Home // BIOTECHNO 2013, The Fifth International Conference on Bioinformatics, Biocomputational Systems and Biotechnologies // View article

Chronological Prediction of Certainty in Recall Tests using Markov Models of Eye Movements

Authors:
Noaya Takahashi
Minoru Nakayama

Keywords: Eye Movements; Hidden Markov Model; Certainty; User Intention

Abstract:
To predict chronologically certainty levels of understanding of question statements during recall tests using observed eye movements, the hidden Markov model was employed. The feasibility of predicting the accuracy of responses was examined using optimization and simulation of the model together with experimental eye movement data. Chronological prediction accuracy could be calculated using this model, and the accuracy decreased with task difficulty. The highest accuracies were observed at 550 msec. after onset of stimuli. The certainty of correct responses was calculated using the probability of transition. This certainty was the highest during the 100-250 msec. after stimuli onset, and decreased with the duration of the response. These results provide the possibility of estimating the progress of understanding.

Pages: 55 to 60

Copyright: Copyright (c) IARIA, 2013

Publication date: March 24, 2013

Published in: conference

ISSN: 2308-4383

ISBN: 978-1-61208-260-8

Location: Lisbon, Portugal

Dates: from March 24, 2013 to March 29, 2013