The amount of information on the World Wide Web (WWW) is rapidly growing in pace and topic diversity. This has made it increasingly difficult, and often frustrating, for information seekers to retrieve the content they are looking for as information retrieval systems (e.g., search engines) are unable to decipher the relevance of the retrieved information as it pertains to the information they are searching for. This issue can be decomposed into two aspects: 1) variability of information relevance as it pertains to an information seeker. In other words, different information seekers may enter the same search text, or keywords, but expect completely different results. It is therefore, imperative that information retrieval systems possess an ability to incorporate a model of the information seeker in order to estimate the relevance and context of use of information before presenting results. Of course, in this context, by a model we mean the capture of trends in the information seeker's search behaviour. This is what many researchers refer to as the personalized search. 2) Information diversity. Information available on the World Wide Web today spans multitudes of inherently overlapping topics, and it is difficult for any information retrieval system to decide effectively on the relevance of the information retrieved in response to an information seeker's query. For example, the information seeker who wishes to use WWW to learn about a cure for a certain illness would receive a more relevant answer if the search engine was optimized into such domains of topics. This is what is being referred to in the WWW nomenclature as a 'specialized search'. This thesis maintains that the information seeker's search is not intended to be completely random and therefore tends to portray itself as consistent patterns of behaviour. Nonetheless, this behaviour, despite being consistent, can be quite complex to capture. To accomplish this goal the thesis proposes a Multi-Agent Personalized Information Retrieval with Specialization Ontology (MAPIRSO). MAPIRSO offers a complete learning framework that is able to model the end user's search behaviour and interests and to organize information into categorized domains so as to ensure maximum relevance of its responses as they pertain to the end user queries. Specialization and personalization are accomplished using a group of collaborative agents. Each agent employs a Reinforcement Learning (RL) strategy to capture end user's behaviour and interests. Reinforcement learning allows the agents to evolve their knowledge of the end user behaviour and interests as they function to serve him or her. Furthermore, REL allows each agent to adapt to changes in an end user's behaviour and interests. Specialization is the process by which new information domains are created based on existing information topics, allowing new kinds of content to be built exclusively for information seekers. One of the key characteristics of specialization domains is the seeker centric - which allows intelligent agents to create new information based on the information seekers' feedback and their behaviours. Specialized domains are created by intelligent agents that collect information from a specific domain topic. The task of these specialized agents is to map the user's query to a repository of specific domains in order to present users with relevant information. As a result, mapping users' queries to only relevant information is one of the fundamental challenges in Artificial Intelligent (AI) and machine learning research. Our approach employs intelligent cooperative agents that specialize in building personalized ontology information domains that pertain to each information seeker's specific needs. Specializing and categorizing information into unique domains is one of the challenge areas that have been addressed and various proposed solutions were evaluated and adopted to address growing information. However, categorizing information into unique domains does not satisfy each individualized information seeker. Information seekers might search for similar topics, but each would have different interests. For example, medical information of a specific medical domain has different importance to both the doctor and patients. The thesis presents a novel solution that will resolve the growing and diverse information by building seeker centric specialized information domains that are personalized through the information seekers' feedback and behaviours. To address this challenge, the research examines the fundamental components that constitute the specialized agent: an intelligent machine learning system, user input queries, an intelligent agent, and information resources constructed through specialized domains. Experimental work is reported to demonstrate the efficiency of the proposed solution in addressing the overlapping information growth. The experimental work utilizes extensive user-centric specialized domain topics. This work employs personalized and collaborative multi learning agents and ontology techniques thereby enriching the queries and domains of the user. Therefore, experiments and results have shown that building specialized ontology domains, pertinent to the information seekers' needs, are more precise and efficient compared to other information retrieval applications and existing search engines.

