Thèse de doctorat en Informatique
Sous la direction de Mounir Mokhtari.
Soutenue en 2008
Modèle abstrait de service pour la fourniture adaptative d'assistance dans les environnements de vie ambiants
Pas de résumé disponible.
The rapid development of information and communication technologies is opening a large variety of new services and aids not only for independent people, but also for dependent persons due to physical/cognitive restriction or the elderly. Combining technical aids and mobile technology allows those people to benefit from an independent living through ambient intelligent environments. The term ambient intelligent (AmI) describes a pervasive, transparent infrastructure able to observe people without interfering in their life, supplying an intelligent environment to adapt to the needs and requirements of the user and the environment itself. Ambient Intelligence (AmI) is a step beyond Ubiquitous and Pervasive Computing. There is an explicit focus on individuals in an environment. So far, the individual has had to adapt to what the computer/device could do for the person; now with AmI the computer/device must adapt to the individual and his current context. This concept should be applied to develop AmI-enabled devices/products to be deployed in different application domains. Personalized home care assistance is an emerging application area where AmI can play an important role. Some examples of claimed services can be summarized as following : - Indoor/outdoor Control Services : open a door, elevator button, traffic light call - Navigation Assistance Services : get accessible circuit to reach a target, navigation inside building… - Information Service : Agenda, reminders, bus timetable… - Security Assistance Services : emergency call, remote assistance… This research work focuses on designing and developing an Assistive Service Provision Framework in Ambient Intelligent space. This architecture, based on a distributed approach, ensures service design, deployment and selection processes. The provision of services is designed according to two main adaptation levels : - Service Selection level : A first adaptation phase concerns the service selection process. In fact, there is a variety of services which can offer assistance for users in their living environment, however they could be more of a hindrance than a help if all of them will be provided at once. A selection according to the location, preference, resource capabilities, etc is relevant in this case (Context aware services). Only suitable services overcoming a handicap situation and satisfied in term of required dependency are eligible to be provided to a user in a given location. - Service Presentation level : The second adaptation phase is about the personalization of the presentation layer of services according to user (user profile). This adaptation is crucial especially when dealing with people having special needs (dependant people). Developed software framework was integrated in a global system deployed within pilot sites (residence of dependant people) in order to validate its impact when involving real end-users in ecological situations.