• Home
  • Browse
    • Current Issue
    • By Issue
    • By Author
    • By Subject
    • Author Index
    • Keyword Index
  • Journal Info
    • About Journal
    • Aims and Scope
    • Editorial Board
    • Editorial Staff
    • Publication Ethics
    • Indexing and Abstracting
    • Related Links
    • FAQ
    • Peer Review Process
    • News
  • Guide for Authors
  • Submit Manuscript
  • Reviewers
  • Contact Us
 
  • Login
  • Register
Home Articles List Article Information
  • Save Records
  • |
  • Printable Version
  • |
  • Recommend
  • |
  • How to cite Export to
    RIS EndNote BibTeX APA MLA Harvard Vancouver
  • |
  • Share Share
    CiteULike Mendeley Facebook Google LinkedIn Twitter Telegram
Journal of Advances in Computer Research
Articles in Press
Current Issue
Journal Archive
Volume Volume 9 (2018)
Volume Volume 8 (2017)
Volume Volume 7 (2016)
Issue Issue 4
Issue Issue 3
Issue Issue 2
Issue Issue 1
Volume Volume 6 (2015)
Volume Volume 5 (2014)
Volume Volume 4 (2013)
Volume Volume 3 (2012)
Volume Volume 2 (2011)
Volume Volume 1 (2010)
Tavana, M., Mohammadi, M., Parvin, H. (2016). A Semi-Supervised Human Action Learning. Journal of Advances in Computer Research, 7(3), 15-32.
Mohsen Tavana; Mohammad Mohammadi; Hamid Parvin. "A Semi-Supervised Human Action Learning". Journal of Advances in Computer Research, 7, 3, 2016, 15-32.
Tavana, M., Mohammadi, M., Parvin, H. (2016). 'A Semi-Supervised Human Action Learning', Journal of Advances in Computer Research, 7(3), pp. 15-32.
Tavana, M., Mohammadi, M., Parvin, H. A Semi-Supervised Human Action Learning. Journal of Advances in Computer Research, 2016; 7(3): 15-32.

A Semi-Supervised Human Action Learning

Editorial, Volume 7, Issue 3 - Serial Number 25, Summer 2016, Page 15-32  XML PDF (1062 K)
Authors
Mohsen Tavana1; Mohammad Mohammadi1; Hamid Parvin 2
1Department of Computer Engineering, Mamasani Branch, Islamic Azad University, Mamasani, Iran
2Department of Computer Engineering, Mamasani Branch, Islamic Azad University, Mamasani, Iran Young Researchers and Elite Club, Mamasani Branch, Islamic Azad University, Mamasani, Iran
Abstract
Exploiting multimodal information like acceleration and heart rate is a promising method to achieve human action recognition. A semi-supervised action recognition approach AUCC (Action Understanding with Combinational Classifier) using the diversity of base classifiers to create a high-quality ensemble for multimodal human action recognition is proposed in this paper. Furthermore, both labeled and unlabeled data are applied to obtain the diversity measure from multimodal human action recognition. Any classifiers can be applied by AUCC as its base classifier to create the human action recognition model, and the diversity of classifier ensemble is embedded in the error function of the model. The model’s error is decayed and back-propagated to the basic classifiers through each iteration. The basic classifiers’ weights are acquired during creation of the ensemble to guarantee the appropriate total accuracy of the model. Considerable experiments have been done during creation of the ensemble. Extensive experiments show the effectiveness of the offered method and suggest its superiority of exploiting multimodal signals.
Keywords
Action Learning; Ensemble Learning; Machine Learning
Statistics
Article View: 1,599
PDF Download: 11,105
Home | Glossary | News | Aims and Scope | Sitemap
Top Top

Journal Management System. Designed by sinaweb.