No description available.

Le développement rapide des technologies de l’information dans l’usine du futur nécessite de repenser l’organisation des systèmes de production. Si l’importance des opérateurs est bien reconnue dans l’industrie 4.0, les facteurs humains restent cependant insuffisamment pris en considération dans les méthodes d’organisation. La simulation est parmi les méthodes largement utilisées pour étudier les systèmes de production et évaluer leurs performances. Toutefois, les approches de simulation existantes et les logiciels disponibles sont centrés sur les dimensions techniques de ces systèmes (machines, transport, règles de priorité, etc.). Malheureusement, les facteurs humains, particulièrement la fatigue des opérateurs, semble être très insuffisamment pris en compte dans les modèles de simulation. Dans ce contexte, la présente thèse vise à étudier dans quelle mesure la fatigue pourrait être intégrée dans les modèles de simulation des ateliers de production. Un cadre conceptuel combinant différents paradigmes de modélisation est ainsi proposé pour aider à concevoir de tels modèles. Le paradigme de simulation à événements discrets est utilisé pour décrire la dynamique de fonctionnement des ateliers. Le paradigme d’agent intelligent est utilisé pour modéliser les opérateurs et intégrer leur comportement de fatigue que nous avons modélisé en utilisant la simulation continue. Nous avons également utilisé la logique floue pour caractériser les facteurs de pénibilité, connus de façon imprécise, et leur impact sur l’évolution de la fatigue. Nous avons montré comment le cadre conceptuel proposé peut être mis en œuvre de façon assez générique avec le logiciel Anylogic. L’approche proposée a ensuite été utilisée pour aborder deux différents problèmes de production: le premier concerne l’affectation dynamique des opérateurs sur les machines et le deuxième est relatif à l’agencement de machines lors de la phase de conception des ateliers. Ceci nous a permis d’illustrer l’utilité de l’approche propose et montrer sa pertinence. L’analyse des résultats de simulation permet d’apporter des connaissances à la fois sur les performances des systèmes et sur les tendances d’évolution de la fatigue des opérateurs durant le travail. De tels résultats aident à réfléchir sur la façon dont laquelle nous pourrions améliorer les méthodes d’organisation et de gestion des ateliers pour contribuer à l’amélioration de leurs performances et au bien-être de leurs opérateurs. / The quick development of information technology in the factory of the future requires rethinking about the organization of production systems. Although the importance of the workers in the industry 4.0, human factors are still insufficiently taken into consideration in the organizational methods. Simulation is among the methods widely used to study production systems and evaluate their performances. However, the existing simulation approaches and the available softwares mainly focus on technical dimensions of these systems (machines, transport, priority rules, etc.). Unfortunately, human factors, particularly workers’ fatigue, seem to be very insufficiently taken into account in the simulation models. In this context, this thesis aims to study how the workers’ fatigue could be integrated into the simulation models of workshops. A framework combining different modelling paradigms is proposed to help in designing such models. Discrete event simulation is used to describe the dynamic of the working process in workshops. The paradigm of intelligent agent is used to model operators and integrate their behavior of fatigue, which has been modeled using continuous simulation paradigms. We have also used fuzzy logic in order to characterize the arduousness’s factors, known imprecisely, and impacts on the evolution of the workers’ fatigue. We have shown how the proposed framework can be implemented can be implemented generically enough with the software ANYLOGIC. The proposed approach has been then used to address two different production problems: the first one concerns the dynamic assignment of workers to machines and the second is related to the machines layout in the design stage of the system. This illustrated the utility of the proposed approach and showed its relevance. The analysis of the simulation results yields some knowledge on both the performance of the systems and on trends of the evolution the operators’ fatigue during the work. Such results help to thank on how to improve the methods of organization and management of the workshops so to contribute to the improvement of their performances and the well-being of their operators.

