A capacidade de reconfiguração de sistemas de manufatura tem sido procurada pelas empresas para assegurar características de agilidade, eficiência e exibilidade para atender as mudanças de tipo/quantidade de produtos, processos, recursos e, além disso, para assegurar a devida reação à ocorrência de falhas. Por outro lado, a Indústria 4.0\" impõe novos desafios para os sistemas de controle, tais como a integração de tecnologias de interação entre homem e máquina em cadeias de valor compondo uma rede de plantas industriais geograficamente dispersas. O controle de sistemas reconfiguráveis de manufatura deve considerar: (i) funcionalidades de sistemas distribuídos e dispersos, tais como agilidade de resposta às mudanças, autonomia e colaboração entre os componentes para alcançar os objetivos do sistema de forma conjunta; (ii) interfaces para sua interoperabilidade e portabilidade; (iii) modularização para facilitar a manutenção, expansão e atualização do sistema, evitando a sobreposição de escopos; e (iv) mecanismos de controle para supervisionar as ações e interações dos componentes, o diagnóstico e a tomada de decisão. O pleno atendimento a estes requisitos não é trivial e formalismos para o desenvolvimento de soluções devem ser adotados. Uma solução é combinar técnicas voltadas para sistema multiagente e holon com arquitetura orientada a serviço através de uma adequada técnica de modelagem usando extensões de rede de Petri: Production Flow Schema e Input Output Place Transition. Portanto, este trabalho prop~oe uma arquitetura de controle e o método de modelagem de seus componentes para sistemas reconfiguráveis de manufatura combinando estas técnicas e considerando os aspectos de personalização, convertibilidade, escalabilidade, modularidade, integrabilidade, diagnosticabilidade, interoperabilidade e colaboração entre os componentes do sistema de controle, inclusive do homem. Um exemplo de aplicação é apresentado para demonstrar a viabilidade da proposta e comprovar os resultados alcançados. / The reconfiguration ability of the manufacturing systems has been approached by companies to ensure agility, efficiency and exibility characteristics to address the changes of type/quantity of products, processes and resources and, furthermore, to ensure proper reaction to the fault occurrence. On the other hand, the\"Industry 4.0\" imposes new challenges for control systems, such as interaction between man and machine into value chains composing a network of geographically dispersed industrial plants. The control of reconfigurable manufacturing systems should consider: (i) functionalities requirements of distributed and disperse systems, such as responsiveness to changes, autonomy and collaboration among components to achieve the global system aim; (ii) interfaces for interoperability and portability; (iii) modularity to facilitate maintenance, expansion and upgrade of the system, avoiding the overlapping of scopes; and (iv) control mechanisms to supervise the actions and interactions among components, diagnosis and decision making. The compliance with these requirements is not trivial and formalisms to develop solutions must be adopted. A solution is combining techniques based on holonic and multi-agent system with service-oriented architecture through appropriate modeling using Petri net extensions: Production Flow Schema and Input Output Place Transition. Therefore, this paper proposes control architecture and a method to model components for reconfigurable manufacturing systems, combining these techniques and considering aspects of customization, convertibility, scalability, modularity, integrability, diagnosability, interoperability and collaboration among control system components, including humans. An application example is presented to demonstrate the feasibility of the proposal and verify the results.