Σήμερα, βρισκόμαστε ήδη στο στάδιο μετάβασης από τις παραδοσιακές επιτραπέζιες υπολογιστικές τεχνολογίες στα διάχυτα (ubiquitous) υπολογιστικά περιβάλλοντα που θα μας υποστηρίζουν σχεδόν σε κάθε καθημερινή μας λειτουργία ή δραστηριότητα. Παράλληλα, υπάρχει μία αυξανόμενη τάση για τοποθέτηση του χρήστη στο κέντρο των υπηρεσιών. Αυτό σημαίνει ότι οι υπηρεσίες θα προσαρμόζονται με βάση το στενό και ευρύτερο περιβάλλον διαβίωσης (context), τις ανάγκες και τις προτιμήσεις των χρηστών. Δύο από τις βασικότερες έννοιες στις οποίες βασίζεται η προσφορά διάχυτων εξατομικευμένων υπηρεσιών είναι η γνώση πλαισίου (context awareness) και η μοντελοποίηση χρηστών (user modeling). Η έλευση του διάχυτου υπολογισμού και η χρησιμοποίηση της διάχυτης μοντελοποίησης χρηστών (ubiquitous user modeling) έχει δημιουργήσει νέες προσδοκίες και προκλήσεις για την παροχή εξατομικευμένων υπηρεσιών σε πολλούς τομείς εφαρμογών μεταξύ των οποίων είναι και ο τομέας της υγείας. Η ιατρική αντιμετώπιση αλλάζει πλέον κατεύθυνση και γίνεται προστατευτική, προληπτική και εύκολα προσεγγίσιμη (π.χ. στη δουλειά, στο σπίτι, κλπ.), συνοδευόμενη από συνεχή και εμμένουσα παροχή υψηλής ποιότητας εξατομικευμένης ιατρικής συμβουλής και υποστήριξης. Οι σύγχρονες ιατρικές υπηρεσίες αναμένονται να είναι διαθέσιμες κάθε στιγμή, 7 ημέρες την εβδομάδα και να παρέχονται με έναν εξατομικευμένο τρόπο ώστε να απευθύνονται στις ιδιαίτερες ανάγκες και απαιτήσεις κάθε ατόμου. Η παρούσα διατριβή πραγματεύεται μία μεθοδολογία παροχής διάχυτων υπηρεσιών σε εξελιγμένα τηλεπικοινωνιακά δίκτυα που συνδυάζει τη γνώση πλαισίου, τη μοντελοποίηση χρηστών και τα κοινωνικά δίκτυα (social networks). Η μεθοδολογία αυτή εφαρμόστηκε στον ιατρικό χώρο και ειδικότερα στις διαταραχές άγχους. Πιο συγκεκριμένα, στη διατριβή καθορίστηκαν πλήρως οι παράμετροι πλαισίου που σχετίζονται άμεσα με τις διαταραχές άγχους και προτάθηκε ένα μοντέλο πλαισίου που βασίζεται σε οντολογίες. Επίσης, μελετήθηκε η δομή και οι τεχνικές κατασκευής και ανανέωσης των μοντέλων χρηστών, ενώ μελετήθηκε η χρήση των κοινωνικών δικτύων για την παροχή ιατρικής φροντίδας και οι ρόλοι των μελών τους στις διαταραχές άγχους. Τέλος, προτάθηκε η αρχιτεκτονική ενός συστήματος γνώσης πλαισίου που ενσωματώνει τις ανωτέρω τεχνολογίες, τμήμα του οποίου αναπτύχθηκε, υλοποιήθηκε και αξιολογήθηκε από επαγγελματίες ιατρούς. Κατά την εφαρμογή της παραπάνω μεθοδολογίας στις διαταραχές άγχους αναπτύχθηκε η εφαρμογή PerMed που αποτελεί ένα εργαλείο αρχειοθέτησης και επεξεργασίας των προσωπικών πληροφοριών των ασθενών και τέσσερις υπηρεσίες που στοχεύουν στην υποστήριξη της θεραπείας των διαταραχών άγχους. Οι τρεις εστιάζουν στην ανακάλυψη πιθανών συσχετίσεων στα δεδομένα πλαισίου, ενώ η τέταρτη στοχεύει στην πρόβλεψη του άγχους που θα παρουσιάσει ένας ασθενής σε ένα δεδομένο πλαίσιο. Τα σχόλια που λάβαμε από επαγγελματίες ψυχιάτρους είναι αρκετά ενθαρρυντικά και ευελπιστούμε ότι η προτεινόμενη προσέγγιση θα αποτελέσει ένα ισχυρό εργαλείο υποστήριξης της θεραπείας των διαταραχών άγχους. / Today, we are already on the transition from the traditional desktop-based computing technologies towards ubiquitous computing environments that will enfold us in almost all our daily situations and activities. Simultaneously, there exists an increased tendency of putting the user into the center of service delivery. This means that the services in the ubiquitous environments should be adapted to the context, the needs and the preferences of users. Two of the key-concepts, based on which the delivery of ubiquitous personalized services is realized, are context-awareness and user modeling. The emergence of ubiquitous computing and ubiquitous user modeling has created new expectations and challenges for the delivery of personalized services in a considerable amount of application domains, among