Skip to Main content Skip to Navigation

Learning Situation Models for Providing Context-Aware Services

Abstract : This thesis addresses the problem of learning situation models for
providing context-aware services in an intelligent environment. First, the
notion of context for modeling human behavior in an intelligent environment
is motivated and introduced. Context is represented by a situation model
describing environment, users and their activities. Two example
implementations for the situation model are proposed. A framework for
acquiring and evolving different layers of a situation model is then
introduced. Several novel learning methods are part of this framework: role
detection per entity, unsupervised extraction of situations from multimodal
data, supervised learning of situation representations, and the evolution of
a predefined situation model with feedback. The situation model serves as
frame and support for the different methods, permitting to stay in an
intuitive declarative framework. The proposed framework has been implemented
and evaluated for an intelligent home environment.
Document type :
Complete list of metadatas

Cited literature [27 references]  Display  Hide  Download
Contributor : Oliver Brdiczka <>
Submitted on : Monday, June 4, 2007 - 2:45:33 PM
Last modification on : Thursday, November 19, 2020 - 12:59:39 PM
Long-term archiving on: : Thursday, April 8, 2010 - 6:51:06 PM


  • HAL Id : tel-00151497, version 1



Oliver Brdiczka. Learning Situation Models for Providing Context-Aware Services. Human-Computer Interaction [cs.HC]. Institut National Polytechnique de Grenoble - INPG, 2007. English. ⟨tel-00151497⟩



Record views


Files downloads