Made available in DSpace on 2016-06-02T19:05:37Z (GMT). No. of bitstreams: 1 2131.pdf: 8350502 bytes, checksum: 4dc12e822d8a4aeea41a8ba2b85769f2 (MD5) Previous issue date: 2008-08-22 / Financiadora de Estudos e Projetos / The development of technologies that assist in the teach-learning process is an rgued subject in some areas of knowledge. The great diffusion of Web-based Educational Systems (WbE-S) has been shown the popularization of distance learning and its support tools. The Tidia-Ae project, support by FAPESP, aim at the development of a WbE-S that can use the concept about high velocity internet. But, the WbE Systems don t have a personal treatment of user s necessities. So, the offers of personalization resources for systems aim at improving the teach-learning process using the treatment of real necessities of each user. The content recommendation, more specifically a recommendation system, is one of several techniques for that and it is a non-intrusive meaning of help user s in a system with a lot of information. This technique was used in Tidia-Ae environment to development of this thesis. This thesis presents the I2P model based on metrics of Interests, Preferences and Popularity which are acquired by the measuring of the relationship of users and system resources. These metrics provide a form to calculate the recommendation offers of resources. The calculation is done using Collaborative Filtering technique and the personalization is offered in collaborative form, considering the group learning. / O desenvolvimento de tecnologias que auxiliem no processo de ensinoaprendizagem é assunto discutido em várias áreas do conhecimento. A grande difusão de Sistemas Educacionais baseados nas tecnologias existentes na Web (também chamados de Sistemas Educacionais baseados na Web Web-based Educational Systems WbE-S) demonstra a popularização da educação a distância e das ferramentas de suporte a esta. O projeto Tidia-Ae, financiado pela FAPESP visa, sobretudo, o desenvolvimento de um WbE-S que possa explorar os conceitos da internet de alta velocidade. Os WbE-S, comumente, não possuem um tratamento personalizado das ações dos usuários no sistema. Assim, a oferta de recursos de personalização de sistemas visa melhorias no processo de ensino-aprendizagem através do tratamento das necessidades reais e pessoais de cada aluno. A recomendação de conteúdo é uma das possíveis técnicas para oferta de personalização. Trata-se de uma forma não intrusiva de auxiliar o processo de escolha dos usuários num sistema com grande conjunto de informações. Está técnica foi amplamente explorada e, junto com o projeto Tidia-Ae, serviu como base para a criação do modelo I2P. Este trabalho define e propõe o modelo I2P baseado em métricas de Interesses, Preferências e Popularidade obtidas no relacionamento entre os usuários e os recursos do sistema. Estas métricas fornecem o embasamento para oferta de recursos adequados às necessidades dos usuários num WbE-S. O cálculo para oferta de recomendação é realizado com a técnica de Filtragem Colaborativa e, assim, a personalização é oferecida de forma colaborativa, considerando o aprendizado em grupo.

