Orientadores: Joao Mauricio Rosario, Carlos Alberto Mariotoni / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Mecanica / Made available in DSpace on 2018-08-10T18:38:42Z (GMT). No. of bitstreams: 1 Canato_DecioAlbino_M.pdf: 1316639 bytes, checksum: 03ff0dfdee3deb1d7b4e3db678e77539 (MD5) Previous issue date: 2007 / Resumo: A automação residencial é uma modernidade cada vez mais presente nas residências. As soluções tecnológicas disponíveis no mercado deixaram de ser vistas como um luxo para poucos e se tornaram sinônimo de conforto e segurança acessível a todos os usuários interessados. Para construtores e incorporadores, o diferencial é oferecer aos clientes uma infraestrutura de automação de modo a permitir que o morador possa adequar o conforto e a segurança às suas necessidades e orçamento. Programar as luzes e cortinas para criar um cenário agradável no ambiente, ou ainda acessar os sistemas de segurança de sua residência, seja por telefone ou através da internet, são algumas das soluções existentes e acessíveis no mundo da automação. Atualmente, para formar um mecanismo automático em uma residência basta ir a qualquer loja de construção civil e comprá-los sem muita dificuldade. A dúvida que gera quando se faz este tipo de automação, compradas em lojas faça você mesmo, ou seja, montadas em blocos e sem planejamento prévio, é a questão da integração entre os dispositivos automáticos, não existe uma comunicação entre eles, agindo de forma independente, criados sem uma modelagem pré-definida, gerando gastos e transtornos nos projetos atuais e futuros. Para que as diversas opções possam ser integradas de maneira única e pessoal, ou seja, de acordo com a escolha de quem irá utilizá-las, é necessária a criação de uma infra-estrutura adequada. Isto significa prever em projeto o cabeamento, a instalação elétrica e seus acessórios responsáveis pela distribuição de sinais de dados, voz e imagens pela residência O compromisso deste trabalho é a realização de uma integração de sistemas domésticos automatizados baseados na vasta experiência locada na indústria, visto através das modelagens e integrações de sistemas complexos, ou seja, transportar a tecnologia já dominada da automação industrial para uma tecnologia já não tão recente que é a automação doméstica / Abstract: Home autonomation is a modern feature that is becoming more common, nowadays technological solutions available are synonym of comfort and safety instead of being considered an expensive luxury. Different autonomation options are now acquirable for general costumers. For contractors and incorporate, the main issue is to offer an autonomation structure allowing the costumer to suit comfort and safety to the family budget. Programming light intensity and curtains for a nicer atmosphere, being able to reach home security system either using phone or internet are some of the solutions available for home autonomation. Nowadays, autonomation systems can be purchased in many different stores. The main issue related to this kind of commercially available autonomation is that the different parts of the system are not integrated and are not able to communicate, being a potential source of extra costs and problems. On the other hand, if the autonomation system is planned for a specific house, considering who is going to use the system, most problems could be avoided. Creating a specific autonomation project means plan the electric installation, the wires design and related accessories responsible for data distribution, voice and image storage. The aim of this work is to provide an integration of home systems based on the wide experience accumulated by industrial autonomation, exporting the well-known technology for home autonomation / Mestrado / Mecanica dos Sólidos e Projeto Mecanico / Mestre em Engenharia Mecânica

Dans beaucoup de pays du monde, on observe une importante augmentation du nombre de personnes âgées vivant seules. Depuis quelques années, un nombre significatif de projets de recherche sur l’assistance aux personnes âgées ont vu le jour. La plupart de ces projets utilisent plusieurs modalités (vidéo, son, détection de chute, etc.) pour surveiller l'activité de la personne et lui permettre de communiquer naturellement avec sa maison "intelligente", et, en cas de danger, lui venir en aide au plus vite. Ce travail a été réalisé dans le cadre du projet ANR VERSO de recherche industrielle, Sweet-Home. Les objectifs du projet sont de proposer un système domotique permettant une interaction naturelle (par commande vocale et tactile) avec la maison, et procurant plus de sécurité à l'habitant par la détection des situations de détresse. Dans ce cadre, l'objectif de ce travail est de proposer des solutions pour la reconnaissance des sons de la vie courante dans un contexte réaliste. La reconnaissance du son