Context-aware modeling for transmitted spatio-Temporal data from wireless body sensor network

Context-aware computing includes applications that can sense, react, and adapt to their environment. Context is any information that characterizes the situation of an entity. Context, as intended in this paper, can be consideredas a specific type of knowledge. Thus, it is quite natural to investigate any known framework for knowledgerepresentation, and reasoning may be appropriate for handling context. The tradeoff between expressiveness andreasoning complexity has driven most of the research in symbolic knowledge representation in the last two decades. Ontological models have clear advantages regarding support for interoperability and heterogeneity andparticularly well suited to the recognition of high-level context abstractions. However, ontological models aloneare generally unsuited to the recognition of simpler context data, such as, e.g., basic physical activities. Butontologies are not well suited to represent some dynamic context data, such as users adaptation preferences and other requirements, such as mobility and timeliness. Therefore, ontological models should be integrated with other models or at least statistical machine learning methods. Hence, in this research, a hybrid of spatial and ontology models is proposed. Combining ontology and spatial data, advantages such as mobility and timeliness are added to the other advantages of the ontology-based model.

Keywords:

hybrid context-aware modeling , ontology model , spatial model , Reification , 4D-fluent , N-ary , Protégé , Chronos , spatio-Temporal Data