Today's technology is becoming more interactive with voice assistants like Siri. However, interactive systems such as Siri make mistakes. The purpose of this thesis is to explore using affect as an implicit feedback channel so that such mistakes would be easily corrected in real time. The CAfFEINE Framework, which was created by Dr. Saha, is a context-aware affective feedback loop in an intelligent environment. For the research described in this thesis, the focus will be on analyzing a user's physiological response to the service provided by an intelligent environment. To test this feedback loop, an experiment was constructed using an on-screen, step-by-step assembly guide for a Tangram puzzle. To categorize the user's response to the experiment, baseline readings were gathered for a user's stressed and non-stressed state. The Paced Stroop Test and two other baseline tests were conducted to gather these two states. The data gathered in the baseline tests was then used to train a support vector machine to predict the user's response to the Tangram experiment. During the data analysis phase of the research, the results for the predictions on the Tangram experiment were not as expected. Multiple trials of training data for the support vector machine were explored, but the data gathered throughout this research was not enough to draw proper conclusions. More focus was then given to analyzing the pre-processed data of the baseline tests in an attempt to find a factor or group of factors to determine if the user's physiological responses would be useful to train the Support Vector Machine. There were trends found when comparing the area under the curves of the Paced Stroop Test phasic driver plots. It was found that these comparison factors might be a useful approach for differentiating users based upon their physiological responses during the Paced Stroop Test. / Master of Science / The purpose of this thesis was to use the CAfFEINE Framework, proposed by Dr. Saha, in a real-world environment. Dr. Saha's Framework utilizes a user's physical responses, i.e. heart rate, in a smart environment to give information to the smart devices. For example, if Siri were to give a user directions to someone's home and told that user to turn right when the user knew they needed to turn left. That user would have a physical reaction as in their heart rate would increase. If the user were wearing a smart watch, Siri would be able to see the heart rate increase and realize, from past experiences with that user, that the information she gave to the user was incorrect. Then she would be able to correct herself. My research focused on measuring user reaction to a smart service provided in a real-world situation using a Tangram puzzle as a mock version of an industrial assembly situation. The users were asked to follow on-screen instructions to assemble the Tangram puzzle. Their reactions were recorded through a smart watch and analyzed post-experiment. Based on the results of a Paced Stroop Test they took before the experiment, a computer algorithm would predict their stress levels for each service provided by the step-by-step instruction guide. However, the results did not turn out as expected. Therefore, the rest of the research focused more on why the results did not support Dr. Saha's previous Framework results.

Location is a primary cue in many context-aware computing systems, and is often represented as a global coordinate, room number, or Euclidean distance various landmarks. A user?s concept of location, however, is often defined in terms of regions in which common activities occur. We show how to partition a space into such regions based on patterns of observed user location and motion. These regions, which we call activity zones, represent regions of similar user activity, and can be used to trigger application actions, retrieve information based on previous context, and present information to users. We suggest that context-aware applications can benefit from a location representation learned from observing users. We describe an implementation of our system and present two example applications whose behavior is controlled by users? entry, exit, and presence in the zones.

No description available.

