektive und effiziente Bewertung des Behandlungserfolgs kann als Voraussetzung für ein erfolgreiches ``Krankheitsmanagement'' angesehen werden. Daher wird in weiteren Untersuchungen für ausgwählten klinische Anwendungen der Einsatz von ML Methoden zur automatischen Quantifizierung von Gesunheitszustand und Therapie-Outcome erprobt. Zusätzlich, als weitere Quelle für Informationen über Therapiewirksamkeiten, wird der Einsatz von Sentiment Analysis Methoden zur Extraktion solcher Informationen aus Medikamenten-Bewertungen untersucht. / Under most medical conditions and indications, a great variety of pharmaceutical drugs and drug combinations are available. Beyond that, trade-offs need to be found between the medical requirements and the patients' preferences and expectations in order to support patients’ satisfaction and adherence to treatments. As a consequence, the selection of an optimal therapy option for an individual patient poses a challenging task to prescribers. Clinical Decision Support Systems (CDSSs), which predict outcome as effectiveness and risk of adverse effects for available treatment options, can support this decision-making process and complement guideline-based decision-making where evidence from scientific literature is missing or inappropriate. To date, no such systems are available. Within this work, the application of methods from the Recommender Systems (RS) domain and Machine Learning (ML) in such decision support systems is studied. Due to their successful application in other recommender systems and good interpretability, neighborhood-based CF algorithms are transferred to the medical domain and are adapted to meet the requirements and challenges of the therapy recommendation task. Moreover, a model-based CF method (SLIM) and a state of the art ML algorithm (GBM) are employed. All algorithms are evaluated in an exemplary therapy recommender system, targeting the treatment of the autoimmune skin disease Psoriasis. In order to reduce the risk of recommending contraindicated or even health-endangering drugs, rules derived from evidence-based guidelines and expert recommendations are implemented to filter such options from the recommendation lists. Especially the neighborhood-based CF algorithms show small average errors between estimated and observed outcome. Also, the recommendations derived from outcome estimates show high agreement with the ground truth. The performance of both model-based approaches is inferior to the neighborhood-based recommender. This is primarily assumed to be due to the limited training data sizes, which renders generalizability of the learned models difficult. Compared with recommendations provided by various experts, all proposed approaches are, however, inferior in terms of agreement with the ground truth. An objective and efficient assessment of treatment response can be regarded a prerequisite for successful ``disease management''. Therefore, the use of ML methods for the automatic quantification of health status and therapy outcome for selected clinical applications is investigated in further experiments. Moreover, as additional source of information about drug effectiveness, the use of Sentiment Analysis, in order to extract such information from drug reviews, is investigated.

Text in English / In recent years, there have been tremendous advances in information technology, robotics, communication technology, nanotechnology, and artificial intelligence, resulting in the merging of physical, digital, and biological worlds that have come to be known as the "fourth industrial revolution”. In this context, the present study engages such technology in the green economy and to tackle the techno-economic environmental impact assessments challenges associated with floating solar system applications in the agricultural sector of South Africa. In response, this exploratory study aimed to examine the development of a Geographical Information System (GIS)-based support platform for Environmental Impact Assessment (EIA) and due-diligence analyses for future planned agricultural floating solar systems, especially with the goal to address the vast differences between the environmental impacts for land-based and water-based photovoltaic energy systems. A research gap was identified in the planning processes for implementing floating solar systems in South Africa’s agricultural sector. This inspired the development of a novel GIS-based modelling tool to assist with floating solar system type energy infrastructure planning in the renewable energy discourse. In this context, there are significant challenges and future research avenues for technical and environmental performance modelling in the new sustainable energy transformation. The present dissertation and geographical research ventured into the conceptualisation, designing and development of a software GIS-based decision support tool to assist environmental impact practitioners, project owners and landscape architects to perform environmental scoping and environmental due-diligence analysis for planned floating solar systems in the local agricultural sector. In terms of the aims and objectives of the research, this project aims at the design and development of a dedicated GIS toolset to determine the environmental feasibility around the use of floating solar systems in agricultural applications in South Africa. In this context, the research objectives of this study included the use of computational modelling and simulation techniques to theoretically determine the energy yield predictions and computing environmental impacts/offsets for future planned agricultural floating solar systems in South Africa. The toolset succeeded in determining these aspects in applications where floating solar systems would substitute Eskom grid power. The study succeeded in developing a digital GIS-based computer simulation model for floating solar systems capable of (a) predicting the anticipated energy yield, (b) calculating the environmental offsets achieved by substituting coal-fired generation by floating solar panels, (c) determining the environmental impact and land-use preservation benefits of any floating solar system, and (d) relating these metrics to water-energy-land-food (WELF) nexus parameters suitable for user project viability analysis and decision support. The research project has demonstrated how the proposed GIS toolset supports the body of geographical knowledge in the fields of Energy and Environmental Geography. The new toolset, called EIAcloudGIS, was developed to assist in solving challenges around energy and environmental sustainability analysis when planning new floating solar installations on farms in South Africa. Experiments conducted during the research showed how the geographical study in general, and the toolset in particular, succeeded in solving a real-world problem. Through the formulation and development of GIS-based computer simulation models embedded into GIS layers, this new tool practically supports the National Environmental Management Act (NEMA Act No. 107 of 1998), and in particular, associated EIA processes. The tool also simplifies and semi-automates certain aspects of environmental impact analysis processes for newly envisioned and planned floating solar installations in South Africa. / Geography / M.Sc. (Geography)