Submitted by Divisão de Documentação/BC Biblioteca Central (ddbc@ufam.edu.br) on 2016-02-04T17:56:58Z No. of bitstreams: 1 Dissertação - Neila Batista Xavier.pdf: 16096870 bytes, checksum: 14fa0cdac4b0ae0046b9b6a6b2e06c88 (MD5) / Approved for entry into archive by Divisão de Documentação/BC Biblioteca Central (ddbc@ufam.edu.br) on 2016-02-04T17:57:48Z (GMT) No. of bitstreams: 1 Dissertação - Neila Batista Xavier.pdf: 16096870 bytes, checksum: 14fa0cdac4b0ae0046b9b6a6b2e06c88 (MD5) / Approved for entry into archive by Divisão de Documentação/BC Biblioteca Central (ddbc@ufam.edu.br) on 2016-02-04T17:58:07Z (GMT) No. of bitstreams: 1 Dissertação - Neila Batista Xavier.pdf: 16096870 bytes, checksum: 14fa0cdac4b0ae0046b9b6a6b2e06c88 (MD5) / Made available in DSpace on 2016-02-04T17:58:07Z (GMT). No. of bitstreams: 1 Dissertação - Neila Batista Xavier.pdf: 16096870 bytes, checksum: 14fa0cdac4b0ae0046b9b6a6b2e06c88 (MD5) Previous issue date: 2015-10-09 / With the continued and increasing use of Learning Management System (LMS) in educational institutions, it is necessary for coordinators and administrators effectively manage the online courses in order to ensure good monitoring and superior levels looking for ways to improve the management of online courses. Thus, considering the difficulties in the aspect of infrastructure and time to become familiar with the resources available, the researchers realized the need to know the opinion of people with experience in Distance Education and higher level positions to decision-making. During the investigation of the problem, was held collection and analysis of information on the performance of LMS in the follow-up courses process. The results revealed the need to implement a tool that would help the monitoring of online courses. Based on this information, this paper proposes and describes an approach based on a Multi-Agent System for this problem. The system has the purpose to support the management of online courses through intelligent agents. From the use of the proposed system, the coordinator of an online courses get condensed and quick information of each current course, facilitating managerial vision by reporting and organized graphics, and receive periodically a message via email about the current status of each course. Thus, intelligent agents show specific situations of access students, tutors and teachers, and help the follow-up activities. To validate the work, was carried out a case study in the postgraduate courses in online mode with several real disciplines concurrently taking place in a Federal Institute of Education (IFE) of Amazonas state. The case study aimed evaluate the feasibility of the proposal, and from the results obtained in the test can be concluded that with using the developed system was possible to improve the monitoring of levels of online courses, assist in making decisions and thus enable the adoption of new teaching strategies / Com o contínuo e crescente uso de Ambientes Virtuais de Aprendizagem (AVA) em instituições de ensino, é necessário que coordenadores e administradores gerenciem efetivamente os cursos de Educação a Distância (EaD), a fim de garantir um bom acompanhamento e níveis de qualidade superior, buscando meios para aperfeiçoar o gerenciamento de cursos on-line. Assim, considerando as dificuldades no aspecto de infraestrutura e tempo para familiarizar-se com os recursos disponíveis, os pesquisadores perceberam a necessidade de conhecer a opinião de pessoas com experiência em EaD e em cargos de nível hierárquico superior para tomada de decisões. Durante a investigação do problema, foi realizada a coleta e a análise de informações sobre o desempenho de AVAs no processo de acompanhamento de cursos. Os resultados revelaram a necessidade da implantação de uma ferramenta que auxiliasse o acompanhamento dos cursos online. Com base nessas informações, o presente trabalho propõe e descreve uma abordagem baseada em um Sistema Multiagente (SMA) para esse problema. O sistema tem como proposta apoiar a gestão de cursos on-line por meio de Agentes Inteligentes (AIs). A partir do uso do sistema proposto, o coordenador dos cursos de um AVA obtêm informações condensadas e rápidas de cada curso corrente, facilitando a visão gerencial mediante a apresentação de relatórios e gráficos organizados, além de receber, periodicamente, uma mensagem via e-mail a respeito da situação atual de cada curso. Desta forma, os AIs evidenciam situações específicas do acesso de alunos, tutores e professores, além de auxiliar o acompanhamento de atividades. Para validar o trabalho, foi realizado um Estudo de Caso em cursos de Pós-Graduação na modalidade EaD com várias disciplinas reais ocorrendo concomitantemente em um Instituto Federal de Educação (IFE) do estado do Amazonas. O Estudo de Caso teve como objetivo avaliar a viabilidade da proposta, e a partir dos resultados obtidos nos testes realizados pode-se concluir que com o uso do sistema desenvolvido foi possível melhorar os níveis de acompanhamento dos cursos on-line, auxiliar no processo de tomada de decisões e, assim, possibilitar a adoção de novas estratégias pedagógicas.