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES / In the last decade the internet has become a tool present in the daily lives of people and organizations and time essential to the smooth operation of businesses. With the increasing development of infrastructure networks and popularization mass of highspeed network, emerges a related Internet use advance making it a global platform to make intelligent machines and objects able to communicate up autonomously. This possibility enables content and services are around people, always available, facilitating communication and paving the way for new applications, enabling new forms of work, interaction and entertainment, making a new pattern of living and working is developed. This new standard is made possible through advances in Information and Communication Technologies - ICTs to a new design set to Internet of Things - IoT. However, with a varied collection of data and information for various purposes, in the daily lives of people and organizations, autonomous data collection and information makes privacy a major challenge regarding the IoT. In this context, this study aimed to investigate the aspects that determine the action of Internet technology users of Things to supply personal information in intelligent environments. The research was characterized as positivist, quantitative, exploratory and descriptive, its implementation took place through field research strategy, with the data collection instrument a self-administered questionnaire, which was available to respondents in Brazil. It was adopted in the analysis of data collected quantitative line based on statistical techniques, in which we attempted to cross the data in order to achieve the objective of the research. Among the main conclusions from the research, it intuited that the use of environment is a determining aspect to providing information to the intelligent environment of greater influence among other aspects found. It was noticed that users tend to devote considerable attention to security and privacy of information we have, providing them with qualifications and care. However sometimes transfer responsibility for security of the information to third parties seeking to reduce the maximum number of criteria to be considered before making the decision to make available their data. / Na ultima década a internet tornou-se uma ferramenta presente no cotidiano das pessoas e das organizações e por vez indispensável ao bom funcionamento dos negócios. Com o crescente incremento das infraestruturas de redes e popularização em massa da rede de alta velocidade, emerge um avanço relacionado à utilização da internet tornando-a uma plataforma global para deixar máquinas e objetos inteligentes capazes de comunicarem-se de forma autônoma. Esta possibilidade permite que conteúdos e serviços estejam em torno das pessoas, sempre disponíveis, facilitando a comunicação e abrindo o caminho para novas aplicações, possibilitando novas formas de trabalho, de interação e de entretenimento, fazendo com que um novo padrão de vida e de trabalho seja desenvolvido. Este novo padrão torna-se possível através dos avanços das Tecnologias da Informação e Comunicação - TIC’s até uma nova concepção definida como Internet of Things - IoT. Entretanto, com uma variada coleta de dados e informações, para variados fins, no cotidiano das pessoas e das organizações, a coleta autônoma dos dados e das informações torna a privacidade um dos principais desafios em relação à IoT. Neste contexto, esta pesquisa objetivou investigar os aspectos que determinam a ação dos usuários de tecnologias da Internet das Coisas ao fornecerem informações pessoais em ambientes inteligentes. A pesquisa caracterizou-se como positivista, de natureza quantitativa, do tipo exploratória e descritiva, sua implementação aconteceu por meio da estratégia de pesquisa de campo, tendo como instrumento de coleta de dados um questionário autoaplicável, que foi disponibilizado para respondentes em território brasileiro. Adotou-se na análise dos dados coletados uma linha quantitativa baseada em técnicas estatísticas, em que buscou-se cruzar os dados a fim de alcançar o objetivo da pesquisa. Dentre as principais conclusões decorrentes da pesquisa, intuiu-se que o ambiente de uso se configura como um aspecto determinante ao fornecimento de informação ao ambiente inteligente de maior influência entre os outros aspectos encontrados. Foi percebido que os usuários tendem a dedicar considerável atenção a segurança e a privacidade das informações que possuem, disponibilizando-as com ressalvas e cuidados. Contudo por vezes, transferem a responsabilidade pela segurança das informações para terceiros, buscando reduzir ao máximo o número de critérios a serem analisados antes de tomar a decisão de disponibilizar seus dados. / São Cristóvão, SE

