- B.Sc., Carnegie Mellon University, 2018
- Associate Research Engineer, NIA, 2018 – present
- Software Engineering Intern, NIA, 2017
- Research Assistant, Department of Physics, Carnegie Mellon University, 2016
- Machine Learning (Deep Learning)
- Digital Signal Processing
Blind Identification of Radio Interference
Radio interference in a given airspace threatens link reliability of radio communication systems onboard autonomous aerial vehicles passing through that airspace. Since these vehicles depend on the radio links for safety critical telemetry and navigation data, link-corrupting radio interference poses a safety hazard. We are trying to develop a machine learning technique to identify link-corrupting radio interference in a blind manner, i.e., without a priori knowledge of the signals in an airspace, so that autonomous aerial vehicles can take safe actions when they encounter an airspace rich in radio interference.