CAREER: Eye Tracking Streaming Analytics

The primary goal of this project is to use real-time processing of eye tracking data to derive non-invasive measurements that can reveal objective and quantifiable information about the attention of individual subjects (e.g., being able to select useful information). Research advances made through this project will be used towards improved training assessment for neurodiverse (e.g., Autism Spectrum Disorder and Attention-Deficit/Hyperactivity Disorder) children, low-vision magnifiers focusing on accessibility, and performance assistance for unmanned aircraft pilot operators.

The integrated research and education goal is to provide a foundation to mentor, train, and attract underrepresented minority and female students from local high schools to a college pathway and transition them towards graduate studies on interdisciplinary areas in STEM. The outreach efforts will provide direct training to a cohort of students involved in a summer camp for neighboring school districts, with the aim of attracting underrepresented high school students to STEM fields.

The project work will also positively impact neurodiverse children and their caregivers through an annual event that provides hands-on activities using the eye tracking technology built in this project.

This research will determine the correlation of neurocognitive indices of attention and gaze transition via an eye tracking streaming analytics framework. The project builds on a converging operations approach using analytic-streams and multi-user eye tracking, and establishes novel eye tracking models during tasks associated with joint attention and gaze transition.

The project work will fundamentally advance research in eye tracking data processing and analytics, by creating a “streaming hub”. Next, it will investigate the possible relationships between eye movement metrics representing gaze transition collected during attentional control tasks and build a gaze transition model. Subsequently, the research will focus on working memory models by answering the research question: “Can eye tracking measures index working memory capacity during complex span tasks?” Furthermore, considering that most existing eye tracking systems only support standard analysis and offline batch-processing of eye movement data, this project will advance computationally efficient stream processing and real-time analytics useful for a broad range of eye tracking applications.

Advances in real-time eye tracking analytics will enable entirely new application areas. For this, the research team will collaborate with different organizations such as Lighthouse Guild (non-profit) and NASA (National Aeronautics and Space Administration), as well as healthcare/medical professionals.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.