One of the most important challenges facing us today is to personalize services based on user preferences. In order to achieve this objective, the design of Recommender Systems (RSs), which are systems designed to aid the users through different decision-making processes by providing recommendations to them, have been an active area of research. RSs may produce personalized and non-personalized recommendations. Non-personalized RSs provide general suggestions to a user, based on the number of times an item has been selected in the past. Personalized RSs, on the other hand, aim to predict the most suitable items for a specific user, based on the user’s preferences and constraints. The latter are the focus of this thesis. While Recommender Systems have been successful in many domains, a number of challenges remain. For example, most implementations consider only single criteria ratings, and consequently are unable to identify why a user prefers an item over others. Many systems classify the user into one single group or cluster which is an unrealistic approach, since in real world users share commonalities in different degrees with diverse types of users. Others require a large amount of previously gathered data about users’ interactions and preferences, in order to be successfully applied. In this study, we introduce a methodology for the creation of Personalized Multi Criteria Context Aware Recommender Systems that aims to overcome these shortcomings. Our methodology incorporates the user’s current context information, and techniques from the Multiple Criteria Decision Analysis (MCDA) field of study to analyze and model the user preferences. To this end, we create a multi criteria user preference model to assess the utility of each item for a specific user, to then recommend the items with the highest utility. The criteria considered when creating the user preference model are the user’s location, mobility level and user profile. The latter is obtained by considering the user specific needs, and generalizing the user data from a large scale demographic database. We present a case study where we applied our methodology into PeRS, a personal Recommender System to recommend events that will take place within the Ottawa/Gatineau Region. Furthermore, we conduct an offline experiment performed to evaluate our methodology, as implemented in our case study. From the experimental results we conclude that our RS is capable to accurately narrow down, and identify, the groups from a demographic database where a user may belong, and subsequently generate highly accurate recommendation lists of items that match with his/her preferences. This means that the system has the ability to understand and typify the user. Moreover, the results show that the obtained system accuracy doesn’t depend on the user profile. Therefore, the system is potentially capable to produce equally accurate recommendations for a wide range of the population.

O desenvolvimento de conteúdos educacionais e a adoção de mecanismos de modelagem representam fatores importantes a serem considerados no contexto de ensino e aprendizagem. Nesse cenário, a utilização de ontologias proporciona vantagens tais como definção formal do conhecimento, reusabilidade e interoperabilidade de informações. Além disso, facilidades como recuperação dos objetos de aprendizagem, reúso do conteúdo de aprendizagem e personalização do conteúdo a partir do desempenho do usuário também são observadas. Diante disso, diversas aplicações com base em ontologias têm sido utilizadas tanto para modelar domínios educacionais como para construir, organizar e atualizar objetos de aprendizagem e perfis de aluno. Ainda, associado ao uso de ontologias em sistemas educacionais, verifica-se um crescente interesse na construção da personalização do conteúdo, de acordo com as preferências e características do usuário envolvendo a utilização de ontologias. O presente projeto está inserido nesse contexto, em que um conjunto de ontologias foi desenvolvido para prover a personalização do conteúdo, com base no perfil do usuário. Foi construído um exemplo na ontologia global (que compõe o conjunto de ontologias), em que o domínio de análise de ponto de função foi instanciado para três usuários com diferentes níveis de conhecimento. A ideia é elicitar a granularidade distinta do conteúdo para cada usuário, em conformidade com suas preferências e nível de conhecimento no domínio, a partir das relações e das inferências estabelecidas nas ontologias / The development of didactic material and adoption of modeling mechanisms represent important factors to be considered in the context teaching and learning. In this scenario, the use of ontologies provides advantages such as a formal definition of knowledge, reusability and interoperability of information. Moreover, facilities such as retrieval of learning objects, learning content reuse and customization of content from the user\'s performance are also observed. Therefore, several applications based on ontologies have been used to model so educational domains and to build, organize and update learning objects and student profiles. Also associated with the use of ontologies educational systems, there is an increasing interest in the personalization of the content, according to the user preferences and characteristics, involving the use of ontologies. This project is inserted in this context, where a set of ontologies was developed to provide the personalization of content based on user profile. We constructed an example in the ontology global (which defines the set of ontologies) in the domain of function point analysis was instantiated to three users with different levels of knowledge. The idea is to elicit the distinct granularity of the content for each learner, in accordance with their preferences and level of knowledge in the domain, from the relationships and inferences in the ontologies