fonctionnera en amont d'un système de Reconnaissance Automatique de la Parole. Les performances de celui-ci dépendent donc de la fiabilité de la séparation entre la parole et les autres sons. Par ailleurs, une bonne reconnaissance de certains sons, complétée par d'autres sources informations (détection de présence, détection de chute, etc.) permettrait de bien suivre les activités de la personne et de détecter ainsi les situations de danger. Dans un premier temps, nous nous sommes intéressés aux méthodes en provenance de la Reconnaissance et Vérification du Locuteur. Dans cet esprit, nous avons testé des méthodes basées sur GMM et SVM. Nous avons, en particulier, testé le noyau SVM-GSL (SVM GMM Supervector Linear Kernel) utilisé pour la classification de séquences. SVM-GSL est une combinaison de SVM et GMM et consiste à transformer une séquence de vecteurs de longueur arbitraire en un seul vecteur de très grande taille, appelé Super Vecteur, et utilisé en entrée d'un SVM. Les expérimentations ont été menées en utilisant une base de données créée localement (18 classes de sons, plus de 1000 enregistrements), puis le corpus du projet Sweet-Home, en intégrant notre système dans un système plus complet incluant la détection multi-canaux du son et la reconnaissance de la parole. Ces premières expérimentations ont toutes été réalisées en utilisant un seul type de coefficients acoustiques, les MFCC. Par la suite, nous nous sommes penchés sur l'étude d'autres familles de coefficients en vue d'en évaluer l'utilisabilité en reconnaissance des sons de l'environnement. Notre motivation fut de trouver des représentations plus simples et/ou plus efficaces que les MFCC. En utilisant 15 familles différentes de coefficients, nous avons également expérimenté deux approches pour transformer une séquence de vecteurs en un seul vecteur, à utiliser avec un SVM linéaire. Dans le première approche, on calcule un nombre fixe de coefficients statistiques qui remplaceront toute la séquence de vecteurs. La seconde approche (une des contributions de ce travail) utilise une méthode de discrétisation pour trouver, pour chaque caractéristique d'un vecteur acoustique, les meilleurs points de découpage permettant d'associer une classe donnée à un ou plusieurs intervalles de valeurs. La probabilité de la séquence est estimée par rapport à chaque intervalle. Les probabilités obtenues ainsi sont utilisées pour construire un seul vecteur qui remplacera la séquence de vecteurs acoustiques. Les résultats obtenus montrent que certaines familles de coefficients sont effectivement plus adaptées pour reconnaître certaines classes de sons. En effet, pour la plupart des classes, les meilleurs taux de reconnaissance ont été observés avec une ou plusieurs familles de coefficients différentes des MFCC. Certaines familles sont, de surcroît, moins complexes et comptent une seule caractéristique par fenêtre d'analyse contre 16 caractéristiques pour les MFCC / In many countries around the world, the number of elderly people living alone has been increasing. In the last few years, a significant number of research projects on elderly people monitoring have been launched. Most of them make use of several modalities such as video streams, sound, fall detection and so on, in order to monitor the activities of an elderly person, to supply them with a natural way to communicate with their “smart-home”, and to render assistance in case of an emergency. This work is part of the Industrial Research ANR VERSO project, Sweet-Home. The goals of the project are to propose a domotic system that enables a natural interaction (using touch and voice command) between an elderly person and their house and to provide them a higher safety level through the detection of distress situations. Thus, the goal of this work is to come up with solutions for sound recognition of daily life in a realistic context. Sound recognition will run prior to an Automatic Speech Recognition system. Therefore, the speech recognition’s performances rely on the reliability of the speech/non-speech separation. Furthermore, a good recognition of a few kinds of sounds, complemented by other sources of information (presence detection, fall detection, etc.) could allow for a better monitoring of the person's activities that leads to a better detection of dangerous situations. We first had been interested in methods from the Speaker Recognition and Verification field. As part of this, we have experimented methods based on GMM and SVM. We had particularly tested a Sequence Discriminant SVM kernel called SVM-GSL (SVM GMM Super Vector Linear Kernel). SVM-GSL is a combination of GMM and SVM whose basic idea is to map a sequence of vectors of an arbitrary length into one high dimensional vector called a Super Vector and used as an input of an SVM. Experiments had been