Dissertations / Theses on the topic 'Video sanatı'

Cette thèse propose des modèles, méthodes et outils destinés aux game designers de jeux thérapeutiques. Le problème de conception le plus fondamental des jeux thérapeutiques est le gameplay, c'est-à-dire des objectifs de jeu et des actions que le joueur doit effectuer pour atteindre ces objectifs. Dans un jeu thérapeutique, le gameplay doit à la fois produire l'effet thérapeutique et motiver le patient à suivre son protocole. Les problèmes sous-jacents de celui-ci sont l'évaluation médicale et ludique du jeu, et l'échange de connaissances entre game designers et experts santé. Nous proposons une méthode de game design de jeu thérapeutique allant de la définition du problème à l'évaluation. Cette méthode intègre les autres solutions que nous proposons, notamment le modèle player/game/therapy et une méthode de formalisation du gameplay<br>This PhD thesis explores the field of therapeutic games in order to propose methods and tools for the game designer of such games. The most fundamental design problem of therapeutic games is the gameplay, ie. the game objectives and the actions the player does to address the objectives. In therapeutic game, the gameplay must, at the same time, provide the therapeutic effects and motivate the patient to follow his protocol. The sub-problems of this are 1. the two-fold evaluation (medical and motivation), 2. the exchange of knowledge between game designers and health experts. We propose a therapeutic game design method which begins with the problem definition and ends with the two-fold evaluation. This method integrates the other solutions we propose, particularly the player / game / therapy model and a method to formalize the gameplay

Cette thèse propose des modèles, méthodes et outils destinés aux game designers de jeux thérapeutiques. Le problème de conception le plus fondamental des jeux thérapeutiques est le gameplay, c'est-à-dire des objectifs de jeu et des actions que le joueur doit effectuer pour atteindre ces objectifs. Dans un jeu thérapeutique, le gameplay doit à la fois produire l'effet thérapeutique et motiver le patient à suivre son protocole. Les problèmes sous-jacents de celui-ci sont l'évaluation médicale et ludique du jeu, et l'échange de connaissances entre game designers et experts santé. Nous proposons une méthode de game design de jeu thérapeutique allant de la définition du problème à l'évaluation. Cette méthode intègre les autres solutions que nous proposons, notamment le modèle player/game/therapy et une méthode de formalisation du gameplay<br>This PhD thesis explores the field of therapeutic games in order to propose methods and tools for the game designer of such games. The most fundamental design problem of therapeutic games is the gameplay, ie. the game objectives and the actions the player does to address the objectives. In therapeutic game, the gameplay must, at the same time, provide the therapeutic effects and motivate the patient to follow his protocol. The sub-problems of this are 1. the two-fold evaluation (medical and motivation), 2. the exchange of knowledge between game designers and health experts. We propose a therapeutic game design method which begins with the problem definition and ends with the two-fold evaluation. This method integrates the other solutions we propose, particularly the player / game / therapy model and a method to formalize the gameplay

L’objectif de cette thèse est d’augmenter le confort visuel de l’ophtalmologue au cours d’examens ou de chirurgies de la rétine. Pour ce faire, nous décidons d’augmenter artificiellement et en temps réel le champ visuel dans le cas de vidéos d’exploration acquises à la lampe à fente et à l’endoscope oculaire. L’augmentation passe par la mise en place de cartes dynamiques en 3D de la rétine. A notre connaissance, il n’existe pas de telle méthode dans la littérature. Notre solution passe par l’étude de différentes méthodes d’estimation de déplacements entre deux images. Nous les regroupons en méthodes « classiques » d’une part, comptant notamment des méthodes basées sur les algorithmes SIFT ou SURF. D’autre part, nous rassemblons des méthodes utilisant l’apprentissage profond (ou méthodes « CNN » pour Convolutional Neural Network). Certaines de ces méthodes, comme celles utilisant les réseaux FlowNet, nécessitent une annotation vérité terrain des déplacements entre images. Comme de telles bases de données n’existent pas en ophtalmologie, des bases généralistes ont été utilisées. De plus, nous avons construit deux bases de données de déplacements artificiels ayant pour fond des images de rétines. Enfin, pour contourner le problème d’annotation, une approche utilisant l’apprentissage auto-supervisé a été étudiée. Après comparaisons des résultats, il apparaît que les méthodes « CNN » surpassent les méthodes classiques. De plus, seule une supervision forte de l’apprentissage permet des résultats satisfaisants. A l’avenir, nous espérons que ces travaux pourront permettre aux chirurgiens d’être plus confiants et efficaces dans des environnements où il peut être compliqué de se repérer<br>The main objective of this thesis is toincrease the visual comfort of theophthalmologists during examinations orsurgeries. To do so, we decided toartificially increase in real time the field ofview in videos of retinal exploration. Thetools used for the acquisition of thesevideos are the slit lamp and theendoscope. The increase of the field ofview passes by the establishment ofdynamic 3D maps of the retina.To our knowledge, there is still no suchmethod in the state of the art.In order to implement our solution, westudied the different methods of motionestimations between two images. Wegrouped them into "classical" methods, onthe one hand, including methods based onSIFT or SURF algorithms. On the otherhand, we grouped deep learning methods(or "CNN" methods for ConvolutionalNeural Network).Some of these methods, such as thoseusing FlowNet networks, required groundtruth annotation of movement betweenimages.Since such bases are very difficult to set upin the medical field and do not exist inophthalmology, general databases havebeen used. In addition, we built twodatabases of artificial displacements whichbackgrounds are composed of images ofretinas. Finally, to get around this problemof annotations, a self-supervised deeplearning approach was studied.After comparing the results, it appears thatmethods using convolutional neuralnetworks outperform conventional methodsfor estimating movements in retinal videos.Moreover, only a strong supervision allowsacceptable results. In the future, we hopethat this work will enable surgeons to bemore confident and effective inenvironments where it is sometimesdifficult to find their bearings

Dissertação (mestrado) - Universidade Federal de Santa Catarina, Centro Tecnologico<br>Made available in DSpace on 2016-01-08T19:10:29Z (GMT). No. of bitstreams: 1 96305.pdf: 1716825 bytes, checksum: 416ccaa015141d76995a4baebe19d76d (MD5) Previous issue date: 1994<br>Este trabalho de pesquisa procura desenvolver uma avaliação do setor de Plástico Reforçado com Fibra de Vidro no Estado de Santa Catarina. O objetivo principal é o conhecimento da estrutura industrial do setor e a análise dos seus principais problemas, definidos a partir da constatação dos seus pontos fortes e fracos. Utilizou-se a metodologia de Porter como um instrumento analítico. O modelo apresenta um sistema geral para a análise da estrutura de um setor e dos concorrentes que dele participam. As informações da estrutura da indústria do setor de PRFV descrevem os principais ítens que colaboram para a maior intensidade das forças atuantes sobre as empresas deste setor, e permitem a análise do tipo de meio industrial no qual estas empresas estão inseridas. A divisão do setor em grupos estratégicos através do método de Clustering, possibilta às empresas a ele pertencentes uma análise do seu posicionamento em relação aos seus concorrentes. Permitindo assim, através destes conhecimentos a formulação de ações estratégicas específicas de acordo com a problemática de cada grupo estratégico.