付記する学位プログラム名: デザイン学大学院連携プログラム / 京都大学 / 0048 / 新制・課程博士 / 博士(情報学) / 甲第22577号 / 情博第714号 / 新制||情||122(附属図書館) / 京都大学大学院情報学研究科社会情報学専攻 / (主査)教授 緒方 広明, 教授 守屋 和幸, 教授 黒田 知宏 / 学位規則第4条第1項該当 / Doctor of Informatics / Kyoto University / DFAM

This thesis presents principles of transmission of digital television broadcasting via satellite placed in orbit of Earth. It also focuses on the satellite receiver as an important part of satellite systems. It mention receiver’s firmware and deals with design and implementation of satellite receiver’s application.  The aim is to create an application that will personalize satellite receiver by monitoring TV stations that have been watched.

El siguiente trabajo de investigación ha sido desarrollado con la finalidad de disminuir el impacto negativo que la alta exposición y uso de dispositivos tecnológicos tiene en los niños. Doggy & Friends soluciona este problema ofreciendo una alternativa de entretenimiento sana para los niños mediante el juego con un peluche que pueden personalizar totalmente, de acuerdo con sus gustos. Esta actividad les permite compartir tiempo con su familia, reforzando los lazos que mantienen, rellenando, vistiendo y caracterizando a su peluche en miles de aventuras gracias a su creatividad e imaginación, convirtiendo a Doggy en un amigo importante que lo acompañará en los momentos especiales de su vida. El mercado de entretenimiento infantil en el Perú es atractivo debido a su crecimiento constante, tanto en consumo, como en tamaño. Así mismo, de acuerdo con las validaciones de producto realizadas, se ha encontrado que 4 de cada 100 leads es una venta; dato con el cual se pueden asegurar atractivos márgenes de ganancia para la compañía y sus inversores con un tamaño de mercado más de 2 millones de familias y un crecimiento anual esperado de 2.4%. Este proyecto, después de un análisis financiero detallado, ofrece a los inversionistas un valor presente neto de s/.1’853,166, a una tasa de retorno del 88.46%. No obstante, a un horizonte de 5 años, el valor presente neto estimado supera los S/. 235,000 soles a una tasa de retorno mayor del 45%, tras una inversión aproximada de s/.100,000. / The following research paper has been developed with the purpose of diminishing the negative impact of high exposure and usage of technological devices on children. Doggy & Friends solves this problem by offering a healthy entertainment alternative for children through a teddy that they can personalize to their taste. This activity allows them to spend time with their family, strengthening their bond, by filling, dressing and characterizing their teddy in thousands of adventures thanks to their creativity and imagination, turning Doggy into an important friend that will be there in the most special time of their life. The children entertainment market in Peru is attractive due to its continued growth, regarding consumption and size. Furthermore, according to the product validation made, it has been found that 4 in every 100 leads turns into a sale. This data assures attractive benefits for the company and its investors with a market size of more than 2 million families and an expected growth rate of more than 2.4%. This project, after a detailed analysis, offers investors a net present value of s/.1’853,166, with a return rate of 88.46%. However, to a 5 years investment horizon, the net present value is over s/. 235,000 soles with a return rate higher than 45%, to an approximate investment of s/.100,000. / Trabajo de investigación

Home rehabilitation training has become an important part for patients to recover and maintain physical conditions due to the high health care cost and limited supervision in the clinic. Various technologies have been designed for assisting rehabilitation training but most of them are not able to provide personalized feedback and support according to different standards of patients’ physical condition and movement capability. The thesis aims to explore what information provided by the technology would be helpful for personalizing rehabilitation by incorporating interactive machine learning as part of a large research project, which has been discussed as an effective tool in motion interaction design to build conversation and provide personalized information. The participatory design methodology was conducted with bodystorming and role-playing approach in the workshops to collect people’s opinions on the role of technology, the design requirements and the way to present personalized feedback in rehabilitation training. The author collaborated with the research group to apply thematic analysis in the analysis of the workshop videos and drew the design spaces for future interaction design including three roles to integrate technology, five design concepts and some design takeaways to present feedback. Two interactive prototypes were envisioned based on the analysis result as an explorative design to incorporate the interplay between patients and machine learning in rehabilitation training.

