DocumentCode
3684168
Title
A multimodal stress monitoring system with canonical correlation analysis
Author
Unsoo Ha;Changhyeon Kim;Yongsu Lee;Hyunki Kim;Taehwan Roh;Hoi-Jun Yoo
Author_Institution
Korean Advanced Institute of Science and Technology(KAIST), 373-1, Guseong-dong, Yuseong-gu, Daejeon, 305-701, Republic of Korea
fYear
2015
Firstpage
1263
Lastpage
1266
Abstract
The multimodal stress monitoring headband is proposed for mobile stress management system. It is composed of headband and earplugs. Electroencephalography (EEG), hemoencephalography (HEG) and heart-rate variability (HRV) can be achieved simultaneously in the proposed system for user status estimation. With canonical correlation analysis (CCA) and temporal-kernel CCA (tkCCA) algorithm, those different signals can be combined for maximum correlation. Thanks to the proposed combination algorithm, the accuracy of the proposed system increased up to 19 percentage points than unimodal monitoring system in n-back task.
Keywords
"Monitoring","Stress","Electroencephalography","Heart rate variability","Biomedical monitoring","Correlation","Support vector machines"
Publisher
ieee
Conference_Titel
Engineering in Medicine and Biology Society (EMBC), 2015 37th Annual International Conference of the IEEE
ISSN
1094-687X
Electronic_ISBN
1558-4615
Type
conf
DOI
10.1109/EMBC.2015.7318597
Filename
7318597
Link To Document