Les infections nosocomiales sont responsables de milliers de décès chaque année. Les soignants, les patients et l'environnement à l'hôpital peuvent être source de contamination. Les objets tels que les téléphones cellulaires, les stéthoscopes, les tensiomètres, les cravates, les blouses et les bagues sont utilisés par les soignants et peuvent être contaminés. Ils deviennent alors des vecteurs potentiels pouvant être responsables d'infections nosocomiales. Les mains des soignants peuvent aussi être un vecteur de la transmission d'agents pathogènes. Respecter l'ensemble des règles d'hygiènes au quotidien est indispensable mais peut être contraignant pour les soignants. Afin d'avoir une mesure plus précise de la désinfection des mains, un outil automatique de mesure appelé MédiHandTrace® (MHT) a été développé, et breveté. Il permet de tracer les soignants grâce à leurs sabots pucés. MHT montre des taux d'observance inférieurs à 50% et aussi que l'hygiène des mains est individuelle. Aussi, Nous avons voulu comprendre le raisonnement des soignants au regard de leurs pratiques d'hygiène. Grâce à la vidéo, nous avons mis en lumière des comportements singuliers. L'amélioration de l'hygiène des mains reste une priorité. En conséquence, nous avons introduit des outils couplés à MHT, envoyé des sms sur les téléphones des soignants donnant leurs performances individuelles. L'hygiène des mains est un geste simple, mais sa réalisation se fait dans des situations de soins souvent complexes. L'adhérence à l'hygiène reste multifactorielle nécessitant l'apport de nouveaux outils d'apprentissage et de communication afin de délivrer des messages simples et efficaces auprès des soignants<br>Nosocomial infections are responsible for thousands of deaths each year. Healthcare workers (HCW), patients and the hospital environment can be a source of contamination. Fomites such as cell phones, stethoscopes, tensiometers, ties, gowns and rings are used by HCW and may be contaminated. They become potential vectors that can be responsible for nosocomial infections. The HCWs hands' can also be a vector for the transmission of pathogens. Respecting all the rules of hand hygiene in everyday life is essential but can be binding for the HCW. In order to have a more accurate measurement of hand disinfection, an automatic measuring tool called MédiHandTrace® (MHT) was developed and patented. It makes it possible to trace the HCWs with tags into their shoe hoofs. MHT shows compliance rates below 50% and also that hand hygiene is individual. Also, we wanted to understand the reasoning of HCW with regard to their hygiene practices. Through the video, we have highlighted some singular behaviors of HCWs. Improving hand hygiene remains a priority. As a result, we introduced tools coupled with MHT, sent sms to the phones of HCWs showing their individual performance. Hand hygiene is a simple gesture, but its realization takes place in often complex care situations. Adherence to hand hygiene remains multifactorial, requiring new learning and communication tools to deliver simple and effective messages to HCWs

La thèse de doctorat intitulée Le serious gaming, un outil de gouvernance contributive et participative du bien-être et de la santé. Le game design des jeux vidéo chez les 14-17 ans, une réalité contrastée est un travail qui s’inscrit dans le champ des Sciences de l’Information et de la Communication. Cette recherche interdisciplinaire s’attache à employer de nombreux concepts et théories rattachées au champ des games studies, des cultural studies, mais aussi à celui de la promotion de la santé en santé publique. Les médias en général et les jeux vidéo en particulier font d’ores et déjà l’objet de nombreux travaux à charge. Aussi, ces objets seront cette fois analysés à décharge. Il s’agit ici de comprendre de quelles manières ces technologies d’information et de communication peuvent finalement devenir des outils permettant de faire pencher la balance risque-bénéfice en faveur de celui du bien-être et de la santé de ses usager.es. L’étude de cas au cœur de cette recherche-action se concentre sur un objet dont l’utilisation chez une tranche d’âge est toujours assujettie aux polémiques institutionnelles et épistémologiques : les jeux vidéo chez les 14-17 ans.Le sujet sera ici traité en trois parties : une première partie qui démontre comment, au croisement de théories, concepts et modèles issus d’une grande variété de disciplines, la pratique et les usages des jeux-vidéo s’inscrit dans des contextes favorables du bien-être et de la santé ; une deuxième dans laquelle s’articule l’étude de cas dans une démarche en communication expérimentale ; La troisième partie qui, à la lecture des résultats obtenus et de leur applicabilité dans un contexte administratif et politique actuel, permet de dégager les éléments de réponse sur le sujet. A l’issu de la démonstration il apparaît effectivement que ce sujet, une fois écrémé des corrélations simplistes et des considérations culturelles, fait bien l’objet d’un traitement ne tenant pas compte des conclusions académiques portant sur l’empowerment que produit le game design en particulier et la pratique vidéoludique en général. Dès lors, si le serious gaming du game design des jeux vidéo se constitue comme un outil efficace lorsqu’il est employé dans une approche populationnelle, se pose finalement la question de son applicabilité et de ses effets sur dans d’autres contextes et/ou les autres médias digitaux ou traditionnels<br>The Doctorate thesis entitled 'Serious gaming, a tool of contributive governance and participant of well-being and health. Game design in video games for the 14 to 17 years old, a contrasted reality' is a work which comes within the scope of science of the information and communication study field. This interdisciplinary research makes sure to use many concepts and theories attached to the field of game studies and cultural studies but also to the field of health promotion and public health.The media in general and video games more particularly are already the object of several works incriminating it. Therefore, in this study, these objects will be analyzed from an exonerating point of view. The point here is to understand how these information and communication technologies can in the end become a tool allowing to tip the scale of risks and benefits in favor of the well-being and health of its users. The case study at the very heart of this study-action focuses on an object which for a certain group age is still under institutional and epistemological polemics: video games for the 14 to 17 years old.The topic will be treated here in three different parts : A first part which will demonstrate how, at the crossroad of theories, concepts and models from a great variety of disciplines, the use of video games inscribes in contexts in favor of well-being and health ; a second one in which the study is built around an experimental communication approach ; the third part which, after reading the final results and their capacity to be applied in the current administrative and political context, allows to uncover the elements of the answer about this topic.At the end of this walk through, it actually appears that this topic, once skimmed from the simplistic correlations and cultural considerations, is indeed the object of an a traitement which does not consider the academic conclusions about the empowerment that the game design in particular and the use of video games in general are creating. Subsequently, if the serious gaming of the game design in video games builds itself like and efficient tool when it is used in a populational approach, the question of its capacity to be applied and of its effects in other contexts and/or in other digital or traditional media can be asked

