Showing papers by "Daqing Zhang published in 2005"

Context-aware infrastructure for personalized healthcare.

Abstract: Ubiquitous computing is shifting healthcare from treatment by professionals in hospitals to self-care, mobile care, home care and preventive care. In order to support the healthcare evolution, a global healthcare system, which links healthcare service providers to an individual's personal and physical spaces, is expected to provide personalized healthcare services at the right time, right place and right manner. This paper presents an overall architecture for such a context-aware healthcare system. The key technologies such as device self-sensing mechanism, context processing framework and a service interoperability platform are identified and elaborated. A personalized healthcare adviser service has been described to illustrate how personalized healthcare can be well supported by the proposed infrastructure.

User preference learning for multimedia personalization in pervasive computing environment

Abstract: Pervasive computing environment and users' demand for multimedia personalization precipitate a need for personalization tools to help people access desired multimedia content at anytime, anywhere, through any devices. User preference learning plays an important role in multimedia personalization. In this paper, we propose a learning approach to acquire and update user preference for multimedia personalization in pervasive computing environment. The approach is based on Master-Slave architecture, of which master device is a device with strong capabilities, such as PC, TV with STB (set-on-box) or PDR (Personal Digital Recorder), etc, and slave devices are pervasive terminals with limited resources. The preference learning and update is done in the master device by utilizing overall user feedback information collected from different devices as opposed to other traditional learning methods that just use partial feedback information in one device. The slave devices are responsible for observing user behavior and uploading feedback information to the master device. The master device is designed to support multiple learning methods: explicit input/modification and implicit learning. The implicit user preference learning algorithm, which applies relevance feedback and Naive Bayes classifier approach, is described in detail.

A peer-to-peer overlay for context information search

Abstract: The widespread use of context information necessitates an efficient wide-area lookup service in pervasive computing. In this paper, we present semantic context space (SCS), a semantic overlay network that facilitates efficient search for context information in distributed environments. Peers in SCS are grouped based on the semantics of their local data and self-organized into a one-dimensional ring space. Context search requests are only routed to the appropriate semantic clusters, reducing unnecessary search cost on peers that have irrelevant context data, and increasing the chances that the context data will be found quickly. By exploring parallelism in a semantic cluster, search request can be found quickly. Our simulation studies demonstrate the effectiveness of SCS.

A peer-to-peer architecture for context lookup

Abstract: As computing technology moves towards pervasive computing, many applications are beginning to make use of context information to adapt to and respond appropriately to their environments. Such a trend necessitates efficient search for context information in wide-area networks. In this paper, we propose a semantic P2P context lookup system. Peers are grouped based on the semantics of their local data which are extracted according to a set of schemas and are self-organized as a semantic overlay network. Context search requests are only routed to the appropriate nodes that have relevant data, reducing unnecessary query traffic and increasing the chances that the context data will be found quickly. To reduce maintenance overheads incurred by high-dimensional semantic overlay networks, we propose a one-dimensional ring space to construct peers and facilitate efficient query routing. Our simulation studies demonstrate the effectiveness of our proposed routing techniques.

Harnessing location-context for content-based services in vehicular systems

Abstract: By incorporating personalised content as context, vehicular telematic services can be made more user-centric, as opposed to vehicle-centric. We develop an ontology based model to integrate both context and content in one unifying framework to facilitate the creation of such services. Scenes captured spontaneously by the user can be a useful index to his or her intent and interests. Our empirical study shows that location-con text leads to a higher precision in recognizing these captured scenes. A "tourist information" prototype based on scene recognition is built, to illustrate one such location-enhanced, user-centric service.