which is the healthcare domain. Healthcare provision changes direction becoming protective, proactive and more reachable (e.g. at home or at work), accompanied by continuous and persistent provision of personalized high-quality health advice and assistance. Modern healthcare services are expected to be available around the clock, seven days a week and delivered in a personalized manner addressing the specific needs and preferences of each individual. The present dissertation presents a methodology of providing ubiquitous services at advanced telecommunication networks, which combines context-awareness, user modeling and social networks. This methodology was implemented in the healthcare domain and more specifically in anxiety disorders. In particular, in this dissertation, the contextual aspects that are directly associated with anxiety disorders were defined and an ontology-based context model was proposed. In addition, the user models’ structure was determined and the techniques for the processing of their content were developed. Furthermore, the use of social networks in anxiety disorders and the role of their members were studied. Finally, the architecture of a context-aware system that integrates all the above technologies was proposed, a part of which was developed, implemented and evaluated by professional psychiatrists. During the implementation of the proposed methodology in anxiety disorders, the PerMed application that provides medical experts with a tool for archiving and processing the patient’s personal data and four treatment supportive services were developed. The three of them focus on the discovery of possible associations between the patient’s contextual data and the last service aims at predicting the stress level a patient might suffer from, in a given context. The feedback received from expertized psychiatrists was very encouraging and we hope that the proposed approach will constitute a powerful treatment supportive tool for anxiety disorders.

Made available in DSpace on 2014-12-17T15:47:53Z (GMT). No. of bitstreams: 1 PedroPCM_DISSERT.pdf: 1574472 bytes, checksum: 51d5716514addf6a4cc91c3445d0a7fa (MD5) Previous issue date: 2011-02-10 / In this work we present the architecture and implementation of MyPersonal-EPG, a personal EPG with support to recommendations, built on top of the Ginga middleware, that fulfill the following requirements: (i) to allow users to build their own personal programming grids, based on programming guides from several broadcasters; (ii) to offer a mechanism to tune the desired channels on the moment the selected programs are about to begin; (iii) to allow users to select the desired programs categories; (iv) to offer programs recommendations, in both synchronous and asynchronous way, based on the categories previously selected by users; (v) to allow users to modify the current configuration options; (vi) to allow the creation of several users accounts, so that each user can store its own information. The application‟s usability test is also presented and its results are discussed and analyzed / Neste trabalho apresentamos a arquitetura e implementa??o do MyPersonal-EPG, um EPG personaliz?vel e com suporte a recomenda??es, constru?do sobre o middleware Ginga, que atende aos seguintes requisitos: (i) permitir aos usu?rios a montagem da sua pr?pria grade de programa??o, com base nas grades de programa??o de diversas emissoras; (ii) oferecer um mecanismo para sintonizar os devidos canais no momento em que os programas selecionados pelo usu?rio estiverem prestes a come?ar; (iii) permitir que os usu?rios selecionem categorias de programas desejadas; (iv) oferecer recomenda??es de programas, de forma s?ncrona e ass?ncrona, com base nas categorias selecionadas previamente pelos usu?rios; (v) permitir que os usu?rios modifiquem as op??es de configura??o; (vi) possibilitar a cria??o de diversas contas de usu?rios, a fim de permitir que cada usu?rio possa armazenar todas as suas informa??es de interesse. A avalia??o de usabilidade da aplica??o ? tamb?m apresentada e seus resultados s?o discutidos e analisados