La compréhension des actions dans les vidéos est un élément crucial de la vision par ordinateur, avec des implications significatives dans divers domaines. À mesure que notre dépendance aux données visuelles augmente, comprendre et interpréter les actions humaines dans les vidéos devient essentiel pour faire progresser les technologies dans la surveillance, les soins de santé, les systèmes autonomes et l'interaction homme-machine. L'interprétation précise des actions dans les vidéos est fondamentale pour créer des systèmes intelligents capables de naviguer efficacement et de répondre aux complexités du monde réel. Dans ce contexte, les avancées dans la compréhension des actions repoussent les limites de la vision par ordinateur et jouent un rôle crucial dans la transformation des applications de pointe qui impactent notre quotidien. La vision par ordinateur a réalisé des progrès significatifs avec l'essor des méthodes d'apprentissage profond, telles que les réseaux de neurones convolutifs (CNN), repoussant les frontières de la vision par ordinateur et permettant à la communauté de progresser dans de nombreux domaines, notamment la segmentation d'images, la détection d'objets, la compréhension des scènes, et bien plus encore. Cependant, le traitement des vidéos reste limité par rapport aux images statiques. Dans cette thèse, nous nous concentrons sur la compréhension des actions, en la divisant en deux parties principales : la reconnaissance d'actions et la détection d'actions, ainsi que leur application dans le domaine médical pour l'analyse de l'autisme. Dans cette thèse, nous explorons les divers aspects et défis de la compréhension des vidéos, tant d'un point de vue général que spécifique à une application. Nous présentons ensuite nos contributions et solutions pour relever ces défis. De plus, nous introduisons le jeu de données ACTIVIS, conçu pour diagnostiquer l'autisme chez les jeunes enfants. Notre travail est divisé en deux parties principales : la modélisation générique et les modèles appliqués. Dans un premier temps, nous nous concentrons sur l'adaptation des modèles d'images pour les tâches de reconnaissance d'actions en incorporant la modélisation temporelle à l'aide de techniques de fine-tuning efficaces en paramètres (PEFT). Nous abordons également la détection et l'anticipation des actions en temps réel en proposant un nouveau modèle conjoint pour l'anticipation des actions et la détection d'actions en ligne dans des scénarios de la vie réelle. En outre, nous introduisons une nouvelle tâche appelée "interaction lâche" dans des situations dyadiques et ses applications dans l'analyse de l'autisme. Enfin, nous nous concentrons sur l'aspect appliqué de la compréhension des vidéos en proposant un modèle de reconnaissance d'actions pour les comportements répétitifs dans les vidéos d'individus autistes. Nous concluons en proposant une méthode faiblement supervisée pour estimer le score de gravité des enfants autistes dans des vidéos longues<br>Understanding actions in videos is a crucial element of computer vision with significant implications across various fields. As our dependence on visual data grows, comprehending and interpreting human actions in videos becomes essential for advancing technologies in surveillance, healthcare, autonomous systems, and human-computer interaction. The accurate interpretation of actions in videos is fundamental for creating intelligent systems that can effectively navigate and respond to the complexities of the real world. In this context, advances in action understanding push the boundaries of computer vision and play a crucial role in shaping the landscape of cutting-edge applications that impact our daily lives. Computer vision has made significant progress with the rise of deep learning methods such as convolutional neural networks (CNNs) pushing the boundaries of computer vision and enabling the computer vision community to advance in many domains, including image segmentation, object detection, scene understanding, and more. However, video processing remains limited compared to static images. In this thesis, we focus on action understanding, dividing it into two main parts: action recognition and action detection, and their application in the medical domain for autism analysis.In this thesis, we explore the various aspects and challenges of video understanding from a general and an application-specific perspective. We then present our contributions and solutions to address these challenges. In addition, we introduce the ACTIVIS dataset, designed to diagnose autism in young children. Our work is divided into two main parts: generic modeling and applied models. Initially, we focus on adapting image models for action recognition tasks by incorporating temporal modeling using parameter-efficient fine-tuning (PEFT) techniques. We also address real-time action detection and anticipation by proposing a new joint model for action anticipation and online action detection in real-life scenarios. Furthermore, we introduce a new task called 'loose-interaction' in dyadic situations and its applications in autism analysis. Finally, we concentrate on the applied aspect of video understanding by proposing an action recognition model for repetitive behaviors in videos of autistic individuals. We conclude by proposing a weakly-supervised method to estimate the severity score of autistic children in long videos

Is essential that the society of Santa Maria and region has knowledge and recognizes the MHASM and its function, as well as their actions and their services, and how to enjoy these, and for this there must be the diffusion of the institution. From this it was questioned: "Can some kind of audiovisual diffusion be develop, as means of communication with society, to promote the MHASM, its actions and its services?". In order to answer this and as a mean of spreading the work of the MHASM, focusing on audiovisual diffusion, this study sought to achieve the following objectives: achieve audiovisual diffusion of MHASM by developing an institutional video that identifies and characterizes the Archive and all that concerns it; conduct a study of corporate videos from state public archives and the Federal District Archive in order to obtain information for the institutional video production from MHASM; and demonstrate the importance of audiovisual diffusion to the Archive. Applied methodology was used with quantitative and qualitative approach, being also exploratory, descriptive and bibliographic, using forms as data collection tools. To support the research, concepts, authors and references were used that were related to patrimony, cultural heritage, archive, public archive, historical archive, diffusion, archival diffusion, audiovisual, and institutional video. Taking into account the literature used, the context of the research universe and the studies and actions taken, the objectives listed above were achieved. Thus, it is displayed here all the theoretical and technical process employed for the institutional video production of the MHASM leading to the audiovisual diffusion of the institution.<br>É essencial que a sociedade de Santa Maria e região tenha ciência e reconheça o AHMSM, sua função, ações e serviços, e como gozar destes, e para isso é preciso que haja a difusão da instituição. A partir disto questionou-se: é possível desenvolver algum recurso de difusão audiovisual, como meio de comunicação com a sociedade, para divulgar o AHMSM, suas ações e serviços? . Com a intenção de responder a isto, tendo por tema a difusão do AHMSM, com enfoque na difusão audiovisual, buscou-se atingir os seguintes objetivos: realizar a difusão audiovisual do AHMSM, por meio do desenvolvimento de vídeo institucional, identificando e caracterizando o Arquivo e tudo que lhe diz respeito; realizar estudo dos vídeos institucionais dos arquivos públicos estaduais e do Distrito Federal, a fim de se obter subsídio para a produção de vídeo institucional do AHMSM; e demonstrar a importância da difusão audiovisual para o Arquivo. Utilizou-se metodologia de natureza aplicada, com abordagem quanti-qualitativa, sendo também exploratória, descritiva e bibliográfica, fazendo-se uso de formulários como instrumentos de coleta de dados. Para subsidiar a pesquisa, abordaram-se conceitos, autores e referenciais relacionados a patrimônio, patrimônio cultural, arquivo, arquivo público, arquivo histórico, difusão, difusão arquivística, audiovisual, vídeo institucional. Levando-se em consideração a literatura abordada, a contextualização do universo da pesquisa e os estudos e ações realizadas, teve-se como resultados obtidos o alcance dos objetivos acima apresentados. Deste modo, é apresentado todo o processo teórico e técnico empregado para a produção do vídeo institucional do AHMSM e, consequentemente, a difusão audiovisual da instituição.

