BROWSE
Detail
Conference Paper
A Practical Approach Implementing a Wearable Human Activity Detector for the Elderly Care
Cited 0 time in 
Share 
Share
- Authors
- Chankyu Park, Jaehong Kim, Ho-jin Choi
- Issue Date
- 2012-12
- Citation
- International Conference on Ubiquitous Information Technologies and Applications (CUTE) 2012 (LNEE 214), v.214, pp.407-414
- Publisher
- Springer
- Language
- English
- Type
- Conference Paper
- Abstract
- Human activity recognition is widely researched in the various filed these days. For the aged care, the one of the most important activities of old people is fall, since it causes often serious physical and psychological results. Many researchers have studied human activity recognition techniques in various domains; however none released to a commercial product satisfying the old people requirements, which are comfortable to wear it, weight-lighted and having exact accuracy to detect emergency activity and longer battery durance. Thus, to address them, we propose a practical approach procedure for getting best minimum feature sets and classification accuracy. We also do experiments for comparing the two features reduction techniques and four classification techniques in order to discriminate five each basic human activities, such as fall for the aged care, walking, hand related shocks, walking with walker and lastly steady activity which includes no movement and slow arbitrary hand and body motions. © 2013 Springer Science+Business Media.
- KSP Keywords
- Classification techniques, Elderly Care, Features reduction, Human activity recognition, Old people, Practical approach, aged care, classification accuracy, feature set, reduction technique