Sampath Jayarathna
Old Dominion University, VA·Computer Science·Early-career
Where we look, and how our gaze shifts from one thing to another, reveals a great deal about attention and memory. This project asks whether eye tracking, which uses cameras to record exactly where a person is looking, can give objective, measurable readouts of a person's attention and working memory as they happen.
- Fields
Computer Science
Psychology
Engineering
- Topics
eye tracking
gaze transition
joint attention
- Grants
- 1 known grant, through Mar 2027
What they work on
- Build a "streaming hub," a framework for real-time, computationally efficient processing of eye-tracking data from one or more users, in place of offline batch analysis.
- Test how eye-movement measures of gaze transition, the shifting of gaze between targets, relate to neurocognitive indices of attention during attentional control and joint attention tasks, and build a gaze transition model.
- Determine whether eye-tracking measures can index working memory capacity while people perform complex span tasks, memory tests done alongside a second task.
- Apply real-time eye tracking analytics to training assessment for children with ASD or ADHD, to low-vision magnifiers, and to performance assistance for unmanned aircraft pilots.
More about the research
Most current eye tracking systems analyze recordings only after a session ends. This project instead aims to process eye-movement data in real time.
Why it matters
Real-time eye tracking could give clinicians and caregivers an objective way to gauge attention in children with autism or ADHD during training. It could also support more responsive low-vision magnifiers for people with visual impairment and help monitor the performance of drone pilots. In addition, faster streaming analytics could make eye tracking practical for many new live applications.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Matthew Engelhard
Duke University, NC·Computer Science·Early-career
Develop machine-learning models that predict autism spectrum disorder and ADHD from early electronic health record data, such as diagnosis codes, labs, vitals and clinical notes, while correcting for differences in health care use.
Krishnendu Roy
Vanderbilt University, TN·Education Research
Pilot connected programs at Vanderbilt, Fisk, UConn and Northeastern that support neurodiverse engineering students from undergraduate study through graduate training and into the workforce.
Alexandra Bey
Duke University, NC·Neuroscience·Early-career
Confirm that less looking at social than nonsocial images goes with lower beta-1 and higher theta EEG brain rhythms in autistic preschoolers, using EEG recorded at the same time as automated eye-gaze tracking.
The school
Old Dominion University: 8 labs on PI Pages, $76M a year on research, 143 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.