Made available in DSpace on 2015-04-11T14:02:58Z (GMT). No. of bitstreams: 1 Andre Alves Nogueira.pdf: 3385945 bytes, checksum: 5c7b555b59610b2dac767f2900bfe5be (MD5) Previous issue date: 2014-02-20 / Weather Extreme Events (WEE) can cause natural disasters because they are often accompanied by dangerous physical activities which cause significant damage to people and properties, including some deaths. A way to soften the damage caused by these disasters is to use Weather Warning System (WWS). These kind of systems can detect an imminent risk and, different types of alerts can be triggered in order to mobilize the emergency personnel in advance. This research aims to help the Amazon Protection System (SIPAM) to solve the communication problem with the alert and mobilization. It is intended, primarily, to assist the Civil Defense with the affected population by WEE. A comparative investigation was performed in ten studies aiming to understand and analyze the main characteristics of a Warning System, which were incorporated into this research, highlighting the support of a Multi-Agent System to assist the WWS, and the use of SMS (Short Message Service) technology and E-mail for sending the alert. System Tests showed that the approach proved promising, with shipping times smaller alerts those found in the literature with a high rate of confirmed users. Also the process of sending the alert factor being faster helps to minimize the effects of EME with the affected population. / Eventos Meteorológicos Extremos (EME) podem gerar desastres naturais, geralmente acompanhados de atividades físicas perigosas que provocam danos significativos a pessoas e propriedades, gerando um grande número de vítimas ou até mesmo mortes. Uma maneira de mitigar os danos causados por estes desastres é a utilização de Sistemas de Alertas Meteorológicos (SAM); sendo detectado um risco iminente, diferentes tipos de alertas podem ser acionados objetivando a mobilização antecipada das equipes de emergência. O presente trabalho visa contribuir com o Sistema de Proteção da Amazônia (SIPAM) ou com órgãos semelhantes para a resolução do problema de comunicação referente à emissão dos alertas e a mobilização, destinando-se principalmente à ação da Defesa Civil e órgãos competentes junto à população em função dos EME ocorridos. Nesta pesquisa foi realizada uma investigação comparativa com dez trabalhos objetivando conhecer e analisar as principais características de um Sistema de Alerta, as quais foram incorporadas neste projeto, destacando-se o apoio de um Sistema Multiagente para auxiliar o SAM, e o uso das tecnologias de SMS (Short Message Service) e E-mail para o envio do alerta. Testes do sistema evidenciaram que a abordagem adotada mostrou-se promissora, apresentando tempos de envio de alertas menores que os encontrados na literatura e com alta taxa de usuários confirmados, fator de muita importância para a minimização dos efeitos dos EME junto à população atingida.

Made available in DSpace on 2016-03-15T19:37:56Z (GMT). No. of bitstreams: 1 KHAOHUN SHIA.pdf: 2242262 bytes, checksum: 97a46586e1ac55fd1097f77a932ad878 (MD5) Previous issue date: 2015-08-25 / In a competitive market of software, companies seek an agile development process with quality. Faced with this challenge, the companies target is a certification to prove the ability to produce a high quality product by following a defined process, for example, Capability Maturity Model Integration for Development (CMMI-DEV). To achieve this goal, the company hires experts to change the existing process, which represents a high cost for small and medium-sized businesses. The assumption in this work is to evaluate the possibility of using an agile methodology which adheres to CMMI-DEV. Feature Driven Development (FDD) was the agile methodology selected to assess their adherence to Project Planning area of CMMI-DEV. The evaluation of specific practices was automated by the multi-agent system with two ontologies. The first of them is the Ontology CMMI/FDD, which defines the concepts and the relationship of FDD with these specific practices. The second is the Ontology of Project Planning Document that defines the concepts used in sections of the Project Planning documents. The mapping between the specific practices and implementation was performed by intelligent mapping agents. The results obtained shown that it is possible to automate the process of evaluation of specific practices by the evidences in sections of