Over the past few years, mining data located in heterogeneous and geographically distributed sites have been designated as one of the key important issues. Loading distributed data into centralized location for mining interesting rules is not a good approach. This is because it violates common issues such as data privacy and it imposes network overheads. The situation becomes worse when the network has limited bandwidth which is the case in most of the real time systems. This has prompted the need for intelligent data analysis to discover the hidden information in these huge amounts of distributed databases. In this research, we present an incremental approach for building an efficient Multi-Agent based algorithm for mining real world databases in geographically distributed sites. First, we propose the Distributed Multi-Agent Association Rules algorithm (DMAAR) to minimize the all-to-all broadcasting between distributed sites. Analytical calculations show that DMAAR reduces the algorithm complexity and minimizes the message communication cost. The proposed Multi-Agent based algorithm complies with the Foundation for Intelligent Physical Agents (FIPA), which is considered as the global standards in communication between agents, thus, enabling the proposed algorithm agents to cooperate with other standard agents. Second, the BitTable Multi-Agent Association Rules algorithm (BMAAR) is proposed. BMAAR includes an efficient BitTable data structure which helps in compressing the database thus can easily fit into the memory of the local sites. It also includes two BitWise AND/OR operations for quick candidate itemsets generation and support counting. Moreover, the algorithm includes three transaction trimming techniques to reduce the size of the mined data. Third, we propose the Pruning Multi-Agent Association Rules algorithm (PMAAR) which includes three candidate itemsets pruning techniques for reducing the large number of generated candidate itemsets, consequently, reducing the total time for the mining process. The proposed PMAAR algorithm has been compared with existing Association Rules algorithms against different benchmark datasets and has proved to have better performance and execution time. Moreover, PMAAR has been implemented on real world distributed medical databases obtained from more than one hospital in Egypt to discover the hidden Association Rules in patients¿ records to demonstrate the merits and capabilities of the proposed model further. Medical data was anonymously obtained without the patients¿ personal details. The analysis helped to identify the existence or the absence of the disease based on minimum number of effective examinations and tests. Thus, the proposed algorithm can help in providing accurate medical decisions based on cost effective treatments, improving the medical service for the patients, reducing the real time response for the health system and improving the quality of clinical decision making.

