Efficient context prediction for decision making in pervasive health care environments: a case study

Mobile real-time Decision Support Systems (DSSs) find themselves deployed in a highly dynamic environment. Decision makers must be assisted taking into account various time-critical requirements. Perhaps even more important, the quality of the support given by the system depends heavily on the knowledge of the current and future context of the system. A DSS should exhibit inherent proactive behavior and automatically derive the decision making person's needs for specific information from the context that surrounds him. We propose to run a DSS on top of a middleware that helps the decision maker to contextualize information. Moreover, we give a set of requirements the middleware should fulfill to learn, detect and predict patterns in context to optimize the information flow to the decision making person. The approach is made concrete and validated in a case study in the domain of medical health care. Representative location prediction algorithms are evaluated using an existing dataset.

ISBN:978-1-4419-7405-1

Publication year:2011

Accessibility:Closed