<p>As the development of context aware applications has evolved, there has been a corresponding increase in need for more sophisticated system. The aim for this thesis is the development of a dynamical P2P network system which is based on locations. The P2P network is self organizing and in a lightweight format. Modern technical solutions including   AGPS have facilitated the work associated with the ability to position users and modern mathematical solutions such as spherical trigonometry provides the P2P system with the necessary accuracy even for short distances. The P2P system works on different Java platforms including JSE, JME and Android. Unfortunately the 3G network distributor has not yet solved a NAT traversal problem, which means that the P2P network self organization and architecture has only been proved by means of simulations. Another problem is that certain mathematical formulas are required for the spherical trigonometry and the limitation for JME is that it is unable to handle inverse trigonometry. However, the Android and JSE versions can form a correct P2P network, under the condition that the Android device uses a WIFI connection point outside the 3G distributor network system. This thesis reports the successful testing of the locations-based P2P network.</p> / MediaSense

Applications that can change their behaviour based on the user’s contextual appearance are called context-aware applications. Applications developed for smart phones, which carry a multitude of different sensors, and actuators have gained a huge penetration within the market. Frequent usage of mobile applications such as home automation, friend finder, car accident notification and tracking etc; have seen an increased growth from the user’s perspective. However, for such applications, it is necessary to have knowledge of the performance and cost parameters, which directly affect the QoE of the application users.  This thesis investigates possible context aware behaviours in real time situations and measures the Quality of Experience (QoE) as well as identifying the Packet Delay Variation (PDV). The background and some state-of-the-art technologies are studied, and based on these studies, three scenarios are designed and implemented and based on their QoE, results and conclusions are presented, with the  results obtained  shown by means of   graphical representations of the QoE and PDV values.

As the development of context aware applications has evolved, there has been a corresponding increase in need for more sophisticated system. The aim for this thesis is the development of a dynamical P2P network system which is based on locations. The P2P network is self organizing and in a lightweight format. Modern technical solutions including   AGPS have facilitated the work associated with the ability to position users and modern mathematical solutions such as spherical trigonometry provides the P2P system with the necessary accuracy even for short distances. The P2P system works on different Java platforms including JSE, JME and Android. Unfortunately the 3G network distributor has not yet solved a NAT traversal problem, which means that the P2P network self organization and architecture has only been proved by means of simulations. Another problem is that certain mathematical formulas are required for the spherical trigonometry and the limitation for JME is that it is unable to handle inverse trigonometry. However, the Android and JSE versions can form a correct P2P network, under the condition that the Android device uses a WIFI connection point outside the 3G distributor network system. This thesis reports the successful testing of the locations-based P2P network. / MediaSense

A speech controlled animation system is both a useful application program as well as a laboratory in which to investigate context aware applications as well as controlling errors. The user need not have prior knowledge or experience in animation and is yet able to create interesting and meaningful animation naturally and fluently. The system can be used in a number of applications ranging from PowerPoint presentations to simulations to children’s storytelling tools. / Singapore-MIT Alliance (SMA)

Aplicações cientes de contexto precisam de mecanismos para recuperar informações sobre o seu contexto de execução. Com base no contexto atual, tais aplicações são capazes de se autoadaptar para fornecer informações e serviços adequados aos seus usuários. A abordagem comum para infraestruturas de apoio às aplicações sensíveis ao contexto fornece serviços para a descoberta de recursos através da utilização de pares <chave-valor> e motores que executam apenas correspondência sintática. Esta abordagem não considera as possíveis relações semânticas entre as palavras-chave usadas. Portanto, a sua expressividade semântica limitada, leva a um serviço de descoberta que provê baixa taxa de recuperação e baixa acurácia. Este trabalho apresenta a utilização de uma outra abordagem para o serviço de contexto e descoberta, que utiliza ontologias para representar os recursos do contexto de execução e capturar a semântica da consulta do usuário, melhorando assim o processo de descoberta para a autoadaptação de sistemas sensíveis ao contexto. A abordagem proposta oferece também pontos de extensão para as aplicações clientes através da utilização de outras ontologias. Esta abordagem foi integrada à infraestrutura CDRF, de forma a adicionar semântica aos serviços desenvolvidos neste projeto. Exemplos de aplicações são também propostos para demonstrar a utilização dos novos serviços. / Context-aware applications demand ways of retrieving context information from the environment. Based on the current context, such applications are able to self-adapt to provide the correct information and services to its users. The usual approach for supporting infrastructures for context-aware applications provides facilities for resource discovery using <key-value> pairs and discovery engines that perform syntactic matching. This approach does not consider the possible semantic relations between the keywords used. So its limited semantic expressiveness often leads to poor discovery results. This paper presents the use of a different approach for service discovery that uses ontologies to represent resources and capture the semantics of the users query, improving the discovery process for self-adaptation of context-aware systems. The proposed approach also offers extension hooks to the client applications through the use of other ontologies. This approach is integrated into the CDRF framework and adds semantics to the services developed in that project. Example applications are also proposed to demonstrate the use of the new services.

