Eye tracking with EEG life-style

Haji Samadi, Mohammad Reza (2016). Eye tracking with EEG life-style. University of Birmingham. Ph.D.

PDF - Accepted Version

Download (2MB)


Innovative human-computer interaction paradigms with minimum motor control provide realistic interactions and have potential for use in assistive technologies. Among the human modalities, the eyes and the brain are the two modalities with minimum motor requirements. Most of the existing assistive technologies based on tracking the eyes (such as electrooculography and videooculography) are intrusive, limited to the laboratory environment and restrictive or are not accurate enough for real-life applications. The same limitations apply to brain activity monitoring systems such as electroencephalography (EEG). In this research, the objective is to employ a less-intrusive, consumer-grade EEG headset designed for mobile applications to track the user’s eyes and reliably estimate focus of foveal attention (FoA). To this end, signal processing approaches are proposed in order to classify different types of eye movements and estimate FoA. The FoA estimation is then improved using the brain responses to flickering stimuli recorded in EEG data. Afterwards, the FoA estimation is again improved by proposing an automated method to remove eye-related artefacts from brain responses to the stimuli. Finally, the FoA estimation is best improved by extracting eye-movement classification and brain-response detection features from EEG data projected into independent sources.

Type of Work: Thesis (Doctorates > Ph.D.)
Award Type: Doctorates > Ph.D.
College/Faculty: Colleges (2008 onwards) > College of Engineering & Physical Sciences
School or Department: School of Engineering, Department of Electronic, Electrical and Systems Engineering
Funders: None/not applicable
Subjects: T Technology > TA Engineering (General). Civil engineering (General)
URI: http://etheses.bham.ac.uk/id/eprint/6862


Request a Correction Request a Correction
View Item View Item


Downloads per month over past year