Estimation of sleepiness using pupillary response and its frequency components

Authors:
M. Nakayama;K. Yamamoto;F. Kobayashi
Affiliations:
Human System Science, Graduate School of Decision Science and Technology, Tokyo Institute of Technology, Ookayama, Meguro, Tokyo 152-8552, Japan;Department of Health and Psychosocial Medicine, Aichi Medical University, Nagakute, Aichi 480-1195, Japan;Department of Health and Psychosocial Medicine, Aichi Medical University, Nagakute, Aichi 480-1195, Japan
Venue:
International Journal of Bioinformatics Research and Applications
Year:
2012

Citing 3
Cited 0

Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
SVMTorch: support vector machines for large-scale regression problems

The Journal of Machine Learning Research
Frequency analysis of task evoked pupillary response and eye-movement

Proceedings of the 2004 symposium on Eye tracking research & applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

Pupillary response has been used as an index of sleepiness, but the validity of the index is not clear. In this paper, the influence of blinks on the Pupillary Unrest Index (PUI) and the Power Spectrum Density (PSD) as indices of pupil instability during a sleepiness test was examined. To create pupillary indices for sleepiness, four frequency components of the compensated pupillary change were extracted from PSD. These factor components were applied to two-class classifications of subjective sleepiness using discriminant analysis, and their performance was assessed. Differences in contribution ratios for the four factor components were observed between the two kinds of subjective sleepiness. Finally, a causal path diagram was created to show the relationship between blink, pupillary indices and subjective sleepiness.