Title: A modular and distributed Bayesian framework for activity recognition in dynamic smart environments
Authors: Ramakrishnan, Arun
Preuveneers, Davy
Berbers, Yolande
Issue Date: 3-Dec-2013
Host Document: Lecture Notes in Computer Science vol:8309 pages:293-298
Conference: International Joint Conference on Ambient Intelligence edition:4 location:Dublin, Ireland date:3-5 Deceember 2013
Abstract: Conditional dependencies between the human activities and different contexts (such as location and time) in which they emerge, are well known and have been utilized in the modern Ambient Intelligence (AmI) applications. But the rigid topology of the inference models in most of the existing
systems adversely affects their flexibility and ability to handle inherent sensor ambiguities. Hence, we propose a framework for activity recognition suitable for a distributed and evolving smart environment. On the one hand,
the framework exhibits flexibility to dynamically add and remove contexts through autonomic learning of individual contexts capitalizing the spatially distributed AmI infrastructures. On the other hand, it shows resilience to missing data by boot-strapping and fusing multiple
heterogeneous context information.
Publication status: published
KU Leuven publication type: IC
Appears in Collections:Informatics Section

Files in This Item:
File Description Status SizeFormat
paper.pdf Published 306KbAdobe PDFView/Open Request a copy

These files are only available to some KU Leuven Association staff members


All items in Lirias are protected by copyright, with all rights reserved.