Presentation 2011-06-09
Stress state classification based on photoplethysmogram by supervised dimensionally reduction
Ying LI, Keiichi HORIO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we introduce a latent variables extraction method to improve a classification of stress states. Features obtained from a photoplethysmogram include various kinds of physical quantities, thus direct comparison between features causes degradation of classification. In this study, Multiple Relational Embedding (MRE) which reconstructs data distribution in low dimensional space based on similarity between data represented in some different measures is used. Furthermore class information of data can be used as one of the measure in MRE, then data distribution which is suitable for classification can be realized.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) stress state classification / photoplethysmogram / supervised dimensionality reduction
Paper # SIS2011-3
Date of Issue

Conference Information
Committee SIS
Conference Date 2011/6/2(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Smart Info-Media Systems (SIS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Stress state classification based on photoplethysmogram by supervised dimensionally reduction
Sub Title (in English)
Keyword(1) stress state classification
Keyword(2) photoplethysmogram
Keyword(3) supervised dimensionality reduction
1st Author's Name Ying LI
1st Author's Affiliation Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology()
2nd Author's Name Keiichi HORIO
2nd Author's Affiliation Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology
Date 2011-06-09
Paper # SIS2011-3
Volume (vol) vol.111
Number (no) 78
Page pp.pp.-
#Pages 4
Date of Issue