This thesis describes research on methods for Ubiquitous/Pervasive Computing to better suit users in an Intelligent Environment. The approach is to create and equip a computing environment, such as our Active Office, with technologies that can identify user needs and meet these need in a timely, efficient and unobtrusive manner.¶ The critical issues in the Intelligent Environment are how to enable transparent, distributed computing to allow continued operation across changing circumstances and how to exploit the changing environment so that it is aware of the context of user location, the collection of nearby people and objects, accessible devices and changes to those objects over time.¶ Since the Intelligent Environment is an environment with rapid and rich computing processing, the distributed context processing architecture (DiCPA) was developed to manage and respond to rapidly changing aggregation of sensor data. This architecture is a scalable distributed context processing architecture that provides: 1. continued operation across changing circumstances for users, 2. the collection of nearby people and objects, 3. accessible devices and 4. the changes to those objects over time in the environment. The DiCPA approach focuses on how the Intelligent Environment provides context information for user location, user mobility and the user activity model. Users are assumed mobile within the Intelligent Environment and can rapidly change their access to relevant information and the availability of communications and computational resources.¶ Context-Aware Computing is a new approach in software engineering for Intelligent Environment. It is an approach in the design and construction of a context-aware application that exploits rapid changes in access to relevant information and the availability of communication and computing resources in the mobile computing environment. The goal of Context-Aware Computing is to make user interaction with the computer easier in the smart environment where technology is spread throughout (pervasive), computers are everywhere at the same time (ubiquitous) and technology is embedded (ambient) in the environment. Context-aware applications need not be difficult, tedious or require the acquisition of new skills on the part of the user. They should be safe, easy, simple to use and should enable new functionality without the need to learn new technology. They should provide relevant information and a simple way for a user to manage.¶ The Intelligent Environment requires a context-aware application to improve its efficiency and to increase productivity and enjoyment for the user. The context awareness mechanism has four fundamental cores i.e. identity (who), activity (what), location (where) and timestamp (when). Based on DiCPA architecture, the model of user location (where), user mobility (where), user activity (what) and Intelligent Environment response (what) were developed. Prototypes were also developed to proof the Context-Aware Computing concept in the Intelligent Environment.¶ An Intelligent Environment uses the multi-disciplinary area of Context-Aware Computing, which combines technology, computer systems, models and reasoning, social aspects, and user support. A “good quality” project for Context-Aware Computing requires core content and provides iterative evaluation processes, which has two types of iteration: design and product iteration of the evaluation. The aim of the development of an evaluation program in Context-Aware Computing is to determine what to test, how to test and the appropriate metrics to use. This work presents the metrics for a good quality project in the Context-Aware Computing area, which is followed by the evaluation of the prototypes of this work.

No Brasil existem milhões de brasileiros com algum tipo de dificuldade de locomoção, sendo que grande parte dessas pessoas com deficiência necessita de cadeira de rodas para se locomover. Com o fato de existirem inúmeros de brasileiros cadeirantes, o desenvolvimento de tecnologias ditas ¨assistivas¨, ou seja, tecnologias que visam assistir estas pessoas em suas atividades, tem recebido uma crescente atenção, tanto do ponto de vista de negócios (com o aumento de produtos), como de pesquisas acadêmicas. Dentre estas linhas de pesquisa, a integração entre cadeiras de rodas automatizadas com sistemas de automação predial e residencial está entre as linhas de pesquisa de maior destaque, pois tem como objetivo tornar a vida do usuário de cadeira de rodas mais produtiva e cômoda, contribuindo para sua independência. Os sistemas de automação predial e residencial mais complexos elevam o nível de um ambiente automatizado para um ambiente inteligente, pois tornam o nível de abstração maior, fornecendo serviços de forma pervasiva. O ambiente inteligente necessita de informações para que possa oferecer seus serviços ao cadeirante, e uma informação importante seria a localização da cadeira de rodas automatizada. Neste contexto, este trabalho propõe um sistema de localização em interiores para cadeiras de rodas automatizadas em ambientes inteligentes. A proposta combina Redes de Sensores Sem Fio (RSSF) e a tecnologia RFID, onde as etiquetas RFID são utilizadas como marcos de referências para a calibração automática dos parâmetros da RSSF, que convencionalmente são obtidos de forma experimental. O estudo de caso para validar o sistema de localização proposto foi realizado numa sala automatizada no prédio da Engenharia Elétrica da Universidade Federal do Rio Grande do Sul (UFRGS) como ambiente inteligente, e uma cadeira de rodas automatizada adaptada para se comunicar com a RSSF. Além deste estudo de caso, foram realizados outros experimentos com intuito de avaliar qual método geraria os melhores resultados para o sistema de localização baseado em RSSF e a tecnologia RFID, combinando diferentes modelos de propagação de sinal RF e diferentes formas de calibrar os parâmetros da rede. Além disso, outras questões sobre o sistema de localização proposto foram analisadas, como por exemplo, a influência do aumento da quantidade de nós da rede na exatidão do sistema, o comportamento do sistema quando, para um mesmo cenário, o sentido do percurso é invertido, e a influência do leiaute dos nós da rede no desempenho do sistema. / In Brazil there are millions of people with some kind of limited mobility, and that most of these disabled people need a wheelchair to get around. With the fact that there are millions of wheelchair users, the development of assistive technologies, i.e. technologies to assist these people in their activities, has received increasing attention both from the standpoint of business (with the increase of products), as academic research. Among these lines of research, the integration of automated wheelchairs with home automation systems are among the research areas of greatest importance because it aims to make the user's life more productive and comfortable, contributing to their independence. The home automation systems more complex increase the level of an automated environment for intelligent environment, as they make the higher level of abstraction, providing pervasive services. The intelligent environment needs information so it can offer your services to the wheelchair user, and important information would be the location of the automated wheelchair. Within this context, this paper proposes an indoor positioning system for wheelchairs in intelligent environments. The proposal combines Wireless Sensor Networks (WSN) and RFID technology, where RFID tags are used as landmark for automatic calibration of the parameters of WSN, which are conventionally obtained experimentally. The case study to validate the proposed indoor positioning system was performed at an automated room in the building of Electrical Engineering, Universidade Federal do Rio Grande do Sul (UFRGS) with the intelligent environment and automated wheelchair adapted to communicate with the WSN. In addition to the case study, other experiments in order to assess which method would produce the best results for the localization system based on RFID and WSN, combining different radio propagation model and different forms of calibrate the parameters of the WSN. In addition, other questions about the proposed indoor positioning system were analyzed, for example, the influence of increasing the amount of network nodes on the system accuracy, the behavior of the system for the same scenario when the direction of travel is reversed, and the influence of the layout of the network nodes on the system performance.

No Brasil existem milhões de brasileiros com algum tipo de dificuldade de locomoção, sendo que grande parte dessas pessoas com deficiência necessita de cadeira de rodas para se locomover. Com o fato de existirem inúmeros de brasileiros cadeirantes, o desenvolvimento de tecnologias ditas ¨assistivas¨, ou seja, tecnologias que visam assistir estas pessoas em suas atividades, tem recebido uma crescente atenção, tanto do ponto de vista de negócios (com o aumento de produtos), como de pesquisas acadêmicas. Dentre estas linhas de pesquisa, a integração entre cadeiras de rodas automatizadas com sistemas de automação predial e residencial está entre as linhas de pesquisa de maior destaque, pois tem como objetivo tornar a vida do usuário de cadeira de rodas mais produtiva e cômoda, contribuindo para sua independência. Os sistemas de automação predial e residencial mais complexos elevam o nível de um ambiente automatizado para um ambiente inteligente, pois tornam o nível de abstração maior, fornecendo serviços de forma pervasiva. O ambiente inteligente necessita de informações para que possa oferecer seus serviços ao cadeirante, e uma informação importante seria a localização da cadeira de rodas automatizada. Neste contexto, este trabalho propõe um sistema de localização em interiores para cadeiras de rodas automatizadas em ambientes inteligentes. A proposta combina Redes de Sensores Sem Fio (RSSF) e a tecnologia RFID, onde as etiquetas RFID são utilizadas como marcos de referências para a calibração automática dos parâmetros da RSSF, que convencionalmente