carried out using a locally created sound database (containing 18 sound classes for over 1000 records), then using the Sweet-Home project's corpus. Our daily sounds recognition system was integrated into a more complete system that also performs a multi-channel sound detection and speech recognition. These first experiments had all been performed using one kind of acoustical coefficients, MFCC coefficients. Thereafter, we focused on the study of other families of acoustical coefficients. The aim of this study was to assess the usability of other acoustical coefficients for environmental sounds recognition. Our motivation was to find a few representations that are simpler and/or more effective than the MFCC coefficients. Using 15 different acoustical coefficients families, we have also experimented two approaches to map a sequence of vectors into one vector, usable with a linear SVM. The first approach consists of computing a set of a fixed number of statistical coefficients and use them instead of the whole sequence. The second one, which is one of the novel contributions of this work, makes use of a discretization method to find, for each feature within an acoustical vector, the best cut points that associates a given class with one or many intervals of values. The likelihood of the sequence is estimated for each interval. The obtained likelihood values are used to build one single vector that replaces the sequence of acoustical vectors. The obtained results show that a few families of coefficients are actually more appropriate to the recognition of some sound classes. For most sound classes, we noticed that the best recognition performances were obtained with one or many families other than MFCC. Moreover, a number of these families are less complex than MFCC. They are actually a one-feature per frame acoustical families, whereas MFCC coefficients contain 16 features per frame

Internet Of Things (IoT) och hemautomation innebär möjligheten att koppla upp diverse enheter i ett hem gentemot internet, som därefter har som mål att underlätta och göra konsumenters vardag mer bekvämt. Hemautomation kan exempelvis handla om att låsa dörrar och tända lampor från en enda enhet (kontrollern), vilket underlättar då konsumenten inte behöver gå till vardera enhet för att utföra önskade aktiviteter. Kontrollers är den del av ett IoT-system inom hemautomation som agerar gränssnittet mellan konsumenten och enheterna.Open-source erbjuder konsumenter ett mer fritt nyttjande av produkter pga. dess öppna källkod. Många problem och frågor som uppstår i samband med dessa produkter härstammar inom området av säkerhet, samt vad som skiljer produkterna åt avseende säkerhet.Denna studie har samlat ihop sex open-source kontrollers och genomfört en jämförelse för att identifiera vilka kontrollers som uppnår säkerhet avseende konfidentialitet, integritet och tillgänglighet. Detta har utförts genom att identifiera vilka värden som förekommer i tidigare artiklar där säkerheten utvärderas för IoT och hemautomation, och för kontrollers.Studien kopplar ihop identifierade värden med CIA modellen, vilket står för confidentiality, integrity och availability (konfidentialitet, integritet och tillgänglighet). I samband med CIA modellen presenteras ett resultat där studiens aktuella kontrollers visar till vilken nivå de upprätthåller CIA modellen, baserat på det identifierade värden som fastställts. De kontrollers som förekommer i studien är Home Genie, OpenHAB, Home Assistant, Domoticz, Calaos och Pimatic.Studiens resultat erhålls via en litterär undersökning av 25 tidigare studier samt 12st tillkommande tekniska dokumentationer och forum för samtliga tillhörande kontrollers. Samtliga studier har blivit hämtade från databaserna Google Scholar, IEEE Xplore och ACM Digital Library och har därefter blivit analyserade och tematiskt kodade för vidare information. Totalt har studiens material genomgått urval i fem steg för att garantera relevant material som stämmer överens med studiens kriterier och mål för innehåll. Studiens resultat presenterar en ögonblicksbild som ger kunskap om jämförda kontrollers, specifikt i samband med CIA modellen, vilket belyser produkterna i samband för området av säkerhet avseende konfidentialitet, integritet och tillgänglighet. / Internet of Things (IoT) and home automation means the opportunity to connect various devices in a home to the Internet, which has the goal of facilitating and making consumers’ everyday lives more comfortable. For example, home automation could be about locking doors and lighting lamps from a single device (the controller), which may make it easier for the consumer since the consumer does not have to go to each device to perform the desired activity. Controllers are the part of a home automation IoT-system that acts as an interface between the consumer