The rise of disruptive technologies and the rapid growth of innovative initiatives have led to a trend of decentralization, deregulation, and distribution of regulated/centralized services. As a result, there is an increasing number of requests for the connection of distributed generators to distribution networks and the need for power utilities to quickly assess the impacts of distributed generators (DGs) to keep up with these requests. Grid integration of DGs brings about protection issues. Current protection systems were not designed for bi-directional power flow, thus the protective devices in the network lose their ability to perform their main functions. To mitigate the impact of distributed generation (DG), some standards and policies constrain the number of DG that can be connected to the distribution network. The problem with these limits is that they are based only on overload and overvoltage, and do not adequately define the DG size/threshold before the occurrence of a protection issue (NRS 097-2-3). The other problem with distributed generation is the vast difference in the technology, location, size, connection sequence, and protection scheme requirements which results in future DG network planning inadequacies – The Network DG Planning Dilemma. To determine the amount of DG to connect to the network, a detailed analysis is required which often involves the use of a simulation tool such as DIgSILENT to model the entire network and perform load flow studies. Modelling networks on DIgSILENT is relatively easy for simple networks but becomes time-consuming for complex, large, and real networks. This brings about a limitation to this method, planning inadequacies, and longer connection approval periods. Thus, there is a need for a fast but accurate system-wide tool that can assess the amount of DG that can be connected to a network. This research aims to present a technique used for calculating protection-based DG penetration limits on MV networks and develop a model to determine medium voltage opportunity network maps. These maps indicate the maximum amount of DG that can be connected to a network without the need for major protection scheme changes in South Africa. The approach to determining protection-based penetration limits is based on supervised machine learning methods. The aim is to rely on protection features present in the distribution network data i.e. fault level, Inverse Definite Minimum Time (IDMT) curve, pick-up current settings, Time Multiplier Settings (TMS), calculated relay operating times and relay positions to see how the network responds at certain DG penetration levels (‘actual' relay operating times). The dataset represents carefully anonymized distribution networks with accepted protection philosophy applied. A supervised machine learning algorithm is applied after nontrivial data pre-processing through recommendation systems and shuffling. The planning dilemma is cast into three parts: the first part is an automated pattern classification (logistic regression for classification of protection miscoordination), the second part involves regression (predicting operating time after different levels of DG penetration), and the last part involves developing a recommendation system (where, when and how much photovoltaic (PV) DG will be connected). Gradient descent, which is an optimisation algorithm that iterates and finds optimal values of the parameters that correspond to the local or global minimum values of the cost function using calculus was used to measure the accuracy of each model's hypothesis function. The cost function (one half mean squared error) for the models that predict ‘actual' relay operating times before DG penetration, at 35%, 65%, and 75% DG penetration converged to values below 120, 20, 15, and 15 seconds2 , respectively, within the first 100 iterations. A high variance problem was observed (cross-validation error was high and training error was low) for the models that used all the network protection features as inputs. The cross-validation and training errors approached the desired performance of 0.3±0.1 for the models that had second-order polynomials added. A training accuracy of 91.30%, 73.91%, 82.61%, and a validation accuracy of 100%, 55.56%, 66.67% was achieved when classifying loss of coordination, loss of grading and desensitization, respectively. A high bias problem was observed (cross-validation error was high and training error was high) for the loss of grading classification (relay positions eliminated) model. When the models (horizontal network features) were applied to four MV distribution networks, loss of coordination was not predicted, the loss of grading model had one false positive and the de-sensitization model had one false negative. However, when the results were compared to the vertical analysis (comparing the operating times of upstream and downstream relays/reclosers), 28 points indicated a loss of coordination (2 at 35%, 1 at 65% and 25 at 75% DG penetration). Protection coordination reinforcements (against loss of grading and desensitization) were found to be a requirement for DG connections where the MV transformer circuit breaker TMS is between 0.5 and 1.1, and where the network fault level is between 650 and 800A. Distribution networks in affluent neighbourhoods similar to those around the Western CapeSomerset West area and Gauteng- Centurion area need to be reinforced to accommodate maximum DG penetration up to the limit of 75% of the After Diversity Maximum Demand (ADMD). For future work, the collection of more data points (results from detailed analytical studies on the impact of DG on MV feeders) to use as training data to solve the observed high variance problem is recommended. Also, modifying the model by adding upstream and downstream network features as inputs in the classification model to solve the high bias problem is recommended.

As society progresses towards a more algorithmic era, the influence of artificial intelligence (AI) is driving a revolution in the digital landscape. At its core, AI applications aim to engage customers by providing carefully tailored and data-driven personalization and customization of products, services, and marketing mix elements. However, the adoption of AI, while promising enhanced personalization, poses challenges due to the increased collection, analysis, and control of consumer data by technology owners. Consequently, concerns over data privacy have emerged as a primary consideration for individuals. This paper delves deeper into the implications of the personalization- privacy paradox, aiming to provide a comprehensive analysis of the challenges and opportunities it presents. The purpose of this thesis is to understand users’ privacy concerns and willingness to disclose their personal information to AI technologies by addressing the limitations of previous research and utilizing qualitative methods to gain a more in-depth understanding of consumer views. To understand users’ privacy concerns and willingness to disclose personal information to AI technologies, a qualitative approach was followed. Combining a deductive and inductive approach to fulfill the purpose of the study, empirical data was collected through 20 semi- structured interviews. The participants were chosen using a purposive sampling technique. Users’ privacy concerns and willingness to disclose personal information to AI technologies differ significantly. It depends not only on the individual, but also on the type of AI technology, the company providing the AI technology, the possibility of obtaining additional benefits, and whether the company is transparent about its data collection and can provide proof of security.

