We address the challenge of providing low-cost, universal access of useful information to people in different parts of the globe. We achieve this by following two strategies. First, we focus on the delivery of information through computerized devices and prototype new methods for making that delivery possible in a secure, low-cost, and universal manner. Second, we focus on the use of participatory media, such as blogs, in the context of news related content, and develop methods to recommend useful information that will be of interest to users. To achieve the first goal, we have designed a low-cost wireless system for Internet access in rural areas, and a smartphone-based system for the opportunistic use of WiFi connectivity to reduce the cost of data transfer on multi-NIC mobile devices. Included is a methodology for secure communication using identity based cryptography. For the second goal of identifying useful information, we make use of sociological theories regarding social networks in mass-media to develop a model of how participatory media can offer users effective news-related information. We then use this model to design a recommender system for participatory media content that pushes useful information to people in a personalized fashion. Our algorithms provide an order of magnitude better performance in terms of recommendation accuracy than other state-of-the-art recommender systems. Our work provides some fundamental insights into the design of low-cost communication systems and the provision of useful messages to users in participatory media through a multi-disciplinary approach. The result is a framework that efficiently and effectively delivers information to people in remote corners of the world.

隨著資訊科技的發展，網際網路成為個人獲得資訊的主要來源之一。但是過多的資訊產生資訊爆炸(information overload)的現象，人們除了要在眾多資訊中找尋想要的資訊外，還需要擔心所尋找到的資訊的品質是否良好。因此，推薦系統提供了一個良好的解決方法。推薦系統透過分群與推薦的技術來達到減少資訊量與推估使用者潛在興趣的目的。目前推薦系統多應用在單一維度的推薦，本論文希望藉由某一情境來探討多維度推薦的應用，所以選擇助理軟體來實現多維度推薦的應用。選擇助理軟體是由於其已經成為個人日常生活中時常使用的工具，且由於助理軟體管理個人日常生活中的大小事務，成為最貼近個人的工具。若專注在個人行事曆的安排上，我們可以發現個人行事曆安排牽涉到有人、事、時、地、物五個維度。因此我們以五維度做分群，透過合作推薦(Collaborative Recommender)的方式將可以達到個人潛在興趣的多維度(Multi-Dimensions)推薦。本研究將以行事歷排定為情境，來說明如何將五個維度的各種可能組合依照其契合個人興趣的程度來進行推薦，這將使得助理軟體的內容更加豐富，且能貼近使用者的需求，提供意想不到的資訊組合。 / With the development of information science and technology, assistant software becomes a tool which often uses in personal daily life, and because all kinds of affairs in personal daily life that assistant software is managed, so assistant software becomes a tool which personally close to people. Intelligent assistant software hopes to make assistant software have intelligence which is similar to the mankind. Just like a personal general secretary, arrange the most proper individualized journey. Further, it can combine the idea of Recommender system to recommend the journey of the potential interest while arranging in the personal journey. This research proposes an intelligent assistant software with five- dimensions include of people, thing, when, location and things, uses cooperative Recommender approach to reach multi-dimension recommendation of personal potential interest. This research will give example of meeting as the situation to explain how to make five-dimensions recommendation according to personal interest. This will make the content of assistant software more abundant, and can press close to the user's demand.

Chaque année, le nombre d’utilisateurs des réseaux sociaux augmente à une très grande vitesse. Des milliers de comptes usagés incluant des données privées sont créés quotidiennement. Un nombre incalculable de données privées et d'informations sensibles sont ainsi lues et partagées par les différents comptes. Ceci met en péril la vie privée et la sécurité de beaucoup d’utilisateurs de ces réseaux sociaux. Il est donc crucial de sensibiliser ces utilisateurs aux dangers potentiels qui les guettent. Nous présentons Protect_U (Hélou, Gandouz et al. 2012), un système de protection de la vie privée des utilisateurs de Facebook. Protect_U analyse le contenu des profils des utilisateurs et les classes selon quatre niveaux de risque : Low risk, medium risk, risky and critical. Il propose ensuite des recommandations personnalisées pour leur permettre de rendre leurs comptes plus sécuritaires. Pour ce faire, il fait appel à deux modèles de protection : local et communautaire. Le premier utilise les données personnelles de l’utilisateur afin de lui proposer des recommandations et le second recherche ses amis de confiance pour les inciter à participer à l’amélioration de la sécurité de son propre compte. / Social networking sites have experienced a steady and dramatic increase in the number of users over the past several years. Thousands of user accounts, each including a significant amount of private data, are created daily. As such, an almost countless amount of sensitive and private information is read and shared across the various accounts. This jeopardizes the privacy and safety of many social network users and mandates the need to increase the users’ awareness about the potential hazards they are exposed to on these sites. We introduce Protect_U (Hélou, Gandouz et al. 2012), a privacy protection system for Facebook users. Protect_U analyzes the content of user profiles and ranks them according to four risk levels: Low Risk, Medium Risk, Risky and Critical. The system then suggests personalized recommendations designed to allow users to increase the safety of their accounts. In order to achieve this, Protect_U draws upon both the local and community-based protection models. The first model uses a Facebook user’s personal data in order to suggest recommendations, and the second seeks out the user’s most trustworthy friends to encourage them to help improve the safety of his/her account. / Article publié dans le journal « Journal of Information Security Research ». March 2012.