Les systèmes de recommandation ont acquis une certaine popularité parmi les chercheurs, où de nombreuses approches ont été proposées dans la littérature. Les utilisateurs des folksonomies partagent des items (e.g., livres, films, sites web, etc.) en les annotant avec des tags librement choisis. Avec l'essor du Web 2.0, les utilisateurs sont devenus les principaux acteurs du système étant donné qu'ils sont à la fois les contributeurs et créateurs de l'information. Ainsi, il est important de répondre à leurs besoins en leur proposant une recommandation plus ciblée. Pour ce faire, nous considérons une nouvelle dimension dans une folksonomie classiquement composée de trois dimensions <utilisateurs,tags,ressources> et nous proposons une approche afin de regrouper les utilisateurs ayant des intérêts proches à travers des structures appelées concepts quadratiques. Ensuite, nous utilisons ces structures afin de proposer un nouveau système personnalisé de recommandation. Nous évaluons nos approches sur divers jeux de données du monde réel. Ces expérimentations ont démontré de bons résultats en termes de précision et de rappel ainsi qu'une bonne évaluation sociale. De plus, nous étudions quelques unes des métriques utilisées pour évaluer le systèmes de recommandations, comme la couverture, la diversité, l'adaptivité, la sérendipité ou encore la scalabilité. Par ailleurs, nous menons une étude de cas sur quelques utilisateurs comme complément à notre évaluation afin d'avoir l'avis des utilisateurs sur notre système. Enfin, nous proposons un nouvel algorithme qui permet de mettre à jour un ensemble de concepts triadiques sans avoir à re-scanner l'entière folksonomie. Les premiers résultats comparant les performances de notre proposition par rapport au redémarrage du processus d'extraction des concepts triadiques sur quatre jeux de données du monde réel a démontré son efficacité. / Recommender systems are now popular both commercially as well as within the research community, where many approaches have been suggested for providing recommendations. Folksonomies' users are sharing items (e.g., movies, books, bookmarks, etc.) by annotating them with freely chosen tags. Within the Web 2.0 age, users become the core of the system since they are both the contributors and the creators of the information. In this respect, it is of paramount importance to match their needs for providing a more targeted recommendation. For such purpose, we consider a new dimension in a folksonomy classically composed of three dimensions <users,tags,resources> and propose an approach to group users with close interests through quadratic concepts. Then, we use such structures in order to propose our personalized recommendation system of users, tags and resources. We carried out extensive experiments on two real-life datasets, i.e., MovieLens and BookCrossing which highlight good results in terms of precision and recall as well as a promising social evaluation. Moreover, we study some of the key assessment metrics namely coverage, diversity, adaptivity, serendipity and scalability. In addition, we conduct a user study as a valuable complement to our evaluation in order to get further insights. Finally, we propose a new algorithm that aims to maintain a set of triadic concepts without the re-scan of the whole folksonomy. The first results comparing the performances of our proposition andthe running from scratch the whole process over four real-life datasets show its efficiency.

