Hierarchical Models for Activity Recognition
- 1 October 2006
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 233-237
- https://doi.org/10.1109/mmsp.2006.285304
Abstract
In this paper we propose a hierarchical dynamic Bayesian network to jointly recognize the activity and environment of a person. The hierarchical nature of the model allows us to implicitly learn data driven decompositions of complex activities into simpler sub-activities. We show by means of our experiments that the hierarchical nature of the model is able to better explain the observed data thus leading to better performance. We also show that joint estimation of both activity and environment of a person outperforms systems in which they are estimated alone. The proposed model yields about 10% absolute improvement in accuracy over existing systemsKeywords
This publication has 5 references indexed in Scilit:
- Recognizing context for annotating a live life recordingPersonal and Ubiquitous Computing, 2006
- Using context-aware computing to reduce the perceived burden of interruptions from mobile devicesPublished by Association for Computing Machinery (ACM) ,2005
- Activity Recognition from User-Annotated Acceleration DataPublished by Springer Nature ,2004
- The graphical models toolkit: An open source software system for speech and time-series processingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Wearable sensing to annotate meeting recordingsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002