Hung-Tien Huang

I am an undergraduate computer science student double minor in mathematics and statistics at University of South Carolina.

My research interests include but not limited to causal inference, continual learning, neuromorphic computing, computer vision, and reinforcement learning. I want to make robots evolve throughout their lifetime so that they can be more adaptable to changes.

Currently, I work with Professor Ray Bai and Professor Pooyan Jamshidi on explainable artificial intelligence. I previously worked with Professor Austin Downey and Professor Jason Bakos on machine learning real-time system detection.

Beyond academics, I like buses a lot because I grew up next to a bus parking lot. I build paper crafts of buses, take photos of buses, and play OMSI 2 - the most fabulous bus simulator in the world. By the way, I am a huge cat person and I meow a lot.

selected publications

Audio-Based Wildfire Detection on Embedded Systems

Hung-Tien Huang, Austin RJ Downey, and Jason D Bakos

Electronics 2022

Abs HTML PDF

The occurrence of wildfires often results in significant fatalities. As wildfires are notorious for their high speed of spread, the ability to identify wildfire at its early stage is essential in quickly obtaining control of the fire and in reducing property loss and preventing loss of life. This work presents a machine learning wildfire detecting data pipeline that can be deployed on embedded systems in remote locations. The proposed data pipeline consists of three main steps: audio preprocessing, feature engineering, and classification. Experiments show that the proposed data pipeline is capable of detecting wildfire effectively with high precision and is capable of detecting wildfire sound over the forest’s background soundscape. When being deployed on a Raspberry Pi 4, the proposed data pipeline takes 66 milliseconds to process a 1 s sound clip. To the knowledge of the author, this is the first edge-computing implementation of an audio-based wildfire detection system.