Our Work Is Local, but Our Impact Is Global

Optimizing ambulance allocation and routing is one of the most efficient ways for EMS to save more lives at virtually no cost. However, current EMS software was developed under models that assume normal demands.

Postpartum mood and anxiety disorders affect as many as one in five women globally. Left untreated, these can have major negative effects on maternal and child health and well-being. While effective treatments are available, nearly 60% of mothers with symptoms are undiagnosed, and 50% of diagnosed mothers are left untreated.

This project addresses the conflict between convenience and privacy inherent to computer vision with the goal of developing future computer vision technologies that support diverse users with visual impairments, especially those who are traditionally underserved.   

This project considers high confidence policy learning as an evaluation criterion for good systems and investigates new algorithms for meeting this criterion. 

We are working with several City of Austin offices to confront the problem of homelessness. People experience homelessness as a continuum, ranging from housing instability to incarceration, couch-surfing to street homelessness, and episodic to chronic.

The goal of this project is to build an AI system using crowd-sourced data to help predict the health impacts of different neighborhood environments.