Presentation 2005-03-30
Estimation performance of pupil size during blinks
Minoru NAKAYAMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Pupillography can be an index of mental activity and sleepiness, however blinks use to prevent the measuring as an artifact. An estimation method for pupil size during blinks from pupillary changes was developed by use of support vector regression. Pupil responses for periodic brightness changes were prepared and appropriate pupil sizes were given for blinks as training data set. The performance of the trained estimation models were compared and the optimized model was obtained. It was examined that the estimation performance was better than that of the estimation method using MLP.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Pupil size / Blink / Estimation / Support Vector Regression
Paper # MBE2004-127
Date of Issue

Conference Information
Committee MBE
Conference Date 2005/3/23(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 ME and Bio Cybernetics (MBE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Estimation performance of pupil size during blinks
Sub Title (in English)
Keyword(1) Pupil size
Keyword(2) Blink
Keyword(3) Estimation
Keyword(4) Support Vector Regression
1st Author's Name Minoru NAKAYAMA
1st Author's Affiliation CRADLE, Tokyo Institute of Technology()
Date 2005-03-30
Paper # MBE2004-127
Volume (vol) vol.104
Number (no) 757
Page pp.pp.-
#Pages 4
Date of Issue