Na última década diversos algoritmos baseados em busca foram desenvolvidos para a geração de níveis em diferentes tipos de jogos. O espaço de busca para geração de níveis geralmente possui restrições, uma vez que a mecânica de um jogo define regras de factibilidade para os níveis. Em alguns métodos, a avaliação de factibilidade requer uma simulação com um agente inteligente que controla o jogo. Esse processo de avaliação geralmente possui ruído, causado por componentes aleatórios no simulador ou na estratégia do agente. Diversos trabalhos têm utilizado simulação como forma de avaliação de conteúdo, no entanto, nenhum deles discutiu profundamente a presença de ruído neste tipo de abordagem. Assim, esse trabalho apresenta um algoritmo genético capaz de gerar níveis factíveis que são avaliados por um agente inteligente em uma simulação ruidosa. O algoritmo foi aplicado a jogos de quebra-cabeças baseados em física com a mecânica do Angry Birds. Uma representação dos níveis em forma de indivíduos é introduzida, a qual permite que o algoritmo genético os evolua com características diferenciadas. O ruído na função de aptidão é tratado por uma nova abordagem, baseada em uma sistema de cache, que auxilia o algoritmo genético a encontrar boas soluções candidatas. Três conjuntos de experimentos foram realizados para avaliar o algoritmo. O primeiro compara o método de cache proposto com outros métodos de redução de ruído da literatura. O segundo mede a expressividade do algoritmo genético considerando as características estruturais dos níveis gerados. O último avalia os níveis gerados considerando aspectos de design (como dificuldade, imersão e diversão), os quais são medidos por meio de questionários respondidos por jogadores humanos via Internet. Os resultados mostraram que o algoritmo genético foi capaz de gerar níveis distintos que são tão imersíveis quanto níveis produzidos manualmente. Além disso, a abordagem de cache lidou apropriadamente com o ruído nos cálculos de aptidão, permitindo uma correta evolução elitista. / In the last decade several search-based algorithms have been developed for generating levels in different types of games. The search space for level generation is typically constrained once the game mechanics define feasibility rules for the levels. In some methods, evaluating level feasibility requires a simulation with an intelligent agent which plays the game. This evaluation process usually has noise, caused by random components in the simulator or in the agent strategy. Several works have used a simulation for content evaluation, however, none of them have deeply discussed the presence of noise in this kind of approach. Thus, this paper presents a genetic algorithm capable of generating feasible levels that are evaluated by an intelligent agent in a noisy simulation. The algorithm was applied to physics-based puzzle games with the Angry Birds mechanics. A level representation in the form of individuals is introduced, which allows the genetic algorithm to evolve them with distinct characteristics. The fitness function noise is handled by a new approach, based on a cache system, which helps the genetic algorithm finding good candidate solutions. Three sets of experiments were conducted to evaluate the algorithm. The first one compares the proposed cache approach with other noise reduction methods of the literature. The second one measures the expressivity of the genetic algorithm considering the structural characteristics of the levels. The last one evaluates design aspects (such as difficulty, immersion and fun) of the generated levels using questionnaires answered by human players via Internet. Results showed the genetic algorithm was capable of generating distinct levels that are as immersive as levels manually designed. Moreover, the cache approach handled properly the noise in the fitness calculations, allowing a correct elitist evolution.