Sistemas de recomendação fazem parte do nosso dia-a-dia. Os métodos usados nesses sistemas tem como objetivo principal predizer as preferências por novos itens baseado no perĄl do usuário. As pesquisas relacionadas a esse tópico procuram entre outras coisas tratar o problema do cold-start do usuário, que é o desaĄo de recomendar itens para usuários que possuem poucos ou nenhum registro de preferências no sistema. Uma forma de tratar o cold-start do usuário é buscar inferir as preferências dos usuários a partir de informações adicionais. Dessa forma, informações adicionais de diferentes tipos podem ser exploradas nas pesquisas. Alguns estudos usam informação social combinada com preferências dos usuários, outros se baseiam nos clicks ao navegar por sites Web, informação de localização geográĄca, percepção visual, informação de contexto, etc. A abordagem típica desses sistemas é usar informação adicional para construir um modelo de predição para cada usuário. Além desse processo ser mais complexo, para usuários full cold-start (sem preferências identiĄcadas pelo sistema) em particular, a maioria dos sistemas de recomendação apresentam um baixo desempenho. O trabalho aqui apresentado, por outro lado, propõe que novos usuários receberão recomendações mais acuradas de modelos de predição que já existem no sistema. Nesta tese foram propostas 4 abordagens para lidar com o problema de cold-start do usuário usando modelos existentes nos sistemas de recomendação. As abordagens apresentadas trataram os seguintes aspectos: o Inclusão de informação social em sistemas de recomendação tradicional: foram investigados os papéis de várias métricas sociais em um sistema de recomendação de preferências pairwise fornecendo subsidíos para a deĄnição de um framework geral para incluir informação social em abordagens tradicionais. o Uso de similaridade por percepção visual: usando a similaridade por percepção visual foram inferidas redes, conectando usuários similares, para serem usadas na seleção de modelos de predição para novos usuários. o Análise dos benefícios de um framework geral para incluir informação de redes de usuários em sistemas de recomendação: representando diferentes tipos de informação adicional como uma rede de usuários, foi investigado como as redes de usuários podem ser incluídas nos sistemas de recomendação de maneira a beneĄciar a recomendação para usuários cold-start. o Análise do impacto da seleção de modelos de predição para usuários cold-start: a última abordagem proposta considerou que sem a informação adicional o sistema poderia recomendar para novos usuários fazendo a troca entre os modelos já existentes no sistema e procurando aprender qual seria o mais adequado para a recomendação. As abordagens propostas foram avaliadas em termos da qualidade da predição e da qualidade do ranking em banco de dados reais e de diferentes domínios. Os resultados obtidos demonstraram que as abordagens propostas atingiram melhores resultados que os métodos do estado da arte. / Recommender systems are in our everyday life. The recommendation methods have as main purpose to predict preferences for new items based on userŠs past preferences. The research related to this topic seeks among other things to discuss user cold-start problem, which is the challenge of recommending to users with few or no preferences records. One way to address cold-start issues is to infer the missing data relying on side information. Side information of different types has been explored in researches. Some studies use social information combined with usersŠ preferences, others user click behavior, location-based information, userŠs visual perception, contextual information, etc. The typical approach is to use side information to build one prediction model for each cold user. Due to the inherent complexity of this prediction process, for full cold-start user in particular, the performance of most recommender systems falls a great deal. We, rather, propose that cold users are best served by models already built in system. In this thesis we propose 4 approaches to deal with user cold-start problem using existing models available for analysis in the recommender systems. We cover the follow aspects: o Embedding social information into traditional recommender systems: We investigate the role of several social metrics on pairwise preference recommendations and provide the Ąrst steps towards a general framework to incorporate social information in traditional approaches. o Improving recommendation with visual perception similarities: We extract networks connecting users with similar visual perception and use them to come up with prediction models that maximize the information gained from cold users. o Analyzing the beneĄts of general framework to incorporate networked information into recommender systems: Representing different types of side information as a user network, we investigated how to incorporate networked information into recommender systems to understand the beneĄts of it in the context of cold user recommendation. o Analyzing the impact of prediction model selection for cold users: The last proposal consider that without side information the system will recommend to cold users based on the switch of models already built in system. We evaluated the proposed approaches in terms of prediction quality and ranking quality in real-world datasets under different recommendation domains. The experiments showed that our approaches achieve better results than the comparison methods. / Tese (Doutorado)

