Learning from less for better: semi-supervised activity recognition via shared structure discovery

Yao, Lina, Nie, Feiping, Sheng, Quan Z., Gu, Tao, Li, Xue and Wang, Sen (2016). Learning from less for better: semi-supervised activity recognition via shared structure discovery. In: UbiComp 2016 - Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing. 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2016, Heidelberg, Germany, (13-24). 12-16 September 2016. doi:10.1145/2971648.2971701

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads

Author Yao, Lina
Nie, Feiping
Sheng, Quan Z.
Gu, Tao
Li, Xue
Wang, Sen
Title of paper Learning from less for better: semi-supervised activity recognition via shared structure discovery
Conference name 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2016
Conference location Heidelberg, Germany
Conference dates 12-16 September 2016
Convener ACM
Proceedings title UbiComp 2016 - Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing
Journal name UbiComp 2016 - Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing
Place of Publication New York, NY, United States
Publisher Association for Computing Machinery
Publication Year 2016
Sub-type Fully published paper
DOI 10.1145/2971648.2971701
Open Access Status Not yet assessed
ISBN 9781450344616
Start page 13
End page 24
Total pages 12
Language eng
Formatted Abstract/Summary
Despite the active research into, and the development of, human activity recognition over the decades, existing techniques still have several limitations, in particular, poor performance due to insufficient ground-truth data and little support of intra-class variability of activities (i.e., the same activity may be performed in different ways by different individuals, or even by the same individuals with different time frames). Aiming to tackle these two issues, in this paper, we present a robust activity recognition approach by extracting the intrinsic shared structures from activities to handle intra-class variability, and the approach is embedded into a semi-supervised learning framework by utilizing the learned correlations from both labeled and easily-obtained unlabeled data simultaneously. We use ℓ2,1 minimization on both loss function and regularizations to effectively resist outliers in noisy sensor data and improve recognition accuracy by discerning underlying commonalities from activities. Extensive experimental evaluations on four community-contributed public datasets indicate that with little training samples, our proposed approach outperforms a set of classical supervised learning methods as well as those recently proposed semisupervised approaches.
Keyword Activity recognition
Optimization
Semi-supervised learning
Shared structure analysis
Q-Index Code E1
Q-Index Status Provisional Code
Institutional Status UQ

Document type: Conference Paper
Sub-type: Fully published paper
Collections: HERDC Pre-Audit
School of Information Technology and Electrical Engineering Publications
 
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 6 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Tue, 01 Nov 2016, 11:06:13 EST by System User on behalf of Learning and Research Services (UQ Library)