La coproduction de service est un aspect essentiel de la production de service, plus encore avec l’avènement de la customisation de masse et de la notion de client/employé partiel. Les scripts, et plus précisément les scripts de services, sont l’un des outils qui permettent aux organisations d’influer sur la coproduction de services. Un des pans des recherches menées sur la coproduction de service se penche sur la formation du client afin que l’organisation sache ce qu’elle peut attendre de lui et réciproquement. Ces recherches sont notamment menées dans le secteur de la Santé à propos de la coproduction de soin. Parmi les outils à disposition des organisations se trouve les serious games, des jeux-vidéo à but informatif et pédagogique. Nos travaux cherchent à savoir selon quelles propriétés et dans quels contextes les serious games peuvent être des véhicules pour les scripts de soins à destination des patients, en amont de leur prise en charge comme lors de celle-ci.Pour ce faire, nous proposons une grille d’analyse basée sur les scripts pour montrer comment les serious games peuvent traduire et encapsuler des objectifs managériaux, en nous appuyant sur l’étude et l’analyse de 4 cas représentant chacun une facette de la coproduction de soins<br>Service co-production is an essential aspect of service production theories, even more with the advent of mass customization and the notion of customer as a partial employee. One of the tools that allows organizations to influence the co-production of services are the scripts and more specifically the service’s scripts. Some of the researches carried out in the field of co-production of service focus on the client’s training so that the organization knows what it can expect from him and vice versa. This research is particularly carried out in the health sector and the co-production of care. Among the tools available to the organizations, we focus on the serious games, which are video games for informative and pedagogical purposes. Our work questions the properties and the contexts in which serious games can be vehicles for the scripts of care to the patients, before and during their nursing and treatment.To do so, we offer a comprehensive script-based analysis grid to show how serious games can translate and encapsulate managerial goals based on the study and analysis of 4 cases each representing a specific aspect of co-production of care

L’amélioration du raisonnement clinique (RC) est un enjeu essentiel pour la Médecine de demain car il est établi que son utilisation imparfaite conduit à des résultats de soins insuffisants. Le RC est un processus cognitif complexe. Cette activité intellectuelle synthétise l’information obtenue à partir de la situation clinique et l’utilise pour faire une analyse diagnostique et prendre une décision de prise en charge du patient en intégrant les connaissances et expériences antérieures. La formation à cette compétence est donc essentielle. Pour améliorer le raisonnement, une connaissance des mécanismes qui le constituent est nécessaire et une revue de ces mécanismes constitue la partie initiale de cette thèse.La formation des professionnels de santé par la simulation se généralise avec pour objectif « jamais la première fois sur le patient ». En plein essor, le jeu sérieux (JS) représente un outil pédagogique intéressant. Une revue de la littérature sur l’efficacité des JS et plus particulièrement dans le cadre du RC est également incluse dans la partie initiale de cette thèse. Ainsi, les JS sont efficaces et peuvent, entre autres, cibler certaines compétences dont le RC. Cependant, la plupart des études sur le RC dans le cadre des JS, restent subjectives avec des évaluations qualitatives ou des autoévaluations des apprenants ou concernent uniquement le résultat (prise de décision). Par conséquent, la valeur éducative et les modalités des JS dans la formation du RC restent à approfondir.Le JS LabForGames Warning a été développé dans le centre de simulation LabForSIMS pour les étudiants infirmiers et cible la détection de l’aggravation d’un patient et la communication. Cette thèse a pour objectif de tester un mode d’apprentissage utilisant la simulation par les JS afin d’améliorer le RC chez les professionnels de santé.Une 1ère étude a évalué la validité du JS LabForGames Warning selon le cadre théorique proposé par Messick. Elle a démontré que les scores et le temps de jeu ne pouvaient pas différencier le niveau des compétences cliniques des infirmiers.Cependant, les preuves de validité étaient obtenues pour le contenu, le processus de réponse et la structure interne. Même si cette version du jeu ne peut donc pas être utilisée pour une évaluation sommative des étudiants, notre étude montre que ce JS est bien accepté par les étudiants et qu’il peut être utilisé pour la formation au sein d’un programme éducatif.Une seconde étude a évalué l’efficacité de 2 modalités pédagogiques sur l’apprentissage du RC à la détection de l’aggravation clinique d’un patient en comparant un groupe d’étudiants infirmiers formé par simulation avec LabForGames Warning par rapport à un groupe formé par un enseignement traditionnel. Le RC a été évalué par les tests de concordance de script immédiatement et 1 mois après. Cette étude multicentrique randomisée a inclus 146 étudiants infirmiers volontaires. Aucune différence significative n’a été observée sur le RC entre la formation par la simulation avec JS et l’enseignement traditionnel. Cependant, la satisfaction et la motivation étaient meilleures avec l’enseignement par simulation.En conclusion, nous avons tout d’abord confirmé la validité du JS LabForGames Warning en tant qu’outil pédagogique à visée formative et non sommative. Puis, bien qu’aucune différence d’apprentissage du RC n’ait été observée entre la formation par la simulation avec JS et l’enseignement traditionnel, la satisfaction et la motivation étaient meilleures avec l’enseignement par simulation avec le jeu. Les études sont à poursuivre pour préciser les modalités et stratégies pédagogiques des JS dans la formation des professionnels de santé, comme par exemple la place du débriefing, le rôle de la motivation. En effet, en plein essor, les développements technologiques telle que l’intelligence artificielle vont transformer la formation au RC ainsi que les outils pédagogiques disponibles dans les années à venir<br>Improvement of clinical reasoning (CR) is a key issue for the future of medicine because it has been established that imperfect reasoning leads to insufficient care results. CR is a complex cognitive process which synthesizes information obtained from the clinical situation, then uses it to make a diagnostic analysis and take a decision on patient management by integrating previous knowledge and experience. Training for this skill is therefore essential. To improve reasoning, knowledge of the mechanisms which build it up is necessary and a review of these mechanisms constitutes the initial part of this thesis.Training of healthcare professionals through simulation is becoming widespread with the objective of "never the first time on a patient". In rapid expansion, the use of serious games (SG) represents an interesting pedagogical tool. A review of the literature on the effectiveness of SG and more particularly in the context of CR is also included in the initial part of this thesis. Thus, SG is effective and may, among other things, target certain skills, including CR. However, most studies dealing with CR by using SG include qualitative assessments or self-assessments of learners or focus only on the outcome (decision making). Therefore, the educational value and modalities of SG in the training of CR of health professionals remain to be further explored.The SG LabForGames Warning was developed in the LabForSIMS simulation center for nursing students and targets detection of patient deterioration and the ensuing communication. The objective of this thesis is to test a learning mode using SG simulation in order to improve CR in healthcare professionals.The first study evaluated the validity of the SG LabForGames Warning according to the Messick’s Framework. This study showed that scores and playing time could not differentiate the level of clinical skills of nurses. However, evidence of validity was obtained for content, response process and internal structure. Although this version of the game cannot therefore be used for summative evaluation of students, our study shows that this SG is well accepted by students and can be used for training within an educational program.A second study evaluated the effectiveness of 2 teaching modalities on learning CR for the detection of clinical patient deterioration by comparing a group of nursing students trained by simulation with LabForGames Warning compared to a group trained by traditional teaching. CR was assessed by script concordance tests immediately and 1 month later. This randomized multicenter study included 146 volunteer nursing students. No significant difference was observed in CR change between simulation training with SG and traditional teaching. However, satisfaction and motivation were better with simulation instruction.In conclusion, we have confirmed the validity of SG LabForGames Warning as an educational tool with formative and not summative aims. Then, although no difference in learning about CR was observed between simulation training with SG and traditional teaching, satisfaction and motivation were better with simulation teaching with the game. Further studies are needed to clarify the modalities and pedagogical strategies of SG in the training of healthcare professionals, such as the place of debriefing and the role of motivation. Moreover, technological developments such as artificial intelligence might transform CR training and the available pedagogical tools in the coming years

