Machine Learning Calibrated Low-Cost Sensing

University of Texas at Dallas, Dallas, TX

University of Texas at Dallas, Dallas, TX team photo
The video above gives a brief overview of how our sensor systems are used to provide up-to-date, real-time information on air pollution. It also outlines the accomplishments of community outreach programs, student mentorships, community outreach programs, and positive media coverage that we have received.

David Lary is the principal investigator. Eight graduate students make up the student team : Adam Aker (Physics), Gokul Balagopal (Electrical Engineering), Ashen Fernando (Physics), Shawhin Talebi (Physics), John Waczak (Physics), Lakitha Wijeratne (Physics), Xiaohe Yu (Geography & Geospatial Science), Yichao Zhang (Physics). Additionally, we have a computer science undergraduate student: Daniel Kiv.

EPA P3 Video Presentation

Poster (click to open a full size image): 
Machine Learning Calibrated Low-Cost Sensing poster

The poster summarizes how machine learning is being used to improve the accuracy of air pollution assessments taken from the sensor systems we built, and summarizes student mentorships, community outreach programs. Additionally, it highlights the positive media coverage we have received.