Submitted by Bruna Oliveira (brunamiyuki@gmail.com) on 2017-08-29T17:05:38Z No. of bitstreams: 1 Tese_versãofinal.pdf: 3842360 bytes, checksum: 086bcf268fcb7702a198316e866fa6a2 (MD5) / Approved for entry into archive by Pamela Beltran Tonsa (pamela.tonsa@fgv.br) on 2017-08-29T19:48:14Z (GMT) No. of bitstreams: 1 Tese_versãofinal.pdf: 3842360 bytes, checksum: 086bcf268fcb7702a198316e866fa6a2 (MD5) / Made available in DSpace on 2017-08-30T13:07:01Z (GMT). No. of bitstreams: 1 Tese_versãofinal.pdf: 3842360 bytes, checksum: 086bcf268fcb7702a198316e866fa6a2 (MD5) Previous issue date: 2017-07-31 / A privacidade de informações na internet é uma das maiores preocupações advindas da ascensão da web 2.0. Entretanto, cada vez é mais comum a requisição e manejamento de dados pessoais por empresas que, por meio de Sistemas de Recomendação (SR), visam garantir aos usuários serviços ou produtos personalizados às suas necessidades. Porém, frequentemente os consumidores enfrentam um paradoxo de privacidade-personalização, pois precisam conceder informações, mas temem como elas serão utilizadas pelas empresas. O uso incoerente de tais dados pode dar ao indivíduo a sensação de que sua liberdade está sendo cerceada, levando-o a reagir de maneira diversa da intenção do sistema. Trata-se, efetivamente, de um efeito bumerangue, entendido como uma resposta oposta à ameaça de sua liberdade na web. Tendo em vista que a literatura de SI explora de maneira insuficiente os efeitos da percepção de intrusão na disposição em revelar informações, sobretudo por meio da teoria da reatância psicológica – de onde advém o efeito bumerangue – o objetivo desta pesquisa foi verificar como a percepção dos usuários sobre a intrusão do Sistema de Recomendação pode afetar a sua disposição em revelar suas informações. Foram realizados dois experimentos, sendo um nos Estados Unidos e outro no Brasil, com amostras válidas de 213 e 237 participantes, respectivamente. Para isto, foi desenvolvido um protótipo de Sistema de Recomendação Experimental na plataforma Qualtrics. As técnicas utilizadas para análise de dados foram a análise de variância de um fator (one-way ANOVA) e a análise de covariância (ANCOVA). Dentre os resultados obtidos, demonstrou-se o efeito bumerangue do SR, pois quanto maior o nível de intrusão do SR, menor a disposição para revelar suas informações; verificou-se a existência de apenas dois níveis de intrusão percebida pelo usuário; foi constatado o impacto das preocupações de privacidade na internet na relação entre percepção de intrusão e disposição em revelar suas informações, além da uniformidade no comportamento entre as duas amostras. Com base nos resultados, espera-se que desenvolvedores de SR e empresas que os utilizam evitem futuros efeitos bumerangue em suas recomendações, o que afugentaria um potencial cliente. / Information privacy on internet is one of the biggest concerns that arise with web 2.0. However, it is increasingly common for companies that use Recommendation Systems (RS) the request and manage of personal data aiming to guarantee personalized services or products to the users. However, consumers often face a privacy-personalization paradox because they need to provide information, but fear how companies will use it. Incoherent use of such data can give to the individual the feeling that their freedom is being curtailed, causing reactions differently than the system’s intention. It is a boomerang effect, understood as an opposed response to the threat of its freedom on the web. Considering that the IS literature insufficiently explores the effects of the perception of intrusion on the willingness to disclose information, especially through the theory of psychological reactance – where the boomerang effect comes from – the objective of this research is to verify how the users' perception of the intrusion of the Recommendation System may affect your willingness to disclose your information. Two experiments were conducted in the United States and Brazil, with valid samples of 213 and 237 participants, respectively. A prototype of an Experimental Recommendation System (ERS) was developed on the Qualtrics platform. The techniques used for data analysis were the analysis of one-way variance (one-way ANOVA) and covariance analysis (ANCOVA). Among the results, the boomerang effect of RS was demonstrated, because the higher the level of SR intrusion, the less is the willingness to disclose its information. It was verified the existence of only two levels of intrusion perceived by the user. The impact of Internet privacy concerns on the relationship between perception of intrusion and willingness to disclose information was verified, as well as the behavioral indifference between the two samples. Based on the results, RS developers and companies that use them are expected to avoid future boomerang effects in their recommendations, which would scare away a potential customer.