Bien que devenant un environnement de plus en plus riche technologiquement, la salle opératoire reste un endroit où la sécurité des patients n'est pas assurée à 100% comme le montre le nombre toujours conséquent d'erreurs chirurgicales. La nécessité de développer des systèmes intelligents au bloc opératoire apparait comme croissante. Un des éléments clés pour ce type de système est la reconnaissance du processus chirurgical, passant par une identification précise des outils chirurgicaux utilisés. L'objectif de cette thèse a donc porté sur la détection en temps-réel des outils chirurgicaux dans des vidéos 2D provenant de microscopes. Devant l'absence de jeux de données de référence, qui plus est dans un contexte neurochirurgical, la première contribution de la thèse a donc été la création d'un nouvel ensemble d'images de chirurgies du cerveau et du rachis cervical, mis à disposition en ligne. Comme seconde contribution, deux approches différentes ont été proposées permettant de détecter des outils chirurgicaux via des techniques d'analyse d'image. Tout d'abord, le SquaresChnFtrs adapté, basé sur une des méthodes de détection de piétons les plus performantes de la littérature. Notre deuxième méthode, le ShapeDetector, est une approche à deux niveaux n'utilisant aucune contrainte ou hypothèse a priori sur le nombre, la position, ou la forme des outils dans l'image. Par rapport aux travaux précédents du domaine, nous avons choisi de représenter les détections potentielles par des polygones plutôt que par des rectangles, obtenant ainsi des détections plus précises. Pour intégration dans des systèmes médicaux, une optimisation de la vitesse de calcul a été effectuée via un usage optimal du CPU, du GPU, et de méthodes ad-hoc. Pour des vidéos de résolution 612x480 pixels, notre ShapeDetector est capable d'effectuer les détections à une vitesse maximale de 8 Hz. Pour la validation de nos méthodes, nous avons pris en compte trois paramètres: la position globale, la position de l'extrémité, et l'orientation des détections. Les méthodes ont été classées et comparées avec des méthodes de référence compétitives. Pour la détection des tubes d'aspiration, nous avons obtenu un taux de manqué de 15% pour un taux de faux positifs par image de 0.1, comparé à un taux de manqué de 55% pour le SquaresChnFtrs adapté. L'orientation future du travail devra porter sur l'intégration des informations 3D, l'amélioration de la couche de labélisation sémantique, et la classification des outils chirurgicaux. Pour finir, un enrichissement du jeu de données et des annotations de plus haute précision seront nécessaires<br>Despite modern-life technological advances and tremendous progress made in surgical techniques including MIS, today's OR is facing many challenges remaining yet to be addressed. The development of CAS systems integrating the SPM methodology was born as a response from the medical community, with the long-term objective to create surgical cockpit systems. Being able to identify surgical tools in use is a key component for systems relying on the SPM methodology. Towards that end, this thesis work has focused on real-time surgical tool detection from microscope 2D images. From the review of the literature, no validation data-sets have been elected as benchmarks by the community. In addition, the neurosurgical context has been addressed only once. As such, the first contribution of this thesis work consisted in the creation of a new surgical tool data-set, made freely available online. Two methods have been proposed to tackle the surgical tool detection challenge. First, the adapted SquaresChnFtrs, evolution of one of the best computer vision state-of-the-art approach for pedestrian detection. Our second contribution, the ShapeDetector, is fully data-driven and performs detection without the use of prior knowledge regarding the number, shape, and position of tools in the image. Compared to previous works, we chose to represent candidate detections with bounding polygons instead of bounding boxes, hence providing more fitting results. For integration into medical systems, we performed different code optimization through CPU and GPU use. Speed gain and accuracy loss from the use of ad-hoc optimization strategies have been thoroughly quantified to find an optimal trade-off between speed and accuracy. Our ShapeDetector is running in-between 5 and 8Hz for 612x480 pixel video sequences.We validated our approaches using a detailed methodology covering the overall tool location, tip position, and orientation. Approaches have been compared and ranked conjointly with a set of competitive baselines. For suction tube detections, we achieved a 15% miss-rate at 0.1 FPPI, compared to a 55% miss-rate for the adapted SquaresChnFtrs. Future works should be directed toward the integration of 3D feature extraction to improve detection performance but also toward the refinement of the semantic labelling step. Coupling the tool detection task to the tool classification in one single framework should be further investigated. Finally, increasing the data-set in diversity, number of tool classes, and detail of annotations is of interest

Refletir sobre as experiências com imagens e sons em tempo real é pensar em uma ampla gama de possibilidades e experiências pela humanidade, desde os tempos mais remotos. Pelo fato dessas experiências audiovisuais em tempo real serem numerosas no tempo e no espaço, e já amplamente citada em diferentes estudos, esta apresentação tem por objetivo realizar um recorte mais restrito às experiências audiovisuais em tempo real no campo cinematográfico contemporâneo: uma arte, meio e processo em expansão que culmina na existência de um fenômeno semiótico, realizado principalmente através de modos experimentais com a presença do(s) autor(es) concebendo a experiência audiovisual, conjuntamente ao aparato tecnológico e ao público, todos participantes da criação e exibição da obra audiovisual no mesmo tempo em que ela ocorre, em transmissão direta para a tela de cinema, monitores, telas digitais ou espaços arquitetônicos. Com base em obras audiovisuais realizadas entre 2007 a 2017 desenvolveremos uma reflexão e análise das poéticas e técnicas das experiências audiovisuais em tempo real, de maneira a compreender com um olhar mais atento as possibilidades criativas e contribuir com a reflexão sobre estes formatos do audiovisual contemporâneo, cujos meios e processos estão em contínua expansão de suas fronteiras. Em estética do cinema, esta pesquisa segue em continuidade aos estudos e práticas do cinema experimental e em sua vértice ao cinema expandido.<br>Reflecting about real-time imagery and sounds experiences is thinking about a wide range of possibilities and experiences for humanity, from the earliest times. Because the real-time audiovisual experiences are numerous in time and space, and already widely quoted in different studies, this presentation aims to make a more restricted cut-off to real-time audiovisual experiences in the contemporary cinematographic field: an art, medium and an expanding process that culminates in the existence of a semiotic phenomenon, performed mainly through experimental modes with the presence of the author(s) directing the audiovisual experience in real-time, together with the technological apparatus, the cast, and the public, all participants in the creation and exhibition of the audiovisual work at the same time as it occurs, in direct transmission to the cinema screen, monitors, digital screens or architectural spaces. Based on audiovisual works carried out between 2007 and 2017 we will develop a reflection and analysis of the poetics and techniques of audiovisual experiences in real-time, in order to understand with a closer look the creatives possibilities in live cinema and contribute with reflection on these forms of the contemporary audiovisual, whose means and processes are in continuous expansion of its borders. In aesthetics of the cinema, this research follows in continuity to the studies and practices of the experimental cinema, and in its vertex to the expanded cinema.