Aplicações cientes de contexto precisam de mecanismos para recuperar informações sobre o seu contexto de execução. Com base no contexto atual, tais aplicações são capazes de se autoadaptar para fornecer informações e serviços adequados aos seus usuários. A abordagem comum para infraestruturas de apoio às aplicações sensíveis ao contexto fornece serviços para a descoberta de recursos através da utilização de pares <chave-valor> e motores que executam apenas correspondência sintática. Esta abordagem não considera as possíveis relações semânticas entre as palavras-chave usadas. Portanto, a sua expressividade semântica limitada, leva a um serviço de descoberta que provê baixa taxa de recuperação e baixa acurácia. Este trabalho apresenta a utilização de uma outra abordagem para o serviço de contexto e descoberta, que utiliza ontologias para representar os recursos do contexto de execução e capturar a semântica da consulta do usuário, melhorando assim o processo de descoberta para a autoadaptação de sistemas sensíveis ao contexto. A abordagem proposta oferece também pontos de extensão para as aplicações clientes através da utilização de outras ontologias. Esta abordagem foi integrada à infraestrutura CDRF, de forma a adicionar semântica aos serviços desenvolvidos neste projeto. Exemplos de aplicações são também propostos para demonstrar a utilização dos novos serviços. / Context-aware applications demand ways of retrieving context information from the environment. Based on the current context, such applications are able to self-adapt to provide the correct information and services to its users. The usual approach for supporting infrastructures for context-aware applications provides facilities for resource discovery using <key-value> pairs and discovery engines that perform syntactic matching. This approach does not consider the possible semantic relations between the keywords used. So its limited semantic expressiveness often leads to poor discovery results. This paper presents the use of a different approach for service discovery that uses ontologies to represent resources and capture the semantics of the users query, improving the discovery process for self-adaptation of context-aware systems. The proposed approach also offers extension hooks to the client applications through the use of other ontologies. This approach is integrated into the CDRF framework and adds semantics to the services developed in that project. Example applications are also proposed to demonstrate the use of the new services.

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21217号 / 情博第670号 / 新制||情||115(附属図書館) / 京都大学大学院情報学研究科通信情報システム専攻 / (主査)教授 五十嵐 淳, 教授 石田 亨, 教授 山本 章博 / 学位規則第4条第1項該当 / Doctor of Informatics / Kyoto University / DFAM

Delivering accurate and opportune information on people's activities and behaviors has become one of the most important tasks within pervasive computing. Its wide spectrum of potential applications in medical, entertainment, and tactical scenarios, motivates further research and development of new strategies to improve accuracy, pervasiveness, and eciency. This dissertation addresses the recognition of human activities (HAR) with wearable sensors in three main regards: In the rst place, physiological signals have been incorporated as a new source of information to improve the recognition accuracy achieved by conventional approaches, which rely on accelerometer signals solely. A new HAR system, Centinela, was born from such concept, employing structural feature extraction along with classier ensembles, and achieving over 95% of recognition accuracy. In the second place, real time activity recognition was enabled by Vigilante, a mobile HAR framework under the AndroidTM platform. Providing immediate feedback on the user's activities is especially benecial in healthcare and military applications, which may require alert triggering or support of decision making. The evaluation demonstrates that Vigilante is energy ecient while maintaining high accuracy (i.e., up to 96.8%) and low response time. The system features MECLA, a mobile library for the evaluation of classification algorithms, which is also suitable for further machine learning applications. Finally, the activity recognition accuracy is improved by two new strategies for decision fusion and selection in multiple classier systems: the failure product and the precision-recall dierence. The experimental analysis conrms that the presented methods are benecial, not only for recognizing human activities, but also for many other classication problems.

