Published in Research project with professor David Shmoys, 2020
This project uses a data-driven approach to understand how each method in the transportation system interacts with each other, particularly the metro syatem and bike-sharing system.
Published in 36th Conference on Uncertainty in Artificial Intelligence (UAI), 2020
In this paper, we propose a finite-state protocol that captures a resource-bounded agent in a multi-armed bandit setting. The proposed protoal is nearly-optimal and human-like.
Published in 26th European Signal Processing Conference (EUSIPCO), 2018
In this paper, we propose a novel and optimized classification algorithm called analog-to-feature (A2F) conversion. It provides a more energy-efficient solution to always-on sensors for audio-event classification.