L’enseignement de la chirurgie nasale est difficile, car l’opération est pratiquée dans le nez en regardant par les narines. Cela signifie que le résident (étudiant en chirurgie) et le patron (chirurgien-enseignant) ne voient pas ce que l’autre fait dans le nez (Ahmidi et al., 2015). Une solution semble être la septoplastie vidéo-assistée (SVA) où une caméra est ajoutée à un instrument chirurgical et projette le champ opératoire sur un écran (Rahal & Charron, 2017). Le but de cette étude est de mesurer l’impact de la SVA sur le processus d’apprentissage des résidents en comparaison à la chirurgie conventionnelle. Projet en 2 étapes : 1. Création d’un outil de mesure a. Création du modèle du processus d’apprentissage au bloc opératoire selon les écrits de Piaget (Piaget, 1975) et Collins (Collins, Brown, & Newman, 1987) b. Création et Validation d’un questionnaire (Quivy & Van Campenhoudt, 2011) 2. Comparaison a. Recrutement de 5 patrons et 4 résidents pour effectuer 38 septoplasties b. Assignation aléatoire du spéculum vidéo vs conventionnel c. Réponse au questionnaire après chaque chirurgie Résultats : Pour chaque élément du modèle d’apprentissage mesuré à l’aide du questionnaire, la SVA s’est avérée supérieure de manière statistiquement et cliniquement significative. Discussion et Conclusion : La SVA améliore la vue du champ opératoire, la communication et le raisonnement clinique tout en permettant d’enseigner la chirurgie nasale à plusieurs étudiants à la fois. En conclusion, la SVA a un impact positif significatif sur le processus d’apprentissage des résidents en comparaison à la chirurgie conventionnelle.<br>Teaching nasal surgery is challenging since the operative field is within the nose and the surgeon perform the surgery by looking through the nostrils. This means the resident and the attending surgeon cannot see what each other are doing in the nose. A solution could be the Video-Assisted Speculum of Rosemont where a high definition flexible endoscope is mounted on a modified nasal speculum. While the surgery is performed in the usual fashion by looking in the nose, the surgery is displayed in the operative room. Methodology The aim of this study was to measure the impact of adding a camera to the nasal speculum on the learning process of residents compared to the conventional speculum. A questionnaire was developed and validated with the help of three experts in education. Then five surgeons and four residents were recruited to perform 32 consecutive septoplasties. Either the Rosemont or the conventional speculum was randomly assigned, and the questionnaire was filled by the participants after each surgery. The scores for the specula were compared with Mann-Whitney U Test. Results For all the 7 elements underlying the learning process of residents in the operative room, the video-assisted Rosemont speculum performed significantly better than the conventional speculum. Discussion and conclusion The Rosemont speculum contribute to offer a better view of the operative field to bystanders, it also helps with verbal communication and clinical reasoning while giving the opportunity to teach several residents at the same time. In conclusion, the Rosemont speculum has a positive impact on the learning process of nasal surgery.

La problématique de l’observance de la biosécurité est présente dans tous les types de production. Il est essentiel de définir des stratégies pour améliorer l’application des mesures de biosécurité. Cette étude décrit l’application des mesures de biosécurité à l’entrée et à la sortie de 24 bâtiments d’élevages avicoles au Québec, Canada. L’effet des audits et de caméras visibles sur l’observance a été étudié, de même que les déterminants de l’observance. De plus, la relation entre l’observance et les profils de personnalité, l’expérience et l’éducation a été décrite. L’application des mesures de biosécurité a été évaluée à l’aide de caméras cachées. L’observance à court terme (deux premières semaines) et à moyen terme (six mois plus tard) a été déterminée. Basés sur les résultats du groupe contrôle, 44 différentes erreurs lors de l’application des mesures de biosécurité ont été observées à l’entrée et la sortie des bâtiments. La plupart étaient reliées à la délimitation des zones (propre versus contaminée). La nature et la fréquence des erreurs suggèrent un manque de compréhension des principes associés aux mesures de biosécurité. Le visionnement des vidéos a révélé 3055 visites par 277 individus différents (136 employés, 123 visiteurs, 3 superviseurs et 15 éleveurs). Les résultats ont démontré que les audits n’avaient pas d’impact sur l’observance des employés. Les caméras visibles ont eu un impact, à court terme, sur le port de bottes et le respect des zones durant la visite. Par contre, six mois plus tard, l’observance avait significativement diminué, au point de ne plus être statistiquement plus élevée que le groupe contrôle. La durée et le moment de la visite, la présence de l’éleveur ou d’un observateur, la conception de l’entrée, le nombre de bâtiments, le nombre de mesures de biosécurité exigé, le type de bottes, le genre et être membre de la famille de l’éleveur étaient significativement associés à l’observance de certaines mesures. Finalement, trois traits de la personnalité étaient associés à l’observance: responsabilité, orienté vers l’action et complexité, de même que le nombre d’années d’expérience et le niveau d’éducation. Il est nécessaire d’améliorer la formation en matière de biosécurité en fournissant du matériel de formation à tous les intervenants qui démontrent pourquoi et comment appliquer les mesures de biosécurité. La formation continue devrait également aborder les problématiques reliées aux caractéristiques de visites et de fermes. Améliorer la conception des entrées de bâtiments devrait contribuer à augmenter et à maintenir l’observance. L’identification de traits de personnalité associés à l’observance peut avoir des implications sur la sélection des candidats à l’embauche ou sur l’attribution de tâches et sur la planification des programmes de formation.<br>Biosecurity compliance issue is present in all types of animal productions, Therefore, it is essential to define strategies to improve the implementation of biosecurity measures. This study described the application of biosecurity measures when entering and exiting 24 poultry barns in Québec, Canada. The effect of audits and visible cameras on compliance was investigated, as well as determinants of compliance. Also, the relationship between compliance and personality profiles, experience and education has been described. Application of biosecurity measures was evaluated using hidden cameras. Short term (first two weeks) and medium term (six months later) compliance were determined. Based on the control group, 44 different biosecurity breaches were observed when getting in and out of poultry barns. Most were related to area delimitation (clean versus contaminated). The nature and frequency of errors suggest a lack of understanding of biosecurity principles. Overall, video viewing revealed 3055 visits done by 277 different individuals (136 employees, 123 visitors, 3 supervisors and 15 growers). Results showed that audits did not have any impact on employee compliance. Visible cameras had a significant impact on changing boots and respecting areas during the visit for the short term period. However, six months later, compliance significantly declined and was no longer statistically higher compared to the control group. Duration and moment of the visit, presence of the grower or an observer, barn entrance design, number of barns, number of biosecurity measures requested, type of boots, gender and being a member of a grower’s family were significantly associated with compliance with some biosecurity measures. Finally, three personality traits were significantly associated with compliance: responsibility, action-oriented and complexity, as well as the number of years of experience and the level of education. There is a need to improve biosecurity training by making training material available to all poultry personnel demonstrating why and how to apply biosecurity measures. Educational meetings should also address issues related to visit and farm characteristics. Improving barn entrance design should contribute to enhance and maintain compliance. The identification of personality traits associated with compliance may have implications for the selection of job applicants or task attribution, and for developing educational materials and training programs.