Na última década diversos algoritmos baseados em busca foram desenvolvidos para a geração de níveis em diferentes tipos de jogos. O espaço de busca para geração de níveis geralmente possui restrições, uma vez que a mecânica de um jogo define regras de factibilidade para os níveis. Em alguns métodos, a avaliação de factibilidade requer uma simulação com um agente inteligente que controla o jogo. Esse processo de avaliação geralmente possui ruído, causado por componentes aleatórios no simulador ou na estratégia do agente. Diversos trabalhos têm utilizado simulação como forma de avaliação de conteúdo, no entanto, nenhum deles discutiu profundamente a presença de ruído neste tipo de abordagem. Assim, esse trabalho apresenta um algoritmo genético capaz de gerar níveis factíveis que são avaliados por um agente inteligente em uma simulação ruidosa. O algoritmo foi aplicado a jogos de quebra-cabeças baseados em física com a mecânica do Angry Birds. Uma representação dos níveis em forma de indivíduos é introduzida, a qual permite que o algoritmo genético os evolua com características diferenciadas. O ruído na função de aptidão é tratado por uma nova abordagem, baseada em uma sistema de cache, que auxilia o algoritmo genético a encontrar boas soluções candidatas. Três conjuntos de experimentos foram realizados para avaliar o algoritmo. O primeiro compara o método de cache proposto com outros métodos de redução de ruído da literatura. O segundo mede a expressividade do algoritmo genético considerando as características estruturais dos níveis gerados. O último avalia os níveis gerados considerando aspectos de design (como dificuldade, imersão e diversão), os quais são medidos por meio de questionários respondidos por jogadores humanos via Internet. Os resultados mostraram que o algoritmo genético foi capaz de gerar níveis distintos que são tão imersíveis quanto níveis produzidos manualmente. Além disso, a abordagem de cache lidou apropriadamente com o ruído nos cálculos de aptidão, permitindo uma correta evolução elitista. / In the last decade several search-based algorithms have been developed for generating levels in different types of games. The search space for level generation is typically constrained once the game mechanics define feasibility rules for the levels. In some methods, evaluating level feasibility requires a simulation with an intelligent agent which plays the game. This evaluation process usually has noise, caused by random components in the simulator or in the agent strategy. Several works have used a simulation for content evaluation, however, none of them have deeply discussed the presence of noise in this kind of approach. Thus, this paper presents a genetic algorithm capable of generating feasible levels that are evaluated by an intelligent agent in a noisy simulation. The algorithm was applied to physics-based puzzle games with the Angry Birds mechanics. A level representation in the form of individuals is introduced, which allows the genetic algorithm to evolve them with distinct characteristics. The fitness function noise is handled by a new approach, based on a cache system, which helps the genetic algorithm finding good candidate solutions. Three sets of experiments were conducted to evaluate the algorithm. The first one compares the proposed cache approach with other noise reduction methods of the literature. The second one measures the expressivity of the genetic algorithm considering the structural characteristics of the levels. The last one evaluates design aspects (such as difficulty, immersion and fun) of the generated levels using questionnaires answered by human players via Internet. Results showed the genetic algorithm was capable of generating distinct levels that are as immersive as levels manually designed. Moreover, the cache approach handled properly the noise in the fitness calculations, allowing a correct elitist evolution.

This thesis focuses on analysis, definition and description of mobile personal assistants as a phenomenon emerging in past few years. Mobile personal assistants are first mentioned in the context of computational linguistics and information needs, which is one of the motivations to use them. Main interest of this thesis is an introduction of the core technologies for the natural language communication between the assistant and its user, followed by an introduction of host environments and possible usage. The thesis also presents the limitations and risks resulting from using them, which are in some ways affecting their usability. Beside the analysis the main focus is on the design and implementation of the natural language understanding (NLU) system, which can be used in particular personal assistant application. This system is implemented as a web service and consists of an annotation scheme with a set of components. The results show that the system architecture and tools used are suitable solution for the construction of a basic NLU system, which has been created and which is in the compliance with the requested parameters. It is still difficult task to achieve high precision, which depends on many factors including the amount of training data, which was very small in this case. However, the resulting application is a solid starting point for its further development and extensions.