Although they clearly exist, affinities among individuals are not all easily identified. Yet, they offer unique opportunities to discover new social networks, strengthen ties among individuals, and provide recommendations. We propose the idea of Implicit Affinity Networks (IANs) to build, visualize, and track affinities among groups of individuals. IANs are simple, interactive graphical representations that users may navigate to uncover interesting patterns. This thesis describes a system supporting the construction of IANs and evaluates it in the context of family history and online communities.

Automated systems for producing product recommendations to users is a relatively new area within the field of machine learning. Matrix factorization techniques have been studied to a large extent on data consisting of explicit feedback such as ratings, but to a lesser extent on implicit feedback data consisting of for example purchases.The aim of this study is to investigate how well matrix factorization techniques perform compared to other techniques when used for producing recommendations based on purchase data. We conducted experiments on data from an online bookstore as well as an online fashion store, by running algorithms processing the data and using evaluation metrics to compare the results. We present results proving that for many types of implicit feedback data, matrix factorization techniques are inferior to various neighborhood- and association rules techniques for producing product recommendations. We also present a variant of a user-based neighborhood recommender system algorithm \textit{(UserNN)}, which in all tests we ran outperformed both the matrix factorization algorithms and the k-nearest neighbors algorithm regarding both accuracy and speed. Depending on what dataset was used, the UserNN achieved a precision approximately 2-22 percentage points higher than those of the matrix factorization algorithms, and 2 percentage points higher than the k-nearest neighbors algorithm. The UserNN also outperformed the other algorithms regarding speed, with time consumptions 3.5-5 less than those of the k-nearest neighbors algorithm, and several orders of magnitude less than those of the matrix factorization algorithms.

Made available in DSpace on 2016-04-04T18:31:34Z (GMT). No. of bitstreams: 1 Alan Menk dos Santos.pdf: 6433244 bytes, checksum: d8118b5fa4198a1f3792738316afd65a (MD5) Previous issue date: 2012-12-03 / With the implementation of the Brazilian Digital TV System (SBTVD) comes a range of new opportunities and possibilities both for viewer and TV stations. For the viewers, they will have an immense amount of channels, programs and interactive advertisements. For TV stations, it increases the possibility of advertising in new media. In this context, the opportunity arises for a recommendation system for applications and interactivity portals. This dissertation presents a proposal of advertising personalization into applications and portals of digital TV environment in order to bring a better experience to the viewer, a new form of income for the broadcasters and also a greater acceptance of specialized products for use. This work develops an application for interactive Digital TV called Smart Marketing capable of capturing viewer navigation data through both implicit and explicit means by performing customized advertising from the process of knowledge discovery. Developed from AstroTV middleware, compatible with the Brazilian specification, its application was evaluated by means of experiment that used varied user profiles, applying into the generated database the process of knowledge discovery, which used tasks of classification and grouping. The results indicated the quality of the recommendation generated by Smart Marketing. / Com a implanta??o do Sistema Brasileiro de TV Digital (SBTVD), inicia-se uma gama de novas oportunidades e possibilidades tanto para o telespectador quanto as emissoras de TV. Para os Telespectadores, eles ter?o uma imensa quantidade de canais, programas e propagandas interativas. Para as emissoras de TV, aumenta a possibilidade de propagandas em novos meios de comunica??o. Neste contexto, surge a oportunidade de um sistema de recomenda??o para os aplicativos e portais de interatividade. Esta disserta??o apresenta uma proposta de personaliza??o de propaganda em aplicativos e portais do ambiente de TV Digital com o objetivo de trazer uma melhor experi?ncia ao telespectador, uma nova forma de obten??o de recursos por parte das teledifusoras e tamb?m uma maior aceita??o de produtos especializados, para uso. Este trabalho desenvolve um aplicativo para a TV Digital interativa denominado Smart Marketing capaz de capturar os dados de navega??o do telespectador tanto por meio impl?cito quanto explicito, realizando a apresenta??o de publicidades personalizadas a partir do processo de descoberta do conhecimento. Elaborado a partir do middleware AstroTV, compat?vel com a especifica??o brasileira, sua aplica??o foi avaliada por meio do experimento que se utilizou, de usu?rios com perfis variados, aplicando na base de dados gerada o processo de descoberta de conhecimento, o qual utilizou-se das tarefas de classifica??o e agrupamento. Os resultados obtidos indicaram a qualidade da recomenda??o gerada pelo Smart Marketing.

