Beta 1


Title Signal processing of visual behavior - Eye tracking and EEG
Author Rabøl, Ditlev Munk
Supervisor Hansen, Lars Kai (Cognitive Systems, Department of Informatics and Mathematical Modeling, Technical University of Denmark, DTU, DK-2800 Kgs. Lyngby, Denmark)
Institution Technical University of Denmark, DTU, DK-2800 Kgs. Lyngby, Denmark
Thesis level Master's thesis
Year 2010
Abstract It is widely accepted that the brain processes visual information in two anatomically separated pathways in the brain. Additionally, two eye-movement patterns has been observed in free picture viewing. Recent studies applying eye-tracking and EEG measurements has provided evidence for a correlation of the active visual pathway and eye-movement pattern. The analysis of eye-tracking and EEG data in these studies are often performed separately and applies static classification methods. In this thesis an approach applying classification of eyetracking and EEG data using Hidden Markov Models (HMM) is presented. HMM are trained on eye-tracking data, and the classification is applied to both eye-tracking and EEG data. Both Discrete Hidden Markov Models (DHMM) and Continues Hidden Markov Models (CHMM) are applied. The DHMM seems to provide a fair classification of both eye-tracking and EEG data compared to previous studies, where the use the CHMM was related with issues.
Imprint Technical University of Denmark (DTU) : Kgs. Lyngby, Denmark
Series IMM-M.Sc.-2010-75
Fulltext
Original PDF ep10_75_net.pdf (36.69 MB)
Admin Creation date: 2010-09-20    Update date: 2010-09-20    Source: dtu    ID: 267011    Original MXD