and the devices.Open-source offers consumers a freer use of products, due to its open-source code. Many problems and issues that arise in connection with these products originate in the field of security, as well as what distinguishes the products in terms of security.This study has collected six open-source controllers and conducted a comparison to identify which controllers achieve security regarding confidentiality, integrity and availability. This has been done by identifying the values that appear in previous articles where security is evaluated for IoT and home automation, and controllers.This study links identified values with the CIA model, which stands for confidentiality, integrity, and availability. In accordance with the CIA model, a result is presented where the study’s current controllers show to what level they maintain the CIA model, based on the identifies values established. The controllers that appears in this study are Home Genie, OpenHAB, Home Assistant, Domoticz, Calaos, and Pimatic.This study’s results are obtained through a literary study of 25 studies, and 12 additional technical documentations and information through forums for all the associated controllers. All studies have been retrieved from the Google Scholar database, IEEE Xplore, and ACM Digital Library, and subsequently analyzed and thematically coded for further information. In total, the material of this study has been selected in five steps to ensure relevant material that meets this study’s criteria and objectives for content. This study’s results present an overview that provides knowledge about compared controllers, specifically in connection with the CIA model which highlights the products in the field of security, regarding confidentiality, integrity, and availability.

No início do século XX, poucas décadas depois do início da eletrificação das casas, o conceito de uma residência automatizada já era utilizado como símbolo de um futuro livre das tarefas domésticas. No entanto, mesmo com o desenvolvimento de tecnologias de suporte, a automação de residências nunca contemplou uma ampla disseminação e uso. Este trabalho realiza uma análise social, econômica, tecnológica, cultural e de saúde da sociedade, desde o início do século XX até os dias atuais, para entender o comportamento humano relativo ao ambiente residencial e identificar as possíveis causas que não favoreceram a implantação de sistemas de controle e automação nestes ambientes. Ele ainda propõe uma arquitetura de sistemas eletrônicos e computacionais para o ambiente residencial, baseada em um conjunto de requerimentos e de abstrações coerentes com o contexto socioeconômico vigente e factível diante das atuais disponibilidades tecnológicas, a fim de direcionar os esforços na área e fomentar o desenvolvimento de aplicações. Adicionalmente, é apresentada uma plataforma de desenvolvimento hardware, firmware e software , denominada Home Sapiens, cuja concepção, projeto e desenvolvimento foram feitos no contexto desta tese. Baseada em nós de controle distribuídos, ela permite o acesso aos dados provenientes de sensores, a geração de informações de contexto, a identificação de serviços e a manipulação das características do ambiente residencial segundo regras de decisão, planejamento e métodos de aprendizado baseados em técnicas de Inteligência Artificial / In the early twentieth century, a few decades after the beginning of the electrification of houses, the concept of an automated home was used as a symbol of a future free of domestic chores. However, even with the development of supporting technologies, the automation of homes never contemplated a wide dissemination and use. This paper presents an analysis social, economic, technological, cultural and health of society, from the early twentieth century to the present day, to understand human behavior on the residential environment and to identify possible causes that did not favor deployment of control systems and automation in these environments. It also proposes an architecture of computer and electronic systems for the residential environment, based on a set of applications and abstractions consistent with the current socioeconomic context and feasible under the available technology in order to direct efforts in the area and promote the development of applications. Additionally, the implementation of a framework hardware, firmware and software called Home Sapiens is presented, whose conception, design and development were made in the context of this thesis. Based on distributed control nodes, it provides access to data from sensors, the generation of information of context, the identification of services and handling characteristics of the residential environment in accordance with rules of decision, planning and learning methods based on Artificial Intelligence.