Made available in DSpace on 2016-06-02T19:06:22Z (GMT). No. of bitstreams: 1 6770.pdf: 4215500 bytes, checksum: 31340bf5dc86076ef8911622315ba83c (MD5) Previous issue date: 2015-02-27 / Financiadora de Estudos e Projetos / The high rate of growth and variety of information available on the Internet can overwhelm users, not leading them to the best decisions. In this context, social recommender systems play an important role on helping users against the effects of information overload. However, these systems need for data collection from its users social context motivates privacy concerns and may discourage its use. Thus, this dissertation presents a privacy negotiation model for social recommender systems to enable user to control his own privacy from the perspective of computer science. So, the user can decide to provide access to their data considering the personalization benefits that the system can offer him in exchange and is not forced to fully accept the privacy policies though. In this model, the privacy control is possible by means of a user interface design pattern using privacy negotiation techniques. The SocialRecSys social recommender system is an implementation of this model that was used in an evaluation with 32 users. The results showed that users are not satisfied with traditional interfaces and the model can better deal with the potentially different privacy preferences of each user. The results also indicated the high usability of the user interfaces of this model, which increase the flexibility of the systems regarding the configuration options of privacy preferences without harm the usage easiness of it. The implementation of this model shows that this is an alternative to reduce the concerns of privacy of social recommender systems users by increasing the flexibility and providing them a better understanding of the recommender systems. So users can feel encouraged to share their data in social recommender systems and take advantage of its personalization benefits. / A alta taxa de crescimento e variedade de informações disponíveis na Internet podem sobrecarregar os usuários, levando-os a não tomar as melhores decisões. Nesse contexto, os sistemas de recomendação social desempenham um importante papel ao auxiliar os usuários contra os efeitos da sobrecarga de informação. No entanto, a necessidade desses sistemas de coletar dados do contexto social dos seus usuários motiva preocupações de privacidade e pode desencorajar o seu uso. Assim, esta dissertação apresenta um modelo de negociação de privacidade para sistemas de recomendação social visando possibilitar ao usuário o controle de sua própria privacidade sob a perspectiva da ciência da computação. Desse modo o usuário pode decidir fornecer acesso aos seus dados considerando os benefícios de personalização que o sistema pode lhe oferecer em troca e ele não é obrigado a aceitar completamente as politicas de privacidade. Nesse modelo, o controle de privacidade é possível por meio de um padrão de projeto de interface de usuário que faz uso de técnicas de negociação de privacidade. O sistema de recomendação social SocialRecSys é uma implementação desse modelo e foi utilizado em uma avaliação com 32 usuários. Os resultados evidenciaram que os usuários não estão satisfeitos com as interfaces tradicionais e que o modelo apresentado pode tratar melhor as potencialmente diferentes preferências de privacidade de cada usuário. Os resultados também indicam a alta usabilidade das interfaces de usuário desse modelo. São interfaces que aumentam a flexibilidade dos sistemas em relação às opções de configuração de preferências de privacidade, sem tornar mais complexo o uso desses sistemas. A implementação do modelo proposto se mostra uma alternativa para reduzir as preocupações com privacidade dos usuários de sistemas de recomendação social, aumentando a flexibilidade e provendo aos usuários maior entendimento desses sistemas. Assim, os usuários podem se sentir encorajados a compartilhar seus dados com os sistemas de recomendação social e desfrutar de seus benefícios de personalização.