L’étude de la conflictualité armée dans les pays en développement et des effets des interventions extérieures visant à la circonscrire constitue un enjeu majeur et multidisciplinaire. La complexité des processus sociaux entrelacés dans de tels contextes génère des défis particuliers pour les approches de modélisation et simulation informatique. En effet la forme des conflits actuels, centrés autour des populations locales, a amené les forces de stabilisation à développer des actions dites d'influence, qui se donnent pour but de convaincre les locaux de la légitimité des opérations. Ce travail en retient trois (opérations psychologiques OMI/PSYOPS, opérations civilo-militaires et Key Leader Engagements) et propose une modélisation permettant de représenter la propagation de leurs effets au sein d'une population virtuelle réaliste. Cela nécessite une représentation détaillée des mécanismes psychologiques de persuasion et d’influence et des structures sociales considérées, et constitue donc un apport à l’analyse des processus de communication au sein de réseaux sociaux. On fait le choix d'une simulation sociale orientée agents permettant de représenter d'une part un échantillon composé uniquement d'individus (jusqu’à environ 10 000) dotés de mécanismes de traitement réalistes, et d'autre part la complexité des sphères de sociabilité collective en générant cette population sous forme d'un réseau multicouche. Le modèle conceptuel ainsi conçu permet d’intégrer pour chaque étape des critères pertinents pour la simulation des actions, mais aussi, eut égard à la nature même de celles-ci et de leurs enjeux, d’éclairer certains mécanismes sociaux caractéristiques d’un conflit armé / The study, analysis and understanding of armed violence phenomenons in developing countries and of the effects of international military interventions aimed at resolving them is a crucial contemporary issue. These situations coincidentally present, considering the plethora and complexity of the implicated and intertwined social processes, a challenge for social computing, modeling and simulation. A challenge but also an opportunity, as the evolution of the forms of conflict, today centered on the local populations, has prompted the armies tasked with implementing stabilization missions to develop influence actions. Such operations, overall concerned with persuading the locals of the legitimacy of the operations, allow a more comprehensive approach to conflict resolution, beyond the simple use of force. Modeling some of these specific actions (PSYOPS, CIMIC, and Key Leader Engagement) is a credible project and a contribution to analysis of communication and persuasion processes in social networks by taking into account detailed and specific social and cultural factors. This research thus presents a conceptual model allowing simulation of the effects of these specific actions of influence in a realistic civilian population. We chose an agent-based approach as these lend particularly well with this type of research, allowing us to generate a group of up to 10,000 agents, composed solely of individuals for a detailed cognitive treatment, and structured as a multilayer network for representing complex sociality. Given the nature of such actions and their context of application, such a model also highlights some social mechanisms typical of armed conflict situations

La maladie d'Alzheimer (MA) est une maladie cérébrale dégénérative qui entraîne une perte progressive de la mémoire, un déclin cognitif et une détérioration graduelle de la capacité d'une personne à faire face à la complexité et à l'exigence des tâches quotidiennes nécessaires pour vivre en autonomie dans notre société actuelle. Les traitements pharmacologiques actuels peuvent ralentir le processus de dégradation attribué à la maladie, mais ces traitements peuvent également provoquer certains effets secondaires indésirables. L'un des traitements non pharmacologiques qui peut soulager efficacement les symptômes est la thérapie assistée par l'animal (T.A.A.). Mais en raison de certaines limitations telles que le prix des animaux et des problèmes d'hygiène, des animaux virtuels sont utilisés dans ce domaine. Cependant, les animaux virtuels animés, la qualité d'image approximative et le mode d'interaction unidirectionnel des animaux qui attendent passivement les instructions de l’utilisateur, peuvent difficilement stimuler le retour émotionnel entre l'utilisateur et les animaux virtuels, ce qui affaiblit considérablement l'effet thérapeutique. Cette étude vise à explorer l'efficacité de l'utilisation d'animaux virtuels à la place d’animaux vivants et leur impact sur la réduction des émotions négatives chez le patient. Cet objectif a été gardé à l'esprit lors de la conception du projet Zoo Therapy, qui présente un environnement immersif d'animaux virtuels en 3D, où l'impact sur l'émotion du patient est mesuré en temps réel par électroencéphalographie (EEG). Les objets statiques et les animaux virtuels de Zoo Therapy sont tous présentés à l'aide de modèles 3D réels. Les mouvements des animaux, les sons et les systèmes de repérage spécialement développés prennent en charge le comportement interactif simulé des animaux virtuels. De plus, pour que l'expérience d'interaction de l'utilisateur soit plus réelle, Zoo Therapy propose un mécanisme de communication novateur qui met en œuvre une interaction