SIA OpenIR  > 机器人学研究室
A Real-time Human Activity Recognition Approach with Generalization Performance
Wei, Shi-Jie1; Zhang B(张弼)2,3; Tan XW(谈晓伟)2,3,4; Zhao XG(赵新刚)2,3; Ye D(叶丹)1
Department机器人学研究室
Conference Name39th Chinese Control Conference, CCC 2020
Conference DateJuly 27-29, 2020
Conference PlaceShenyang, China
Author of SourceSystems Engineering Society of China (SESC) ; Technical Committee on Control Theory (TCCT) of Chinese Association of Automation (CAA)
Source PublicationProceedings of the 39th Chinese Control Conference, CCC 2020
PublisherIEEE Computer Society
Publication PlaceWashington, USA
2020
Pages6334-6339
Indexed ByEI
EI Accession number20203909242603
Contribution Rank2
ISSN1934-1768
ISBN978-9-8815-6390-3
KeywordHuman Activity Recognition Feature Selection Generalization Performance Real-time Performance Transfer Learning
AbstractThe current human activity recognition (HAR) methods need training data from users. The data collection causes discomfort to the users and most of the studies ignore the real-time performance of classification. This paper presents a real-time human activity recognition approach with strong generalization performance. It uses existing dataset to avoid long-term data collection of subjects, so that the machine can be quickly applied to each specific individual. Also, it takes advantage of both combined accuracy and limited feature selection proposed by this paper to implement feature-selection-based transfer learning which improves HAR in both real-time and generalization performance. In view of the recognition time and accuracy, the depth neural network is selected, changeable structure of which is more suitable for feature selection. This approach utilizes four inertial measurement units placed on the outside of human thighs and shanks. A total of seven activities are taken into account that includes level-walking, upstairs, downstairs, uphill, downhill, standing and sitting. The experiments are performed on six healthy male subjects in free-living settings to evaluate the efficacy of the algorithm. This approach achieved a notable activity recognition accuracy of 98.89%, and reported a fast average activity classification time of 28.6 ms.
Language英语
Document Type会议论文
Identifierhttp://ir.sia.cn/handle/173321/27703
Collection机器人学研究室
Corresponding AuthorZhang B(张弼)
Affiliation1.College of Information Science and Engineering, Northeastern University, Shenyang 110819, P. R. China
2.State Key Lab of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, P. R. China
3.Institutes of Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110016, P. R. China
4.University of Chinese Academy of Sciences, Beijing 100049, P. R. China
Recommended Citation
GB/T 7714
Wei, Shi-Jie,Zhang B,Tan XW,et al. A Real-time Human Activity Recognition Approach with Generalization Performance[C]//Systems Engineering Society of China (SESC), Technical Committee on Control Theory (TCCT) of Chinese Association of Automation (CAA). Washington, USA:IEEE Computer Society,2020:6334-6339.
Files in This Item:
File Name/Size DocType Version Access License
A Real-time Human Ac(2941KB)会议论文 开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wei, Shi-Jie]'s Articles
[Zhang B(张弼)]'s Articles
[Tan XW(谈晓伟)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wei, Shi-Jie]'s Articles
[Zhang B(张弼)]'s Articles
[Tan XW(谈晓伟)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wei, Shi-Jie]'s Articles
[Zhang B(张弼)]'s Articles
[Tan XW(谈晓伟)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: A Real-time Human Activity Recognition Approach with Generalization Performance.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.