Made available in DSpace on 2016-08-17T14:52:39Z (GMT). No. of bitstreams: 1 Heider Cristian Moura Quintao.pdf: 4191526 bytes, checksum: 3053fbdd9113f05514fce93fc176aa9e (MD5) Previous issue date: 2008-02-15 / When equipment failure occur in complex industrial plants, the automation and control system generates a great amount of alarms that can confuse the operators and lead them to take wrong decisions - the time for decision taking is very short and the amount of generated information is higher, being impossible for the operator read all of them before taking the correct decision. The new industrial systems have presented functionalities that try to minimize this deficiency presenting some support to the user, but still in an inefficient form. This work presents a proposal of an Alarm Management System based on Action Recommendation - SIGARA, a knowledge-based tool which aims supporting users of industrial control systems, when abnormal events occur. SIGARA is an action recommender multi-agent system, shaped on the basis of the described tasks and phases of the ONTORMAS ontology and MAAEM methodology. Beyond searching the solution of a problem of the real world in the industries, the proposed SIGARA presents some additional features not present on existing systems, as the application of information filtering techniques in different processing phases, and also the use of MAAEM and ONTORMAS in this new domain. / Quando ocorrem falhas de equipamentos em plantas industriais complexas, o sistema de automação e controle gera uma grande quantidade de alarmes que podem confundir os operadores e induzi-los a tomar decisões erradas. O tempo para a tomada de decisão é muito curto e a quantidade de informação gerada é muito grande, sendo impossível que o operador consiga ler todas antes de tomar a decisão correta. Os novos sistemas industriais têm apresentado funcionalidades que buscam minimizar essa deficiência apresentando algum suporte ao usuário, mas ainda de forma ineficiente. O presente trabalho apresenta como proposta um Sistema Informatizado de Gerenciamento de Alarmes baseado na Recomendação de Ações (SIGARA). É uma ferramenta baseada em conhecimento que objetiva suportar usuários de sistemas industriais de automação e controle, quando da ocorrência de alguma anomalia. O SIGARA é um sistema multiagente de recomendação de ações, modelado com base nas tarefas e fases descritas na ontologia ONTORMAS ( Ontology for Reusing Multi-agent Software ), conforme a metodologia MAAEM ( Multi-Agent Application Engineering Methodology ). Além de buscar a solução de um problema do mundo real presente nas indústrias, o SIGARA proposto apresenta alguns diferenciais frente aos existentes no mercado, como o uso de técnicas de filtragem de informação em várias etapas do processamento das informações, e também a aplicação da MAAEM e ONTORMAS que ainda não haviam sido utilizadas nesse domínio.

Manual data exploration in data cubes and searching for potentially interesting and useful information starts to be time-consuming and ineffective from certain volume of the data. In my thesis, I designed, implemented and tested a system, automating the data cube exploration and offering potentially interesting views on OLAP data to the end user. The system is based on integration of two data analytics methods - OLAP analysis data visualisation and data mining, represented by GUHA association rules mining. Another contribution of my work is a research of possibilities how to solve differences between OLAP analysis and association rule mining. Implemented solutions of the differences include data discretization, dimensions commensurability, design of automatic data mining task algorithm based on the data structure and mapping definition between mined association rules and corresponding OLAP visualisation. The system was tested with real retail sales data and with EU structural funds data. The experiments proved that complementary usage of the association rule mining together with OLAP analysis identifies relationships in the data with higher success rate than the isolated use of both techniques.

This thesis deals with the field of Recommendation systems using Deep Neural Networks and their use in book recommendation. There are the main traditional recommender systems analysed and their representations are summarized, as well as systems with more advancec techniques based on machine learning.. The core of the thesis is the use of convolutional neural networks for natural language processing and the creation of a book recommendation system. Suggested system make recommendation based on user data, including user reviews and book data, including full texts.

No description available.

No description available.