No início do século XX, poucas décadas depois do início da eletrificação das casas, o conceito de uma residência automatizada já era utilizado como símbolo de um futuro livre das tarefas domésticas. No entanto, mesmo com o desenvolvimento de tecnologias de suporte, a automação de residências nunca contemplou uma ampla disseminação e uso. Este trabalho realiza uma análise social, econômica, tecnológica, cultural e de saúde da sociedade, desde o início do século XX até os dias atuais, para entender o comportamento humano relativo ao ambiente residencial e identificar as possíveis causas que não favoreceram a implantação de sistemas de controle e automação nestes ambientes. Ele ainda propõe uma arquitetura de sistemas eletrônicos e computacionais para o ambiente residencial, baseada em um conjunto de requerimentos e de abstrações coerentes com o contexto socioeconômico vigente e factível diante das atuais disponibilidades tecnológicas, a fim de direcionar os esforços na área e fomentar o desenvolvimento de aplicações. Adicionalmente, é apresentada uma plataforma de desenvolvimento hardware, firmware e software , denominada Home Sapiens, cuja concepção, projeto e desenvolvimento foram feitos no contexto desta tese. Baseada em nós de controle distribuídos, ela permite o acesso aos dados provenientes de sensores, a geração de informações de contexto, a identificação de serviços e a manipulação das características do ambiente residencial segundo regras de decisão, planejamento e métodos de aprendizado baseados em técnicas de Inteligência Artificial / In the early twentieth century, a few decades after the beginning of the electrification of houses, the concept of an automated home was used as a symbol of a future free of domestic chores. However, even with the development of supporting technologies, the automation of homes never contemplated a wide dissemination and use. This paper presents an analysis social, economic, technological, cultural and health of society, from the early twentieth century to the present day, to understand human behavior on the residential environment and to identify possible causes that did not favor deployment of control systems and automation in these environments. It also proposes an architecture of computer and electronic systems for the residential environment, based on a set of applications and abstractions consistent with the current socioeconomic context and feasible under the available technology in order to direct efforts in the area and promote the development of applications. Additionally, the implementation of a framework hardware, firmware and software called Home Sapiens is presented, whose conception, design and development were made in the context of this thesis. Based on distributed control nodes, it provides access to data from sensors, the generation of information of context, the identification of services and handling characteristics of the residential environment in accordance with rules of decision, planning and learning methods based on Artificial Intelligence.

Made available in DSpace on 2014-12-17T15:48:11Z (GMT). No. of bitstreams: 1 SarahGS_DISSERT.pdf: 3588433 bytes, checksum: 0666242cc7f5f91a2c02c4cfdac4a80f (MD5) Previous issue date: 2014-02-25 / Coordena??o de Aperfei?oamento de Pessoal de N?vel Superior / Com o desenvolvimento tecnol?gico ocorrido nas ?ltimas d?cadas, o ambiente residencial vem incorporando a cada dia novos equipamentos eletroeletr?nicos de consumo dom?stico a fim de facilitar as atividades do cotidiano e promover uma melhor qualidade de vida dos moradores-usu?rios. Controlar esse ambiente no mundo contempor?neo demanda intera??o com diferentes interfaces de controle, tornando essa tarefa, relativamente, complexa. Torna-se necess?rio, portanto, prover interfaces de usu?rio mais adequadas para controlar esses equipamentos. Os dispositivos m?veis surgem como uma plataforma vi?vel para realizar esse controle, trazendo comodidade, flexibilidade e diferentes mecanismos de intera??o com os equipamentos desse ambiente. Por?m, ao se projetar novas solu??es para esse contexto de uso ? necess?rio considerar a diversidade de usu?rios e a riqueza de situa??es de uso desse ambiente. O estudo realizado nesta pesquisa visa compreender aspectos da intera??o desse contexto espec?fico considerando a rela??o entre os usu?rios, a tecnologia e o ambiente. Como resultados, apresentamos um abrangente levantamento de aplica??es, a identifica??o de desafios desse dom?nio sob a perspectiva da diversidade e o levantamento de requisitos para aplica??es desse contexto baseado no referencial te?rico-metodol?gico da Semi?tica Organizacional e no uso de aplicativos. Ainda, ser?o apresentados os passos da concep??o de um aplicativo que apoia o controle de recursos do ambiente residencial via dispositivo m?vel juntamente com os resultados de um experimento realizado com potenciais usu?rios da solu??o computacional implementada

