Context Information Refinement for Pervasive Medical Systems
No Thumbnail Available
Date
2007-06
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Addis Ababa University
Abstract
In pervasive medical systems with context-aware computing facility, the quality of
decisions made by medical professionals is influenced by the quality of context information
supplied by the context management sub-system. Central to context management is context
information refinement aimed at deriving context information that can assist applications in
making valuable decisions about what to deliver to users. In this thesis, we identified the
shortcomings of existing works in relation to context information refinement in pervasive
medical systems. The shortcomings are lack of adequate consideration for: quality
parameters of context information, relevance of context information and particular
requirements of the pervasive healthcare domain.
In order to overcome these shortcomings, we proposed a context information refinement
architecture that facilitates and coordinates the refinement procedure starting from
acquisition of context information up until the refined context information is delivered to
the target application (user) in a pervasive medical system by addressing the abovementioned
shortcomings. The architecture is composed of the client mobile device end and
the context refinement server. The client mobile device end consists of components
responsible for tracking the device context (E.g. location), listening to incoming events
from the server, providing interface for specifying service constraints and local caching
services. On the context refinement server side, the major components are the reasoning
and decision engine that performs ontology-supported context reasoning, the service
parameters manager that maintains up-to-date list of service constraints, the context
ontology that models the concepts and relationships between concepts in the pervasive
healthcare domain and the context acquisition component that collects and aggregates
context data from potential context data sources like sensors.
To demonstrate the validity of the proposed architecture, we developed a prototype that
implements the core components of the proposed architecture. The implementation has
been evaluated with a real-life pervasive healthcare scenario and encouraging initial results
have been obtained as an indication to the usability of the proposed architecture in a reallife
setting.
Description
Keywords
Pervasive; Medical ;Systems