Modeling Uncertain Context Information via Event Probabilities

A.H. van Bunningen, L. Feng, Peter M.G. Apers

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

2 Citations (Scopus)


To be able to support context-awareness in an Ambient Intelligent (AmI) environment, one needs a way to model context. Previous research shows that a good way to model context is using Description Logics (DL). Since context data is often coming from sensors and therefore exhibits uncertain character, it is essential to take this uncertainty into account when exploiting and reasoning about context data. In this paper, we provide an event-based probabilistic method to model context uncertainty. Each context can be viewed as a probabilistic event, which can be either a basic or complex event. We show how to deal with correlations of events (i.e., inclusion, identicalness, disjunction, and independence) which are inherent in context data and investigate their in uences on the context uncertainty.
Original languageUndefined
Title of host publicationProceedings of the 2nd Twente Data Management Workshop (TDM'06) on Uncertainty in Databases
EditorsAnder de Keijzer, A. de Keijzer, M. van Keulen, Maurice van Keulen
Place of PublicationEnschede, The Netherlands
PublisherCentre for Telematics and Information Technology (CTIT)
Number of pages8
Publication statusPublished - 6 Jun 2006

Publication series

NameCTIT Workshop Series
PublisherCentre for Telematics and Information Technology University of Twente
VolumeWP 06-01
ISSN (Print)1574-0846
ISSN (Electronic)0929-0672


  • METIS-238258
  • EWI-7652
  • IR-63606

Cite this