the documents, reducing the costs involved in hiring a specialist of CMMI. The evaluation of Intelligent Agents of Specific Practices shown that the FDD partially attends to the specific practices, being necessary to change the two documents elaborated from the FDD Document (Project Plan and List of Functionality) and add three auxiliary documents (Risk Management, Data Management and Training Management) to meet all the specific practices of the Project Planning Area of the CMMI-DEV. / Em um mercado competitivo de desenvolvimento de software, as empresas buscam um processo ágil com qualidade. Diante desse desafio, procuram uma certificação para comprovar a capacidade de produzir com qualidade, seguindo um processo definido, por exemplo, o Capability Maturity Model Integration for Development (CMMI-DEV). Para atingir essa meta, a empresa contrata especialistas para alterar o processo existente, o que representa um alto custo para empresas de pequeno e médio porte. A hipótese neste trabalho é avaliar a possibilidade de utilizar uma metodologia ágil aderente ao CMMI-DEV. O Desenvolvimento Guiado por Funcionalidades (FDD) é a metodologia ágil selecionada para computar a sua aderência em relação à área de Planejamento de Projetos do CMMI-DEV. A avaliação das práticas específicas foi automatizada por um sistema multiagentes com duas ontologias. A primeira delas é a ontologia CMMI/FDD, que define os conceitos e a relação do FDD com essas práticas específicas. A segunda é a ontologia dos Documentos do Planejamento de Projeto, que define os conceitos utilizados nas seções dos documentos do Planejamento de Projeto. O mapeamento entre a prática específica e a implementação nas seções de documentação foi realizado pelos Agentes Inteligentes de Mapeamento. Os resultados obtidos mostram que é possível automatizar o processo de avaliação das práticas específicas, mostrando as evidências nas seções dos documentos, reduzindo os custos envolvidos na contratação de um especialista em CMMI. A avaliação dos Agentes Inteligentes de Práticas Específicas mostra que o FDD atende parcialmente às práticas específicas, sendo necessário alterar os dois documentos elaborados a partir do documento do FDD (Plano de Projeto e Lista de Funcionalidade) e adicionar três documentos auxiliares (Gestão de Risco, Gestão de Dados e Gestão de Treinamento) para satisfazer a todas as práticas específicas da área de Planejamento de Projeto.

La gestion de crise est devenue une activité indispensable à toute organisation publique ou privée. Elle repose le plus souvent sur un dispositif particulier appelé « cellule de crise » qui a pour objectif de mettre en œuvre des mesures d'anticipation, de vigilance, d'intervention et de sauvegarde et fait intervenir de multiples acteurs qui interagissent. Pour se préparer aux situations de crise, les communes ont l'obligation de définir un PCS (Plan Communal de Sauvegarde), mais ce dernier ne suffit pas à lui seul à garantir l'efficacité de l'organisation de crise. L'objectif de ce travail est de proposer une méthodologie, principalement fondée sur la pensée systémique et sur les Systèmes Multi-Agents, pour étudier la vulnérabilité organisationnelle de la cellule de crise et en évaluer sa performance. Un outil de simulation a été développé à destination des responsables. Il intègre des indicateurs de performance organisationnels pour identifier les défaillances potentielles de l'organisation. Les résultats de la simulation sont consignés sous la forme d'un tableau de bord dont l'analyse peut servir à améliorer l'organisation de crise. / Crisis management has become an essential activity in public and private organizations. It is most often supported by a "crisis cell" that aims to implement anticipation, vigilance, response and backup measures by involving multiple actors interactions. To be prepared for emergencies, municipalities have to define a EOP (Emergency Operations Plan). However, EOP on its own is not sufficient to ensure the effectiveness of crisis organization. The objective of this work is to propose a methodology mainly based on systems thinking and Multi-Agent Systems, to study the organizational vulnerability of crisis cell and assess its performance. A simulation tool is developed for decision makers. Organizational performance indicators are integrated to identify potential failures of the organization. Simulation results are reported in the form of a dashboard whose analysis can be used to improve crisis organization.