são obtidos de forma experimental. O estudo de caso para validar o sistema de localização proposto foi realizado numa sala automatizada no prédio da Engenharia Elétrica da Universidade Federal do Rio Grande do Sul (UFRGS) como ambiente inteligente, e uma cadeira de rodas automatizada adaptada para se comunicar com a RSSF. Além deste estudo de caso, foram realizados outros experimentos com intuito de avaliar qual método geraria os melhores resultados para o sistema de localização baseado em RSSF e a tecnologia RFID, combinando diferentes modelos de propagação de sinal RF e diferentes formas de calibrar os parâmetros da rede. Além disso, outras questões sobre o sistema de localização proposto foram analisadas, como por exemplo, a influência do aumento da quantidade de nós da rede na exatidão do sistema, o comportamento do sistema quando, para um mesmo cenário, o sentido do percurso é invertido, e a influência do leiaute dos nós da rede no desempenho do sistema. / In Brazil there are millions of people with some kind of limited mobility, and that most of these disabled people need a wheelchair to get around. With the fact that there are millions of wheelchair users, the development of assistive technologies, i.e. technologies to assist these people in their activities, has received increasing attention both from the standpoint of business (with the increase of products), as academic research. Among these lines of research, the integration of automated wheelchairs with home automation systems are among the research areas of greatest importance because it aims to make the user's life more productive and comfortable, contributing to their independence. The home automation systems more complex increase the level of an automated environment for intelligent environment, as they make the higher level of abstraction, providing pervasive services. The intelligent environment needs information so it can offer your services to the wheelchair user, and important information would be the location of the automated wheelchair. Within this context, this paper proposes an indoor positioning system for wheelchairs in intelligent environments. The proposal combines Wireless Sensor Networks (WSN) and RFID technology, where RFID tags are used as landmark for automatic calibration of the parameters of WSN, which are conventionally obtained experimentally. The case study to validate the proposed indoor positioning system was performed at an automated room in the building of Electrical Engineering, Universidade Federal do Rio Grande do Sul (UFRGS) with the intelligent environment and automated wheelchair adapted to communicate with the WSN. In addition to the case study, other experiments in order to assess which method would produce the best results for the localization system based on RFID and WSN, combining different radio propagation model and different forms of calibrate the parameters of the WSN. In addition, other questions about the proposed indoor positioning system were analyzed, for example, the influence of increasing the amount of network nodes on the system accuracy, the behavior of the system for the same scenario when the direction of travel is reversed, and the influence of the layout of the network nodes on the system performance.

No Brasil existem milhões de brasileiros com algum tipo de dificuldade de locomoção, sendo que grande parte dessas pessoas com deficiência necessita de cadeira de rodas para se locomover. Com o fato de existirem inúmeros de brasileiros cadeirantes, o desenvolvimento de tecnologias ditas ¨assistivas¨, ou seja, tecnologias que visam assistir estas pessoas em suas atividades, tem recebido uma crescente atenção, tanto do ponto de vista de negócios (com o aumento de produtos), como de pesquisas acadêmicas. Dentre estas linhas de pesquisa, a integração entre cadeiras de rodas automatizadas com sistemas de automação predial e residencial está entre as linhas de pesquisa de maior destaque, pois tem como objetivo tornar a vida do usuário de cadeira de rodas mais produtiva e cômoda, contribuindo para sua independência. Os sistemas de automação predial e residencial mais complexos elevam o nível de um ambiente automatizado para um ambiente inteligente, pois tornam o nível de abstração maior, fornecendo serviços de forma pervasiva. O ambiente inteligente necessita de informações para que possa oferecer seus serviços ao cadeirante, e uma informação importante seria a localização da cadeira de rodas automatizada. Neste contexto, este trabalho propõe um sistema de localização em interiores para cadeiras de rodas automatizadas em ambientes inteligentes. A proposta combina Redes de Sensores Sem Fio (RSSF) e a tecnologia RFID, onde as etiquetas RFID são utilizadas como marcos de referências para a calibração automática dos parâmetros da RSSF, que convencionalmente são obtidos de forma experimental. O estudo de caso para validar o sistema de localização proposto foi realizado numa sala automatizada no prédio da Engenharia