Made available in DSpace on 2016-06-02T19:07:09Z (GMT). No. of bitstreams: 1 BERBEL_Talita_2015.pdf: 2383674 bytes, checksum: 3c3c42908a145864cffb9aa42b7d45b7 (MD5) Previous issue date: 2015-03-23 / With the rapid growth of unstructured data, such as text documents, it becomes more and more interesting and necessary to extract such information to support decision making in business intelligence systems. Recommendations can be used in the OLAP process, because they allow users to have a particular experience in exploiting data. The process of recommendation, together with the possibility of query personalisation, allows recommendations to be increasingly relevant. The main contribution of this work is to propose an effective solution for semantic recommendation of documents through personalisation of OLAP aggregation queries in a data warehousing environment. In order to aggregate and recommend documents, we propose the use of semantic similarity. Domain ontology and the statistical measure of frequency are used in order to verify the similarity between documents. The threshold of similarity between documents in the recommendation process is adjustable and this is the personalisation that provides to the user an interactive way to improve the relevance of the results. The proposed case study is based on articles from PubMed and its domain ontology in order to create a prototype using real data. The results of the experiments are presented and discussed, showing that good recommendations and aggregations are possible with the suggested approach. The results are discussed on the basis of evaluation measures: precision, recall and F1-measure. / Com o crescimento do volume dos dados não estruturados, como os documentos de texto, torna-se cada vez mais interessante e necessário extrair informações deste tipo de dado para dar suporte à tomada de decisão em sistemas de Business Intelligence. Recomendações podem ser utilizadas no processo OLAP, pois permitem que os usuários tenham uma experiência diferenciada na exploração dos dados. O processo de recomendação, aliado à possibilidade da personalização das consultas dos usuários, tomadores de decisão, permite que as recomendações possam ser cada vez mais relevantes. A principal contribuição deste trabalho é a proposta de uma solução eficaz para a recomendação semântica de documentos mediante a personalização de consultas de agregação OLAP em um ambiente de Data Warehousing. Com o intuito de agregar e recomendar documentos propõe-se a utilização da similaridade semântica. A ontologia de domínio e a medida estatística de frequência são utilizadas com o objetivo de verificar a similaridade entre os documentos. O limiar de similaridade entre os documentos no processo de recomendação pode ser parametrizado e é esta a personalização que oferece ao usuário uma maneira interativa de melhorar a relevância dos resultados obtidos. O estudo de caso proposto se baseia em artigos da PubMed e em sua ontologia de domínio com o propósito de criar um protótipo utilizando dados reais. Os resultados dos experimentos realizados são expostos e analisados, mostrando que boas recomendações e agregações são possíveis utilizando a abordagem sugerida. Os resultados são discutidos com base nas métricas de avaliação: precision, recall e F1-measure.

Made available in DSpace on 2015-05-14T12:36:29Z (GMT). No. of bitstreams: 1 arquivototal.pdf: 2909809 bytes, checksum: 27b0cc11fa58c3080c9bf2558be74b71 (MD5) Previous issue date: 2011-08-22 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / Due to particular interactivy mode performed by TV services, engines are requeried that allow to retrieve informations beyond those provided directly. In this sense, context-aware applications use relevant informations to provide support in tasks execution. To develop these kind of applications presents challenges in context capture from heterogeneous sources, as sensors; by representation more adjusted to perform context-aware behavior; and to enable infer knowledges. This dissertation proposes an approach for content personalization of Interactive TV Applications by context handling. To this end, a context modelling was achieved to describe the user information and sports content information semantic in an integrated way and services were developed whose features provides support to context usage. / Graças ao modo peculiar de interatividade realizada por aplicativos na TV, são necessários mecanismos que possibilitem recuperar informações além daquelas fornecidas diretamente. Neste sentido, aplicações sensíveis ao contexto utilizam informações consideradas relevantes para fornecer suporte à realização de tarefas. Desenvolver aplicações desta natureza apresenta desafios quanto a captura de dados a partir de diferentes fontes, tais como sensores; quanto a representação mais adequada para realizar comportamento sensível ao contexto; e capacitar a inferência de conhecimentos. Este trabalho propõe uma abordagem para personalização do conteúdo de aplicações de TV Digital Interativa através da manipulação de informações de contexto. Para tanto, foi realizada a especificação de um modelo contextual que descreve semântica de informações do usuário e de conteúdo esportivo de maneira integrada, e foram desenvolvidos serviços cujas funcionalidades oferecem suporte ao uso de contexto.

