Thèse de l ’ Université de Lyon The Context - aware Middleware in Ambient Intelligence Pour l ’ obtention du titre de Docteur

Almost 20 years ago, Marc Weiser envisioned the prospect of computer in 21st century, and pr o-posed the pioneering notion of ubiquitous computing. One of Weiser’s primary ideas has recently evolvedto a more general paradigm known as context awareness, becoming a central research theme in many otherubiquitous computing programs. From Active Badge considered as the first context -aware application,there are numerous attempts to build effective context-aware systems. However, how to acquire context,how to process context and how to create context-aware applications is still faced with enormous chal-lenges in the both of research and practice. This dissertation investigates deeply some chosen key issues in context awareness and develops acontext-aware middleware. The main research contributions are presented in three categories: a spatial -temporal context represent model, a context-aware middleware and an intelligence context inference en-gine. The spatial-temporal context representation model is proposed to organize context and relations forcontext-aware system. Ontology-based method is adopted to construct our model, supporting bothknowledge sharing and reuse as well as logic inference. This model adopts two -layer hierarchy structurefor different situation. The higher layer comes up with the generic common context, while the lower layerfocuses on various specific situations. Differing from existing models, besides taking locational factors i n-to account, it supports different historical context service depending on different context resource. Thesecontext histories may be used to predict and infer the context. A context-aware middleware is designed as a platform associated with context retrieval and contextprocessing. It is organized in two layers: the low layer provides a solution to integrate sensors and actu a-tors with a standardized data representation; the high layer: versatile context interpreter focuses on contextprocessing, which is made up of four parts: Context Aggregator, Inference Engine, Context KnowledgeBase, and Query Engine in charge of context inferences, expressive query, and persistent storage. Thismiddleware provides an environment for rapid prototyping of context aware services in ambient intellig ent. The intelligent inference engine is the central and intellectual component of context -aware middle-ware. We review all the methods on activity context recognition published in three premier conferences inpast decade and conclude that activity context recognition is divided into three facets: basic activity infer-ence, dynamic activity analysis and future activity recommendation. Then we propose an intelligent infe r-ence engine based on our context-aware middleware. Beside satisfying requirements of checking the con-text consistency, our inference engine integrates the three most popular methods on activity contextrecognition: Rules, Decision Tree, and Hide Markov Model. It provides a solution for all facets of activitycontext recognition based on our context-ware middleware. The individuals’ information collecting fromtheir social networks under permission are leveraged to train intelligent inference engine. We finally use two scenarios (applications) to explain the generic process to develop applicatio n viaour middleware, and compare and analyze the main aspects of our middleware with other five represent a-tive context-aware applications. Our middleware profits good features from existing context -aware sys-tems and improve intelligence via supporting activity context recognition. It provides an efficient platformfor a rapid developing of new context-aware applications in ambient intelligence.