Depuis ses fondements, le domaine de l’Interaction Homme-Machine (IHM) est marqué par le souci constant de concevoir et de produire des systèmes numériques utiles et utilisables, c’est-à-dire adaptés aux utilisateurs dans leur contexte. Vu le développement exponentiel des recherches dans les IHM, deux états des lieux s’imposent dans les environnements en ligne : le concept de confiance et le comportement de l’usager. Ces deux états ne cessent de proliférer dans la plupart des solutions conçues et sont à la croisée des travaux dans les interfaces de paiements en ligne et dans les systèmes de recommandation. Devant les progrès des solutions conçues, l’objectif de cette recherche réside dans le fait de mieux comprendre les différents enjeux dans ces deux domaines, apporter des améliorations et proposer de nouvelles solutions adéquates aux usagers en matière de perception et de comportement en ligne. Outre l’état de l’art et les problématiques, ce travail est divisé en cinq parties principales, chacune contribue à mieux enrichir l’expérience de l’usager en ligne en matière de paiement et recommandations en ligne : • Analyse des multi-craintes en ligne : nous analysons les différents facteurs des sites de commerce électronique qui influent directement sur le comportement des consommateurs en matière de prise de décision et de craintes en ligne. Nous élaborons une méthodologie pour mesurer avec précision le moment où surviennent la question de la confidentialité, les perceptions en ligne et les craintes de divulgation et de pertes financières. • Intégration de personnalisation, contrôle et paiement conditionnel : nous proposons une nouvelle plateforme de paiement en ligne qui supporte à la fois la personnalisation et les paiements multiples et conditionnels, tout en préservant la vie privée du détenteur de carte. • Exploration de l’interaction des usagers en ligne versus la sensibilisation à la cybersécurité : nous relatons une expérience de magasinage en ligne qui met en relief la perception du risque de cybercriminalité dans les activités en ligne et le comportement des utilisateurs lié à leur préoccupation en matière de confidentialité. • Équilibre entre utilité des données et vie privée : nous proposons un modèle de préservation de vie privée basé sur l’algorithme « k-means » et sur le modèle « k-coRating » afin de soutenir l’utilité des données dans les recommandations en ligne tout en préservant la vie privée des usagers. • Métrique de stabilité des préférences des utilisateurs : nous ciblons une meilleure méthode de recommandation qui respecte le changement des préférences des usagers par l’intermédiaire d’un réseau neural. Ce qui constitue une amélioration à la fois efficace et performante pour les systèmes de recommandation. Cette thèse porte essentiellement sur quatre aspects majeurs liés : 1) aux plateformes des paiements en ligne, 2) au comportement de l’usager dans les transactions de paiement en ligne (prise de décision, multi-craintes, cybersécurité, perception du risque), 3) à la stabilité de ses préférences dans les recommandations en ligne, 4) à l’équilibre entre vie privée et utilité des données en ligne pour les systèmes de recommandation. / Technologies in Human-Machine Interaction (HMI) are playing a vital role across the entire production process to design and deliver advanced digital systems. Given the exponential development of research in this field, two concepts are largely addressed to increase performance and efficiency of online environments: trust and user behavior. These two extents continue to proliferate in most designed solutions and are increasingly enriched by continuous investments in online payments and recommender systems. Along with the trend of digitalization, the objective of this research is to gain a better understanding of the various challenges in these two areas, make improvements and propose solutions more convenient to the users in terms of online perception and user behavior. In addition to the state of the art and challenges, this work is divided into five main parts, each one contributes to better enrich the online user experience in both online payments and system recommendations: • Online customer fears: We analyze different components of the website that may affect customer behavior in decision-making and online fears. We focus on customer perceptions regarding privacy violations and financial loss. We examine the influence on trust and payment security perception as well as their joint effect on three fundamentally important customers’ aspects: confidentiality, privacy concerns and financial fear perception. • Personalization, control and conditional payment: we propose a new online payment platform that supports both personalization and conditional multi-payments, while preserving the privacy of the cardholder. • Exploring user behavior and cybersecurity knowledge: we design a new website to conduct an experimental study in online shopping. The results highlight the impact of user’s perception in cybersecurity and privacy concerns on his online behavior when dealing with shopping activities. • Balance between data utility and user privacy: we propose a privacy-preserving method based on the “k-means” algorithm and the “k-coRating” model to support the utility of data in online recommendations while preserving user’s privacy. • User interest constancy metric: we propose a neural network to predict the user’s interests in recommender systems. Our aim is to provide an efficient method that respects the constancy and variations in user preferences. In this thesis, we focus on four major contributions related to: 1) online payment platforms, 2) user behavior in online payments regarding decision making, multi-fears and cyber security 3) user interest constancy in online recommendations, 4) balance between privacy and utility of online data in recommender systems.