EMHMM: Eye Movement Analysis with Hidden Markov Models and Its Applications in Cognitive Research

AbstractRecent studies have reported substantial individual differences in eye movements during cognitive tasks. To quantitatively measure these differences, Chuk, Chan, and Hsiao (2014) have developed the Eye Movement analysis with Hidden Markov Models (EMHMM) approach (Matlab Toolbox available at http://visal.cs.cityu.edu.hk/research/emhmm/). Each individual’s eye movement pattern is summarised using a hidden Markov model (HMM), including person-specific regions of interest (ROIs) and transition probabilities among these ROIs. Individual HMMs are clustered to discover common patterns. Differences among individual patterns are quantified through similarity measures with the common patterns. This approach has been applied to face recognition research and made discoveries thus far not revealed by other methods. New methodologies for tasks involving cognitive state changes and stimuli with different feature layouts have also been developed. We will first introduce EMHMM and its applications with a short demo, followed by a tutorial with recommendations and sample data for attendees to have hands-on experience.

Return to previous page