A growing number of information retrieval applications rely on search behavior aggregated over many users. If aggregated data such as search query reformulations is not handled properly, it can allow users to be identified and their privacy compromised. Besides leveraging aggregate data, it is also common for applications to make use of user-specific behavior in order to provide a personalized experience for users. Unlike aggregate data, privacy is not an issue in individual personalization since users are the only consumers of their own data. The goal of this work is to explore the effects of personalization and privacy preservation methods on three information retrieval applications, namely search task identification, task-aware query recommendation, and searcher frustration detection. We pursue this goal by first introducing a novel framework called CrowdLogging for logging and aggregating data privately over a distributed set of users. We then describe several privacy mechanisms for sanitizing global data, including one novel mechanism based on differential privacy. We present a template for describing how local user data and global aggregate data are collected, processed, and used within an application, and apply this template to our three applications. We find that sanitizing feature vectors aggregated across users has a low impact on performance for classification applications (search task identification and searcher frustration detection). However, sanitizing free-text query reformulations is extremely detrimental to performance for the query recommendation application we consider. Personalization is useful to some degree in all the applications we explore when integrated with global information, achieving gains for search task identification, task-aware query recommendation, and searcher frustration detection. Finally we introduce an open source system called CrowdLogger that implements the CrowdLogging framework and also serves as a platform for conducting in-situ user studies of search behavior, prototyping and evaluating information retrieval applications, and collecting labeled data.

No description available.

I have in this project studied the area of personalized design as a way to create stronger bounds between artifacts and user. The way we relate to what we surround us with is important when we want to expose our personalities and tell who we really are. Today, in a world of mass-production, design and production seldom occurs at the same place. It feels like we are gliding away from the way we were connected to our things in the past. When we needed new cupboards for the kitchen, we went to the local carpenter and let him design and produce what we needed. The clothes were brought from travelling vendors, produced in the village or made by someone in your family, often with self-made yarn from the family farm’s sheep. We often had a connection to what we owned in another way than today. People knew exactly where their possessions came from, what material had been used and where that material had grown.I have within this project investigated how to create that personal connection to an artifact and adapt it to the contemporary. To achieve this I have looked into the different kinds of invisible information that our bodies contain. Information that is produced by numerous processes all the time, which we may not think about. I’ve been studying how people react when their inner processes are visualized through usage tests, exhibitions and finally interviews. The result is a concept I call Emotional Artifacts. The concept is describing how the idea of personalized fashion can be realized. A prototype has been built to show some of the possibilities with this kind of design that, with certain rules and ground sets, is generated by the user and later applied to different media.

Social networking sites are channels that allow companies to appeal to their target audience through personalized advertising which has become an increasingly common way for companies to reach their target customers. Personalization is possible through the use of customer data which allows designing an advertisement based on individual consumers' preferences benefiting the consumers with more personally appealing advertisements. However, the collection of the data has led to consumers’ experiencing costs from the personalization involving concerns for the safety of personal information. Because of the tension between benefits and costs of personalization, consumers' behavior has become paradoxical. The consumers’ behaviour does not always correspond to their concerns by which the consumers trade off their privacy to receive benefits from the personalization in return. With that said, this study aims to explore how the personalization privacy paradox appears in the consumers’ response to personalized advertisements on social networking sites by assessing their perception of the benefits and costs of personalized advertisements. Semi-structured interviews of eight participants lead to the main findings of this research identifying four factors that have an impact on consumers’ interaction with the advertisement; (1) simplified purchase decisions, (2) personal interest, (3) personal gain, and (4) trustworthiness. In addition, the research revealed additional findings indicating that consumers' concern for data collection could be changing from privacy risks regarding themselves to concerns about the consequence of data collection on a societal level. Furthermore, the findings show an indication for an emerging dilemma of personalized advertising for companies to overcome. Finally, this research provides implications for both academia as well as practitioners.