Sarah (Hyojin) Lee

I'm a ML engineer of Digital Health Team at Samsung Electronics in South Korea. My Research interests lie in developing machine learning model for monitoring and improving general health, especially Sleep.

At Digital Health Team, I am developing ML algorithms for monitoring Sleep Apnea and Sleep Staging. I am also working on health foundation models for diverse health-related downstream tasks using wearable sensor data. I am part of Samsung Sponsored Research collaboration with MIT Media Lab, which includes projects on Sleep Entrainment and Digital Biomarkers for Sleep.

Previously, I completed my Master's degree at Seoul National University Graduate School of Data Science, where I was advised by Prof. Hyung-Sin Kim and co-advised by Prof. Hyun-woo Shin from Seoul National University College of Medicine.

Before that, I received a Bachelor's degree in Biology and Business Administration from Seoul National University.

Email / CV / Google Scholar / LinkedIn / Github

News

01/2025 — Paper on interpretable automatic sleep staging has been accepted for npj Digital Medicine
10/2024 — Abstract on interpretable automatic sleep staging has been accepted for oral presentation at Sleep Europe 2024
06/2024 — Poster on On-device OSA detection with video won Best Poster Award at MobiSys 2024
05/2024 — Started full-time machine learning engineer at Digital Health Team, Samsung Electronics
08/2023 — Paper on On-device OSA detection with video has been accepted for ICCV CVAMD 2023 workshop
03/2022 — Started MS in Data Science Seoul National University Graduate School of Data Science

Research

My research interests focus on developing computational models for personalized diagnosis and treatment, with an emphasis on deployment in real-world clinical settings. I am particularly interested in multi-modal time-series data and in building foundation models that can generalize across multiple health-related downstream tasks. While sleep research is the primary focus of my work, I am also interested in extending these approaches to neurodegenerative diseases.

	Per-Second, Explainable Obstructive Sleep Apnea Detection from Multimodal Time-Series using Vision Transformer Joopyo Hong, Kunmin Jang, Hyojin Lee, Hyun Keun Ahn, Hyun-Woo Shin, Hyung-Sin Kim Communications Medicine (Revision), 2026 paper
	Explainable Vision Transformer for Automatic Visual Sleep Staging on Multimodal PSG Signals Hyojin Lee, You Rim Choi, Hyun Kyung Lee, Jaemin Jeong, Joopyo Hong, Hyun-Woo Shin, Hyung-Sin Kim npj Digital Medicine*, 2025 code / paper / youtube
	SlAction: Non-intrusive, Lightweight Obstructive Sleep Apnea Detection using Infrared Video You Rim Choi, Gyeongseon Eo, Wonhyuck Youn, Hyojin Lee, Haemin Jang, Dongyoon Kim, Hyun-Woo Shin, Hyung-Sin Kim ICCV Workshop, 2023 paper / poster

Source code credit to Dr.Jon Barron