casa 14(1): e5

Research Article

Chronological states of viewer’s intentions using hidden Markov models and features of eye movement

Download264 downloads
  • @ARTICLE{10.4108/casa.1.1.e5,
        author={Minoru Nakayama and Naoya Takahashi},
        title={Chronological states of viewer’s intentions using hidden Markov models and features of eye movement},
        journal={EAI Endorsed Transactions on Context-aware Systems and Applications},
        volume={1},
        number={1},
        publisher={ICST},
        journal_a={CASA},
        year={2014},
        month={9},
        keywords={User intention, hidden Markov model, features of eye movements},
        doi={10.4108/casa.1.1.e5}
    }
    
  • Minoru Nakayama
    Naoya Takahashi
    Year: 2014
    Chronological states of viewer’s intentions using hidden Markov models and features of eye movement
    CASA
    ICST
    DOI: 10.4108/casa.1.1.e5
Minoru Nakayama1,*, Naoya Takahashi1
  • 1: Human System Science, Tokyo Institute of Technology Ookayama, Meguro, Tokyo, Japan
*Contact email: nakayama@cradle.titech.ac.jp

Abstract

To determine the possibility of predicting viewer’s internal states using the hidden Markov model, several features of eye movements were introduced to the model. Performance was measured using the data from a set of eye movement features recorded during recall tests which consisted of observations of three levels of task difficulty. The features were the temporal appearances of fixations and saccades, and combinations of 8 viewed directions during long and short eye movements. As a result, features of long eye movements, such as saccade information, contributed to prediction accuracy. Also, this prediction accuracy was regulated by the difficulty of the task.