bidirectionnelle homme-machine soutenue par 3 méthodes d'interaction : le menu sur les panneaux, les instructions vocales et le Neurofeedback. La manière la plus directe d'interagir avec l'environnement de réalité virtuelle (RV) est le menu sur les panneaux, c'est-à-dire une interaction en cliquant sur les boutons des panneaux par le contrôleur de RV. Cependant, il était difficile pour certains utilisateurs ayant la MA d'utiliser le contrôleur de RV. Pour accommoder ceux qui ne sont pas bien adaptés ou compatibles avec le contrôleur de RV, un système d'instructions vocales peut être utilisé comme interface. Ce système a été reçu positivement par les 5 participants qui l'ont essayé. Même si l'utilisateur choisit de ne pas interagir activement avec l'animal virtuel dans les deux méthodes ci-dessus, le système de Neurofeedback guidera l'animal pour qu'il interagisse activement avec l'utilisateur en fonction des émotions de ce dernier. Le système de Neurofeedback classique utilise un système de règles pour donner des instructions. Les limites de cette méthode sont la rigidité et l'impossibilité de prendre en compte la relation entre les différentes émotions du participant. Pour résoudre ces problèmes, ce mémoire présente une méthode basée sur l'apprentissage par renforcement (AR) qui donne des instructions à différentes personnes en fonction des différentes émotions. Dans l'expérience de simulation des données émotionnelles synthétiques de la MD, la méthode basée sur l’AR est plus sensible aux changements émotionnels que la méthode basée sur les règles et peut apprendre automatiquement des règles potentielles pour maximiser les émotions positives de l'utilisateur. En raison de l'épidémie de Covid-19, nous n'avons pas été en mesure de mener des expériences à grande échelle. Cependant, un projet de suivi a combiné la thérapie de RV Zoo avec la reconnaissance des gestes et a prouvé son efficacité en évaluant les valeurs d'émotion EEG des participants. / Alzheimer’s disease (AD) is a degenerative brain disease that causes progressive memory loss, cognitive decline, and gradually impairs one’s ability to cope with the complexity and requirement of the daily routine tasks necessary to live in autonomy in our current society. Actual pharmacological treatments can slow down the degradation process attributed to the disease, but such treatments may also cause some undesirable side effects. One of the non-pharmacological treatments that can effectively relieve symptoms is animal-assisted treatment (AAT). But due to some limitations such as animal cost and hygiene issues, virtual animals are used in this field. However, the animated virtual animals, the rough picture quality presentation, and the one-direction interaction mode of animals passively waiting for the user's instructions can hardly stimulate the emotional feedback background between the user and the virtual animals, which greatly weakens the therapeutic effect. This study aims to explore the effectiveness of using virtual animals in place of their living counterpart and their impact on the reduction of negative emotions in the patient. This approach has been implemented in the Zoo Therapy project, which presents an immersive 3D virtual reality animal environment, where the impact on the patient’s emotion is measured in real-time by using electroencephalography (EEG). The static objects and virtual animals in Zoo Therapy are all presented using real 3D models. The specially developed animal movements, sounds, and pathfinding systems support the simulated interactive behavior of virtual animals. In addition, for the user's interaction experience to be more real, the innovation of this approach is also in its communication mechanism as it implements a bidirectional human-computer interaction supported by 3 interaction methods: Menu panel, Speech instruction, and Neurofeedback. The most straightforward way to interact with the VR environment is through Menu panel, i.e., interaction by clicking buttons on panels by the VR controller. However, it was difficult for some AD users to use the VR controller. To accommodate those who are not well suited or compatible with VR controllers, a speech instruction system can be used as an interface, which was received positively by the 5 participants who tried it. Even if the user chooses not to actively interact with the virtual animal in the above two methods, the Neurofeedback system will guide the animal to actively interact with the user according to the user's emotions. The mainstream Neurofeedback system has been using artificial rules to give instructions. The limitation of this method is inflexibility and cannot take into account the relationship between the various emotions of the participant. To solve these problems, this thesis presents a reinforcement learning (RL)-based method that gives instructions to different people based on multiple emotions accordingly. In the synthetic AD emotional data simulation experiment, the RL-based method is more sensitive to emotional changes than the rule-based method and can automatically learn potential rules to maximize the user's positive emotions. Due to the Covid-19 epidemic, we were unable to conduct large-scale experiments. However, a follow-up project combined VR Zoo Therapy with gesture recognition and proved the effectiveness by evaluating participant's EEG emotion values.