Context : Alzheimer's disease is a memory impairment disease which mostly affects elderly people. Currently, about 4 million Americans and 5 million Europeans are affected by this disease. The occurrence of Alzheimer's disease is expected to quadruple by the year 2020. Alzheimer's disease cannot be cured or stopped its progression rather delay its progression. Early diagnosis of the disease helps the patients, the caregivers and health institutions to save time, cost and minimize patients suffering. Objectives : In this thesis, different machine learning algorithms used for classification purpose are evaluated and various Alzheimer's disease diagnosis techniques are identified. Among these algorithms, a suitable classifier that has better classification accuracy on the National Alzheimer Coordinating Center (NACC) dataset is selected. This classifier is customized in order to make it compatible for the NACC dataset and to receive the new instance from the user. Then a multi-agent system model is develop that can improve the classification accuracy. Methods : Different research works are reviewed and experiments are conducted throughout this research work. A dataset for this research is obtained from National Alzheimer's Coordinating Center, university of Washington. Using this dataset, two experiments are conducted in WEKA. In the first experiment, the five candidate algorithms are compared to select the significant classifier for medical history and cognitive function data. For the second experiment, two datasets are used; a dataset contains Medical History (MH) with Cognitive Function (CF) data and a dataset that contains only medical history data to check in which dataset the selected classifier has better accuracy. Results : From the first experiment, J48 classifier has a better stage prediction accuracy than the candidate algorithms with 61.12%. J48 is customized to classify a new instance received from the user and to improve the classification accuracy. Then the accuracy increase to 87.09% when the classifier's parameters are optimized. When the medical history and cognitive function data is experimented in WEKA separately, the classification accuracies of J48 on MH, CF and their combination datasets are 81.42%, 64.20% and 87.09% respectively. The agents simulation result showed that some misclassified instances by J48 algorithm can be corrected by using multi agent system. The experimental results are presented in graphical format. Conclusions : Hence we conclude that machine learning and agent system in combination can be used for Alzheimer's disease diagnosis and its stage prediction by extracting knowledge from a dataset which contains patients medical history and cognitive function data. / Syftet med detta examensarbeta var att diagnostiserar Alzheimer patienter använder mönstret från en samling av andra tidigare diagnoserad patienter information och diagnosdata. Examensarbete hade tre huvuduppgifter: Förberedelse av data (mer än 10000 patienter data) för forskningen, maskininlärning algoritmer utvärderade med WEKA verktyg för att välja den bästa algoritmen och förbättra noggrannheten av den valda algoritmen med hjälp av agent system tekniker . - SQL queries används på uppgifter förberedelsefas. - WEKA programvara används för algoritmer utvärdering. - Agent arkitektur är utvecklat för att förbättra förutsäga av noggrannhets. Det bidrag av detta examensarbeta är identifiera Alzheimer patienter diagnos metod som använder en samling av patienternas diagnos information / biliyala.ezd2@gmail.com, them22dayz@gmail.com

De nos jours, l’intérêt porté à la préservation de l’environnement à travers la réduction des émissions de gaz à effet de serre prend de plus en plus d’ampleur. Depuis 2006,la politique multimodale a évolué vers une politique co-modale qui n’oppose plus la voiture au transport public mais encourage une combinaison de tous les modes de transport sans favorisation dans le but d’une optimisation du service. Placés dans ce cadre, le but de cette thèse est de mettre en œuvre un système de gestion de véhicules partagés qui recouvre tous les services de transports existants tel que le transport public, le covoiturage, les véhicules en libre service et qui capable de satisfaire les demandes des utilisateurs en leur fournissant des itinéraires co-modaux optimisés en terme de temps, coût et émission des gaz à effet de serre tout en respectant leurs préférences et priorités. En recevant plusieurs requêtes simultanées en un court laps de temps, le système doit être capable à la fois de décomposer les solutions en tronçons que nous appelons Routes, en respectant toutes les similarités entre les différentes demandes et de regrouper les informations de manière cohérente pour déterminer les combinaisons de Routes possibles. Vu l’aspect dynamique et distribué du problème, une stratégie de résolution efficace mettant à profit une mixture de concepts ; à savoir les systèmes multi-agents et l’optimisation a été mise en place. Les résultats expérimentaux présentés dans cette thèse justifient l’importance de la co-modalité et la nécessité de mettre à profit la complémentarité entre les véhicules partagés et les autres moyens de transport à travers un système intelligent et global / Nowadays, the protection of the environment through the reduction of greenhouse gases is becoming more and more important. In order to resolve environmental problems, a multimodal policy is firstly adopted in order to encourage the use of public transport. Since 2006, a new notion: the co-modality is introduced and it consists on developing infrastructures and taking measures and actions that will ensure optimum combination of individual and public transport modes. In this context, the purpose of this thesis is to implement co-modal transport system that covers all the existing