Como os interagentes selecionam conteúdo sob a influência dos sistemas de recomendação digital é o problema de pesquisa apresentado nesta tese. A abundância de dados nos repositórios digitais exige sistemas de recuperação de informação eficazes para auxiliar o usuário na gestão e na seleção de itens de informação. Desta forma, o objetivo geral deste trabalho pretende investigar o comportamento dos interagentes na seleção de itens frente ao sistema de recomendação digital do website da loja virtual Amazon. O sistema de recomendação da Amazon foi investigado com a intenção de se compreender como o usuário utiliza um sistema automatizado de listas de referências em forma de recomendação de conteúdo. O funcionamento dos sistemas de recomendação é fundamentado com a proposta de conhecer suas características e funcionalidades. Como o problema de pesquisa tem em sua temática a recomendação de itens de informação, tornou-se necessário compreender como os usuários interagem com os sistemas para perceber como as recomendações são feitas. O aporte teórico desta pesquisa aproxima os estudos dos campos da Informação e da Comunicação. As técnicas de pesquisas aplicadas envolvem métodos de pesquisa qualitativa. Ao distinguir as recomendações a partir das interações reativas e mútuas dos usuários, propõe-se nesta tese a Matriz de Recomendações de Itens de Informação constituída pelos seguintes quadrantes: Recomendações Objetivas Digitais; Recomendações Subjetivas Digitais; Recomendações Objetivas Analógicas e Recomendações Subjetivas Analógicas. Digitais; Recomendações Objetivas Analógicas e Recomendações Subjetivas Analógicas. Para analisar o comportamento dos interagentes no uso dessas recomendações, a estratégia metodológica aplicou entrevista em profundidade e observação direta. Os resultados desta pesquisa consideram que o internauta recorre a mais de um tipo de recomendação quando a seleção envolve conteúdo significativo, enquanto segue passivamente sistemas de recomendações automatizados quando o custo pessoal diretamente aplicado é baixo ou inexistente. / As the interacting select content under the influence of digital recommender systems is the research problem presented in this thesis. The abundance of data in digital repositories recovery requires effective information systems to assist the user in the management and selection of information items. Thus, the objective of this study was to investigate the behavior of the interacting in the selection of digital items across the recommendation of the Amazon’s bookshop website. The Amazon's recommendation system was investigated with the aim of understanding how the user uses an automated reference lists in the form of content recommendation. The performance of recommender systems is founded with the purpose of knowing their characteristics and functionalities. As the research problem is in your subject to the recommendation of information items, it became necessary to understand how users interact with this system to understand how the recommendations are made. The theoretical contribution of this research approaches the fields of Information and Communication. The technique applied involves qualitative research methods. By distinguishing the recommendations from reactive and mutual interactions of users, is propos in this research the Model of Recommendation Information Items consist of the following quadrants: Digital Objective Recommendations; Digital Subjective Recommendations; Analog Subjective Recommendations and Analog Objective Recommendations. To analyze the behavior of interactors in the use of these recommendations, the methodological strategy applied in-depth interviews and direct observation. The results of this research consider that the Internet uses more than one type of recommendation when the selection involves significant content, while passively follows recommendations of automated systems when applied directly to the personal cost is low or nonexistent.

Recommendation systems are gaining more popularity because of the complexity of problems that they provide a solution to. There are many applications of recommendation systems everywhere around us. Implementation of these systems differs and there are two approaches that are most distinguished. First approach is a system without Machine Learning, while the other one includes Machine Learning. The second approach, used in this project, is based on Machine Learning collaborative filtering techniques. These techniques include numerous algorithms and data processing methods. This document describes a process that focuses on building a job recommendation system for a recruitment industry, starting from data acquisition to the final result. Data used in the project is collected from the Pitchler AB company, which provides an online recruitment platform. Result of this project is a machine learning based recommendation system used as an engine for the Pitchler AB IT recruitment platform.

