Pupil size as input data to distinguish comprehension state in auditory word association task using machine learning

Kosei Minami, Keiichi Watanuki, Kazunori Kaede, Keiichi Muramatsu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In communication, it is very important for a speaker to understand the comprehension state of the speaking partner. In this study, the “comprehension state” is defined as whether or not the speaker’s message is clearly understood, which is difficult to accurately evaluate. This study aims to evaluate the comprehension state from the pupil size using machine learning. We conduct a word association task using elements that are similar to those used in conversations and measure the pupil size; this pupil size data is used as input data for machine learning. The results show that high accuracy is achieved by learning the low frequency components of the pupil size.

Original languageEnglish
Title of host publicationIntelligent Human Systems Integration 2019 - Proceedings of the 2nd International Conference on Intelligent Human Systems Integration IHSI 2019
Subtitle of host publicationIntegrating People and Intelligent Systems, 2019
EditorsTareq Ahram, Waldemar Karwowski
PublisherSpringer Verlag
Pages123-129
Number of pages7
ISBN (Print)9783030110505
DOIs
Publication statusPublished - 2019
Externally publishedYes
Event2nd International Conference on Intelligent Human Systems Integration, IHSI 2019 - San Diego, United States
Duration: 2019 Feb 72019 Feb 10

Publication series

NameAdvances in Intelligent Systems and Computing
Volume903
ISSN (Print)2194-5357

Conference

Conference2nd International Conference on Intelligent Human Systems Integration, IHSI 2019
CountryUnited States
CitySan Diego
Period19/2/719/2/10

Keywords

  • Comprehension state
  • Pupil size
  • Word association task

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science(all)

Fingerprint Dive into the research topics of 'Pupil size as input data to distinguish comprehension state in auditory word association task using machine learning'. Together they form a unique fingerprint.

Cite this