Submitted by Johnny Rodrigues (johnnyrodrigues@ufcg.edu.br) on 2018-08-03T21:52:09Z No. of bitstreams: 1 HUGO FEITOSA DE FIGUEIRÊDO - DISSERTAÇÃO PPGCC 2009..pdf: 2524258 bytes, checksum: 14119ff36e281c839965a8a0ddc61686 (MD5) / Made available in DSpace on 2018-08-03T21:52:09Z (GMT). No. of bitstreams: 1 HUGO FEITOSA DE FIGUEIRÊDO - DISSERTAÇÃO PPGCC 2009..pdf: 2524258 bytes, checksum: 14119ff36e281c839965a8a0ddc61686 (MD5) Previous issue date: 2009-09-18 / As aplicações cientes de contexto estão se tornando populares, como consequência de avanços tecnológicos em dispositivos móveis, sensores e comunicação de redes sem fio. Entretanto, desenvolver um sistema ciente de contexto envolve vários desafios. Por exemplo, quais serão as informações contextuais, como representar, adquirir e processar essas informações e como estas serão utilizadas pelo sistema. Alguns frameworks e middlewares foram propostos na literatura para auxiliar programadores a superar esses desafios, porém ainda faltam mecanismos que auxiliem usuários finais na personalização dessas aplicações. Além disso, a maioria das soluções propostas não possui um modelo de contexto extensível baseado em ontologias ou n˜ao utiliza uma comunicação que permita aproveitar as potencialidades dos modelos que seguem esta abordagem. Este trabalho propõe uma infraestrutura de suporte a aplicações cientes de contexto que possui um modelo de contexto extensível baseado em ontologias e comunicação entre os elementos utilizando SPARQL e SPARQL Update. Também são propostas ferramentas para usuários finais criarem e validarem visualmente regras contextuais. / Context-aware applications have become popular as a consequence of the technological advances on mobile devices, sensors, and wireless network communication. However, there are many challenges in the development of these applications. For instance, which contextual information will be used, how to represent, capture, proccess and use the context in the system are some of such application development challenges. Frameworks and middlewares to improve context-aware application development have been proposed, but they still lack helping users in customizing their applications. Furthemore most proposed solutions do not have an extensible ontology-based context model and an efficient communication which enables to explore the main features of such approach. This work proposes an infrastructure to support context-aware applications, which uses an extensible ontology-based context model and communication through SPARQL and SPARQL Update. Also there are visual tools aiming to helpend-users in the creation and validation of context rules.

De nos jours, la façon d’utiliser les applications mobiles dans le domaine des transports offre de nouveaux défis liés aux spécificités de l’environnement, comme la forte mobilité des terminaux, leur répartition, ou encore le réseau instable de communication. La plupart des applications existantes ont des contraintes de fonctionnement qui les rendent inadaptées si les conditions d’exécution évoluent rapidement. Cela rend intéressant l’utilisation d’un cadre unifié de conception et d’exécution, capable de gérer ces applications. Nos travaux portent, dans un premier temps, sur une étude des applications mobiles et de leur comportement, en fonction du contexte d’exécution. Nous considérons le cas des applications dédiées aux transports, conçues pour accompagner et assister un usager dans son déplacement (navigation, sécurité routière, applications des moyens de transports, etc.). Nous identifions les éléments du contexte propres aux applications fortement mobiles et les modélisons. Dans un second temps, nous proposons un cadre dynamique et sensible au contexte, permettant le déploiement de nouveaux services « à la volée » ainsi que leur adaptation pour une meilleure utilisation des ressources dans des milieux très évolutifs. Nous nous focalisons sur le côté réactif, permettant d’adapter le comportement des applications à leurs nouvelles conditions d’utilisation. Les applications sont décomposées en services de base avec un couplage lâche pour une plus grande flexibilité. Nous utilisons une architecture orientée service, qui permet la réutilisation des services communs à plusieurs applications mais aussi la gestion du contexte au travers de services équivalents mais capables de fonctionner dans des conditions différentes.Nous montrons, grâce au prototype de notre plateforme CATS (Context-Aware Transportation Services), d’abord la faisabilité d’une plateforme à services sur des terminaux portables. Nous testons ensuite plusieurs scénarios afin de démontrer la réactivité des adaptations aux changements de contexte. Dans cette thèse nous proposons une vue d’ensemble sur la création et la gestion des applications sensibles au contexte pour le domaine des transports. Le but de notre démarche est d’assurer le bon fonctionnement de l’ensemble des applications d’un utilisateur, malgré les changements dynamiques du contexte. / The use of mobile applications in the transportation domain raises a multitude ofchallenges, related to the specific execution environment: highly mobile and distributed devices, unstable communication networks, etc. Most of the existing applications are not flexible enough to cope with the rapidly changing environment. It would be interesting to provide a unified frame for the design and execution of such applications, offering management capabilities as well. We propose a study of the mobile applications and their behavior in relation with thecontext. We consider a certain type of applications, designed to accompany and assist users on the move (navigation, traffic security, applications related to a means of transport, etc.). We identify the context elements which are characteristic to highly mobile applications and we propose a context model for the transportation domain. In order to handle multiple applications at a time, we propose a dynamic and contextaware framework, capable of deploying services “on the fly”. We consider applications built through the assembly of services, allowing them to adapt to the execution environment and make the best use of the available resources. We focus on the reaction of the applications to the changes in the environment. Applications are built of services and thus benefit from loose coupling, allowing them to be flexible. A service oriented architecture brings further advantages, notably that services can be shared between applications and that a service can have multiple implementations. We manage the adaptation to new conditions of use through equivalent services built for different context situations. The framework that we have proposed, called CATS (Context-Aware Transportation Services), has been tested thanks to a prototype. We were able to prove the feasibility of the framework as well as evaluate several testing scenarios, showing the reactivity of the applications to context changes. This work proposes a complete view of the design and management of context-aware applications for the transport domain. Our goal is to enhance user experience by ensuring the well functioning of his/her applications despite the ever changing context.