En Afrique, un continent où le paludisme est prévalent, la fièvre constitue le premier motif de consultation médicale. Des études sur l'utilisation des tests de diagnostic rapide du paludisme au Burkina Faso ont toutefois révélé qu'une proportion croissante de maladies fébriles aiguës ne sont pas liées au paludisme (Bottger et al., 2017). Dans certains cas, il pourrait s’agir de la dengue, puisqu’une épidémie de cette maladie a été déclarée au Burkina Faso en 2013, suivie d’une nouvelle flambée en 2016. Or, la formation des agents de santé burkinabè quant au traitement de la dengue est déficiente (Munoz, Ridde, Yaro, et Bottger, 2015). Cela représente un problème de santé publique quand on sait que la détection précoce et l’accès à des soins médicaux adaptés permettent de ramener les taux de mortalité en dessous de 1 %. La vidéo pourrait contribuer à pallier ce manque de formation puisqu’elle constitue un outil de transfert de connaissances efficace (Armstrong, Idriss, et Kim, 2011; Fiorella et Mayer, 2018; Yeung, Justice, et Pasic, 2009). Son utilisation a toutefois été peu étudiée en fonction de son genre narratif. La présente étude vise donc à évaluer l'efficacité relative de trois vidéos qui empruntent autant de genres narratifs distincts (1-reportage, 2-théâtre, 3- animation) pour améliorer les connaissances des prestataires de soins de santé burkinabè. Elle a aussi pour objectif d’identifier les éléments narratifs qui bonifient la vidéo comme outil de transfert de connaissances. Les vidéos ont été testées auprès d’étudiants en soins infirmiers à Ouagadougou (n = 482) à l’aide d’un test de connaissances. Trois groupes de discussion ont été formés avec des étudiants (N = 46) et des entretiens individuels ont été menés avec des professionnels de la santé (n = 10).<br>In Africa, a continent where malaria is prevalent, fever is the main reason for medical consultation. Studies on the use of malaria rapid diagnostic tests in Burkina Faso have shown, however, that an increasing proportion of acute febrile diseases are not related to malaria (Bottger et al., 2017). Some of these cases could be dengue fever, as an epidemic of this disease was declared in Burkina Faso in 2013, followed by a new outbreak in 2016. However, Burkinabe health workers have not received adequate training to treat dengue fever (Munoz et al., 2015). This is a public health problem, since it is known that early detection and access to appropriate medical care can reduce mortality rates to below 1%. Video could help fill this training gap, as it is an effective knowledge transfer tool (Armstrong, Idriss, & Kim, 2011; Fiorella & Mayer, 2018; Yeung, Justice, & Pasic, 2009). However, its use has been little studied in relation to narrative genre. The present study therefore aimed to evaluate the relative effectiveness of three videos adopting different narrative genres (1-journalism, 2- drama, 3-graphic animation) in improving the knowledge of Burkinabe healthcare providers. It also aimed to determine what narrative elements enhance video as a knowledge transfer tool. The videos were tested with nursing students (n = 482) in Ouagadougou using a knowledge questionnaire. Three focus groups were held with students (n = 46), and individual interviews were conducted with health professionals (n = 10).