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES / It has long been observed that new technologies have brought transformations to society and with it new ways of interacting and transmitting knowledge, as well as collaborating effectively with the teaching and learning processes. In this context, hybrid education emerges as an innovative practice in education, presenting a pedagogical approach that combines classroom activities with activities carried out through the technologies. In our research, we intend to demonstrate how this kind of teaching, which mixes the classroom with the virtual, adapting the conventional classroom to the new technologies, can be used in the personalization of teaching and learning actions. For that, we proposed to elaborate a set of activities based on the combination of face-to-face and online moments, starting with the poem Rapsódia Sergipana by Stella Leonardos, in order to resize the traditional methodology, and present a type of innovative learning which uses hybrid teaching, in the "rotation by seasons" model, to be worked with a class of Elementary School students in the EJA modality, IV stage (or 9th grade). In this hybrid lesson proposal, the poem Rapsódia Sergipana by Stella Leonardos, in addition to rescuing the Sergipe culture, will also serve as a basis for the construction of an example of a hybrid classroom where the teacher can contribute to the education of young people and adults. diversity of groups, and can put into practice the personalization of teaching, using new technologies, considering that today's society is seen as the information society, and in it the Internet establishes new forms of communication, it is up to the school to provide the this new generation tools to build new senses through virtuality. (MARCUSCHI, 2010). Authors and authors such as Stephanou and Bastos (2005), Lima and Moura (2015), Bacich (2015), and Christensen, Horn & Staker (2017), among others, integrate the theoretical basis of our approach. / Há muito se observa que as novas tecnologias trouxeram transformações à sociedade e com isso novas formas de interagir e de transmitir o conhecimento, além de colaborar efetivamente com os processos de ensino e aprendizagem. Nesse contexto o ensino híbrido desponta como uma prática inovadora na educação, apresentando uma abordagem pedagógica que combina atividades presenciais com atividades realizadas por meio das tecnologias. Em nossa pesquisa pretendemos demonstrar como esse tipo de ensino, que mescla o presencial com o virtual, adaptando a sala de aula convencional às novas tecnologias, pode ser utilizado na personalização das ações de ensino e de aprendizagem. Para isso, propusemos elaborar um conjunto de atividades a partir da combinação de momentos presenciais e on-line, que terá como ponto de partida o poema Rapsódia Sergipana de Stella Leonardos, a fim de redimensionar a metodologia tradicional, e apresentar um tipo de aprendizagem inovadora que se utiliza do ensino híbrido, no modelo de ―rotação por estações‖, para ser trabalhada com uma turma de estudantes do Ensino Fundamental na modalidade EJA, IV etapa, (ou 9º ano). Nessa proposta de aula híbrida, o poema Rapsódia Sergipana, de Stella Leonardos, além de resgatar a cultura sergipana também servirá como base para construção de um exemplo de aula híbrida em que o professor poderá contribuir para que a educação de jovens e adultos atenda sua grande diversidade de grupos, e possa colocar em prática a personalização do ensino, utilizando-se das novas tecnologias, visto que a sociedade atual é vista como a sociedade da informação, e nela a Internet estabelece novas formas de comunicação, cabe à escola proporcionar a essa nova geração ferramentas para construir novos sentidos através da virtualidade. (MARCUSCHI, 2010). Autores e autoras como Stephanou e Bastos (2005), Lima e Moura (2015), Bacich (2015), e Christensen, Horn & Staker (2017), entre outros/as, integram a base teórica de nossa abordagem. / Itabaiana, SE

La modélisation du système musculo-squelettique est un outil permettant l'amélioration des connaissances du fonctionnement biomécanique des structures ostéo-articulaires et musculo- tendineuses. Nos travaux de recherche portent sur le développement d'une méthodologie de modélisation personnalisée, volumique, déformable et à capacité contractile du système musculo- squelettique du membre inférieur, intégrant l'ensemble des outils, le plus possible automatisés, de construction (basée sur l'imagerie médicale), de simulation (en couplage avec un modèle multi-corps dynamique) et d'analyse (comme la cartographie des raideurs locales dans le muscle) nécessaires à leur mise en œuvre dans le cadre d'études orthopédiques / Musculo-skeletal modeling can update our knowledge concerning the biomechanical behavior of the osteoarticular and musculotendinous structures. This research work is focus on the development of methodology and tools for the generation of a personalized model of the lower limb musculoskeletal system, taking account of the deformable and contractile behavior of the muscles. This workflow automatically builds the model dataset (from medical imagery), performs the simulations (coupled with a multibody dynamic model), and offers specific analysis tools (as local stiffness mapping in the active muscle) required for various orthopedic studies