Title
Recognizing Household Activities From Human Motion Data Using Active Learning And Feature Selection
Keywords
Active learning; Activity recognition; Conditional random fields; Feature selection; Support vector machines
Abstract
The ability to accurately recognize human household activities is an important stepping stone toward creating home living assistance systems in the future. Classifying these activities can be difficult due to noisy sensor data, lack of labeled training samples for rare actions and large individual differences in activity execution. In this article, we present two techniques for improving the supervised classification of human activities from motion data: 1) an active learning framework to improve sample efficiency and 2) intelligent feature selection to reduce training time. We demonstrate our techniques using the CMU Multimodal Activity database. © 2010-IOS Press and the authors. All rights reserved.
Publication Date
6-25-2010
Publication Title
Technology and Disability
Volume
22
Issue
1-2
Number of Pages
17-26
Document Type
Article
Personal Identifier
scopus
DOI Link
https://doi.org/10.3233/TAD-2010-0284
Copyright Status
Unknown
Socpus ID
77953763789 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/77953763789
STARS Citation
Zhao, Liyue; Wang, Xi; and Sukthankar, Gita, "Recognizing Household Activities From Human Motion Data Using Active Learning And Feature Selection" (2010). Scopus Export 2010-2014. 832.
https://stars.library.ucf.edu/scopus2010/832