Timothy Do

I am a currently Computer Vision Engineering Intern at SiMa.ai!

I graduated with a Master's of Science Student in Electrical and Computer Engineering at UCLA earlier this June! My area of study is in Signals and Systems, where my specialization in Signal Processing. I've taken courses in Embedded Systems, Computational Imaging, Digital Speech Processing, Modern Wireless Communications, and Advanced Neural Networks & Deep Learning while at UCLA.

Earlier than that, I was an undergraduate student in Electrical Engineering at UC Irvine. I was part of the Accelerated Status program, allowing me to partake in graduate courses in Image Processing & Hardware Accelerators during undergrad. I was fourtante to be advised by Professor Glenn Healey as an undergraduate researcher in the Irvine Computer Vision Laboratory. There, I conducted hyperspectral image analysis for detecting emissions often seen in wildfires.

Email  /  Resume  /  Bio  /  Twitter  /  Github

profile photo

Research

I'm interested in computer vision, deep learning, image/speech processing, & wireless communications. The works seen below is a culmination of my research experiences to broaden my knowledge in these fields.

End to End Deep Learning Architectures for Automatic Modulation Recognition
Timothy Do
Jan. - Mar. 2024
Proposal  /  Paper  /  Code

This project explores the application of Convolutional Neural Networks for Automatic Modulation Recognition on the RadioML and HisarMod Datasets.

Neural Network Architectures for EEG Action Classification
Timothy Do, Brandon Kam, Josh McDermott, Steve Zang
Feb. - Mar. 2024
Paper  /  Code

This project explores the task of EEG Action Classification on the BCI dataset.

Dialect Classification in African American Speakers
Keith Chen, Timothy Do, James Shiffer, Thomas Sison
Feb. - Mar. 2024
Paper  /  Code

This project explores the task of Dialect Region Classification of African American Speakers in the CORAAL Dataset.

RuHuman: A Resilient Multimodal AI-Powered Audio Verification System
Timothy Do,
Sep. - Dec. 2023
Proposal  /  Demo  /  Slides  /  Report  /  Code

This project explores models for deepfake audio detection across versatile environments and many embedded IoT devices.