Published works cite that 70-80% of the total cost of a product is established during conceptual design, and that improvements in time-to-market, quality, affordability, and global competitiveness require the development of better approaches to assist decision-making during the early stages of product design, as well as facilitate enterprise knowledge management and reuse. For many years, concurrent engineering and teaming have been viewed as “the answer” to product development woes, but studies reveal teaming is not sufficient to handle the task complexities of product development and the long-term goal of enterprise learning. The work of Roberto Verganti provides new insights with regard to reciprocal interdependencies (RIs), feedforward planning, selective anticipation in the context of improving teaming and concurrent engineering, as well as enterprise learning, knowledge management, reuse. In this research, reciprocal interdependencies management (RIM) is offered as a means of addressing product development and concurrent engineering issues occurring in the early stages of design. RIM is combination of Verganti’s concepts, a conceptual RIs structure, new RIM-application strategies, RIM-diagramming, and a conceptual RIM-based decisions support system, which come together to form a vision of a RIM-based enterprise knowledge management system. The conceptual RIM-based DSS is presented using the specific case of supporting a working-level integrated product team (IPT) engaged in the design of an aircraft bulkhead. A qualitative assessment tool is used to compare RIM to other approaches in the literature, and initial results are very favorable.

This paper deals with data warehouses and OLAP. These technologies are defined and described here. Then an introduction of the architecture of product MS SQL Server and its tools for work with data warehouses and OLAP folow. The knowledge gained is used for creation of sample application.

System dynamics modelling has been used for around 40 years to address complex, systemic, dynamic problems, those often described as wicked. But, system dynamics modelling is not an exact science and arguments about the most suitable techniques to use in which circumstances, continues. The nature of these wicked problems is investigated through a series of case studies where poor situational awareness among stakeholders was identified. This was found to be an underlying cause for management failure, suggesting need for better ways of recognising and managing wicked problem situations. Human cognition is considered both as a limitation and enabler to decision-making in wicked problem environments. Naturalistic and deliberate decision-making are reviewed. The thesis identifies the need for integration of qualitative and quantitative techniques. Case study results and a review of the literature led to identification of a set of principles of method to be applied in an integrated framework, the aim being to develop an improved way of addressing wicked problems. These principles were applied to a series of cases in an action research setting. However, organisational and political barriers were encountered. This limited the exploitation and investigation of cases to varying degrees. In response to a need identified in the literature review and the case studies, a tool is designed to facilitate analysis of multi-factorial, non-linear causality. This unique tool and its use to assist in problem conceptualisation, and as an aid to testing alternate strategies, are demonstrated. Further investigation is needed in relation to the veracity of combining causal influences using this tool and system dynamics, broadly. System dynamics modelling was found to have utility needed to support analysis of wicked problems. However, failure in a particular modelling project occurred when it was found necessary to rely on human judgement in estimating values to be input into the models. This was found to be problematic and unacceptably risky for sponsors of the modelling effort. Finally, this work has also identified that further study is required into: the use of human judgement in decision-making and the validity of system dynamics models that rely on the quantification of human judgement.