Tese de mestrado em Ecologia e Gestão Ambiental, apresentada à Universidade de Lisboa, através da Faculdade de Ciências, 2017<br>Como consequência de um declínio com mais de duas décadas no recrutamento da enguia-europeia, a Comissão Europeia, aconselhada pelo ICES, adotou em 2007 um plano que visa a recuperação da espécie. O Regulamento (CE) nº 1100/2007 obrigou os Estados Membros a desenvolver Planos de Gestão da Enguia com o objetivo de reduzir a mortalidade relacionada com causas antropogénicas e garantir a fuga para o mar de 40% das enguias prateadas, que escapariam de cada bacia hidrográfica em condições pristinas. Na Lagoa de Santo André, uma lagoa costeira com um curto período de ligação ao mar, que se encontra integrada na Reserva Natural da Lagoa de Santo André e da Sancha, a implementação de medidas de restrição à pesca da enguia tem-se revelado ineficaz neste sentido. A redução das pescas, como medida, tem a sua eficiência limitada pela magnitude do recrutamento e a sobrevivência dos recrutas. Tendo presentes os estatutos de conservação da enguia-europeia e da LSA, a pesca da enguia, com tradição secular na LSA, tem sido reduzida. A sustentabilidade da pesca passa também pela redistribuição do esforço de pesca neste sistema. Conhecer o espectro de espécies piscícolas que recrutam na LSA é um passo importante na direção de um planeamento ponderado e uma gestão conseguida. É neste sentido que foi realizado o presente estudo, que contemplou duas partes distintas: 1) Caracterizar o recrutamento larvar e juvenil da ictiofauna (com exceção da enguia-europeia) na Lagoa de Santo André e compreender os fatores que o condicionam; 2) Caracterizar o recrutamento e clarificar da dinâmica espácio-temporal da colonização da enguia de vidro na Lagoa de Santo André, relacionando-a com as condições da lagoa. A captura de estados larvares e juvenis de ictiofauna, durante o período em que decorreu a abertura da lagoa ao mar, consistiu numa única abordagem. Com recurso a um botirão, as pescas concretizaram-se durante as marés enchentes. O ano do presente estudo foi marcado por um período curto de ligação entre o mar e a lagoa (9 dias). Foram ainda utilizados dados relativos às pescas desde a criação da Reserva Natural (cedidos pelo ICNF) e consultados os dados de pesca relativos aos projetos GROUNDSCENE (2011) e PELSA (2016), procurando relacionar o rendimento da pesca com as características da abertura da lagoa ao mar. A captura de juvenis de enguia, após o término da comunicação da lagoa com o mar, foi realizada com recurso a uma metodologia inovadora, desenvolvida para o propósito específico do trabalho. A “trouxa”, uma arte de pesca passiva, foi pensada com o intuito de recolher indivíduos que procuram estabelecer-se num local onde as condições favorecem o seu estabelecimento. Esta componente do trabalho culminou na produção de um modelo explicativo BRT (Boosted regression trees), com o objetivo de compreender os fatores que afetam o estabelecimento dos juvenis de enguia na LSA. Os resultados da primeira parte do trabalho revelaram que no ano 2016, a dourada (Sparus aurata) foi, entre as espécies exploradas localmente, a mais capturada durante a abertura da lagoa ao mar. A espécie mais capturada foi a sardinha (Sardina pilchardus), seguindo-se a galeota-menor (Ammodytes tobianus). As proporções de indivíduos capturados durante a noite e o dia, revelaram que o recrutamento de estados larvares e juvenis de ictiofauna na LSA ocorre principalmente durante a noite. A corrente da enchente afeta de forma diferente o recrutamento de larvas de sardinhas e galeotas-menores de diferentes tamanhos, na LSA. Os dados de pesca cedidos pelo ICNF e obtidos pelos projetos GROUDSCENE e PELSA, revelaram diferenças na quantidade de pesca entre aberturas de curta e longa duração assim como aberturas realizadas antes e depois de 20 de março. Os resultados relativos à segunda parte do trabalho indicaram que as enguias de vidro capturadas durante o período de abertura têm dimensões inferiores àquelas encontradas em águas portuguesas e outras bacias europeias, resultado de um recrutamento tardio. As enguias de vidro capturadas nos dois primeiros dias de pesca são as de menor comprimento. Contudo, os indivíduos capturados durante o primeiro dia de pesca apresentam um fator de condição superior aos dos restantes indivíduos. As análises realizadas a diferentes estados de pigmentação das enguias de vidro indicam diferenças de comprimento e peso entre os estados de pigmentação VA e VIA0. O valor estimado para o recrutamento total de enguias de vidro na LSA foi 23,97 kg ± 4,47 (SE), sendo considerado baixo. O principal fator a contribuir para este número é o número de dias em que a lagoa permanece ligada ao mar. A contribuir para o recrutamento está também o facto de o período de abertura poder estar desfasado do o pico de recrutamento de enguias de vidro para as águas continentais portuguesas. Os resultados obtidos com o BRT revelaram que a temperatura é a principal variável a contribuir para a deteção de juvenis de enguia nas trouxas, seguida do oxigénio e salinidade. A distância a cada uma das ribeiras também revelou ter impacto no ajustamento do modelo, assim como a abundância de caranguejos. Seguindo os princípios da sustentabilidade, o presente estudo culmina na recomendação de medidas orientadoras no que diz respeito à concretização da abertura da lagoa ao mar. Estas medidas foram ponderadas visando potenciar a pesca através do aumento do recrutamento larvar e juvenil das várias espécies de ictiofauna na LSA. Apresentam-se ainda medidas que se destinam a otimizar a sobrevivência dos juvenis de enguia que colonizam a LSA e aconselha-se sobre os próximos passos no estudo da ecologia da enguia de vidro na LSA.<br>Following a decline of more than two decades in the the European eel stock, the European Commision, advised by the ICES, adopted a plan in 2007 for the recovery of the species. The Eel Regulation obliged the EU Member States to develop Eel Management Plans aiming at reducing anthropogenic mortality and guarantee the escapement to the sea of at least 40% of silver that would have escaped from river basins under pristine conditions. In Santo André Lagoon, an enclosed coastal lagoon with a short opening period to the adjoining sea, which is integrated in a Natural Reservoir, the implementation of restrictions on fishery is not being successful towards achieving the Eel Regulation’s goal. Here, the traditional eel fishing is restricted by the Eel Regulation and due to the conservation regimes of the protected area. Fishing restriction, as a measure, is limited by the magnitude of recruitment of glass eels and their survival during settlement. The distribution of fishing effort among other species should also be a goal of fisheries sustainability. Knowing the fish species that recruit in this coastal lagoon is a crucial step in achieving careful planning and adequate management of fisheries. Hence, this study included two parts: 1) To characterize recruitment of fish larvae and juveniles of fish (excluding the European eel) while understanding the factors that undermine it; 2) To characterize glass eel recruitment and the dynamics of their spatio-temporal colonization following settlement in the LSA, while relating it to the lagoon’s conditions. During the period of connection with the sea (9 days) larvae and juveniles of fish were caught, in each flood tide, using a net adjusted to the conditions of the lagoon. Fishing survey data was analysed to understand how the conditions of the inlet could impact fishing. After inlet closure, juvenile eels were caught using a trap (trouxa) that acts as an artificial habitat, which was designed for the sole purpose of this study. This trap was manufactured with the aim of capturing eels that seek to settle in a place where conditions are suitable. This provided the information needed to adjust a BRT model to understand the relationship between juvenile eel distribution and the conditions of the lagoon subsistence. While the lagoon remained connected to the sea, the gilthead seabream (Sparus aurata) was, among fish with economical interest in the LSA, the most captured species. The European pilchard (sardine), followed by the lesser sand-eel, were the overall most captured species. The results obtained showed that recruitment of larvae and juvenile fish to the lagoon, occurs mostly at night and that flood tide currents affect differently the recruitment of individuals (sardine and lesser sand-eel) with different sizes. Survey data revealed differences between years, in biomass fished, with inlets which remained open for longer or shorter periods. Th opening of the lagoon before and after the 20th of march also have significant differences in the amount fished. Regarding the 2nd part of this study, results showed that glass eels caught while the lagoon was connected to the sea seem to be smaller than those found in other Portuguese and European water basins, suggesting late recruitment. Glass eels caught in the first two days of fishing, are the smallest, however, those caught in the first day of fishing have a higher condition factor than those of the remaining days. Analyses of pigmentation stages showed that there were significant differences between the stage VA and VIA0 in total length and weight. Glass eel recruitment at LSA was estimated to be 23,97 kg ± 4,47, which was considered low. The reduced number of days that the lagoon remained connected to the sea (9 days) was considered the main factor contributing to this recruitment value. The opening of the lagoon occurred outside the peak of recruitment of glass eels to Portuguese water basins and this can also contribute to the low levels of recruitment. Temperature was the main variable adjusted by the BRT model to identify the presence of juvenile eels inside the trap (trouxa), followed by oxygen and salinity. Distance to freshwater streams and the abundance of crabs also had an impact on the adjustment of the BRT model. Following sustainability standards, this study culminates by providing advice on the opening of the lagoon while aiming at optimizing fishing activity through an increase of fish larvae and juvenile recruitment. This study also provides measures destined to increase the survival and settlement of juvenile eels and as well advice on the next steps to be taken in the study of the ecology of glass eels in LSA.