We propose preferential and trust-based frameworks for Information Retrieval and Recommender Systems, which utilize the power of Hyperreal Numbers. In the first part of our research, we propose a preferential framework for Information Retrieval which enables expressing preference annotations on search keywords and document elements, respectively. Our framework is flexible and allows expressing preferences such as “A is infinitely more preferred than B,” which we capture by using hyperreal numbers. Due to widespread use of XML as a standard for representing documents, we consider XML documents in this research and propose a consistent preferential weighting scheme for nested document elements. We show how to naturally incorporate preferences on search keywords and document elements into an IR ranking process using the well-known TF-IDF (Term Frequency - Inverse Document Frequency) ranking measure. In the second part of our research we propose a novel recommender system which enhances user-based collaborative filtering by using a trust-based social network. Again, we use hyperreal numbers and polynomials for capturing natural preferences in aggregating opinions of trusted users. We use these opinions to “help” users who are similar to an active user to come up with recommendations for items for which they might not have an opinion themselves. We argue that the method we propose reflects better the real life behaviour of the people. Our method is justified by the experimental results; we are the first to break a stated “barrier” of 0.73 for the mean absolute error (MAE) of the predicted ratings. Our results are based on a large, real life dataset from Epinions.com, for which, we also achieve a prediction coverage that is significantly better than that of the state-of-the-art methods.

L'accès aux informations pertinentes, adaptées aux besoins et au profil de l'utilisateur est un enjeu majeur dans le cadre actuel caractérisé par une prolifération massive des ressources d'information hétérogènes. Le développement d'appareils mobiles équipés de plusieurs fonctionnalités telles que la caméra, le WIFI, la géo-localisation et bien plus d'autres permettent aux systèmes mobiles de recommandation actuels d'être hautement contextualisés et pouvant fournir à l'utilisateur des informations pertinentes au bon moment quand il en a le plus besoin, sans attendre qu'il établisse une interaction avec son appareil. C'est dans ce cadre que s'insère notre travail de thèse. En effet, nous proposons une approche de recommandation contextuelle et proactive dans un environnement mobile qui permet de recommander des informations pertinentes à l'utilisateur sans attendre à ce que ce dernier initie une interaction. Un système proactif peut prendre la forme d'un guide touristique personnalisé qui se base sur la localisation et les préférences de l'utilisateur pour suggérer à ce dernier des endroits intéressants sans qu'il fournisse, sa préférence ou une requête explicite. Cela permettra de réduire les efforts, le temps et l'interaction de l'utilisateur avec son appareil mobile et de présenter les informations pertinentes au bon moment et au bon endroit. Cette approche prend aussi en considération les situations où la recommandation pourrait déranger l'utilisateur. Il s'agit d'équilibrer le processus de recommandation contre les interruptions intrusives. En effet, il existe différents facteurs et situations qui rendent l'utilisateur moins ouvert aux recommandations. Comme nous travaillons dans le contexte des appareils mobiles, nous considérons que les applications mobiles telles que la caméra, le clavier, l'agenda, etc., sont de bons représentants de l'interaction de l'utilisateur avec son appareil puisqu'ils représentent en quelque sorte la plupart des activités qu'un utilisateur pourrait entreprendre avec son appareil mobile au quotidien, comme envoyer des messages, converser, tweeter, naviguer ou prendre des photos. / Just-In-Time recommender systems involve all systems able to provide recommendations tailored to the preferences and needs of users in order to help them access useful and interesting resources within a large data space. The user does not need to formulate a query, this latter is implicit and corresponds to the resources that match the user's interests at the right time. Our work falls within this framework and focuses on developing a proactive context-aware recommendation approach for mobile devices that covers many domains. It aims at recommending relevant items that match users' personal interests at the right time without waiting for the users to initiate any interaction. Indeed, the development of mobile devices equipped with persistent data connections, geolocation, cameras and wireless capabilities allows current context-aware recommender systems (CARS) to be highly contextualized and proactive. We also take into consideration to which degree the recommendation might disturb the user. It is about balancing the process of recommendation against intrusive interruptions. As a matter of fact, there are different factors and situations that make the user less open to recommendations. As we are working within the context of mobile devices, we consider that mobile applications functionalities such as the camera, the keyboard, the agenda, etc., are good representatives of the user's interaction with his device since they somehow stand for most of the activities that a user could use in a mobile device in a daily basis such as texting messages, chatting, tweeting, browsing or taking selfies and pictures.