H διατριβή διερευνά προβλήματα αποδοτικής οργάνωσης χωροταξικών δεδομένων, προτείνει συγκεκριμένες δενδρικές δομές για τη διαχείρισή τους και, τέλος, δίνει παραδείγματα χρήσης τους σε ειδικές περιοχές εφαρμογών. Το πρώτο κεφάλαιο ασχολείται με το γεωμετρικό πρόβλημα της εύρεσης των ισo-προσανατολισμένων ορθογωνίων που περικλείουν ένα query αντικείμενο που μπορεί να είναι ένα ισο-προσανατολισμένο ορθογώνιο είτε σημείο ή κάθετο / οριζόντιο ευθύγραμμο τμήμα. Για την επίλυσή του προτείνεται μια πολυεπίπεδη δενδρική δομή που βελτιώνει τις πολυπλοκότητες των προηγούμενων καλύτερων λύσεων. Το δεύτερο κεφάλαιο εξετάζει το πρόβλημα της ανάκτησης σημείων σε πολύγωνα. H προτεινόμενη γεωμετρική δομή είναι επίσης πολυεπίπεδη και αποδοτική όταν το query πολύγωνο έχει συγκεκριμένες ιδιότητες. Το τρίτο κεφάλαιο ασχολείται με την εφαρμογή δενδρικών δομών σε δύο βιομηχανικά προβλήματα. Το πρώτο αφορά στη μείωση της πολυπλοκότητας ανίχνευσης συγκρούσεων κατά την κίνηση ενός ρομποτικού βραχίονα σε μια επίπεδη σκηνή με εμπόδια. Ο αλγόριθμος επίλυσης κάνει χρήση μιας ουράς προτεραιότητας και μιας UNION-FIND δομής ενώ αξιοποιεί γνωστές δομές και αλγόριθμους της Υπολογιστικής Γεωμετρίας όπως υπολογισμός κυρτών καλυμμάτων, έλεγχος polygon inclusion, κλπ. Το δεύτερο πρόβλημα ασχολείται με το σχεδιασμό απαιτήσεων υλικών (MRP) σε ένα βιομηχανικό σύστημα παραγωγής. Για το σκοπό αυτό αναπτύχθηκε ένας MRP επεξεργαστής που χρησιμοποιεί διασυνδεμένες λίστες και εκτελείται στην κύρια μνήμη για να είναι αποδοτικός. Το τελευταίο κεφάλαιο εξετάζει το πρόβλημα του ελέγχου της παραγωγής και συγκεκριμένα της δρομολόγησης εργασιών. Στο πλαίσιο αυτό σχεδιάστηκε και υλοποιήθηκε ένα ευφυές σύστημα δρομολόγησης σε περιβάλλον ροής που συνδυάζει γνωσιακή τεχνολογία και προσομοίωση με on-line έλεγχο προκειμένου να υποστηρίξει το διευθυντή παραγωγής στη λήψη αποφάσεων. / Τhe dissertation examines problems of efficient organization of spatial data, proposes specific tree structures for their management, and finally, gives examples of their use in specific application areas. The first chapter is about the problem of finding the iso-oriented rectangles that enclose a query object which can be an iso-oriented rectangle either a point or a vertical / horizontal line segment. A multilevel tree structure is proposed to solve the problem which improves the complexities of the best previous known solutions. The second chapter examines the problem of point retrieval on polygons. The proposed geometric structure is also multileveled and efficient when the query polygon has specific properties. The third chapter is about the application of tree structures in two manufacturing problems. The first one concerns the reduction in the complexity of collision detection as a robotic arm moves on a planar scene with obstacles. For the solution a priority queue and a UNION-FIND structure are used, whereas known data structures and algorithms of Computational Geometry such as construction of convex hulls, polygon inclusion testing, etc. are applied. The second problem is about material requirements planning (MRP) in a manufacturing production system. To this end an MRP processor was developed, which uses linked lists and runs in main memory to retain efficiency. The last chapter examines the production control problem, and more specifically the job scheduling problem. In this context, an intelligent scheduling system was designed and developed for flow shop production control which combines knowledge-based technology and simulation with on-line control in order to support the production manager in decision making.

System dynamics modelling has been used for around 40 years to address complex, systemic, dynamic problems, those often described as wicked. But, system dynamics modelling is not an exact science and arguments about the most suitable techniques to use in which circumstances, continues. The nature of these wicked problems is investigated through a series of case studies where poor situational awareness among stakeholders was identified. This was found to be an underlying cause for management failure, suggesting need for better ways of recognising and managing wicked problem situations. Human cognition is considered both as a limitation and enabler to decision-making in wicked problem environments. Naturalistic and deliberate decision-making are reviewed. The thesis identifies the need for integration of qualitative and quantitative techniques. Case study results and a review of the literature led to identification of a set of principles of method to be applied in an integrated framework, the aim being to develop an improved way of addressing wicked problems. These principles were applied to a series of cases in an action research setting. However, organisational and political barriers were encountered. This limited the exploitation and investigation of cases to varying degrees. In response to a need identified in the literature review and the case studies, a tool is designed to facilitate analysis of multi-factorial, non-linear causality. This unique tool and its use to assist in problem conceptualisation, and as an aid to testing alternate strategies, are demonstrated. Further investigation is needed in relation to the veracity of combining causal influences using this tool and system dynamics, broadly. System dynamics modelling was found to have utility needed to support analysis of wicked problems. However, failure in a particular modelling project occurred when it was found necessary to rely on human judgement in estimating values to be input into the models. This was found to be problematic and unacceptably risky for sponsors of the modelling effort. Finally, this work has also identified that further study is required into: the use of human judgement in decision-making and the validity of system dynamics models that rely on the quantification of human judgement.