computing and networking environments as being filled with sensors that can determine various types of contexts of its inhabitants, such as location, activity and vital signs. While such information is useful in providing context-sensitive services to the inhabitants to promote intelligent independent living, however in reality, both sensed and interpreted contexts may often be ambiguous. Thus, a challenge facing the development of realistic and deployable context-aware services is the ability to handle am- biguous contexts to prevent hazardous situations. In this paper, we propose a framework which supports efficient context-aware data fusion for healthcare applications that assume contexts could be ambiguous. Our framework provides a systematic approach to derive context fragments, and deal with context ambiguity in a probabilistic manner. We also incorporate the ability to represent contexts within the applications, and the ability to easily compose rules to mediate ambiguous contexts. Through simulation and analysis, we demonstrate the effectiveness of our proposed framework for monitoring elderly people in the smart home environment.
展开▼
