Presentation 1998/7/18
A Smoothing and Prediction Model of Pupil Size for Blink Artifact in watching TV program
Minoru Nakayama, Yasutaka Shimizu,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) It is well known that pupil size measuring is influenced by pupillary noise and blink. This paper describes a development of smoothing and prediction model of pupil size for blink artifact. The model development was based on 3 layered perceptron with backpropagation method. First, the model was trained by pupil response to brightness change, and the model could smooth down the pupil temporal changes. Second, the model was trained by pupil response with artificial blinks. The model could also smooth down the pupillary changes, and predict pupil size while blinks. The model was applied to pupillary changes in watching TV program. The performance of removing brightness influence was evaluated one-way ANOVA. The sampling rate for pupil size could be improved to 10Hz from 3Hz by using the model processing.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Pupil size / Pupillary noise / Blinks / Artificial Neural Networks / TV program
Paper # ET98-50
Date of Issue

Conference Information
Committee ET
Conference Date 1998/7/18(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 Educational Technology (ET)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Smoothing and Prediction Model of Pupil Size for Blink Artifact in watching TV program
Sub Title (in English)
Keyword(1) Pupil size
Keyword(2) Pupillary noise
Keyword(3) Blinks
Keyword(4) Artificial Neural Networks
Keyword(5) TV program
1st Author's Name Minoru Nakayama
1st Author's Affiliation CRADLE(The Center for Research and Development of Educational Technology), Tokyo Institute of Technology()
2nd Author's Name Yasutaka Shimizu
2nd Author's Affiliation Graduate School of Decision Science and Technology, Tokyo Institute of Technology
Date 1998/7/18
Paper # ET98-50
Volume (vol) vol.98
Number (no) 183
Page pp.pp.-
#Pages 8
Date of Issue