Made available in DSpace on 2014-12-17T15:48:12Z (GMT). No. of bitstreams: 1 AnaCCC_DISSERT.pdf: 3071027 bytes, checksum: f4371a8fcded80257054fb3d4384fea0 (MD5) Previous issue date: 2014-03-24 / Conselho Nacional de Desenvolvimento Cient?fico e Tecnol?gico / Control and automation of residential environments domotics is emerging area of computing application. The development of computational systems for domotics is complex, due to the diversity of potential users, and because it is immerse in a context of emotional relationships and familiar construction. Currently, the focus of the development of this kind of system is directed, mainly, to physical and technological aspects. Due to the fact, gestural interaction in the present research is investigated under the view of Human-Computer Interaction (HCI). First, we approach the subject through the construction of a conceptual framework for discussion of challenges from the area, integrated to the dimensions: people, interaction mode and domotics. A further analysis of the domain is accomplished using the theoretical-methodological referential of Organizational Semiotics. After, we define recommendations to the diversity that base/inspire the inclusive design, guided by physical, perceptual and cognitive abilities, which aim to better represent the concerned diversity. Although developers have the support of gestural recognition technologies that help a faster development, these professionals face another difficulty by not restricting the gestural commands of the application to the standard gestures provided by development frameworks. Therefore, an abstraction of the gestural interaction was idealized through a formalization, described syntactically by construction blocks that originates a grammar of the gestural interaction and, semantically, approached under the view of the residential system. So, we define a set of metrics grounded in the recommendations that are described with information from the preestablished grammar, and still, we conceive and implement in Java, under the foundation of this grammar, a residential system based on gestural interaction for usage with Microsoft Kinect. Lastly, we accomplish an experiment with potential end users of the system, aiming to better analyze the research results / O controle e automa??o de ambientes residenciais dom?tica ? uma ?rea emergente de aplica??o da computa??o. O desenvolvimento de sistemas computacionais para dom?tica ? complexo, devido ? diversidade de potenciais usu?rios e por imergir em um contexto de uso de rela??es emocionais e de constru??o familiar. Atualmente, o foco do desenvolvimento desse tipo de sistema est? direcionado, sobretudo, aos aspectos tecnol?gicos e f?sicos. Em virtude deste fato, a intera??o gestual nesta pesquisa ? investigada sob a ?tica da ?rea de Intera??o Humano-Computador (IHC). Inicialmente, abordamos a tem?tica atrav?s da constru??o de um framework conceitual para discuss?o de desafios da ?rea, de forma integrada as dimens?es: pessoas, modo de intera??o e dom?tica. Uma an?lise mais aprofundada do dom?nio ? realizada empregando o referencial te?rico-metodol?gico da Semi?tica Organizacional. Posteriormente, s?o definidas recomenda??es para a diversidade que embasam/inspiram o design inclusivo, norteado pelas habilidades f?sicas, perceptivas e cognitivas, que visam melhor representar a diversidade em quest?o. Embora os desenvolvedores tenham o apoio de tecnologias de reconhecimento gestual que auxiliam o desenvolvimento mais r?pido , esses profissionais enfrentam outra dificuldade em n?o restringir os comandos gestuais da aplica??o aos gestos padr?es fornecidos por frameworks de desenvolvimento. Portanto, uma abstra??o da intera??o gestual foi idealizada por meio de uma formaliza??o, descrita de forma sint?tica atrav?s de blocos de constru??o que origina uma gram?tica da intera??o gestual e, de forma sem?ntica, abordada sob o ponto de vista do sistema residencial. Assim, definimos um conjunto de m?tricas fundamentadas nas recomenda??es que s?o descritas com informa??es oriundas da gram?tica preestabelecida e, ainda, concebemos e implementamos em Java, sob o alicerce dessa gram?tica, um sistema residencial baseada em intera??o gestual para uso com o Microsoft Kinect. Por fim, realizamos experimento com potenciais usu?rios finais do sistema com o intuito de melhor analisar os resultados da pesquisa