transport services such as the public transport, the carpooling or the free use vehicles (bikes, cars). In order to satisfy the user’s requests, the system offers optimized co-modal itineraries in terms of three criteria: total time, total cost and greenhouse gases emission taking into account their preferences and constraints. In a short time interval, many transport users can formulate simultaneously a set of requests. So the system should find feasible decompositions in terms of independent sub-itineraries called Routes recognizing similarities and recognize the different possibilities of Routes Combinations to compose each itinerary demand. Considering the dynamic and distributed aspect of the problem, an effective strategy combining different concepts like multi-agent system and optimization methods is applied. The experimental results presented in this thesis justify the importance of co-modality and the necessity of taking advantage of the complementarity between the shared vehicles and other means of transportation through an intelligent and global system

Les crises projettent la plupart du temps le décideur sur une durée plus ou moins longue dans l’urgence de la décision, avec l’obligation de minimiser les conséquences possibles sur les enjeux. Une équipe de gestion de crise est organisée en cellule et a pour objectif de construire des stratégies de réponse concertées et appropriées. Or, il s’avère que certaines des compétences nécessaires ne peuvent être acquises que par expérience. Ce travail s’attache ainsi à améliorer les processus de formation des décisionnaires en définissant, suivant quatre étapes, un environnement semi-virtuel de formation à la gestion stratégique de crise. Une phase de conception sert tout d’abord de point de départ au cahier des charges d’une implantation physique, d’une ingénierie système et d’une ingénierie pédagogique dédiées. Puis, une étape de modélisation d’un exercice de gestion de crise structure une méthodologie visant à définir les objectifs pédagogiques retenus, et propose une méthode appliquée de génération semi-automatique d’un scénario didactique. Une attention particulière est notamment portée sur l’élaboration d’une typologie d’évènements et d’éléments logiciels permettant la simulation multi-agents de crises virtualisées. Enfin, une méthodologie d’évaluation des participants est proposée dans le but d’enrichir la phase classique de débriefing. Seize indicateurs sont définis et permettent en particulier de construire des arbres de compétences. Une phase de validation porte sur trois de ces quatre axes méthodologiques, et il est montré que les premiers résultats obtenus tendent à valider les spécifications retenues pour l’environnement semi-virtuel de formation développé. / Currently, actors who deal with crisis situations have to make decision under stress and to act in emergency for mitigating the consequences or avoiding the impacts on critical stakes. To achieve this common goal efficiently, these actors must constitute a crisis cell and collaborate in a coordinated way. But crisis management requires skills which depend mainly on experience. That is why, this work aims to propose a set of methods in order to characterize training decision makers. In order to develop a semi-virtual training environment for strategic crisis management, four axes are studied. The first one focuses on a design pattern – based on chronological, systemic and functional analyzes – and leads to the specification of a real generic training platform. The second one defines a methodology for the semi-automatic generation of dynamic crisis scenarios (models, databases, etc.). The third one deals with a simulation model (based on a multi-agent system), and especially a dedicated typology for required events: the phenomena (reactive agents), the operational and tactical actors (archetypical agents), and the pedagogical events (action of trainers). The last one contributes to facilitate the exercises animation and the debriefings management, thanks to three methods of participant assessment. Sixteen indicators are defined and used, in particular, to build capability trees. Finally, three of these four topics have been validated and the first results seem to fit with the aim of the semi-virtual training environment developed.

In preparation for the influx of renewable energy sources that will be added to the electrical system, flexible and adaptable control schemes are necessary to accommodate the changing infrastructure. Microgrids have been gaining much attention as the main solution to the challenges of distributed and intermittent generation, but due to their low inertia, they need fast-acting control systems in order to maintain stability. Multi-Agent Systems have been proposed as dynamic control and communication frameworks. Decentralized arrangements of agents can provide resiliency and the much-desired “plug and play” behavior. This thesis describes a control system that implements droop control and the diffusion communication scheme without the need of a centralized controller to coordinate the Microgrid agents to maintain the frequency and stable operating conditions of the system. Moreover, the inter-agent communication is unaffected by changing network configurations and can achieve optimal economic dispatch through distributed optimization.

The aim of this work is to design and implement a graphic development environment of agent language ALLL. Language ALLL going to be described in details, such as the ANTLR framework for generating language recognition tools. Theoretical basis of multi-agent systems, together with the features of the selected platform, will be discussed as well. Description of the implementation is followed by the presentation of testing. Closure deals with the discussion of the achieved results.