Elétrica da Universidade Federal do Rio Grande do Sul (UFRGS) como ambiente inteligente, e uma cadeira de rodas automatizada adaptada para se comunicar com a RSSF. Além deste estudo de caso, foram realizados outros experimentos com intuito de avaliar qual método geraria os melhores resultados para o sistema de localização baseado em RSSF e a tecnologia RFID, combinando diferentes modelos de propagação de sinal RF e diferentes formas de calibrar os parâmetros da rede. Além disso, outras questões sobre o sistema de localização proposto foram analisadas, como por exemplo, a influência do aumento da quantidade de nós da rede na exatidão do sistema, o comportamento do sistema quando, para um mesmo cenário, o sentido do percurso é invertido, e a influência do leiaute dos nós da rede no desempenho do sistema. / In Brazil there are millions of people with some kind of limited mobility, and that most of these disabled people need a wheelchair to get around. With the fact that there are millions of wheelchair users, the development of assistive technologies, i.e. technologies to assist these people in their activities, has received increasing attention both from the standpoint of business (with the increase of products), as academic research. Among these lines of research, the integration of automated wheelchairs with home automation systems are among the research areas of greatest importance because it aims to make the user's life more productive and comfortable, contributing to their independence. The home automation systems more complex increase the level of an automated environment for intelligent environment, as they make the higher level of abstraction, providing pervasive services. The intelligent environment needs information so it can offer your services to the wheelchair user, and important information would be the location of the automated wheelchair. Within this context, this paper proposes an indoor positioning system for wheelchairs in intelligent environments. The proposal combines Wireless Sensor Networks (WSN) and RFID technology, where RFID tags are used as landmark for automatic calibration of the parameters of WSN, which are conventionally obtained experimentally. The case study to validate the proposed indoor positioning system was performed at an automated room in the building of Electrical Engineering, Universidade Federal do Rio Grande do Sul (UFRGS) with the intelligent environment and automated wheelchair adapted to communicate with the WSN. In addition to the case study, other experiments in order to assess which method would produce the best results for the localization system based on RFID and WSN, combining different radio propagation model and different forms of calibrate the parameters of the WSN. In addition, other questions about the proposed indoor positioning system were analyzed, for example, the influence of increasing the amount of network nodes on the system accuracy, the behavior of the system for the same scenario when the direction of travel is reversed, and the influence of the layout of the network nodes on the system performance.

Cette thèse s’intéresse à la problématique de l’adaptation automatique de services dans ledomaine de l’intelligence ambiante. L’étude de la littérature montre que la sensibilité aucontexte est devenue un élément central pour la conception et la mise en place de servicesadaptatifs. Cependant, sa prise en compte se limite généralement à des descriptionsélémentaires de situations ou à des modèles prédéfinis. Afin de permettre une adaptation auxchangements d’habitudes des utilisateurs, à la dynamique de l’environnement et àl’hétérogénéité des sources de perception, nous proposons des mécanismes de découverte decontexte et de situations déclencheurs d’adaptation. Ces mécanismes s’appuient sur destechniques de fouille de données et sont intégrés au sein d’une architecture d’adaptationautomatique de services. Ces travaux ont été réalisés et appliqués à des projets d’intelligenceambiante pour de l’assistance à des personnes et plus particulièrement dans le cadre du projetITEA- MIDAS. / This thesis addresses the problem of dynamic adaptation of services in the context of ambientintelligence applications. Literature study shows how context-awareness plays a central rolein the design and implementation of adaptive services. However, its use is still limited toelementary descriptions and predefined situational models. Dynamic adaptation should becapable of following user habits to yield dynamic answers to environmental change, and tosupport heterogeneous sources of context. To this end, we propose mechanisms to discovercontexts and situations that trigger adaptation. These mechanisms rely on data miningtechniques, and are integrated within an architecture for dynamic adaptation of services. Thiswork was carried out and applied to ambient intelligence projects for the elderly, providingsupport and assistance in their daily lives, particularly in the context of the ITEA-MIDASproject.